From 412a3bd77bd76014472d93aa65ce8d7b75809ebb Mon Sep 17 00:00:00 2001 From: Karl Berry Date: Sat, 5 Sep 2015 22:01:10 +0000 Subject: arabxetex (4sep15) git-svn-id: svn://tug.org/texlive/trunk@38299 c570f23f-e606-0410-a88d-b1316a301751 --- .../arabxetex/arabtex-farsi-fullvoc.map | 491 ++++++++++++++++++++ .../arabxetex/arabtex-farsi-fullvoc.tec | Bin 0 -> 5115 bytes .../fontmapping/arabxetex/arabtex-farsi-novoc.map | 476 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-farsi-novoc.tec | Bin 0 -> 4186 bytes .../fontmapping/arabxetex/arabtex-farsi-voc.map | 486 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-farsi-voc.tec | Bin 0 -> 4234 bytes .../arabxetex/arabtex-fdf2alif-farsi-fullvoc.map | 495 -------------------- .../arabxetex/arabtex-fdf2alif-farsi-fullvoc.tec | Bin 5095 -> 0 bytes .../arabxetex/arabtex-fdf2alif-farsi-novoc.map | 480 ------------------- .../arabxetex/arabtex-fdf2alif-farsi-novoc.tec | Bin 4158 -> 0 bytes .../arabxetex/arabtex-fdf2alif-farsi-voc.map | 490 -------------------- .../arabxetex/arabtex-fdf2alif-farsi-voc.tec | Bin 4198 -> 0 bytes .../arabxetex/arabtex-fdf2alif-fullvoc.map | 482 ------------------- .../arabxetex/arabtex-fdf2alif-fullvoc.tec | Bin 4798 -> 0 bytes .../arabtex-fdf2alif-kashmiri-fullvoc.map | 513 --------------------- .../arabtex-fdf2alif-kashmiri-fullvoc.tec | Bin 5278 -> 0 bytes .../arabxetex/arabtex-fdf2alif-kashmiri-novoc.map | 498 -------------------- .../arabxetex/arabtex-fdf2alif-kashmiri-novoc.tec | Bin 4312 -> 0 bytes .../arabxetex/arabtex-fdf2alif-kashmiri-voc.map | 508 -------------------- .../arabxetex/arabtex-fdf2alif-kashmiri-voc.tec | Bin 4326 -> 0 bytes .../arabxetex/arabtex-fdf2alif-kurdish.map | 290 ------------ .../arabxetex/arabtex-fdf2alif-kurdish.tec | Bin 2385 -> 0 bytes .../arabtex-fdf2alif-maghribi-fullvoc.map | 482 ------------------- .../arabtex-fdf2alif-maghribi-fullvoc.tec | Bin 4807 -> 0 bytes .../arabxetex/arabtex-fdf2alif-maghribi-novoc.map | 465 ------------------- .../arabxetex/arabtex-fdf2alif-maghribi-novoc.tec | Bin 3838 -> 0 bytes .../arabxetex/arabtex-fdf2alif-maghribi-voc.map | 476 ------------------- .../arabxetex/arabtex-fdf2alif-maghribi-voc.tec | Bin 3910 -> 0 bytes .../arabxetex/arabtex-fdf2alif-malay-fullvoc.map | 485 ------------------- .../arabxetex/arabtex-fdf2alif-malay-fullvoc.tec | Bin 4969 -> 0 bytes .../arabxetex/arabtex-fdf2alif-malay-novoc.map | 470 ------------------- .../arabxetex/arabtex-fdf2alif-malay-novoc.tec | Bin 4053 -> 0 bytes .../arabxetex/arabtex-fdf2alif-malay-voc.map | 480 ------------------- .../arabxetex/arabtex-fdf2alif-malay-voc.tec | Bin 4067 -> 0 bytes .../arabxetex/arabtex-fdf2alif-novoc.map | 465 ------------------- .../arabxetex/arabtex-fdf2alif-novoc.tec | Bin 3828 -> 0 bytes .../arabxetex/arabtex-fdf2alif-pashto-fullvoc.map | 491 -------------------- .../arabxetex/arabtex-fdf2alif-pashto-fullvoc.tec | Bin 5030 -> 0 bytes .../arabxetex/arabtex-fdf2alif-pashto-novoc.map | 476 ------------------- .../arabxetex/arabtex-fdf2alif-pashto-novoc.tec | Bin 4099 -> 0 bytes .../arabxetex/arabtex-fdf2alif-pashto-voc.map | 486 ------------------- .../arabxetex/arabtex-fdf2alif-pashto-voc.tec | Bin 4122 -> 0 bytes .../arabxetex/arabtex-fdf2alif-sindhi-fullvoc.map | 461 ------------------ .../arabxetex/arabtex-fdf2alif-sindhi-fullvoc.tec | Bin 4872 -> 0 bytes .../arabxetex/arabtex-fdf2alif-sindhi-novoc.map | 446 ------------------ .../arabxetex/arabtex-fdf2alif-sindhi-novoc.tec | Bin 3890 -> 0 bytes .../arabxetex/arabtex-fdf2alif-sindhi-voc.map | 456 ------------------ .../arabxetex/arabtex-fdf2alif-sindhi-voc.tec | Bin 3916 -> 0 bytes .../arabxetex/arabtex-fdf2alif-turk-fullvoc.map | 485 ------------------- .../arabxetex/arabtex-fdf2alif-turk-fullvoc.tec | Bin 4957 -> 0 bytes .../arabxetex/arabtex-fdf2alif-turk-novoc.map | 470 ------------------- .../arabxetex/arabtex-fdf2alif-turk-novoc.tec | Bin 4017 -> 0 bytes .../arabxetex/arabtex-fdf2alif-turk-voc.map | 480 ------------------- .../arabxetex/arabtex-fdf2alif-turk-voc.tec | Bin 4047 -> 0 bytes .../arabxetex/arabtex-fdf2alif-uighur.map | 277 ----------- .../arabxetex/arabtex-fdf2alif-uighur.tec | Bin 2252 -> 0 bytes .../arabxetex/arabtex-fdf2alif-urdu-fullvoc.map | 499 -------------------- .../arabxetex/arabtex-fdf2alif-urdu-fullvoc.tec | Bin 5120 -> 0 bytes .../arabxetex/arabtex-fdf2alif-urdu-novoc.map | 484 ------------------- .../arabxetex/arabtex-fdf2alif-urdu-novoc.tec | Bin 4171 -> 0 bytes .../arabxetex/arabtex-fdf2alif-urdu-voc.map | 494 -------------------- .../arabxetex/arabtex-fdf2alif-urdu-voc.tec | Bin 4181 -> 0 bytes .../fontmapping/arabxetex/arabtex-fdf2alif-voc.map | 476 ------------------- .../fontmapping/arabxetex/arabtex-fdf2alif-voc.tec | Bin 3901 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-farsi-fullvoc.map | 495 -------------------- .../arabxetex/arabtex-fdf2noalif-farsi-fullvoc.tec | Bin 5100 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-farsi-novoc.map | 480 ------------------- .../arabxetex/arabtex-fdf2noalif-farsi-novoc.tec | Bin 4170 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-farsi-voc.map | 490 -------------------- .../arabxetex/arabtex-fdf2noalif-farsi-voc.tec | Bin 4194 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-fullvoc.map | 482 ------------------- .../arabxetex/arabtex-fdf2noalif-fullvoc.tec | Bin 4799 -> 0 bytes .../arabtex-fdf2noalif-kashmiri-fullvoc.map | 513 --------------------- .../arabtex-fdf2noalif-kashmiri-fullvoc.tec | Bin 5279 -> 0 bytes .../arabtex-fdf2noalif-kashmiri-novoc.map | 498 -------------------- .../arabtex-fdf2noalif-kashmiri-novoc.tec | Bin 4324 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-kashmiri-voc.map | 508 -------------------- .../arabxetex/arabtex-fdf2noalif-kashmiri-voc.tec | Bin 4338 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-kurdish.map | 290 ------------ .../arabxetex/arabtex-fdf2noalif-kurdish.tec | Bin 2382 -> 0 bytes .../arabtex-fdf2noalif-maghribi-fullvoc.map | 482 ------------------- .../arabtex-fdf2noalif-maghribi-fullvoc.tec | Bin 4813 -> 0 bytes .../arabtex-fdf2noalif-maghribi-novoc.map | 465 ------------------- .../arabtex-fdf2noalif-maghribi-novoc.tec | Bin 3832 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-maghribi-voc.map | 476 ------------------- .../arabxetex/arabtex-fdf2noalif-maghribi-voc.tec | Bin 3931 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-malay-fullvoc.map | 485 ------------------- .../arabxetex/arabtex-fdf2noalif-malay-fullvoc.tec | Bin 4956 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-malay-novoc.map | 470 ------------------- .../arabxetex/arabtex-fdf2noalif-malay-novoc.tec | Bin 4066 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-malay-voc.map | 480 ------------------- .../arabxetex/arabtex-fdf2noalif-malay-voc.tec | Bin 4045 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-novoc.map | 465 ------------------- .../arabxetex/arabtex-fdf2noalif-novoc.tec | Bin 3826 -> 0 bytes .../arabtex-fdf2noalif-pashto-fullvoc.map | 491 -------------------- .../arabtex-fdf2noalif-pashto-fullvoc.tec | Bin 5026 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-pashto-novoc.map | 476 ------------------- .../arabxetex/arabtex-fdf2noalif-pashto-novoc.tec | Bin 4100 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-pashto-voc.map | 486 ------------------- .../arabxetex/arabtex-fdf2noalif-pashto-voc.tec | Bin 4111 -> 0 bytes .../arabtex-fdf2noalif-sindhi-fullvoc.map | 461 ------------------ .../arabtex-fdf2noalif-sindhi-fullvoc.tec | Bin 4862 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-sindhi-novoc.map | 446 ------------------ .../arabxetex/arabtex-fdf2noalif-sindhi-novoc.tec | Bin 3892 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-sindhi-voc.map | 456 ------------------ .../arabxetex/arabtex-fdf2noalif-sindhi-voc.tec | Bin 3897 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-turk-fullvoc.map | 485 ------------------- .../arabxetex/arabtex-fdf2noalif-turk-fullvoc.tec | Bin 4966 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-turk-novoc.map | 470 ------------------- .../arabxetex/arabtex-fdf2noalif-turk-novoc.tec | Bin 4027 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-turk-voc.map | 480 ------------------- .../arabxetex/arabtex-fdf2noalif-turk-voc.tec | Bin 4054 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-uighur.map | 277 ----------- .../arabxetex/arabtex-fdf2noalif-uighur.tec | Bin 2257 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-urdu-fullvoc.map | 499 -------------------- .../arabxetex/arabtex-fdf2noalif-urdu-fullvoc.tec | Bin 5126 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-urdu-novoc.map | 484 ------------------- .../arabxetex/arabtex-fdf2noalif-urdu-novoc.tec | Bin 4169 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-urdu-voc.map | 494 -------------------- .../arabxetex/arabtex-fdf2noalif-urdu-voc.tec | Bin 4207 -> 0 bytes .../arabxetex/arabtex-fdf2noalif-voc.map | 476 ------------------- .../arabxetex/arabtex-fdf2noalif-voc.tec | Bin 3922 -> 0 bytes .../fontmapping/arabxetex/arabtex-fullvoc.map | 479 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-fullvoc.tec | Bin 0 -> 4837 bytes .../arabxetex/arabtex-kashmiri-fullvoc.map | 509 ++++++++++++++++++++ .../arabxetex/arabtex-kashmiri-fullvoc.tec | Bin 0 -> 5299 bytes .../arabxetex/arabtex-kashmiri-novoc.map | 494 ++++++++++++++++++++ .../arabxetex/arabtex-kashmiri-novoc.tec | Bin 0 -> 4343 bytes .../fontmapping/arabxetex/arabtex-kashmiri-voc.map | 504 ++++++++++++++++++++ .../fontmapping/arabxetex/arabtex-kashmiri-voc.tec | Bin 0 -> 4372 bytes .../fontmapping/arabxetex/arabtex-kurdish.map | 284 ++++++++++++ .../fontmapping/arabxetex/arabtex-kurdish.tec | Bin 0 -> 2393 bytes .../arabxetex/arabtex-maghribi-fullvoc.map | 479 +++++++++++++++++++ .../arabxetex/arabtex-maghribi-fullvoc.tec | Bin 0 -> 4845 bytes .../arabxetex/arabtex-maghribi-novoc.map | 461 ++++++++++++++++++ .../arabxetex/arabtex-maghribi-novoc.tec | Bin 0 -> 3857 bytes .../fontmapping/arabxetex/arabtex-maghribi-voc.map | 472 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-maghribi-voc.tec | Bin 0 -> 3954 bytes .../arabxetex/arabtex-malay-fullvoc.map | 481 +++++++++++++++++++ .../arabxetex/arabtex-malay-fullvoc.tec | Bin 0 -> 4975 bytes .../fontmapping/arabxetex/arabtex-malay-novoc.map | 466 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-malay-novoc.tec | Bin 0 -> 4100 bytes .../fontmapping/arabxetex/arabtex-malay-voc.map | 476 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-malay-voc.tec | Bin 0 -> 4084 bytes .../xetex/fontmapping/arabxetex/arabtex-novoc.map | 461 ++++++++++++++++++ .../xetex/fontmapping/arabxetex/arabtex-novoc.tec | Bin 0 -> 3852 bytes .../arabxetex/arabtex-pashto-fullvoc.map | 487 +++++++++++++++++++ .../arabxetex/arabtex-pashto-fullvoc.tec | Bin 0 -> 5043 bytes .../fontmapping/arabxetex/arabtex-pashto-novoc.map | 472 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-pashto-novoc.tec | Bin 0 -> 4132 bytes .../fontmapping/arabxetex/arabtex-pashto-voc.map | 482 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-pashto-voc.tec | Bin 0 -> 4150 bytes .../arabxetex/arabtex-sindhi-fullvoc.map | 457 ++++++++++++++++++ .../arabxetex/arabtex-sindhi-fullvoc.tec | Bin 0 -> 4887 bytes .../fontmapping/arabxetex/arabtex-sindhi-novoc.map | 442 ++++++++++++++++++ .../fontmapping/arabxetex/arabtex-sindhi-novoc.tec | Bin 0 -> 3920 bytes .../fontmapping/arabxetex/arabtex-sindhi-voc.map | 452 ++++++++++++++++++ .../fontmapping/arabxetex/arabtex-sindhi-voc.tec | Bin 0 -> 3940 bytes .../fontmapping/arabxetex/arabtex-turk-fullvoc.map | 481 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-turk-fullvoc.tec | Bin 0 -> 4979 bytes .../fontmapping/arabxetex/arabtex-turk-novoc.map | 466 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-turk-novoc.tec | Bin 0 -> 4052 bytes .../fontmapping/arabxetex/arabtex-turk-voc.map | 476 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-turk-voc.tec | Bin 0 -> 4102 bytes .../xetex/fontmapping/arabxetex/arabtex-uighur.map | 271 +++++++++++ .../xetex/fontmapping/arabxetex/arabtex-uighur.tec | Bin 0 -> 2256 bytes .../fontmapping/arabxetex/arabtex-urdu-fullvoc.map | 495 ++++++++++++++++++++ .../fontmapping/arabxetex/arabtex-urdu-fullvoc.tec | Bin 0 -> 5146 bytes .../fontmapping/arabxetex/arabtex-urdu-novoc.map | 480 +++++++++++++++++++ .../fontmapping/arabxetex/arabtex-urdu-novoc.tec | Bin 0 -> 4187 bytes .../fontmapping/arabxetex/arabtex-urdu-voc.map | 490 ++++++++++++++++++++ .../fontmapping/arabxetex/arabtex-urdu-voc.tec | Bin 0 -> 4251 bytes .../xetex/fontmapping/arabxetex/arabtex-voc.map | 472 +++++++++++++++++++ .../xetex/fontmapping/arabxetex/arabtex-voc.tec | Bin 0 -> 3943 bytes 174 files changed, 13442 insertions(+), 27120 deletions(-) create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-fullvoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-fullvoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-novoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-novoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-voc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kurdish.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kurdish.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-uighur.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-uighur.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kurdish.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kurdish.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-uighur.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-uighur.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-fullvoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-fullvoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-novoc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-novoc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-voc.tec delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-voc.map delete mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-voc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fullvoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fullvoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-fullvoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-fullvoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-novoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-novoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-voc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-voc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kurdish.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kurdish.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-fullvoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-fullvoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-novoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-novoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-voc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-voc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-fullvoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-fullvoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-novoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-novoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-voc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-voc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-novoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-novoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-fullvoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-fullvoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-novoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-novoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-voc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-voc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-fullvoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-fullvoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-novoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-novoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-voc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-voc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-fullvoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-fullvoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-novoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-novoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-voc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-voc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-uighur.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-uighur.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-fullvoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-fullvoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-novoc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-novoc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-voc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-voc.tec create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-voc.map create mode 100644 Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-voc.tec (limited to 'Master/texmf-dist/fonts/misc') diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-fullvoc.map new file mode 100644 index 00000000000..f6d3285e711 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-fullvoc.map @@ -0,0 +1,491 @@ +LHSName "ArabTeX-farsi-fullvocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +E > I +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +A / BEG _ > HA ;; ADD MORE ? <<< +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ ^# > U+0627 @q1 i y ; -I... +Z Q?=qq (I|E) / _ (#|Z) > @qq i y ; +UL Q?=q1 U > @q1 U +Q?=q1 U / # _ # > U+0627 @q1 u w +Q BAR > U+0020; "| to separate compounds >> IN TRANSLIT THIS WILL BE REMOVED + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix +U+0048 > U+0647 U+200C ; H is always heh final +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda +U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs +U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha +[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) +;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant +U+FDF2 > U+0644 U+0644 U+0647 ; +Q > ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-fullvoc.tec new file mode 100644 index 00000000000..24791521239 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-fullvoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-novoc.map new file mode 100644 index 00000000000..dece5f62cc7 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-novoc.map @@ -0,0 +1,476 @@ +LHSName "ArabTeX-farsi-novowels" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode +CO O > U+06FC ; +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +E > I +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0627 ; +[VWL]=v1 / BEG _ > A @v1 +A / BEG _ > HA ;; ADD MORE ? <<< +Q?=q1 U / BEG _ > A @q1 u w ; -U +; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! +Q?=q1 I / BEG _ ^# > A @q1 i y ; -I... +Z Q?=qq (I|E) / _ (#|Z) > @qq i y ; +UL Q?=q1 U > @q1 U +Q?=q1 U / # _ # > U+0627 @q1 u w +Q BAR > U+0020; "| to separate compounds >> IN TRANSLIT THIS WILL BE REMOVED + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m Q i A Hy Q a +m Q i H a / _ (T|t) > m Q i A Hy +m i H Q a / _ (T|t) > m A Hy Q a +m i H a / _ (T|t) > m A Hy + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Y Y > U+0649 U+0651 ;;SHADDA +Y > U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +Q U > U+064F U+0648 +[Uw] [Uw] > U+0648 U+0651 ;;SHADDA +[Uw] > U+0648 +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +Q u N > U+064C +u N > +Q u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 U+064B ;;SHADDA +T Q AN > U+0629 U+064B +T AN > U+0629 +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +I > U+064A +Q i N > U+064D +i N > ; +Q i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix +U+0048 > U+0647 U+200C ; H is always heh final +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+0649 +UL a > U+0670 +UL u > ; +UL i > ; +Q AN / (A H|Ha) _ > U+064B +AN / (A H|Ha) _ > ; +Q AN > U+064B U+0627 +AN > U+0627 +Q a > U+064E +Q A > U+064E U+0627 +A > U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +[VWL] > ;stripoff vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +Z > ;- +BAR > ;| + +U+FDF2 > U+0644 U+0644 U+0647 ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-novoc.tec new file mode 100644 index 00000000000..6535412e7ec Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-novoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-voc.map new file mode 100644 index 00000000000..2b7168aec72 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-voc.map @@ -0,0 +1,486 @@ +LHSName "ArabTeX-farsi-vocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +E > I +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +A / BEG _ > HA ;; ADD MORE ? <<< +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ ^# > U+0627 @q1 i y ; -I... +Z Q?=qq (I|E) / _ (#|Z) > @qq i y ; +UL Q?=q1 U > @q1 U +Q?=q1 U / # _ # > U+0627 @q1 u w +Q BAR > U+0020; "| to separate compounds >> IN TRANSLIT THIS WILL BE REMOVED + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix +U+0048 > U+0647 U+200C ; H is always heh final +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +U+FDF2 > U+0644 U+0644 U+0647 ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-voc.tec new file mode 100644 index 00000000000..9c45c4bfd7f Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-farsi-voc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-fullvoc.map deleted file mode 100644 index 12dbfa01c63..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-fullvoc.map +++ /dev/null @@ -1,495 +0,0 @@ -LHSName "ArabTeX-farsi-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ ^# > U+0627 @q1 i y ; -I... -Z Q?=qq (I|E) / _ (#|Z) > @qq i y ; -UL Q?=q1 U > @q1 U -Q?=q1 U / # _ # > U+0627 @q1 u w -Q BAR > U+0020; "| to separate compounds >> IN TRANSLIT THIS WILL BE REMOVED - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-fullvoc.tec deleted file mode 100644 index 5ea246518ac..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-novoc.map deleted file mode 100644 index dfdfa837b35..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-novoc.map +++ /dev/null @@ -1,480 +0,0 @@ -LHSName "ArabTeX-farsi-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ ^# > A @q1 i y ; -I... -Z Q?=qq (I|E) / _ (#|Z) > @qq i y ; -UL Q?=q1 U > @q1 U -Q?=q1 U / # _ # > U+0627 @q1 u w -Q BAR > U+0020; "| to separate compounds >> IN TRANSLIT THIS WILL BE REMOVED - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-novoc.tec deleted file mode 100644 index 418f6566e43..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-voc.map deleted file mode 100644 index 35c789edd42..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-voc.map +++ /dev/null @@ -1,490 +0,0 @@ -LHSName "ArabTeX-farsi-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ ^# > U+0627 @q1 i y ; -I... -Z Q?=qq (I|E) / _ (#|Z) > @qq i y ; -UL Q?=q1 U > @q1 U -Q?=q1 U / # _ # > U+0627 @q1 u w -Q BAR > U+0020; "| to separate compounds >> IN TRANSLIT THIS WILL BE REMOVED - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-voc.tec deleted file mode 100644 index 8345fe580fe..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-farsi-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-fullvoc.map deleted file mode 100644 index 11bd7a0a39b..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-fullvoc.map +++ /dev/null @@ -1,482 +0,0 @@ -LHSName "ArabTeX-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0671 l Z ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so min al- must be written mina 'l- in fullvocalize mode -;; wasla on initial alif : NEW! NOT TESTED! -[VWL]=v1 Z / BEG _ > @v1 U+0671 ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so huwa irtifA` must be written huwa i-rtifA` in fullvocalize mode -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > U+0627 a -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 [VWL]? / [VWL] Z _ > U+0671 ; e.g. fa-isti_hraj -> wasla on initial alif -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-fullvoc.tec deleted file mode 100644 index 46a3e4c598e..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-fullvoc.map deleted file mode 100644 index 769b6bde7e8..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-fullvoc.map +++ /dev/null @@ -1,513 +0,0 @@ -LHSName "ArabTeX-kashmiri-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e / # _ # > U+0627 U+06D2 U+0658 ; Alif + yeh barree + bow accent -e / _ # > U+06D2 U+0658 ; yeh barree + bow accent -e / # _ > U+0627 y U+0658 ; alif + ya + bow accent -e > y U+0658 -E / # _ # > U+0627 U+06D2 ; Alif + yeh barree -E / _ # > U+06D2 ; yeh barree -E / # _ > U+0627 y ; alif + ya -E > y -o / # _ > U+0627 U+06C6 -o > U+06C6 -P A > U+0672 -P U > U+0673 ; > this is the initial or lone form, but medial and final require wavy hamza below previous letter (not in Unicode)! Perhaps an OT font could solve this :: in Scheherazade the glyph needed is named _wavyHamza <<< -P a / # _ > U+0623 -P a > U+0654 -P u > U+0655 -P o / # _ > U+0627 U+06C4 -P o > U+06C4 -P O / # _ > U+0627 U+06C4 U+0627 U+064E -P O > U+06C4 U+0627 U+064E -I > y U+0656 -I / _ # > y -U / _ # > U+0627 w U+0657 -U > w U+0657 - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -CO z CO z > U+0636 U+0651 ;;SHADDA -CO z > U+0636 -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; .b with ring below : FIXME not in Unicode! but U+06EA is a poor replacement: -P y / # _ # > U+0627 U+06D2 U+06EA -P y / _ # > U+0649 -P y > U+066E U+06EA -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-fullvoc.tec deleted file mode 100644 index 7ed4f7bb38c..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-novoc.map deleted file mode 100644 index 99b2e76a64d..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-novoc.map +++ /dev/null @@ -1,498 +0,0 @@ -LHSName "ArabTeX-kashmiri-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e / # _ # > U+0627 U+06D2 U+0658 ; Alif + yeh barree + bow accent -e / _ # > U+06D2 U+0658 ; yeh barree + bow accent -e / # _ > U+0627 y U+0658 ; alif + ya + bow accent -e > y U+0658 -E / # _ # > U+0627 U+06D2 ; Alif + yeh barree -E / _ # > U+06D2 ; yeh barree -E / # _ > U+0627 y ; alif + ya -E > y -o / # _ > U+0627 U+06C6 -o > U+06C6 -P A > U+0672 -P U > U+0673 ; > this is the initial or lone form, but medial and final require wavy hamza below previous letter (not in Unicode)! Perhaps an OT font could solve this :: in Scheherazade the glyph needed is named _wavyHamza <<< -P a / # _ > U+0623 -P a > U+0654 -P u > U+0655 -P o / # _ > U+0627 U+06C4 -P o > U+06C4 -P O / # _ > U+0627 U+06C4 U+0627 U+064E -P O > U+06C4 U+0627 U+064E -I > y U+0656 -I / _ # > y -U / _ # > U+0627 w U+0657 -U > w U+0657 - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -CO z CO z > U+0636 U+0651 ;;SHADDA -CO z > U+0636 -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -;; .b with ring below : FIXME not in Unicode! but U+06EA is a poor replacement: -P y / # _ # > U+0627 U+06D2 U+06EA -P y / _ # > U+0649 -P y > U+066E U+06EA -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-novoc.tec deleted file mode 100644 index ec6bf0a081d..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-voc.map deleted file mode 100644 index 791aab5df95..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-voc.map +++ /dev/null @@ -1,508 +0,0 @@ -LHSName "ArabTeX-kashmiri-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e / # _ # > U+0627 U+06D2 U+0658 ; Alif + yeh barree + bow accent -e / _ # > U+06D2 U+0658 ; yeh barree + bow accent -e / # _ > U+0627 y U+0658 ; alif + ya + bow accent -e > y U+0658 -E / # _ # > U+0627 U+06D2 ; Alif + yeh barree -E / _ # > U+06D2 ; yeh barree -E / # _ > U+0627 y ; alif + ya -E > y -o / # _ > U+0627 U+06C6 -o > U+06C6 -P A > U+0672 -P U > U+0673 ; > this is the initial or lone form, but medial and final require wavy hamza below previous letter (not in Unicode)! Perhaps an OT font could solve this :: in Scheherazade the glyph needed is named _wavyHamza <<< -P a / # _ > U+0623 -P a > U+0654 -P u > U+0655 -P o / # _ > U+0627 U+06C4 -P o > U+06C4 -P O / # _ > U+0627 U+06C4 U+0627 U+064E -P O > U+06C4 U+0627 U+064E -I > y U+0656 -I / _ # > y -U / _ # > U+0627 w U+0657 -U > w U+0657 - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -CO z CO z > U+0636 U+0651 ;;SHADDA -CO z > U+0636 -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; .b with ring below : FIXME not in Unicode! but U+06EA is a poor replacement: -P y / # _ # > U+0627 U+06D2 U+06EA -P y / _ # > U+0649 -P y > U+066E U+06EA -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-voc.tec deleted file mode 100644 index 03596e0df92..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kashmiri-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kurdish.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kurdish.map deleted file mode 100644 index 85c3e365354..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kurdish.map +++ /dev/null @@ -1,290 +0,0 @@ -LHSName "ArabTeX-Kurdish" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define LLAH U+006C U+006C U+005F U+0061 U+0068 - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) - - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -(a|A) l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL)' -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE)' -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels - -E / # _ > U+0626 U+06CE -E > U+06CE -e / # _ > U+0626 U+0647 U+200C ; h always final -e > U+0647 U+200C -i / # _ > U+0626 -Q i > U+0650 -i > ; -Q I / # _ > U+0626 U+064A U+0650 -Q I > U+064A U+0650 -I / # _ > U+0626 U+064A -I > U+064A -(a|A) / # _ > U+0626 U+0627 -(a|A) > U+0627 -(o|O) / # _ > U+0626 U+06C6 -(o|O) > U+06C6 -u / # _ > U+0626 U+0648 -u > U+0648 -U / # _ > U+0626 U+0648 U+0648 -U > U+0648 U+0648 -Ain e > U+0639 U+0647 U+200C - - -P z P z > U+0638 U+0651 ;;SHADDA -P z > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;pashto ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -V t V t > U+0679 U+0651 ; urdu ;;SHADDA -V t > U+0679 -UL t UL t > U+062B U+0651 ;;SHADDA -UL t > U+062B -P t P t > U+0637 U+0651 ;;SHADDA -P t > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -(C|V) s (C|V) s > U+0634 U+0651 ;;SHADDA -(C|V) s > U+0634 -P s P s > U+0635 U+0651 ;;SHADDA -P s > U+0635 -CO s CO s > U+069B U+0651 -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -;; also missing U+0694 : r with dot below -V r V r > U+0694 U+0651 ;Kurdish ;;SHADDA -V r > U+0694 -C r C r > U+0692 U+0651 ;Kurdish ;;SHADDA ; missing in ArabTeX <<< -C r > U+0692 -P r P r > U+0695 U+0651 ;Kurdish ;;SHADDA -P r > U+0695 -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ; urdu ;;SHADDA -P n > U+06BA ; -V n V n > U+06BC U+0651 ; Pashto -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;kurdish ;;SHADDA -C l > U+06B5 -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ; pashto urdu ;;SHADDA -P k > U+06A9 -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -c c > U+062C U+0651 ;;SHADDA -c > U+062C -x x > U+062E U+0651 ;;SHADDA -x > U+062E -j j > U+0698 U+0651 ;;SHADDA -j > U+0698 -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -P h P h > U+062D U+0651 ;;SHADDA -P h > U+062D -V h V h > U+06C1 U+0651 -V h > U+06C1 -h h > U+200C U+06BE U+0651 ;;SHADDA -h > U+200C U+06BE ; h always initial form -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P (g|x) P (g|x) > U+063A U+0651 ;;SHADDA -P (g|x) > U+063A -C g C g > U+063A U+0651 ;;SHADDA -C g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;pashto ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0688 U+0651 ;urdu ;;SHADDA -V d > U+0688 ;urdu -C d C d > U+06EE ; not defined in ArabTeX U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -UL d UL d > U+0630 U+0651 ;;SHADDA -UL d > U+0630 -P d P d > U+0636 U+0651 ;;SHADDA -P d > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -(C|V) c (C|V) c > U+0686 U+0651 ;;SHADDA -(C|V) c > U+0686 -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H > U+0626 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / . _ . > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... -U+005B / . _ . > U+200D U+005B U+200D ; ... (but of course this screws up contextual analysis, so quoting of hamzas etc may be necessary) -Q > ; -N > ; -C > ;^ -Z > ;- -BAR > ;| - - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kurdish.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kurdish.tec deleted file mode 100644 index 6e09ac77e56..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-kurdish.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-fullvoc.map deleted file mode 100644 index 70154d32267..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-fullvoc.map +++ /dev/null @@ -1,482 +0,0 @@ -LHSName "ArabTeX-maghribi-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0671 l Z ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so min al- must be written mina 'l- in fullvocalize mode -;; wasla on initial alif : NEW! NOT TESTED! -[VWL]=v1 Z / BEG _ > @v1 U+0671 ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so huwa irtifA` must be written huwa i-rtifA` in fullvocalize mode -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > U+0627 a -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A5 U+0651 ;;SHADDA -v > U+06A5 ;; maghribi -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+06A7 U+0651 ;; maghribi -q > U+06A7 ;; maghribi -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+06A2 U+0651 ;; SHADDA -f > U+06A2 ;; maghribi -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 [VWL]? / [VWL] Z _ > U+0671 ; e.g. fa-isti_hraj -> wasla on initial alif -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-fullvoc.tec deleted file mode 100644 index f475104efeb..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-novoc.map deleted file mode 100644 index 237c45ab8e6..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-novoc.map +++ /dev/null @@ -1,465 +0,0 @@ -LHSName "ArabTeX-maghribi-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -A / BEG _ > A a -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -P I P I / _ # > U+06CC U+0651 ;; SHADDA -P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A5 U+0651 ;;SHADDA -v > U+06A5 ;; maghribi -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+06A7 U+0651 ;; maghribi -q > U+06A7 ;; maghribi -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+06A2 U+0651 ;; SHADDA -f > U+06A2 ;; maghribi -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-novoc.tec deleted file mode 100644 index 2bc13123142..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-voc.map deleted file mode 100644 index c85d129e046..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-voc.map +++ /dev/null @@ -1,476 +0,0 @@ -LHSName "ArabTeX-maghribi-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > U+0627 a -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A5 U+0651 ;;SHADDA -v > U+06A5 ;; maghribi -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+06A7 U+0651 ;; maghribi -q > U+06A7 ;; maghribi -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+06A2 U+0651 ;; SHADDA -f > U+06A2 ;; maghribi -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -U+0627 [VWL]? / [VWL] Z _ > U+0627 ; e.g. fa-isti_hraj -> initial alif has no vowel -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-voc.tec deleted file mode 100644 index 5b4893b492a..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-maghribi-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-fullvoc.map deleted file mode 100644 index ff1726ac820..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-fullvoc.map +++ /dev/null @@ -1,485 +0,0 @@ -LHSName "ArabTeX-malay-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06CF U+0651 ;;SHADDA -v > U+06CF -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+06A8 U+0651 ;;SHADDA -p > U+06A8 ;Old malay -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06BD U+0651 ;;SHADDA -C n > U+06BD ; <<< ArabTeX yields nūn with three dots below, which is not in Unicode! -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+0762 U+0651 ;;SHADDA -g > U+0762 -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0686 U+0651 ;;SHADDA -c > U+0686 -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-fullvoc.tec deleted file mode 100644 index 043262206de..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-novoc.map deleted file mode 100644 index 36ab97dcdb2..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-novoc.map +++ /dev/null @@ -1,470 +0,0 @@ -LHSName "ArabTeX-malay-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -P I P I / _ # > U+06CC U+0651 ;; SHADDA -P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06CF U+0651 ;;SHADDA -v > U+06CF -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+06A8 U+0651 ;;SHADDA -p > U+06A8 ;Old malay -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06BD U+0651 ;;SHADDA -C n > U+06BD ; <<< ArabTeX yields nūn with three dots below, which is not in Unicode! -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+0762 U+0651 ;;SHADDA -g > U+0762 -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0686 U+0651 ;;SHADDA -c > U+0686 -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-novoc.tec deleted file mode 100644 index 691e4718dd0..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-voc.map deleted file mode 100644 index d73e75b98d0..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-voc.map +++ /dev/null @@ -1,480 +0,0 @@ -LHSName "ArabTeX-malay-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06CF U+0651 ;;SHADDA -v > U+06CF -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+06A8 U+0651 ;;SHADDA -p > U+06A8 ;Old malay -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06BD U+0651 ;;SHADDA -C n > U+06BD ; <<< ArabTeX yields nūn with three dots below, which is not in Unicode! -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+0762 U+0651 ;;SHADDA -g > U+0762 -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0686 U+0651 ;;SHADDA -c > U+0686 -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-voc.tec deleted file mode 100644 index 44b62900a48..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-malay-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-novoc.map deleted file mode 100644 index 152faffe029..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-novoc.map +++ /dev/null @@ -1,465 +0,0 @@ -LHSName "ArabTeX-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -A / BEG _ > A a -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -P I P I / _ # > U+06CC U+0651 ;; SHADDA -P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-novoc.tec deleted file mode 100644 index 9e0f4c98f80..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-fullvoc.map deleted file mode 100644 index 7b4d8a0fcc2..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-fullvoc.map +++ /dev/null @@ -1,491 +0,0 @@ -LHSName "ArabTeX-pashto-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -a e > a U+0626 -E e > U+0659 U+06CD -e e > U+0659 U+0626 -E > U+0659 U+06D0 -CO O > U+06FC ; -O > U+0657 w -o > U+0657 -a o > a w -CO U > U+06C7 ; -e > U+0659 -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+067C U+0651 ;;SHADDA -V t > U+067C ; pashto -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0693 U+0651 ;;SHADDA -V r > U+0693 ;Pashto -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0689 U+0651 ;;SHADDA -V d > U+0689 ;pashto -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-fullvoc.tec deleted file mode 100644 index b02bb82642f..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-novoc.map deleted file mode 100644 index 62536030416..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-novoc.map +++ /dev/null @@ -1,476 +0,0 @@ -LHSName "ArabTeX-pashto-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -a e > a U+0626 -E e > U+0659 U+06CD -e e > U+0659 U+0626 -E > U+0659 U+06D0 -CO O > U+06FC ; -O > U+0657 w -o > U+0657 -a o > a w -CO U > U+06C7 ; -e > U+0659 -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+067C U+0651 ;;SHADDA -V t > U+067C ; pashto -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0693 U+0651 ;;SHADDA -V r > U+0693 ;Pashto -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0689 U+0651 ;;SHADDA -V d > U+0689 ;pashto -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-novoc.tec deleted file mode 100644 index 14a35b434d8..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-voc.map deleted file mode 100644 index 09ca243a912..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-voc.map +++ /dev/null @@ -1,486 +0,0 @@ -LHSName "ArabTeX-pashto-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -a e > a U+0626 -E e > U+0659 U+06CD -e e > U+0659 U+0626 -E > U+0659 U+06D0 -CO O > U+06FC ; -O > U+0657 w -o > U+0657 -a o > a w -CO U > U+06C7 ; -e > U+0659 -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+067C U+0651 ;;SHADDA -V t > U+067C ; pashto -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0693 U+0651 ;;SHADDA -V r > U+0693 ;Pashto -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0689 U+0651 ;;SHADDA -V d > U+0689 ;pashto -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-voc.tec deleted file mode 100644 index 18cfd87bbd2..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-pashto-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-fullvoc.map deleted file mode 100644 index 477d056b134..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-fullvoc.map +++ /dev/null @@ -1,461 +0,0 @@ -LHSName "ArabTeX-sindhi-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - -;; special code for sindhi -;; U+004D U+0049 U+004E > U+06FE ; define macro \MIN in sindhi env -P m I N > U+06FE ; .mIN -;; U+0049 U+004E > U+06FD ; IN define macro \IN in sindhi env -H BAR I N > U+06FD ; '|IN - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t h V t h > U+067A U+0651 ;;SHADDA -V t h > U+067A -t h t h > U+067F U+0651 ;;SHADDA -t h > U+067F -V t V t > U+067D U+0651 ;;SHADDA -V t > U+067D -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0699 U+0651 ;;SHADDA -V r > U+0699 -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p h p h > U+06A6 U+0651 ;;SHADDA -p h > U+06A6 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+0683 U+0651 ;;SHADDA -C n > U+0683 -P P n P P n > U+06B2 U+0651 ;;SHADDA -P P n > U+06B2 ;; old sindhi? (not in ArabTeX) <<< -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BB U+0651 ;;SHADDA -V n > U+06BB -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -k h k h > U+06A9 U+0651 ;;SHADDA -k h > U+06A9 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+06AA U+0651 ;;SHADDA -k > U+06AA ; kaf swash -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE -P CO g P CO g > U+06B4 U+0651 ;;SHADDA -P CO g > U+06B4 ;; old sindhi? (not in ArabTeX) <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d h V d h > U+068D U+0651 ;;SHADDA -V d h > U+068D -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -d h d h > U+068C U+0651 ;;SHADDA -d h > U+068C -C d C d > U+068E ;;SHADDA -C d > U+068E ; old sindhi: not in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -C c h C c h > U+0687 U+0651 ;;SHADDA -C c h > U+0687 -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -b h b h > U+0680 U+0651 ;;SHADDA -b h > U+0680 -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-fullvoc.tec deleted file mode 100644 index b0c44696c6a..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-novoc.map deleted file mode 100644 index 50efef6c46f..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-novoc.map +++ /dev/null @@ -1,446 +0,0 @@ -LHSName "ArabTeX-sindhi-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - -;; special code for sindhi -;; U+004D U+0049 U+004E > U+06FE ; define macro \MIN in sindhi env -P m I N > U+06FE ; .mIN -;; U+0049 U+004E > U+06FD ; IN define macro \IN in sindhi env -H BAR I N > U+06FD ; '|IN - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -P I P I / _ # > U+06CC U+0651 ;; SHADDA -P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t h V t h > U+067A U+0651 ;;SHADDA -V t h > U+067A -t h t h > U+067F U+0651 ;;SHADDA -t h > U+067F -V t V t > U+067D U+0651 ;;SHADDA -V t > U+067D -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0699 U+0651 ;;SHADDA -V r > U+0699 -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p h p h > U+06A6 U+0651 ;;SHADDA -p h > U+06A6 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+0683 U+0651 ;;SHADDA -C n > U+0683 -P P n P P n > U+06B2 U+0651 ;;SHADDA -P P n > U+06B2 ;; old sindhi? (not in ArabTeX) <<< -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BB U+0651 ;;SHADDA -V n > U+06BB -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -k h k h > U+06A9 U+0651 ;;SHADDA -k h > U+06A9 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+06AA U+0651 ;;SHADDA -k > U+06AA ; kaf swash -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE -P CO g P CO g > U+06B4 U+0651 ;;SHADDA -P CO g > U+06B4 ;; old sindhi? (not in ArabTeX) <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d h V d h > U+068D U+0651 ;;SHADDA -V d h > U+068D -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -d h d h > U+068C U+0651 ;;SHADDA -d h > U+068C -C d C d > U+068E ;;SHADDA -C d > U+068E ; old sindhi: not in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -C c h C c h > U+0687 U+0651 ;;SHADDA -C c h > U+0687 -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -b h b h > U+0680 U+0651 ;;SHADDA -b h > U+0680 -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-novoc.tec deleted file mode 100644 index 70837ac2edf..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-voc.map deleted file mode 100644 index 8d8c99e055e..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-voc.map +++ /dev/null @@ -1,456 +0,0 @@ -LHSName "ArabTeX-sindhi-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - -;; special code for sindhi -;; U+004D U+0049 U+004E > U+06FE ; define macro \MIN in sindhi env -P m I N > U+06FE ; .mIN -;; U+0049 U+004E > U+06FD ; IN define macro \IN in sindhi env -H BAR I N > U+06FD ; '|IN - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t h V t h > U+067A U+0651 ;;SHADDA -V t h > U+067A -t h t h > U+067F U+0651 ;;SHADDA -t h > U+067F -V t V t > U+067D U+0651 ;;SHADDA -V t > U+067D -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0699 U+0651 ;;SHADDA -V r > U+0699 -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p h p h > U+06A6 U+0651 ;;SHADDA -p h > U+06A6 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+0683 U+0651 ;;SHADDA -C n > U+0683 -P P n P P n > U+06B2 U+0651 ;;SHADDA -P P n > U+06B2 ;; old sindhi? (not in ArabTeX) <<< -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BB U+0651 ;;SHADDA -V n > U+06BB -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -k h k h > U+06A9 U+0651 ;;SHADDA -k h > U+06A9 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+06AA U+0651 ;;SHADDA -k > U+06AA ; kaf swash -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE -P CO g P CO g > U+06B4 U+0651 ;;SHADDA -P CO g > U+06B4 ;; old sindhi? (not in ArabTeX) <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d h V d h > U+068D U+0651 ;;SHADDA -V d h > U+068D -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -d h d h > U+068C U+0651 ;;SHADDA -d h > U+068C -C d C d > U+068E ;;SHADDA -C d > U+068E ; old sindhi: not in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -C c h C c h > U+0687 U+0651 ;;SHADDA -C c h > U+0687 -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -b h b h > U+0680 U+0651 ;;SHADDA -b h > U+0680 -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-voc.tec deleted file mode 100644 index eb595c097ff..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-sindhi-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-fullvoc.map deleted file mode 100644 index 06507da1eec..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-fullvoc.map +++ /dev/null @@ -1,485 +0,0 @@ -LHSName "ArabTeX-turk-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0636 U+0651 ;;SHADDA -V z > U+0636 -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+0634 U+0651 ;;SHADDA -V s > U+0634 -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+0642 U+0651 ;;SHADDA -P k > U+0642 ; Ottoman qaf -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+0698 U+0651 ;;SHADDA -j > U+0698 -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0686 U+0651 ;;SHADDA -V c > U+0686 ; Ottoman ç -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+062C U+0651 ;;SHADDA -c > U+062C -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-fullvoc.tec deleted file mode 100644 index b4613e1a9cf..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-novoc.map deleted file mode 100644 index 65660b94daf..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-novoc.map +++ /dev/null @@ -1,470 +0,0 @@ -LHSName "ArabTeX-turk-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0636 U+0651 ;;SHADDA -V z > U+0636 -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+0634 U+0651 ;;SHADDA -V s > U+0634 -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+0642 U+0651 ;;SHADDA -P k > U+0642 ; Ottoman qaf -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+0698 U+0651 ;;SHADDA -j > U+0698 -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0686 U+0651 ;;SHADDA -V c > U+0686 ; Ottoman ç -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+062C U+0651 ;;SHADDA -c > U+062C -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-novoc.tec deleted file mode 100644 index b63f2ef8ee8..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-voc.map deleted file mode 100644 index 0ab30050577..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-voc.map +++ /dev/null @@ -1,480 +0,0 @@ -LHSName "ArabTeX-turk-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0636 U+0651 ;;SHADDA -V z > U+0636 -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+0634 U+0651 ;;SHADDA -V s > U+0634 -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+0642 U+0651 ;;SHADDA -P k > U+0642 ; Ottoman qaf -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+0698 U+0651 ;;SHADDA -j > U+0698 -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0686 U+0651 ;;SHADDA -V c > U+0686 ; Ottoman ç -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+062C U+0651 ;;SHADDA -c > U+062C -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-voc.tec deleted file mode 100644 index 9ee96c4ac3f..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-turk-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-uighur.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-uighur.map deleted file mode 100644 index 11c28abd2bc..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-uighur.map +++ /dev/null @@ -1,277 +0,0 @@ -LHSName "ArabTeX-Uighur" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define LLAH U+006C U+006C U+005F U+0061 U+0068 - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) - - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -(a|A) l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL)' -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE)' -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels - -a / # _ > U+0626 U+0627 -a > U+0627 -(CO a|U+00E4) / # _ > U+0626 U+0647 U+200C -(CO a|U+00E4) > U+0647 U+200C -o / # _ > U+0626 U+0648 ; -o > U+0648 ; -(CO o|U+00F6) / # _ > U+0626 U+06C6 -(CO o|U+00F6) > U+06C6 -i / # _ # > U+0626 U+0649 -i / # _ > U+0626 U+066E -i / _ # > U+0649 -i > U+066E -e / # _ > U+0626 U+06D0 -e > U+06D0 -u / # _ > U+0626 U+06C7 ; -u > U+06C7 ; -(CO u|U+00FC) / # _ > U+0626 U+06C8 ; -(CO u|U+00FC) > U+06C8 ; -l Q a > U+0644 U+064E U+0627 ; -l a > U+0644 U+0627 ; - -P z P z > U+0638 U+0651 ;;SHADDA -P z > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;pashto ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -w w > U+06CB U+0651 ;;SHADDA -w > U+06CB -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -V t V t > U+0679 U+0651 ; urdu ;;SHADDA -V t > U+0679 -UL t UL t > U+062B U+0651 ;;SHADDA -UL t > U+062B -P t P t > U+0637 U+0651 ;;SHADDA -P t > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -P s P s > U+0635 U+0651 ;;SHADDA -P s > U+0635 -V s V s > U+069A U+0651 ;Pashto ;;SHADDA -V s > U+069A ;Pashto -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+0692 U+0651 ;Kurdish ;;SHADDA ; missing in ArabTeX <<< -C r > U+0692 -P r P r > U+0695 U+0651 ;Kurdish ;;SHADDA -P r > U+0695 -V r V r > U+0691 U+0651 ;Urdu ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ; urdu ;;SHADDA -P n > U+06BA ; -V n V n > U+06BC U+0651 ; Pashto -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -C l C l > U+06B5 U+0651 ;kurdish ;;SHADDA -C l > U+06B5 -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ; pashto urdu ;;SHADDA -P k > U+06A9 -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -P h P h > U+062D U+0651 ;;SHADDA -P h > U+062D -V h V h > U+06C1 U+0651 -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -C g C g > U+063A U+0651 ;;SHADDA -C g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;pashto ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0688 U+0651 ;urdu ;;SHADDA -V d > U+0688 ;urdu -C d C d > U+06EE ; not defined in ArabTeX U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -UL d UL d > U+0630 U+0651 ;;SHADDA -UL d > U+0630 -P d P d > U+0636 U+0651 ;;SHADDA -P d > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;pashto ;;SHADDA -V c > U+0685 -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -c c > U+0681 U+0651 -c > U+0681 ; ح with hamza above -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H > U+0626 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / . _ . > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... -U+005B / . _ . > U+200D U+005B U+200D ; ... (but of course this screws up contextual analysis, so quoting of hamzas etc may be necessary) -Q > ; -N > ; -C > ;^ -Z > ;- -BAR > ;| - - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-uighur.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-uighur.tec deleted file mode 100644 index 91d0abeba9e..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-uighur.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-fullvoc.map deleted file mode 100644 index 1a43e25170d..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-fullvoc.map +++ /dev/null @@ -1,499 +0,0 @@ -LHSName "ArabTeX-urdu-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -H E > U+06D3 ;; hamza + yeh barree -E / _ # > U+06D2 -E > y -a e / _ # > a U+06D2 -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 > U+06C3 -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -H H > U+06C1 U+0651 ;;SHADDA -H > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE ; urdu -;; fix letter+h letter+h > letter+h shadda in URDU <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0688 U+0651 ;;SHADDA -V d > U+0688 ;urdu -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -CO CO d CO CO d > U+0690 U+0651 ;;SHADDA -CO CO d > U+0690 ; old urdu: not in ArabTeX -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| -P P > U+06D4 ; urdu full stop << check - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-fullvoc.tec deleted file mode 100644 index 4de34ae02d8..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-novoc.map deleted file mode 100644 index 5104ee1e2e8..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-novoc.map +++ /dev/null @@ -1,484 +0,0 @@ -LHSName "ArabTeX-urdu-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -H E > U+06D3 ;; hamza + yeh barree -E / _ # > U+06D2 -E > y -a e / _ # > a U+06D2 -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 > U+06C3 -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -H H > U+06C1 U+0651 ;;SHADDA -H > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE ; urdu -;; fix letter+h letter+h > letter+h shadda in URDU <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0688 U+0651 ;;SHADDA -V d > U+0688 ;urdu -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -CO CO d CO CO d > U+0690 U+0651 ;;SHADDA -CO CO d > U+0690 ; old urdu: not in ArabTeX -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| -P P > U+06D4 ; urdu full stop << check - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-novoc.tec deleted file mode 100644 index 62a714e8c17..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-voc.map deleted file mode 100644 index f91a76587f0..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-voc.map +++ /dev/null @@ -1,494 +0,0 @@ -LHSName "ArabTeX-urdu-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -H E > U+06D3 ;; hamza + yeh barree -E / _ # > U+06D2 -E > y -a e / _ # > a U+06D2 -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 > U+06C3 -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -H H > U+06C1 U+0651 ;;SHADDA -H > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE ; urdu -;; fix letter+h letter+h > letter+h shadda in URDU <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0688 U+0651 ;;SHADDA -V d > U+0688 ;urdu -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -CO CO d CO CO d > U+0690 U+0651 ;;SHADDA -CO CO d > U+0690 ; old urdu: not in ArabTeX -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| -P P > U+06D4 ; urdu full stop << check - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-voc.tec deleted file mode 100644 index 07e3b00cfe6..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-urdu-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-voc.map deleted file mode 100644 index 17f2ea72f33..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-voc.map +++ /dev/null @@ -1,476 +0,0 @@ -LHSName "ArabTeX-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: -U+0041 U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'ALLAH' -U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > U+0627 a -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -U+0627 [VWL]? / [VWL] Z _ > U+0627 ; e.g. fa-isti_hraj -> initial alif has no vowel -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-voc.tec deleted file mode 100644 index 78569e6f549..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2alif-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-fullvoc.map deleted file mode 100644 index f53c3d35d06..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-fullvoc.map +++ /dev/null @@ -1,495 +0,0 @@ -LHSName "ArabTeX-farsi-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ ^# > U+0627 @q1 i y ; -I... -Z Q?=qq (I|E) / _ (#|Z) > @qq i y ; -UL Q?=q1 U > @q1 U -Q?=q1 U / # _ # > U+0627 @q1 u w -Q BAR > U+0020; "| to separate compounds >> IN TRANSLIT THIS WILL BE REMOVED - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-fullvoc.tec deleted file mode 100644 index 2165c5131ef..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-novoc.map deleted file mode 100644 index a653b5e3d97..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-novoc.map +++ /dev/null @@ -1,480 +0,0 @@ -LHSName "ArabTeX-farsi-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ ^# > A @q1 i y ; -I... -Z Q?=qq (I|E) / _ (#|Z) > @qq i y ; -UL Q?=q1 U > @q1 U -Q?=q1 U / # _ # > U+0627 @q1 u w -Q BAR > U+0020; "| to separate compounds >> IN TRANSLIT THIS WILL BE REMOVED - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-novoc.tec deleted file mode 100644 index fc32f96c9ad..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-voc.map deleted file mode 100644 index 9617d027c28..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-voc.map +++ /dev/null @@ -1,490 +0,0 @@ -LHSName "ArabTeX-farsi-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ ^# > U+0627 @q1 i y ; -I... -Z Q?=qq (I|E) / _ (#|Z) > @qq i y ; -UL Q?=q1 U > @q1 U -Q?=q1 U / # _ # > U+0627 @q1 u w -Q BAR > U+0020; "| to separate compounds >> IN TRANSLIT THIS WILL BE REMOVED - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-voc.tec deleted file mode 100644 index f0b3adcec46..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-farsi-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-fullvoc.map deleted file mode 100644 index f6772aa68c4..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-fullvoc.map +++ /dev/null @@ -1,482 +0,0 @@ -LHSName "ArabTeX-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0671 l Z ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so min al- must be written mina 'l- in fullvocalize mode -;; wasla on initial alif : NEW! NOT TESTED! -[VWL]=v1 Z / BEG _ > @v1 U+0671 ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so huwa irtifA` must be written huwa i-rtifA` in fullvocalize mode -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > U+0627 a -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 [VWL]? / [VWL] Z _ > U+0671 ; e.g. fa-isti_hraj -> wasla on initial alif -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-fullvoc.tec deleted file mode 100644 index 6ca10fc26be..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-fullvoc.map deleted file mode 100644 index a2516e210e7..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-fullvoc.map +++ /dev/null @@ -1,513 +0,0 @@ -LHSName "ArabTeX-kashmiri-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e / # _ # > U+0627 U+06D2 U+0658 ; Alif + yeh barree + bow accent -e / _ # > U+06D2 U+0658 ; yeh barree + bow accent -e / # _ > U+0627 y U+0658 ; alif + ya + bow accent -e > y U+0658 -E / # _ # > U+0627 U+06D2 ; Alif + yeh barree -E / _ # > U+06D2 ; yeh barree -E / # _ > U+0627 y ; alif + ya -E > y -o / # _ > U+0627 U+06C6 -o > U+06C6 -P A > U+0672 -P U > U+0673 ; > this is the initial or lone form, but medial and final require wavy hamza below previous letter (not in Unicode)! Perhaps an OT font could solve this :: in Scheherazade the glyph needed is named _wavyHamza <<< -P a / # _ > U+0623 -P a > U+0654 -P u > U+0655 -P o / # _ > U+0627 U+06C4 -P o > U+06C4 -P O / # _ > U+0627 U+06C4 U+0627 U+064E -P O > U+06C4 U+0627 U+064E -I > y U+0656 -I / _ # > y -U / _ # > U+0627 w U+0657 -U > w U+0657 - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -CO z CO z > U+0636 U+0651 ;;SHADDA -CO z > U+0636 -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; .b with ring below : FIXME not in Unicode! but U+06EA is a poor replacement: -P y / # _ # > U+0627 U+06D2 U+06EA -P y / _ # > U+0649 -P y > U+066E U+06EA -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-fullvoc.tec deleted file mode 100644 index 83e488e9069..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-novoc.map deleted file mode 100644 index b14151f77cd..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-novoc.map +++ /dev/null @@ -1,498 +0,0 @@ -LHSName "ArabTeX-kashmiri-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e / # _ # > U+0627 U+06D2 U+0658 ; Alif + yeh barree + bow accent -e / _ # > U+06D2 U+0658 ; yeh barree + bow accent -e / # _ > U+0627 y U+0658 ; alif + ya + bow accent -e > y U+0658 -E / # _ # > U+0627 U+06D2 ; Alif + yeh barree -E / _ # > U+06D2 ; yeh barree -E / # _ > U+0627 y ; alif + ya -E > y -o / # _ > U+0627 U+06C6 -o > U+06C6 -P A > U+0672 -P U > U+0673 ; > this is the initial or lone form, but medial and final require wavy hamza below previous letter (not in Unicode)! Perhaps an OT font could solve this :: in Scheherazade the glyph needed is named _wavyHamza <<< -P a / # _ > U+0623 -P a > U+0654 -P u > U+0655 -P o / # _ > U+0627 U+06C4 -P o > U+06C4 -P O / # _ > U+0627 U+06C4 U+0627 U+064E -P O > U+06C4 U+0627 U+064E -I > y U+0656 -I / _ # > y -U / _ # > U+0627 w U+0657 -U > w U+0657 - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -CO z CO z > U+0636 U+0651 ;;SHADDA -CO z > U+0636 -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -;; .b with ring below : FIXME not in Unicode! but U+06EA is a poor replacement: -P y / # _ # > U+0627 U+06D2 U+06EA -P y / _ # > U+0649 -P y > U+066E U+06EA -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-novoc.tec deleted file mode 100644 index 1c781a55e8f..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-voc.map deleted file mode 100644 index ad72262643b..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-voc.map +++ /dev/null @@ -1,508 +0,0 @@ -LHSName "ArabTeX-kashmiri-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e / # _ # > U+0627 U+06D2 U+0658 ; Alif + yeh barree + bow accent -e / _ # > U+06D2 U+0658 ; yeh barree + bow accent -e / # _ > U+0627 y U+0658 ; alif + ya + bow accent -e > y U+0658 -E / # _ # > U+0627 U+06D2 ; Alif + yeh barree -E / _ # > U+06D2 ; yeh barree -E / # _ > U+0627 y ; alif + ya -E > y -o / # _ > U+0627 U+06C6 -o > U+06C6 -P A > U+0672 -P U > U+0673 ; > this is the initial or lone form, but medial and final require wavy hamza below previous letter (not in Unicode)! Perhaps an OT font could solve this :: in Scheherazade the glyph needed is named _wavyHamza <<< -P a / # _ > U+0623 -P a > U+0654 -P u > U+0655 -P o / # _ > U+0627 U+06C4 -P o > U+06C4 -P O / # _ > U+0627 U+06C4 U+0627 U+064E -P O > U+06C4 U+0627 U+064E -I > y U+0656 -I / _ # > y -U / _ # > U+0627 w U+0657 -U > w U+0657 - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -CO z CO z > U+0636 U+0651 ;;SHADDA -CO z > U+0636 -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; .b with ring below : FIXME not in Unicode! but U+06EA is a poor replacement: -P y / # _ # > U+0627 U+06D2 U+06EA -P y / _ # > U+0649 -P y > U+066E U+06EA -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-voc.tec deleted file mode 100644 index 8b417908fcd..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kashmiri-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kurdish.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kurdish.map deleted file mode 100644 index c98b3f38b7d..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kurdish.map +++ /dev/null @@ -1,290 +0,0 @@ -LHSName "ArabTeX-Kurdish" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define LLAH U+006C U+006C U+005F U+0061 U+0068 - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) - - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -(a|A) l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL)' -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE)' -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels - -E / # _ > U+0626 U+06CE -E > U+06CE -e / # _ > U+0626 U+0647 U+200C ; h always final -e > U+0647 U+200C -i / # _ > U+0626 -Q i > U+0650 -i > ; -Q I / # _ > U+0626 U+064A U+0650 -Q I > U+064A U+0650 -I / # _ > U+0626 U+064A -I > U+064A -(a|A) / # _ > U+0626 U+0627 -(a|A) > U+0627 -(o|O) / # _ > U+0626 U+06C6 -(o|O) > U+06C6 -u / # _ > U+0626 U+0648 -u > U+0648 -U / # _ > U+0626 U+0648 U+0648 -U > U+0648 U+0648 -Ain e > U+0639 U+0647 U+200C - - -P z P z > U+0638 U+0651 ;;SHADDA -P z > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;pashto ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -V t V t > U+0679 U+0651 ; urdu ;;SHADDA -V t > U+0679 -UL t UL t > U+062B U+0651 ;;SHADDA -UL t > U+062B -P t P t > U+0637 U+0651 ;;SHADDA -P t > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -(C|V) s (C|V) s > U+0634 U+0651 ;;SHADDA -(C|V) s > U+0634 -P s P s > U+0635 U+0651 ;;SHADDA -P s > U+0635 -CO s CO s > U+069B U+0651 -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -;; also missing U+0694 : r with dot below -V r V r > U+0694 U+0651 ;Kurdish ;;SHADDA -V r > U+0694 -C r C r > U+0692 U+0651 ;Kurdish ;;SHADDA ; missing in ArabTeX <<< -C r > U+0692 -P r P r > U+0695 U+0651 ;Kurdish ;;SHADDA -P r > U+0695 -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ; urdu ;;SHADDA -P n > U+06BA ; -V n V n > U+06BC U+0651 ; Pashto -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;kurdish ;;SHADDA -C l > U+06B5 -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ; pashto urdu ;;SHADDA -P k > U+06A9 -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -c c > U+062C U+0651 ;;SHADDA -c > U+062C -x x > U+062E U+0651 ;;SHADDA -x > U+062E -j j > U+0698 U+0651 ;;SHADDA -j > U+0698 -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -P h P h > U+062D U+0651 ;;SHADDA -P h > U+062D -V h V h > U+06C1 U+0651 -V h > U+06C1 -h h > U+200C U+06BE U+0651 ;;SHADDA -h > U+200C U+06BE ; h always initial form -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P (g|x) P (g|x) > U+063A U+0651 ;;SHADDA -P (g|x) > U+063A -C g C g > U+063A U+0651 ;;SHADDA -C g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;pashto ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0688 U+0651 ;urdu ;;SHADDA -V d > U+0688 ;urdu -C d C d > U+06EE ; not defined in ArabTeX U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -UL d UL d > U+0630 U+0651 ;;SHADDA -UL d > U+0630 -P d P d > U+0636 U+0651 ;;SHADDA -P d > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -(C|V) c (C|V) c > U+0686 U+0651 ;;SHADDA -(C|V) c > U+0686 -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H > U+0626 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / . _ . > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... -U+005B / . _ . > U+200D U+005B U+200D ; ... (but of course this screws up contextual analysis, so quoting of hamzas etc may be necessary) -Q > ; -N > ; -C > ;^ -Z > ;- -BAR > ;| - - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kurdish.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kurdish.tec deleted file mode 100644 index 7cd94973133..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-kurdish.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-fullvoc.map deleted file mode 100644 index cb0e146df4f..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-fullvoc.map +++ /dev/null @@ -1,482 +0,0 @@ -LHSName "ArabTeX-maghribi-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0671 l Z ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so min al- must be written mina 'l- in fullvocalize mode -;; wasla on initial alif : NEW! NOT TESTED! -[VWL]=v1 Z / BEG _ > @v1 U+0671 ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so huwa irtifA` must be written huwa i-rtifA` in fullvocalize mode -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > U+0627 a -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A5 U+0651 ;;SHADDA -v > U+06A5 ;; maghribi -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+06A7 U+0651 ;; maghribi -q > U+06A7 ;; maghribi -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+06A2 U+0651 ;; SHADDA -f > U+06A2 ;; maghribi -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 [VWL]? / [VWL] Z _ > U+0671 ; e.g. fa-isti_hraj -> wasla on initial alif -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-fullvoc.tec deleted file mode 100644 index 8710e3b387e..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-novoc.map deleted file mode 100644 index 304f32cf64a..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-novoc.map +++ /dev/null @@ -1,465 +0,0 @@ -LHSName "ArabTeX-maghribi-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -A / BEG _ > A a -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -P I P I / _ # > U+06CC U+0651 ;; SHADDA -P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A5 U+0651 ;;SHADDA -v > U+06A5 ;; maghribi -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+06A7 U+0651 ;; maghribi -q > U+06A7 ;; maghribi -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+06A2 U+0651 ;; SHADDA -f > U+06A2 ;; maghribi -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-novoc.tec deleted file mode 100644 index 4541204cd25..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-voc.map deleted file mode 100644 index a6f76d42406..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-voc.map +++ /dev/null @@ -1,476 +0,0 @@ -LHSName "ArabTeX-maghribi-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > U+0627 a -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A5 U+0651 ;;SHADDA -v > U+06A5 ;; maghribi -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+06A7 U+0651 ;; maghribi -q > U+06A7 ;; maghribi -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+06A2 U+0651 ;; SHADDA -f > U+06A2 ;; maghribi -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -U+0627 [VWL]? / [VWL] Z _ > U+0627 ; e.g. fa-isti_hraj -> initial alif has no vowel -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-voc.tec deleted file mode 100644 index f3088c36a23..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-maghribi-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-fullvoc.map deleted file mode 100644 index c1cf78a23a2..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-fullvoc.map +++ /dev/null @@ -1,485 +0,0 @@ -LHSName "ArabTeX-malay-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06CF U+0651 ;;SHADDA -v > U+06CF -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+06A8 U+0651 ;;SHADDA -p > U+06A8 ;Old malay -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06BD U+0651 ;;SHADDA -C n > U+06BD ; <<< ArabTeX yields nūn with three dots below, which is not in Unicode! -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+0762 U+0651 ;;SHADDA -g > U+0762 -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0686 U+0651 ;;SHADDA -c > U+0686 -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-fullvoc.tec deleted file mode 100644 index c83fa403bd6..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-novoc.map deleted file mode 100644 index 7e4076dd309..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-novoc.map +++ /dev/null @@ -1,470 +0,0 @@ -LHSName "ArabTeX-malay-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -P I P I / _ # > U+06CC U+0651 ;; SHADDA -P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06CF U+0651 ;;SHADDA -v > U+06CF -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+06A8 U+0651 ;;SHADDA -p > U+06A8 ;Old malay -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06BD U+0651 ;;SHADDA -C n > U+06BD ; <<< ArabTeX yields nūn with three dots below, which is not in Unicode! -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+0762 U+0651 ;;SHADDA -g > U+0762 -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0686 U+0651 ;;SHADDA -c > U+0686 -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-novoc.tec deleted file mode 100644 index 4a6b8f92a3e..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-voc.map deleted file mode 100644 index 6f0f56dd139..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-voc.map +++ /dev/null @@ -1,480 +0,0 @@ -LHSName "ArabTeX-malay-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06CF U+0651 ;;SHADDA -v > U+06CF -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+06A8 U+0651 ;;SHADDA -p > U+06A8 ;Old malay -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06BD U+0651 ;;SHADDA -C n > U+06BD ; <<< ArabTeX yields nūn with three dots below, which is not in Unicode! -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+0762 U+0651 ;;SHADDA -g > U+0762 -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0686 U+0651 ;;SHADDA -c > U+0686 -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-voc.tec deleted file mode 100644 index 1b0f5b2b835..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-malay-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-novoc.map deleted file mode 100644 index 027f959c45f..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-novoc.map +++ /dev/null @@ -1,465 +0,0 @@ -LHSName "ArabTeX-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -A / BEG _ > A a -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -P I P I / _ # > U+06CC U+0651 ;; SHADDA -P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-novoc.tec deleted file mode 100644 index ba62340d6b3..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-fullvoc.map deleted file mode 100644 index 0b1057d5908..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-fullvoc.map +++ /dev/null @@ -1,491 +0,0 @@ -LHSName "ArabTeX-pashto-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -a e > a U+0626 -E e > U+0659 U+06CD -e e > U+0659 U+0626 -E > U+0659 U+06D0 -CO O > U+06FC ; -O > U+0657 w -o > U+0657 -a o > a w -CO U > U+06C7 ; -e > U+0659 -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+067C U+0651 ;;SHADDA -V t > U+067C ; pashto -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0693 U+0651 ;;SHADDA -V r > U+0693 ;Pashto -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0689 U+0651 ;;SHADDA -V d > U+0689 ;pashto -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-fullvoc.tec deleted file mode 100644 index c62c017c0b5..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-novoc.map deleted file mode 100644 index a3588c87c53..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-novoc.map +++ /dev/null @@ -1,476 +0,0 @@ -LHSName "ArabTeX-pashto-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -a e > a U+0626 -E e > U+0659 U+06CD -e e > U+0659 U+0626 -E > U+0659 U+06D0 -CO O > U+06FC ; -O > U+0657 w -o > U+0657 -a o > a w -CO U > U+06C7 ; -e > U+0659 -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+067C U+0651 ;;SHADDA -V t > U+067C ; pashto -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0693 U+0651 ;;SHADDA -V r > U+0693 ;Pashto -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0689 U+0651 ;;SHADDA -V d > U+0689 ;pashto -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-novoc.tec deleted file mode 100644 index d05a8143417..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-voc.map deleted file mode 100644 index e76a8ec86d1..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-voc.map +++ /dev/null @@ -1,486 +0,0 @@ -LHSName "ArabTeX-pashto-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -a e > a U+0626 -E e > U+0659 U+06CD -e e > U+0659 U+0626 -E > U+0659 U+06D0 -CO O > U+06FC ; -O > U+0657 w -o > U+0657 -a o > a w -CO U > U+06C7 ; -e > U+0659 -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+067C U+0651 ;;SHADDA -V t > U+067C ; pashto -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0693 U+0651 ;;SHADDA -V r > U+0693 ;Pashto -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix -U+0048 > U+0647 U+200C ; H is always heh final -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0689 U+0651 ;;SHADDA -V d > U+0689 ;pashto -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-voc.tec deleted file mode 100644 index aab09f97ec6..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-pashto-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-fullvoc.map deleted file mode 100644 index 8c9fbcc7722..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-fullvoc.map +++ /dev/null @@ -1,461 +0,0 @@ -LHSName "ArabTeX-sindhi-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - -;; special code for sindhi -;; U+004D U+0049 U+004E > U+06FE ; define macro \MIN in sindhi env -P m I N > U+06FE ; .mIN -;; U+0049 U+004E > U+06FD ; IN define macro \IN in sindhi env -H BAR I N > U+06FD ; '|IN - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t h V t h > U+067A U+0651 ;;SHADDA -V t h > U+067A -t h t h > U+067F U+0651 ;;SHADDA -t h > U+067F -V t V t > U+067D U+0651 ;;SHADDA -V t > U+067D -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0699 U+0651 ;;SHADDA -V r > U+0699 -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p h p h > U+06A6 U+0651 ;;SHADDA -p h > U+06A6 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+0683 U+0651 ;;SHADDA -C n > U+0683 -P P n P P n > U+06B2 U+0651 ;;SHADDA -P P n > U+06B2 ;; old sindhi? (not in ArabTeX) <<< -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BB U+0651 ;;SHADDA -V n > U+06BB -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -k h k h > U+06A9 U+0651 ;;SHADDA -k h > U+06A9 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+06AA U+0651 ;;SHADDA -k > U+06AA ; kaf swash -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE -P CO g P CO g > U+06B4 U+0651 ;;SHADDA -P CO g > U+06B4 ;; old sindhi? (not in ArabTeX) <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d h V d h > U+068D U+0651 ;;SHADDA -V d h > U+068D -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -d h d h > U+068C U+0651 ;;SHADDA -d h > U+068C -C d C d > U+068E ;;SHADDA -C d > U+068E ; old sindhi: not in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -C c h C c h > U+0687 U+0651 ;;SHADDA -C c h > U+0687 -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -b h b h > U+0680 U+0651 ;;SHADDA -b h > U+0680 -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-fullvoc.tec deleted file mode 100644 index 34b9a0e1d72..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-novoc.map deleted file mode 100644 index 4e03d67e8cf..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-novoc.map +++ /dev/null @@ -1,446 +0,0 @@ -LHSName "ArabTeX-sindhi-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - -;; special code for sindhi -;; U+004D U+0049 U+004E > U+06FE ; define macro \MIN in sindhi env -P m I N > U+06FE ; .mIN -;; U+0049 U+004E > U+06FD ; IN define macro \IN in sindhi env -H BAR I N > U+06FD ; '|IN - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -P I P I / _ # > U+06CC U+0651 ;; SHADDA -P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t h V t h > U+067A U+0651 ;;SHADDA -V t h > U+067A -t h t h > U+067F U+0651 ;;SHADDA -t h > U+067F -V t V t > U+067D U+0651 ;;SHADDA -V t > U+067D -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0699 U+0651 ;;SHADDA -V r > U+0699 -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p h p h > U+06A6 U+0651 ;;SHADDA -p h > U+06A6 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+0683 U+0651 ;;SHADDA -C n > U+0683 -P P n P P n > U+06B2 U+0651 ;;SHADDA -P P n > U+06B2 ;; old sindhi? (not in ArabTeX) <<< -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BB U+0651 ;;SHADDA -V n > U+06BB -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -k h k h > U+06A9 U+0651 ;;SHADDA -k h > U+06A9 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+06AA U+0651 ;;SHADDA -k > U+06AA ; kaf swash -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE -P CO g P CO g > U+06B4 U+0651 ;;SHADDA -P CO g > U+06B4 ;; old sindhi? (not in ArabTeX) <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d h V d h > U+068D U+0651 ;;SHADDA -V d h > U+068D -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -d h d h > U+068C U+0651 ;;SHADDA -d h > U+068C -C d C d > U+068E ;;SHADDA -C d > U+068E ; old sindhi: not in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -C c h C c h > U+0687 U+0651 ;;SHADDA -C c h > U+0687 -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -b h b h > U+0680 U+0651 ;;SHADDA -b h > U+0680 -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-novoc.tec deleted file mode 100644 index 6e8fc3767c1..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-voc.map deleted file mode 100644 index 7acfe951345..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-voc.map +++ /dev/null @@ -1,456 +0,0 @@ -LHSName "ArabTeX-sindhi-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - -;; special code for sindhi -;; U+004D U+0049 U+004E > U+06FE ; define macro \MIN in sindhi env -P m I N > U+06FE ; .mIN -;; U+0049 U+004E > U+06FD ; IN define macro \IN in sindhi env -H BAR I N > U+06FD ; '|IN - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t h V t h > U+067A U+0651 ;;SHADDA -V t h > U+067A -t h t h > U+067F U+0651 ;;SHADDA -t h > U+067F -V t V t > U+067D U+0651 ;;SHADDA -V t > U+067D -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0699 U+0651 ;;SHADDA -V r > U+0699 -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p h p h > U+06A6 U+0651 ;;SHADDA -p h > U+06A6 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+0683 U+0651 ;;SHADDA -C n > U+0683 -P P n P P n > U+06B2 U+0651 ;;SHADDA -P P n > U+06B2 ;; old sindhi? (not in ArabTeX) <<< -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BB U+0651 ;;SHADDA -V n > U+06BB -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -k h k h > U+06A9 U+0651 ;;SHADDA -k h > U+06A9 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+06AA U+0651 ;;SHADDA -k > U+06AA ; kaf swash -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE -P CO g P CO g > U+06B4 U+0651 ;;SHADDA -P CO g > U+06B4 ;; old sindhi? (not in ArabTeX) <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d h V d h > U+068D U+0651 ;;SHADDA -V d h > U+068D -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -d h d h > U+068C U+0651 ;;SHADDA -d h > U+068C -C d C d > U+068E ;;SHADDA -C d > U+068E ; old sindhi: not in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -C c h C c h > U+0687 U+0651 ;;SHADDA -C c h > U+0687 -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -b h b h > U+0680 U+0651 ;;SHADDA -b h > U+0680 -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-voc.tec deleted file mode 100644 index 7583ec76be2..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-sindhi-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-fullvoc.map deleted file mode 100644 index 62aa619b8e9..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-fullvoc.map +++ /dev/null @@ -1,485 +0,0 @@ -LHSName "ArabTeX-turk-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0636 U+0651 ;;SHADDA -V z > U+0636 -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+0634 U+0651 ;;SHADDA -V s > U+0634 -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+0642 U+0651 ;;SHADDA -P k > U+0642 ; Ottoman qaf -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+0698 U+0651 ;;SHADDA -j > U+0698 -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0686 U+0651 ;;SHADDA -V c > U+0686 ; Ottoman ç -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+062C U+0651 ;;SHADDA -c > U+062C -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-fullvoc.tec deleted file mode 100644 index 7182c9ccd7f..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-novoc.map deleted file mode 100644 index 824eab5c57d..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-novoc.map +++ /dev/null @@ -1,470 +0,0 @@ -LHSName "ArabTeX-turk-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0636 U+0651 ;;SHADDA -V z > U+0636 -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+0634 U+0651 ;;SHADDA -V s > U+0634 -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+0642 U+0651 ;;SHADDA -P k > U+0642 ; Ottoman qaf -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+0698 U+0651 ;;SHADDA -j > U+0698 -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0686 U+0651 ;;SHADDA -V c > U+0686 ; Ottoman ç -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+062C U+0651 ;;SHADDA -c > U+062C -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-novoc.tec deleted file mode 100644 index 95903a8c0ab..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-voc.map deleted file mode 100644 index 60c1d10e045..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-voc.map +++ /dev/null @@ -1,480 +0,0 @@ -LHSName "ArabTeX-turk-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0636 U+0651 ;;SHADDA -V z > U+0636 -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+0634 U+0651 ;;SHADDA -V s > U+0634 -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+0642 U+0651 ;;SHADDA -P k > U+0642 ; Ottoman qaf -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+06A0 U+0651 ;;SHADDA -C g > U+06A0 -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+0698 U+0651 ;;SHADDA -j > U+0698 -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0686 U+0651 ;;SHADDA -V c > U+0686 ; Ottoman ç -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+062C U+0651 ;;SHADDA -c > U+062C -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-voc.tec deleted file mode 100644 index bb08e4bfaae..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-turk-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-uighur.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-uighur.map deleted file mode 100644 index 2b3923d1e2a..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-uighur.map +++ /dev/null @@ -1,277 +0,0 @@ -LHSName "ArabTeX-Uighur" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define LLAH U+006C U+006C U+005F U+0061 U+0068 - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) - - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -(a|A) l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL)' -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE)' -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels - -a / # _ > U+0626 U+0627 -a > U+0627 -(CO a|U+00E4) / # _ > U+0626 U+0647 U+200C -(CO a|U+00E4) > U+0647 U+200C -o / # _ > U+0626 U+0648 ; -o > U+0648 ; -(CO o|U+00F6) / # _ > U+0626 U+06C6 -(CO o|U+00F6) > U+06C6 -i / # _ # > U+0626 U+0649 -i / # _ > U+0626 U+066E -i / _ # > U+0649 -i > U+066E -e / # _ > U+0626 U+06D0 -e > U+06D0 -u / # _ > U+0626 U+06C7 ; -u > U+06C7 ; -(CO u|U+00FC) / # _ > U+0626 U+06C8 ; -(CO u|U+00FC) > U+06C8 ; -l Q a > U+0644 U+064E U+0627 ; -l a > U+0644 U+0627 ; - -P z P z > U+0638 U+0651 ;;SHADDA -P z > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;pashto ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -w w > U+06CB U+0651 ;;SHADDA -w > U+06CB -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -V t V t > U+0679 U+0651 ; urdu ;;SHADDA -V t > U+0679 -UL t UL t > U+062B U+0651 ;;SHADDA -UL t > U+062B -P t P t > U+0637 U+0651 ;;SHADDA -P t > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -P s P s > U+0635 U+0651 ;;SHADDA -P s > U+0635 -V s V s > U+069A U+0651 ;Pashto ;;SHADDA -V s > U+069A ;Pashto -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+0692 U+0651 ;Kurdish ;;SHADDA ; missing in ArabTeX <<< -C r > U+0692 -P r P r > U+0695 U+0651 ;Kurdish ;;SHADDA -P r > U+0695 -V r V r > U+0691 U+0651 ;Urdu ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ; urdu ;;SHADDA -P n > U+06BA ; -V n V n > U+06BC U+0651 ; Pashto -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -C l C l > U+06B5 U+0651 ;kurdish ;;SHADDA -C l > U+06B5 -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ; pashto urdu ;;SHADDA -P k > U+06A9 -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -P h P h > U+062D U+0651 ;;SHADDA -P h > U+062D -V h V h > U+06C1 U+0651 -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -C g C g > U+063A U+0651 ;;SHADDA -C g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;pashto ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0688 U+0651 ;urdu ;;SHADDA -V d > U+0688 ;urdu -C d C d > U+06EE ; not defined in ArabTeX U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -UL d UL d > U+0630 U+0651 ;;SHADDA -UL d > U+0630 -P d P d > U+0636 U+0651 ;;SHADDA -P d > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;pashto ;;SHADDA -V c > U+0685 -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -c c > U+0681 U+0651 -c > U+0681 ; ح with hamza above -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H > U+0626 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / . _ . > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... -U+005B / . _ . > U+200D U+005B U+200D ; ... (but of course this screws up contextual analysis, so quoting of hamzas etc may be necessary) -Q > ; -N > ; -C > ;^ -Z > ;- -BAR > ;| - - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-uighur.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-uighur.tec deleted file mode 100644 index be1845fa6e6..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-uighur.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-fullvoc.map deleted file mode 100644 index 6dcb6cec050..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-fullvoc.map +++ /dev/null @@ -1,499 +0,0 @@ -LHSName "ArabTeX-urdu-fullvocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -H E > U+06D3 ;; hamza + yeh barree -E / _ # > U+06D2 -E > y -a e / _ # > a U+06D2 -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 > U+06C3 -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -H H > U+06C1 U+0651 ;;SHADDA -H > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE ; urdu -;; fix letter+h letter+h > letter+h shadda in URDU <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0688 U+0651 ;;SHADDA -V d > U+0688 ;urdu -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -CO CO d CO CO d > U+0690 U+0651 ;;SHADDA -CO CO d > U+0690 ; old urdu: not in ArabTeX -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| -P P > U+06D4 ; urdu full stop << check - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda -U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs -U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha -[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) -;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant -Q > ; -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-fullvoc.tec deleted file mode 100644 index 1eeca763f5f..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-fullvoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-novoc.map deleted file mode 100644 index e606cd8bcce..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-novoc.map +++ /dev/null @@ -1,484 +0,0 @@ -LHSName "ArabTeX-urdu-novowels" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode -CO O > U+06FC ; -H E > U+06D3 ;; hamza + yeh barree -E / _ # > U+06D2 -E > y -a e / _ # > a U+06D2 -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0627 ; -[VWL]=v1 / BEG _ > A @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > A @q1 u w ; -U -; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! -Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m Q i A Hy Q a -m Q i H a / _ (T|t) > m Q i A Hy -m i H Q a / _ (T|t) > m A Hy Q a -m i H a / _ (T|t) > m A Hy - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Y Y > U+0649 U+0651 ;;SHADDA -Y > U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -Q U > U+064F U+0648 -[Uw] [Uw] > U+0648 U+0651 ;;SHADDA -[Uw] > U+0648 -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -Q u N > U+064C -u N > -Q u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 U+064B ;;SHADDA -T Q AN > U+0629 U+064B -T AN > U+0629 -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -I > U+064A -Q i N > U+064D -i N > ; -Q i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 > U+06C3 -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -H H > U+06C1 U+0651 ;;SHADDA -H > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE ; urdu -;; fix letter+h letter+h > letter+h shadda in URDU <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0688 U+0651 ;;SHADDA -V d > U+0688 ;urdu -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -CO CO d CO CO d > U+0690 U+0651 ;;SHADDA -CO CO d > U+0690 ; old urdu: not in ArabTeX -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+0649 -UL a > U+0670 -UL u > ; -UL i > ; -Q AN / (A H|Ha) _ > U+064B -AN / (A H|Ha) _ > ; -Q AN > U+0627 U+064B -AN > U+0627 -Q a > U+064E -Q A > U+064E U+0627 -A > U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -[VWL] > ;stripoff vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -Z > ;- -BAR > ;| -P P > U+06D4 ; urdu full stop << check - diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-novoc.tec deleted file mode 100644 index 91e99f0c3d7..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-novoc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-voc.map deleted file mode 100644 index 0a6c00808a0..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-voc.map +++ /dev/null @@ -1,494 +0,0 @@ -LHSName "ArabTeX-urdu-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -H E > U+06D3 ;; hamza + yeh barree -E / _ # > U+06D2 -E > y -a e / _ # > a U+06D2 -a e > a y -a o > a w -(o|u)? O / # _ > U+0627 w -(o|u)? O > w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -I / _ # > i y - - -;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) -U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< -U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I -Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e -Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I -Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i -Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i -Z / U+0048 _ > U+0020 ; -b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > HA ;; ADD MORE ? <<< -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots -y y > U+06CC U+0651 ;;SHADDA -y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -U+0048 > U+06C3 -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -H H > U+06C1 U+0651 ;;SHADDA -H > U+06C1 -h h > U+06BE U+0651 ;;SHADDA -h > U+06BE ; urdu -;; fix letter+h letter+h > letter+h shadda in URDU <<< -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+0688 U+0651 ;;SHADDA -V d > U+0688 ;urdu -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -CO CO d CO CO d > U+0690 U+0651 ;;SHADDA -CO CO d > U+0690 ; old urdu: not in ArabTeX -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+064F; -UL i > U+0650; -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArEasternDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| -P P > U+06D4 ; urdu full stop << check - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-voc.tec deleted file mode 100644 index bf93543e3fb..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-urdu-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-voc.map deleted file mode 100644 index 2555ba6e924..00000000000 --- a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-voc.map +++ /dev/null @@ -1,476 +0,0 @@ -LHSName "ArabTeX-vocalized" -RHSName "UNICODE" - -Define a U+0061 ;a -Define b U+0062 ;b -Define c U+0063 ;c -Define d U+0064 ;d -Define e U+0065 ;e -Define f U+0066 ;f -Define g U+0067 ;g -Define h U+0068 ;h -Define i U+0069 ;i -Define j U+006A ;j -Define k U+006B ;k -Define l U+006C ;l -Define m U+006D ;m -Define n U+006E ;n -Define o U+006F ;o -Define p U+0070 ;p -Define q U+0071 ;q -Define r U+0072 ;r -Define s U+0073 ;s -Define t U+0074 ;t -Define u U+0075 ;u -Define v U+0076 ;v -Define w U+0077 ;w -Define x U+0078 ;x -Define y U+0079 ;y -Define z U+007A ;z -Define A U+0041 ;A -Define B U+0042 ;B -Define E U+0045 ;E -Define G U+0047 ;G -Define I U+0049 ;I -Define N U+004E ;N -Define O U+004F ;O -Define T U+0054 ;T -Define U U+0055 ;U -Define W U+0057 ;W -Define Y U+0059 ;Y -Define C U+005E ;^ << CARET -Define UL U+005F ;_ << UNDERLINE -Define P U+002E ;. << DOT -Define V U+002C ;, << COMMA (_V_irgule) -Define CO U+003A ;: << COLON -Define SC U+003B ;; << SEMICOLON -Define Ain U+0060 ;` -Define H U+0027 ;' << HAMZA -Define Q U+0022 ;" << QUOTE -Define Z U+002D ;- << HYPHEN -Define BAR U+007C ;| -Define AN U+0061 U+004E ; aN -Define LLAH U+006C U+006C U+005F U+0061 U+0068 -;Define NUL U+00A6; -Define Ha U+0623 -Define Hi U+0625 -Define Hy U+0626 -Define Hw U+0624 -Define Hh U+06C0 ;; = U+0647 U+0654 -Define HA U+0622 -Define HB U+0640 U+0654 -Define HBAR U+0621 ; '| - -pass(Unicode) - -U+E000 > ; eliminate special code for capitalization in transliterations - -pass(Unicode) - -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [AVWL] = (U+064B..U+0650); -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` -Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” -Class [PUNCT] = (V SC P CO) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) -Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) -;Class [ae] = (U+0061 U+0065) ;(a e) -;Class [ou] = (U+0075 U+006F) ;(u o) -Class [Iyi] = (U+0069 U+0079 U+0049) -Class [UI] = (U+0049 U+0055) ; U I -Class [Digits] = (U+0030..U+0039) - -Define BEG (#|Z|[BRACKETS]) -Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) -Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) - -; special ligatures -;; 1. Standard ArabTeX input -;; WARNING! there are, alas, two classes of Arabic fonts: -;; a) Those that are Unicode-compliant and include the initial alif in glyph U+FDF2 -;; For these the ligature llah can be accessed by the sequence lam-lam-ha -;; b) Those that do not have the initial alif in U+FDF2 -;; The BAR is used in the DMG transliteration to suppress the initial A -(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' -LLAH > U+FDF2 ;; 'll_ah' > U+FDF2 -;; UPPERCASE mnemonics for various ligatures or special glyphs -;; 2a. custom ArabXeTeX input for ligatures not defined in Unicode -U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' -U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' : ligature in Adobe Arabic -;; 2b. Ligatures and glyphs defined in Unicode: - U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+FDF2 ; 'ALLAH' - U+004C U+004C U+0041 U+0048 > U+FDF2 ; 'LLAH' - -U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam -U+0028 U+0028 > U+FD3F ;; '((' : ornate right par -U+0029 U+0029 > U+FD3E ;; '))' : ornate left par -U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign -;; most fonts won't have the following ones: -U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) -U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign -U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' -U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' -U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' -U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') -U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') -U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' -U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' -U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" -U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik - -U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY -U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY -U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- -U+005E U+004C U+0041 > U+06D9 ;; ^LA -U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM -U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS -U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN -U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB -U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO -U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO -U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM -U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM -U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN -U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA -U+0057 U+0041 U+0057 > U+06E5 ;; WAW -U+0059 U+0045 U+0048 > U+06E6 ;; YEH -U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH -U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN -U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA -U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP -U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP -U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP -U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM - -U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") - -;; This is to enclose digits within glyph U+06DD, see http://scripts.sil.org/cms/scripts/page.php?site_id=nrsi&item_id=ArabicFonts -U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+202E U+06DD @dig U+202C ; [[digits]] - - -; vowels -u u > U -i i > I -a a > A -CO O > U+06FC ; -a e > a y -a o > a w -CO U > U+06C7 ; -e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) -o > u -E > I -O > U - - - -;; initial characters ... -a l Z / BEG _ > U+0627 l Z -H l Z / BEG _ > U+0627 l Z -;; wasla on initial alif : NEW! NOT TESTED! -H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI -[VWL]=v1 / BEG _ > U+0627 @v1 -A / BEG _ > U+0627 a -Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U -; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I -Q?=q1 I / BEG _ > U+0627 @q1 i y - - -;; Words with anomalous orthography: - -; mi'aT -> ماية -;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy -m Q i H Q a / _ (T|t) > m U+0627 Hy -m Q i H a / _ (T|t) > m U+0627 Hy a -m i H Q a / _ (T|t) > m i U+0627 Hy -m i H a / _ (T|t) > m i U+0627 Hy a - - -;; contextual analysis of hamzas -;; THESE DO NOT APPLY FOR SINDHI - -; initial hamzas -H / (#|^[LTR]) _ Q? [Iyi] > Hi -H Q A / (#|^[LTR]) _ > HA ; alif madda -H / (#|^[LTR]) _ Q? [Uwu] > Ha -H / (#|^[LTR]) _ Q? a > Ha -Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word - -; quoted hamzas in contextual mode, equivalent to verbatim mode -a Q H > Ha -i Q H > Hi -y Q H > Hy -w Q H > Hw -h Q H > Hh -A Q H > HA -B Q H > HB -BAR Q H > HBAR - -; hamza + fathatan -H / a _ Q? AN > Ha -;;H / [Iyi] _ Q? AN > Hy -H / _ Q? AN > Hy - -;final hamzas -H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR -H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... -H / a _ Q? (#|^[LTR]) > Ha ; not AN... -H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... -H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy -H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw - -;;and more hamzas ... - -; n°1: kasra/ya -H / [LTR] _ Q? [Iyi] ^N > Hy -H / [Iyi] _ > Hy - -; n°2: damma/waw -H / [LTR] _ Q? (U|u) ^N > Hw -H / (U|u) _ Q? ^[Iyi] > Hw -H / U _ > HBAR - -; n°3: fatha/alif -H Q? A > HA -H / A _ Q? a > HBAR -H / ^[UI] _ Q? a > Ha -H / a _ Q? ^[UI] > Ha - - -pass(Unicode) - -Class [Digits] = (U+0030..U+0039) -Class [ArDigits] = (U+0660..U+0669) -Class [ArEasternDigits] = (U+06F0..U+06F9) -Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) -Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) -Class [Iy] = (U+0049 U+0079) ;(I y) -Class [Uw] = (U+0055 U+0077) ;(U w) - - - - -;normal code - - -(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA -(P z|U+1E93) > U+0638 -C z C z > U+0698 U+0651 ;;SHADDA -C z > U+0698 -V z V z > U+0696 U+0651 ;;SHADDA -V z > U+0696 ;pashto -z z > U+0632 U+0651 ;;SHADDA -z > U+0632 -Q Y Y > U+0649 U+0651 ;;SHADDA -Q Y > U+0649 -Y Y > U+064E U+0649 U+0651 ;;SHADDA -Y > U+064E U+0649 -P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA -P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic -y y > U+064A U+0651 ;;SHADDA -y > U+064A -v v > U+06A4 U+0651 ;;SHADDA -v > U+06A4 -W > U+0648 U+0627 ; waw + alif -C U > U+064F U+0648 U+0653; historical spelling : madda on waw -C w C w > U+06C9 U+0651 ;;SHADDA -C w > U+06C9 -CO w CO w > U+06CA U+0651 ;,SHADDA -CO w > U+06CA -U A / _ # > U+064F U+0648 U+0627 -Q U [Uw] > U+0648 U+0651 ;;SHADDA -Q U > U+0648 -U [Uw] > U+064F U+0648 U+0651 ;;SHADDA -U > U+064F U+0648 -w w > U+0648 U+0651 ;;SHADDA -w > U+0648 -Q u N? > -u N > U+064C -u > U+064F -V t V t > U+0679 U+0651 ;;SHADDA -V t > U+0679 ;urdu -UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA -UL (t|s) > U+062B -(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA -(P t|U+1E6D) > U+0637 -t t > U+062A U+0651 ;;SHADDA -t > U+062A -T T Q AN > U+0629 U+0651 ;;SHADDA -T Q AN > U+0629 -T AN > U+0629 U+064B -T T > U+0629 U+0651 ;;SHADDA -T > U+0629 -C s C s > U+0634 U+0651 ;;SHADDA -C s > U+0634 -(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA -(P s|U+1E63) > U+0635 -V s V s > U+069A U+0651 ;;SHADDA -V s > U+069A ;Pashto -CO s CO s > U+069B U+0651 ;;SHADDA -CO s > U+069B ; sin with 3 dots below -s s > U+0633 U+0651 ;;SHADDA -s > U+0633 -C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< -C r > U+06EF -CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< -CO r > U+0697 ; Dargwa language, Dagestan -P r P r > U+0694 U+0651 ;;SHADDA -P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 -V r V r > U+0691 U+0651 ;;SHADDA -V r > U+0691 ;Urdu -r r > U+0631 U+0651 ;;SHADDA -r > U+0631 -P q P q > U+066F U+0651 ;;SHADDA -P q > U+066F -q q > U+0642 U+0651 ;;SHADDA -q > U+0642 -p p > U+067E U+0651 ;;SHADDA -p > U+067E -CO n CO n > U+06B1 U+0651 ;;SHADDA -CO n > U+06B1 -C n C n > U+06AD U+0651 ;;SHADDA -C n > U+06AD -P n P n > U+06BA U+0651 ;;SHADDA -P n > U+06BA ; urdu -V n V n > U+06BC U+0651 ;;SHADDA -V n > U+06BC ; Pashto -n n > U+0646 U+0651 ;;SHADDA -n > U+0646 -m m > U+0645 U+0651 ;;SHADDA -m > U+0645 -P l P l > U+06B6 U+0651 ; -P l > U+06B6 ; ADDED <<< -C l C l > U+06B5 U+0651 ;;SHADDA -C l > U+06B5 ;kurdish -l l > U+0644 U+0651 ;;SHADDA -l > U+0644 -P k P k > U+06A9 U+0651 ;;SHADDA -P k > U+06A9 ; pashto urdu -UL k UL k > U+063A U+0651 ;;SHADDA -UL k > U+063A -k k > U+0643 U+0651 ;;SHADDA -k > U+0643 -C g C g > U+062C U+0651 ;;SHADDA -C g > U+062C -CO j CO j > U+0684 U+0651 ;;SHADDA -CO j > U+0684 -j j > U+062C U+0651 ;;SHADDA -j > U+062C -Q I > U+064A -I > U+0650 U+064A -C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya -UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### -Q i N? > ; -i N > U+064D -i > U+0650 -x x > U+062E U+0651 ;;SHADDA -x > U+062E -UL h UL h > U+062E U+0651 ;;SHADDA -UL h > U+062E -(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA -(P h|U+1E25) > U+062D -V h V h > U+06C1 U+0651 ;;SHADDA -V h > U+06C1 -h h > U+0647 U+0651 ;;SHADDA -h > U+0647 -CO g CO g > U+06B3 U+0651 ;;SHADDA -CO g > U+06B3 -V g V g > U+06AC U+0651 ;;SHADDA -V g > U+06AC ; kaf with dot above -P g P g > U+063A U+0651 ;;SHADDA -P g > U+063A -g g > U+06AF U+0651 ;;SHADDA -g > U+06AF -G G > U+06AB U+0651 ;;SHADDA -G > U+06AB ;pashto -P f P f > U+06A1 U+0651 ;;SHADDA -P f > U+06A1 -f f > U+0641 U+0651 ;;SHADDA -f > U+0641 -V d V d > U+068A U+0651 ;;SHADDA -V d > U+068A -P V d P V d > U+068B U+0651 ;;SHADDA -P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) -C d C d > U+06EE U+0651 ;;SHADDA -C d > U+06EE ; not defined in ArabTeX -CO d CO d > U+068F U+0651 ;;SHADDA -CO d > U+068F -UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA -UL (d|z) > U+0630 -(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA -(P d|U+1E0D) > U+0636 -d d > U+062F U+0651 ;;SHADDA -d > U+062F -V c V c > U+0685 U+0651 ;;SHADDA -V c > U+0685 ;pashto -C c C c > U+0686 U+0651 ;;SHADDA -C c > U+0686 -P C c P C c > U+06BF U+0651 ;;SHADDA -P C c > U+06BF ;; cheh with dot above <<< -c c > U+0681 U+0651 ;;SHADDA -c > U+0681 ; ح with hamza above -CO c CO c > U+0682 U+0651 ;;SHADDA -CO c > U+0682 ; old pashto -CO b CO b > U+067B U+0651 ;;SHADDA -CO b > U+067B -P b P b > U+066E U+0651 ;;SHADDA -P b > U+066E -b b > U+0628 U+0651 ;;SHADDA -b > U+0628 -H A > U+0622 -C A > U+064E U+0622 ; historical spelling -UL A > U+064E U+0649 -UL a > U+0670 -UL u > U+0657 ; inverted damma -UL i > U+0656 ; subscript alif -Q AN / (A H|Ha) _ > ; -AN / (A H|Ha) _ > U+064B -Q AN > U+0627 -AN > U+0627 U+064B -Q a > -a > U+064E -Q A > U+0627 -A > U+064E U+0627 -Ain Ain > U+0639 U+0651 ;;SHADDA -Ain > U+0639 -H H > U+0621 U+0651 ;;SHADDA -H > U+0621 -U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma -Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash -(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks -[Digits] > [ArDigits] -Z Z Z / # _ # > U+2014 -Z Z / # _ # > U+2013 -Z Z > U+0640 -B > U+0640 -Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" -Z / _ # > U+200D ; x- > force final form -U+003C U+003C > U+00BB ;<< -U+003E U+003E > U+00AB ;>> -U+00AB > U+00BB -U+00BB > U+00AB -UL > U+0640 ;_ -U+003F > U+061F ;? -U+003B > U+061B ;; -U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... -U+002C > U+060C ;, -U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... -U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual - ; analysis, so quoting of hamzas etc may be necessary -;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules -;U+005B > U+005D ;[ -Q [VWL] > ;stripoff quoted vowels -Q > U+0652 -U+00B0 > U+0652 ; ° -N > ; -C > ;^ -BAR > ;| - -pass(Unicode) - -Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) -Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. -Class [VWL] = (U+0627 U+0648..U+0650 U+0670); -U+0627 [VWL]? / [VWL] Z _ > U+0627 ; e.g. fa-isti_hraj -> initial alif has no vowel -Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-voc.tec deleted file mode 100644 index cc89d2fea85..00000000000 Binary files a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fdf2noalif-voc.tec and /dev/null differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fullvoc.map new file mode 100644 index 00000000000..23db35b5cde --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fullvoc.map @@ -0,0 +1,479 @@ +LHSName "ArabTeX-fullvocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +Z (a|A) l Z LLAH > U+0671 U+FDF2 ;; '-al-ll_ah' or '-Al-ll_ah' +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +E > I +O > U + + + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +H l Z / BEG _ > U+0671 l Z ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so min al- must be written mina 'l- in fullvocalize mode +;; wasla on initial alif : NEW! NOT TESTED! +[VWL]=v1 Z / BEG _ > @v1 U+0671 ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so huwa irtifA` must be written huwa i-rtifA` in fullvocalize mode +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +A / BEG _ > U+0627 a +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA +P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+0657 ; inverted damma +UL i > U+0656 ; subscript alif +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda +U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs +U+0627 [VWL]? / [VWL] Z _ > U+0671 ; e.g. fa-isti_hraj -> wasla on initial alif +U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha +[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) +;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant +U+FDF2 > U+0644 U+0644 U+0647 ; +Q > ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fullvoc.tec new file mode 100644 index 00000000000..21184d712da Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-fullvoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-fullvoc.map new file mode 100644 index 00000000000..2aba8b33124 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-fullvoc.map @@ -0,0 +1,509 @@ +LHSName "ArabTeX-kashmiri-fullvocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e / # _ # > U+0627 U+06D2 U+0658 ; Alif + yeh barree + bow accent +e / _ # > U+06D2 U+0658 ; yeh barree + bow accent +e / # _ > U+0627 y U+0658 ; alif + ya + bow accent +e > y U+0658 +E / # _ # > U+0627 U+06D2 ; Alif + yeh barree +E / _ # > U+06D2 ; yeh barree +E / # _ > U+0627 y ; alif + ya +E > y +o / # _ > U+0627 U+06C6 +o > U+06C6 +P A > U+0672 +P U > U+0673 ; > this is the initial or lone form, but medial and final require wavy hamza below previous letter (not in Unicode)! Perhaps an OT font could solve this :: in Scheherazade the glyph needed is named _wavyHamza <<< +P a / # _ > U+0623 +P a > U+0654 +P u > U+0655 +P o / # _ > U+0627 U+06C4 +P o > U+06C4 +P O / # _ > U+0627 U+06C4 U+0627 U+064E +P O > U+06C4 U+0627 U+064E +I > y U+0656 +I / _ # > y +U / _ # > U+0627 w U+0657 +U > w U+0657 + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +CO z CO z > U+0636 U+0651 ;;SHADDA +CO z > U+0636 +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +;; .b with ring below : FIXME not in Unicode! but U+06EA is a poor replacement: +P y / # _ # > U+0627 U+06D2 U+06EA +P y / _ # > U+0649 +P y > U+066E U+06EA +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda +U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs +U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha +[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) +;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant +U+FDF2 > U+0644 U+0644 U+0647 ; +Q > ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-fullvoc.tec new file mode 100644 index 00000000000..9a4872303df Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-fullvoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-novoc.map new file mode 100644 index 00000000000..587599eae51 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-novoc.map @@ -0,0 +1,494 @@ +LHSName "ArabTeX-kashmiri-novowels" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode +CO O > U+06FC ; +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e / # _ # > U+0627 U+06D2 U+0658 ; Alif + yeh barree + bow accent +e / _ # > U+06D2 U+0658 ; yeh barree + bow accent +e / # _ > U+0627 y U+0658 ; alif + ya + bow accent +e > y U+0658 +E / # _ # > U+0627 U+06D2 ; Alif + yeh barree +E / _ # > U+06D2 ; yeh barree +E / # _ > U+0627 y ; alif + ya +E > y +o / # _ > U+0627 U+06C6 +o > U+06C6 +P A > U+0672 +P U > U+0673 ; > this is the initial or lone form, but medial and final require wavy hamza below previous letter (not in Unicode)! Perhaps an OT font could solve this :: in Scheherazade the glyph needed is named _wavyHamza <<< +P a / # _ > U+0623 +P a > U+0654 +P u > U+0655 +P o / # _ > U+0627 U+06C4 +P o > U+06C4 +P O / # _ > U+0627 U+06C4 U+0627 U+064E +P O > U+06C4 U+0627 U+064E +I > y U+0656 +I / _ # > y +U / _ # > U+0627 w U+0657 +U > w U+0657 + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0627 ; +[VWL]=v1 / BEG _ > A @v1 +Q?=q1 U / BEG _ > A @q1 u w ; -U +; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! +Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m Q i A Hy Q a +m Q i H a / _ (T|t) > m Q i A Hy +m i H Q a / _ (T|t) > m A Hy Q a +m i H a / _ (T|t) > m A Hy + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +CO z CO z > U+0636 U+0651 ;;SHADDA +CO z > U+0636 +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Y Y > U+0649 U+0651 ;;SHADDA +Y > U+0649 +;; .b with ring below : FIXME not in Unicode! but U+06EA is a poor replacement: +P y / # _ # > U+0627 U+06D2 U+06EA +P y / _ # > U+0649 +P y > U+066E U+06EA +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +Q U > U+064F U+0648 +[Uw] [Uw] > U+0648 U+0651 ;;SHADDA +[Uw] > U+0648 +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +Q u N > U+064C +u N > +Q u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 U+064B ;;SHADDA +T Q AN > U+0629 U+064B +T AN > U+0629 +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +I > U+064A +Q i N > U+064D +i N > ; +Q i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+0649 +UL a > U+0670 +UL u > ; +UL i > ; +Q AN / (A H|Ha) _ > U+064B +AN / (A H|Ha) _ > ; +Q AN > U+064B U+0627 +AN > U+0627 +Q a > U+064E +Q A > U+064E U+0627 +A > U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +[VWL] > ;stripoff vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +Z > ;- +BAR > ;| + +U+FDF2 > U+0644 U+0644 U+0647 ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-novoc.tec new file mode 100644 index 00000000000..7e85abcae5d Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-novoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-voc.map new file mode 100644 index 00000000000..d4421023a9a --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-voc.map @@ -0,0 +1,504 @@ +LHSName "ArabTeX-kashmiri-vocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e / # _ # > U+0627 U+06D2 U+0658 ; Alif + yeh barree + bow accent +e / _ # > U+06D2 U+0658 ; yeh barree + bow accent +e / # _ > U+0627 y U+0658 ; alif + ya + bow accent +e > y U+0658 +E / # _ # > U+0627 U+06D2 ; Alif + yeh barree +E / _ # > U+06D2 ; yeh barree +E / # _ > U+0627 y ; alif + ya +E > y +o / # _ > U+0627 U+06C6 +o > U+06C6 +P A > U+0672 +P U > U+0673 ; > this is the initial or lone form, but medial and final require wavy hamza below previous letter (not in Unicode)! Perhaps an OT font could solve this :: in Scheherazade the glyph needed is named _wavyHamza <<< +P a / # _ > U+0623 +P a > U+0654 +P u > U+0655 +P o / # _ > U+0627 U+06C4 +P o > U+06C4 +P O / # _ > U+0627 U+06C4 U+0627 U+064E +P O > U+06C4 U+0627 U+064E +I > y U+0656 +I / _ # > y +U / _ # > U+0627 w U+0657 +U > w U+0657 + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +CO z CO z > U+0636 U+0651 ;;SHADDA +CO z > U+0636 +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +;; .b with ring below : FIXME not in Unicode! but U+06EA is a poor replacement: +P y / # _ # > U+0627 U+06D2 U+06EA +P y / _ # > U+0649 +P y > U+066E U+06EA +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +U+FDF2 > U+0644 U+0644 U+0647 ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-voc.tec new file mode 100644 index 00000000000..8aca4e5cd70 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kashmiri-voc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kurdish.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kurdish.map new file mode 100644 index 00000000000..7e15a75cd4c --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kurdish.map @@ -0,0 +1,284 @@ +LHSName "ArabTeX-Kurdish" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define LLAH U+006C U+006C U+005F U+0061 U+0068 + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) + + +; special ligatures +;; 1. Standard ArabTeX input +(a|A) l Z LLAH > U+0627 U+0644 U+0644 U+0647 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL)' +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE)' +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels + +E / # _ > U+0626 U+06CE +E > U+06CE +e / # _ > U+0626 U+0647 U+200C ; h always final +e > U+0647 U+200C +i / # _ > U+0626 +Q i > U+0650 +i > ; +Q I / # _ > U+0626 U+064A U+0650 +Q I > U+064A U+0650 +I / # _ > U+0626 U+064A +I > U+064A +(a|A) / # _ > U+0626 U+0627 +(a|A) > U+0627 +(o|O) / # _ > U+0626 U+06C6 +(o|O) > U+06C6 +u / # _ > U+0626 U+0648 +u > U+0648 +U / # _ > U+0626 U+0648 U+0648 +U > U+0648 U+0648 +Ain e > U+0639 U+0647 U+200C + + +P z P z > U+0638 U+0651 ;;SHADDA +P z > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;pashto ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Y Y > U+0649 U+0651 ;;SHADDA +Y > U+0649 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +V t V t > U+0679 U+0651 ; urdu ;;SHADDA +V t > U+0679 +UL t UL t > U+062B U+0651 ;;SHADDA +UL t > U+062B +P t P t > U+0637 U+0651 ;;SHADDA +P t > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +(C|V) s (C|V) s > U+0634 U+0651 ;;SHADDA +(C|V) s > U+0634 +P s P s > U+0635 U+0651 ;;SHADDA +P s > U+0635 +CO s CO s > U+069B U+0651 +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +;; also missing U+0694 : r with dot below +V r V r > U+0694 U+0651 ;Kurdish ;;SHADDA +V r > U+0694 +C r C r > U+0692 U+0651 ;Kurdish ;;SHADDA ; missing in ArabTeX <<< +C r > U+0692 +P r P r > U+0695 U+0651 ;Kurdish ;;SHADDA +P r > U+0695 +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ; urdu ;;SHADDA +P n > U+06BA ; +V n V n > U+06BC U+0651 ; Pashto +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;kurdish ;;SHADDA +C l > U+06B5 +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ; pashto urdu ;;SHADDA +P k > U+06A9 +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +c c > U+062C U+0651 ;;SHADDA +c > U+062C +x x > U+062E U+0651 ;;SHADDA +x > U+062E +j j > U+0698 U+0651 ;;SHADDA +j > U+0698 +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +P h P h > U+062D U+0651 ;;SHADDA +P h > U+062D +V h V h > U+06C1 U+0651 +V h > U+06C1 +h h > U+200C U+06BE U+0651 ;;SHADDA +h > U+200C U+06BE ; h always initial form +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P (g|x) P (g|x) > U+063A U+0651 ;;SHADDA +P (g|x) > U+063A +C g C g > U+063A U+0651 ;;SHADDA +C g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;pashto ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+0688 U+0651 ;urdu ;;SHADDA +V d > U+0688 ;urdu +C d C d > U+06EE ; not defined in ArabTeX U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +UL d UL d > U+0630 U+0651 ;;SHADDA +UL d > U+0630 +P d P d > U+0636 U+0651 ;;SHADDA +P d > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +(C|V) c (C|V) c > U+0686 U+0651 ;;SHADDA +(C|V) c > U+0686 +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H > U+0626 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / . _ . > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... +U+005B / . _ . > U+200D U+005B U+200D ; ... (but of course this screws up contextual analysis, so quoting of hamzas etc may be necessary) +Q > ; +N > ; +C > ;^ +Z > ;- +BAR > ;| + + diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kurdish.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kurdish.tec new file mode 100644 index 00000000000..a770e1f6ca7 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-kurdish.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-fullvoc.map new file mode 100644 index 00000000000..3b2f8526795 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-fullvoc.map @@ -0,0 +1,479 @@ +LHSName "ArabTeX-maghribi-fullvocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +Z (a|A) l Z LLAH > U+0671 U+FDF2 ;; '-al-ll_ah' or '-Al-ll_ah' +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +E > I +O > U + + + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +H l Z / BEG _ > U+0671 l Z ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so min al- must be written mina 'l- in fullvocalize mode +;; wasla on initial alif : NEW! NOT TESTED! +[VWL]=v1 Z / BEG _ > @v1 U+0671 ; THIS IS NOT AN ARABTEX CONVENTION! it's a work-around coz pattern-matching across word boundaries does not work in teckit , so huwa irtifA` must be written huwa i-rtifA` in fullvocalize mode +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +A / BEG _ > U+0627 a +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA +P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06A5 U+0651 ;;SHADDA +v > U+06A5 ;; maghribi +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+06A7 U+0651 ;; maghribi +q > U+06A7 ;; maghribi +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+06A2 U+0651 ;; SHADDA +f > U+06A2 ;; maghribi +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+0657 ; inverted damma +UL i > U+0656 ; subscript alif +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda +U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs +U+0627 [VWL]? / [VWL] Z _ > U+0671 ; e.g. fa-isti_hraj -> wasla on initial alif +U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha +[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) +;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant +U+FDF2 > U+0644 U+0644 U+0647 ; +Q > ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-fullvoc.tec new file mode 100644 index 00000000000..2c47861c6b5 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-fullvoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-novoc.map new file mode 100644 index 00000000000..51d496cbcb7 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-novoc.map @@ -0,0 +1,461 @@ +LHSName "ArabTeX-maghribi-novowels" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +E > I +O > U + + + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +H l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0627 ; +[VWL]=v1 / BEG _ > A @v1 +A / BEG _ > A a +Q?=q1 U / BEG _ > A @q1 u w ; -U +; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! +Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m Q i A Hy Q a +m Q i H a / _ (T|t) > m Q i A Hy +m i H Q a / _ (T|t) > m A Hy Q a +m i H a / _ (T|t) > m A Hy + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Y Y > U+0649 U+0651 ;;SHADDA +Y > U+0649 +P I P I / _ # > U+06CC U+0651 ;; SHADDA +P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06A5 U+0651 ;;SHADDA +v > U+06A5 ;; maghribi +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +Q U > U+064F U+0648 +[Uw] [Uw] > U+0648 U+0651 ;;SHADDA +[Uw] > U+0648 +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +Q u N > U+064C +u N > +Q u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 U+064B ;;SHADDA +T Q AN > U+0629 U+064B +T AN > U+0629 +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+06A7 U+0651 ;; maghribi +q > U+06A7 ;; maghribi +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +I > U+064A +Q i N > U+064D +i N > ; +Q i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+06A2 U+0651 ;; SHADDA +f > U+06A2 ;; maghribi +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+0649 +UL a > U+0670 +UL u > U+0657 ; inverted damma +UL i > U+0656 ; subscript alif +Q AN / (A H|Ha) _ > U+064B +AN / (A H|Ha) _ > ; +Q AN > U+064B U+0627 +AN > U+0627 +Q a > U+064E +Q A > U+064E U+0627 +A > U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +[VWL] > ;stripoff vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +Z > ;- +BAR > ;| + +U+FDF2 > U+0644 U+0644 U+0647 ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-novoc.tec new file mode 100644 index 00000000000..762fffbb975 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-novoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-voc.map new file mode 100644 index 00000000000..313c6646023 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-voc.map @@ -0,0 +1,472 @@ +LHSName "ArabTeX-maghribi-vocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +E > I +O > U + + + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +H l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +A / BEG _ > U+0627 a +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA +P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06A5 U+0651 ;;SHADDA +v > U+06A5 ;; maghribi +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+06A7 U+0651 ;; maghribi +q > U+06A7 ;; maghribi +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+06A2 U+0651 ;; SHADDA +f > U+06A2 ;; maghribi +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+0657 ; inverted damma +UL i > U+0656 ; subscript alif +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +U+0627 [VWL]? / [VWL] Z _ > U+0627 ; e.g. fa-isti_hraj -> initial alif has no vowel +U+FDF2 > U+0644 U+0644 U+0647 ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-voc.tec new file mode 100644 index 00000000000..3b3356de03d Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-maghribi-voc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-fullvoc.map new file mode 100644 index 00000000000..2dc9728dac9 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-fullvoc.map @@ -0,0 +1,481 @@ +LHSName "ArabTeX-malay-fullvocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA +P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06CF U+0651 ;;SHADDA +v > U+06CF +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+06A8 U+0651 ;;SHADDA +p > U+06A8 ;Old malay +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06BD U+0651 ;;SHADDA +C n > U+06BD ; <<< ArabTeX yields nūn with three dots below, which is not in Unicode! +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+06A0 U+0651 ;;SHADDA +C g > U+06A0 +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+0762 U+0651 ;;SHADDA +g > U+0762 +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0686 U+0651 ;;SHADDA +c > U+0686 +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda +U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs +U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha +[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) +;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant +U+FDF2 > U+0644 U+0644 U+0647 ; +Q > ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-fullvoc.tec new file mode 100644 index 00000000000..35e99304173 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-fullvoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-novoc.map new file mode 100644 index 00000000000..6566602c1a8 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-novoc.map @@ -0,0 +1,466 @@ +LHSName "ArabTeX-malay-novowels" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0627 ; +[VWL]=v1 / BEG _ > A @v1 +Q?=q1 U / BEG _ > A @q1 u w ; -U +; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! +Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m Q i A Hy Q a +m Q i H a / _ (T|t) > m Q i A Hy +m i H Q a / _ (T|t) > m A Hy Q a +m i H a / _ (T|t) > m A Hy + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Y Y > U+0649 U+0651 ;;SHADDA +Y > U+0649 +P I P I / _ # > U+06CC U+0651 ;; SHADDA +P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06CF U+0651 ;;SHADDA +v > U+06CF +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +Q U > U+064F U+0648 +[Uw] [Uw] > U+0648 U+0651 ;;SHADDA +[Uw] > U+0648 +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +Q u N > U+064C +u N > +Q u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 U+064B ;;SHADDA +T Q AN > U+0629 U+064B +T AN > U+0629 +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+06A8 U+0651 ;;SHADDA +p > U+06A8 ;Old malay +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06BD U+0651 ;;SHADDA +C n > U+06BD ; <<< ArabTeX yields nūn with three dots below, which is not in Unicode! +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+06A0 U+0651 ;;SHADDA +C g > U+06A0 +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +I > U+064A +Q i N > U+064D +i N > ; +Q i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+0762 U+0651 ;;SHADDA +g > U+0762 +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0686 U+0651 ;;SHADDA +c > U+0686 +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+0649 +UL a > U+0670 +UL u > ; +UL i > ; +Q AN / (A H|Ha) _ > U+064B +AN / (A H|Ha) _ > ; +Q AN > U+064B U+0627 +AN > U+0627 +Q a > U+064E +Q A > U+064E U+0627 +A > U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +[VWL] > ;stripoff vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +Z > ;- +BAR > ;| + +U+FDF2 > U+0644 U+0644 U+0647 ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-novoc.tec new file mode 100644 index 00000000000..4430c39ac2f Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-novoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-voc.map new file mode 100644 index 00000000000..610f8ae21cc --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-voc.map @@ -0,0 +1,476 @@ +LHSName "ArabTeX-malay-vocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA +P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06CF U+0651 ;;SHADDA +v > U+06CF +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+06A8 U+0651 ;;SHADDA +p > U+06A8 ;Old malay +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06BD U+0651 ;;SHADDA +C n > U+06BD ; <<< ArabTeX yields nūn with three dots below, which is not in Unicode! +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+06A0 U+0651 ;;SHADDA +C g > U+06A0 +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+0762 U+0651 ;;SHADDA +g > U+0762 +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0686 U+0651 ;;SHADDA +c > U+0686 +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +U+FDF2 > U+0644 U+0644 U+0647 ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-voc.tec new file mode 100644 index 00000000000..09744fcce1d Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-malay-voc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-novoc.map new file mode 100644 index 00000000000..da2ed9b9ce3 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-novoc.map @@ -0,0 +1,461 @@ +LHSName "ArabTeX-novowels" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +E > I +O > U + + + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +H l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0627 ; +[VWL]=v1 / BEG _ > A @v1 +A / BEG _ > A a +Q?=q1 U / BEG _ > A @q1 u w ; -U +; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! +Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m Q i A Hy Q a +m Q i H a / _ (T|t) > m Q i A Hy +m i H Q a / _ (T|t) > m A Hy Q a +m i H a / _ (T|t) > m A Hy + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Y Y > U+0649 U+0651 ;;SHADDA +Y > U+0649 +P I P I / _ # > U+06CC U+0651 ;; SHADDA +P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +Q U > U+064F U+0648 +[Uw] [Uw] > U+0648 U+0651 ;;SHADDA +[Uw] > U+0648 +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +Q u N > U+064C +u N > +Q u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 U+064B ;;SHADDA +T Q AN > U+0629 U+064B +T AN > U+0629 +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +I > U+064A +Q i N > U+064D +i N > ; +Q i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+0649 +UL a > U+0670 +UL u > U+0657 ; inverted damma +UL i > U+0656 ; subscript alif +Q AN / (A H|Ha) _ > U+064B +AN / (A H|Ha) _ > ; +Q AN > U+064B U+0627 +AN > U+0627 +Q a > U+064E +Q A > U+064E U+0627 +A > U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +[VWL] > ;stripoff vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +Z > ;- +BAR > ;| + +U+FDF2 > U+0644 U+0644 U+0647 ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-novoc.tec new file mode 100644 index 00000000000..e3b19841c5d Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-novoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-fullvoc.map new file mode 100644 index 00000000000..15bbdb6090c --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-fullvoc.map @@ -0,0 +1,487 @@ +LHSName "ArabTeX-pashto-fullvocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +a e > a U+0626 +E e > U+0659 U+06CD +e e > U+0659 U+0626 +E > U+0659 U+06D0 +CO O > U+06FC ; +O > U+0657 w +o > U+0657 +a o > a w +CO U > U+06C7 ; +e > U+0659 +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+067C U+0651 ;;SHADDA +V t > U+067C ; pashto +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0693 U+0651 ;;SHADDA +V r > U+0693 ;Pashto +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix +U+0048 > U+0647 U+200C ; H is always heh final +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+0689 U+0651 ;;SHADDA +V d > U+0689 ;pashto +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda +U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs +U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha +[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) +;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant +U+FDF2 > U+0644 U+0644 U+0647 ; +Q > ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-fullvoc.tec new file mode 100644 index 00000000000..f9962a69912 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-fullvoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-novoc.map new file mode 100644 index 00000000000..4627fad14ac --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-novoc.map @@ -0,0 +1,472 @@ +LHSName "ArabTeX-pashto-novowels" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode +a e > a U+0626 +E e > U+0659 U+06CD +e e > U+0659 U+0626 +E > U+0659 U+06D0 +CO O > U+06FC ; +O > U+0657 w +o > U+0657 +a o > a w +CO U > U+06C7 ; +e > U+0659 +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0627 ; +[VWL]=v1 / BEG _ > A @v1 +Q?=q1 U / BEG _ > A @q1 u w ; -U +; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! +Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m Q i A Hy Q a +m Q i H a / _ (T|t) > m Q i A Hy +m i H Q a / _ (T|t) > m A Hy Q a +m i H a / _ (T|t) > m A Hy + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Y Y > U+0649 U+0651 ;;SHADDA +Y > U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +Q U > U+064F U+0648 +[Uw] [Uw] > U+0648 U+0651 ;;SHADDA +[Uw] > U+0648 +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +Q u N > U+064C +u N > +Q u > U+064F +V t V t > U+067C U+0651 ;;SHADDA +V t > U+067C ; pashto +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 U+064B ;;SHADDA +T Q AN > U+0629 U+064B +T AN > U+0629 +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0693 U+0651 ;;SHADDA +V r > U+0693 ;Pashto +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +I > U+064A +Q i N > U+064D +i N > ; +Q i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix +U+0048 > U+0647 U+200C ; H is always heh final +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+0689 U+0651 ;;SHADDA +V d > U+0689 ;pashto +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+0649 +UL a > U+0670 +UL u > ; +UL i > ; +Q AN / (A H|Ha) _ > U+064B +AN / (A H|Ha) _ > ; +Q AN > U+064B U+0627 +AN > U+0627 +Q a > U+064E +Q A > U+064E U+0627 +A > U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +[VWL] > ;stripoff vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +Z > ;- +BAR > ;| + +U+FDF2 > U+0644 U+0644 U+0647 ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-novoc.tec new file mode 100644 index 00000000000..d78fc1dc9d5 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-novoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-voc.map new file mode 100644 index 00000000000..cf1b57075bd --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-voc.map @@ -0,0 +1,482 @@ +LHSName "ArabTeX-pashto-vocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +a e > a U+0626 +E e > U+0659 U+06CD +e e > U+0659 U+0626 +E > U+0659 U+06D0 +CO O > U+06FC ; +O > U+0657 w +o > U+0657 +a o > a w +CO U > U+06C7 ; +e > U+0659 +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+067C U+0651 ;;SHADDA +V t > U+067C ; pashto +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0693 U+0651 ;;SHADDA +V r > U+0693 ;Pashto +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +U+0048 Z > U+0647 U+200C U+0020 ;eH-suffix > eH suffix +U+0048 > U+0647 U+200C ; H is always heh final +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+0689 U+0651 ;;SHADDA +V d > U+0689 ;pashto +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +U+FDF2 > U+0644 U+0644 U+0647 ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-voc.tec new file mode 100644 index 00000000000..2037a598246 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-pashto-voc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-fullvoc.map new file mode 100644 index 00000000000..74298ab8bb1 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-fullvoc.map @@ -0,0 +1,457 @@ +LHSName "ArabTeX-sindhi-fullvocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + +;; special code for sindhi +;; U+004D U+0049 U+004E > U+06FE ; define macro \MIN in sindhi env +P m I N > U+06FE ; .mIN +;; U+0049 U+004E > U+06FD ; IN define macro \IN in sindhi env +H BAR I N > U+06FD ; '|IN + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA +P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t h V t h > U+067A U+0651 ;;SHADDA +V t h > U+067A +t h t h > U+067F U+0651 ;;SHADDA +t h > U+067F +V t V t > U+067D U+0651 ;;SHADDA +V t > U+067D +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0699 U+0651 ;;SHADDA +V r > U+0699 +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p h p h > U+06A6 U+0651 ;;SHADDA +p h > U+06A6 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+0683 U+0651 ;;SHADDA +C n > U+0683 +P P n P P n > U+06B2 U+0651 ;;SHADDA +P P n > U+06B2 ;; old sindhi? (not in ArabTeX) <<< +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BB U+0651 ;;SHADDA +V n > U+06BB +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +k h k h > U+06A9 U+0651 ;;SHADDA +k h > U+06A9 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+06AA U+0651 ;;SHADDA +k > U+06AA ; kaf swash +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+06BE U+0651 ;;SHADDA +h > U+06BE +P CO g P CO g > U+06B4 U+0651 ;;SHADDA +P CO g > U+06B4 ;; old sindhi? (not in ArabTeX) <<< +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d h V d h > U+068D U+0651 ;;SHADDA +V d h > U+068D +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +d h d h > U+068C U+0651 ;;SHADDA +d h > U+068C +C d C d > U+068E ;;SHADDA +C d > U+068E ; old sindhi: not in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +C c h C c h > U+0687 U+0651 ;;SHADDA +C c h > U+0687 +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +b h b h > U+0680 U+0651 ;;SHADDA +b h > U+0680 +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda +U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs +U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha +[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) +;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant +U+FDF2 > U+0644 U+0644 U+0647 ; +Q > ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-fullvoc.tec new file mode 100644 index 00000000000..7381d6ff85f Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-fullvoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-novoc.map new file mode 100644 index 00000000000..e1cf47ef662 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-novoc.map @@ -0,0 +1,442 @@ +LHSName "ArabTeX-sindhi-novowels" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode +CO O > U+06FC ; +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0627 ; +[VWL]=v1 / BEG _ > A @v1 +Q?=q1 U / BEG _ > A @q1 u w ; -U +; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! +Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m Q i A Hy Q a +m Q i H a / _ (T|t) > m Q i A Hy +m i H Q a / _ (T|t) > m A Hy Q a +m i H a / _ (T|t) > m A Hy + + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + +;; special code for sindhi +;; U+004D U+0049 U+004E > U+06FE ; define macro \MIN in sindhi env +P m I N > U+06FE ; .mIN +;; U+0049 U+004E > U+06FD ; IN define macro \IN in sindhi env +H BAR I N > U+06FD ; '|IN + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Y Y > U+0649 U+0651 ;;SHADDA +Y > U+0649 +P I P I / _ # > U+06CC U+0651 ;; SHADDA +P I / _ # > U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +Q U > U+064F U+0648 +[Uw] [Uw] > U+0648 U+0651 ;;SHADDA +[Uw] > U+0648 +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +Q u N > U+064C +u N > +Q u > U+064F +V t h V t h > U+067A U+0651 ;;SHADDA +V t h > U+067A +t h t h > U+067F U+0651 ;;SHADDA +t h > U+067F +V t V t > U+067D U+0651 ;;SHADDA +V t > U+067D +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 U+064B ;;SHADDA +T Q AN > U+0629 U+064B +T AN > U+0629 +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0699 U+0651 ;;SHADDA +V r > U+0699 +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p h p h > U+06A6 U+0651 ;;SHADDA +p h > U+06A6 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+0683 U+0651 ;;SHADDA +C n > U+0683 +P P n P P n > U+06B2 U+0651 ;;SHADDA +P P n > U+06B2 ;; old sindhi? (not in ArabTeX) <<< +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BB U+0651 ;;SHADDA +V n > U+06BB +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +k h k h > U+06A9 U+0651 ;;SHADDA +k h > U+06A9 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+06AA U+0651 ;;SHADDA +k > U+06AA ; kaf swash +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +I > U+064A +Q i N > U+064D +i N > ; +Q i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+06BE U+0651 ;;SHADDA +h > U+06BE +P CO g P CO g > U+06B4 U+0651 ;;SHADDA +P CO g > U+06B4 ;; old sindhi? (not in ArabTeX) <<< +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d h V d h > U+068D U+0651 ;;SHADDA +V d h > U+068D +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +d h d h > U+068C U+0651 ;;SHADDA +d h > U+068C +C d C d > U+068E ;;SHADDA +C d > U+068E ; old sindhi: not in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +C c h C c h > U+0687 U+0651 ;;SHADDA +C c h > U+0687 +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +b h b h > U+0680 U+0651 ;;SHADDA +b h > U+0680 +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+0649 +UL a > U+0670 +UL u > ; +UL i > ; +Q AN / (A H|Ha) _ > U+064B +AN / (A H|Ha) _ > ; +Q AN > U+064B U+0627 +AN > U+0627 +Q a > U+064E +Q A > U+064E U+0627 +A > U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +[VWL] > ;stripoff vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +Z > ;- +BAR > ;| + +U+FDF2 > U+0644 U+0644 U+0647 ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-novoc.tec new file mode 100644 index 00000000000..ac4885e4edb Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-novoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-voc.map new file mode 100644 index 00000000000..7d9d2b27280 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-voc.map @@ -0,0 +1,452 @@ +LHSName "ArabTeX-sindhi-vocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + +;; special code for sindhi +;; U+004D U+0049 U+004E > U+06FE ; define macro \MIN in sindhi env +P m I N > U+06FE ; .mIN +;; U+0049 U+004E > U+06FD ; IN define macro \IN in sindhi env +H BAR I N > U+06FD ; '|IN + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA +P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t h V t h > U+067A U+0651 ;;SHADDA +V t h > U+067A +t h t h > U+067F U+0651 ;;SHADDA +t h > U+067F +V t V t > U+067D U+0651 ;;SHADDA +V t > U+067D +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0699 U+0651 ;;SHADDA +V r > U+0699 +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p h p h > U+06A6 U+0651 ;;SHADDA +p h > U+06A6 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+0683 U+0651 ;;SHADDA +C n > U+0683 +P P n P P n > U+06B2 U+0651 ;;SHADDA +P P n > U+06B2 ;; old sindhi? (not in ArabTeX) <<< +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BB U+0651 ;;SHADDA +V n > U+06BB +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +k h k h > U+06A9 U+0651 ;;SHADDA +k h > U+06A9 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+06AA U+0651 ;;SHADDA +k > U+06AA ; kaf swash +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+06BE U+0651 ;;SHADDA +h > U+06BE +P CO g P CO g > U+06B4 U+0651 ;;SHADDA +P CO g > U+06B4 ;; old sindhi? (not in ArabTeX) <<< +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d h V d h > U+068D U+0651 ;;SHADDA +V d h > U+068D +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +d h d h > U+068C U+0651 ;;SHADDA +d h > U+068C +C d C d > U+068E ;;SHADDA +C d > U+068E ; old sindhi: not in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +C c h C c h > U+0687 U+0651 ;;SHADDA +C c h > U+0687 +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +b h b h > U+0680 U+0651 ;;SHADDA +b h > U+0680 +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +U+FDF2 > U+0644 U+0644 U+0647 ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-voc.tec new file mode 100644 index 00000000000..d86baa6c769 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-sindhi-voc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-fullvoc.map new file mode 100644 index 00000000000..1c29e15bfc1 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-fullvoc.map @@ -0,0 +1,481 @@ +LHSName "ArabTeX-turk-fullvocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0636 U+0651 ;;SHADDA +V z > U+0636 +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+0634 U+0651 ;;SHADDA +V s > U+0634 +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+0642 U+0651 ;;SHADDA +P k > U+0642 ; Ottoman qaf +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+06A0 U+0651 ;;SHADDA +C g > U+06A0 +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+0698 U+0651 ;;SHADDA +j > U+0698 +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0686 U+0651 ;;SHADDA +V c > U+0686 ; Ottoman ç +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+062C U+0651 ;;SHADDA +c > U+062C +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda +U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs +U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha +[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) +;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant +U+FDF2 > U+0644 U+0644 U+0647 ; +Q > ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-fullvoc.tec new file mode 100644 index 00000000000..73bbab84ef7 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-fullvoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-novoc.map new file mode 100644 index 00000000000..727f3224048 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-novoc.map @@ -0,0 +1,466 @@ +LHSName "ArabTeX-turk-novowels" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0627 ; +[VWL]=v1 / BEG _ > A @v1 +Q?=q1 U / BEG _ > A @q1 u w ; -U +; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! +Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m Q i A Hy Q a +m Q i H a / _ (T|t) > m Q i A Hy +m i H Q a / _ (T|t) > m A Hy Q a +m i H a / _ (T|t) > m A Hy + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0636 U+0651 ;;SHADDA +V z > U+0636 +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Y Y > U+0649 U+0651 ;;SHADDA +Y > U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +Q U > U+064F U+0648 +[Uw] [Uw] > U+0648 U+0651 ;;SHADDA +[Uw] > U+0648 +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +Q u N > U+064C +u N > +Q u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 U+064B ;;SHADDA +T Q AN > U+0629 U+064B +T AN > U+0629 +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+0634 U+0651 ;;SHADDA +V s > U+0634 +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+0642 U+0651 ;;SHADDA +P k > U+0642 ; Ottoman qaf +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+06A0 U+0651 ;;SHADDA +C g > U+06A0 +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+0698 U+0651 ;;SHADDA +j > U+0698 +Q I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +I > U+064A +Q i N > U+064D +i N > ; +Q i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0686 U+0651 ;;SHADDA +V c > U+0686 ; Ottoman ç +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+062C U+0651 ;;SHADDA +c > U+062C +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+0649 +UL a > U+0670 +UL u > ; +UL i > ; +Q AN / (A H|Ha) _ > U+064B +AN / (A H|Ha) _ > ; +Q AN > U+064B U+0627 +AN > U+0627 +Q a > U+064E +Q A > U+064E U+0627 +A > U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +[VWL] > ;stripoff vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +Z > ;- +BAR > ;| + +U+FDF2 > U+0644 U+0644 U+0647 ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-novoc.tec new file mode 100644 index 00000000000..b624d81122e Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-novoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-voc.map new file mode 100644 index 00000000000..8d41171c70e --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-voc.map @@ -0,0 +1,476 @@ +LHSName "ArabTeX-turk-vocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0636 U+0651 ;;SHADDA +V z > U+0636 +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+0634 U+0651 ;;SHADDA +V s > U+0634 +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+0642 U+0651 ;;SHADDA +P k > U+0642 ; Ottoman qaf +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+06A0 U+0651 ;;SHADDA +C g > U+06A0 +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+0698 U+0651 ;;SHADDA +j > U+0698 +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0686 U+0651 ;;SHADDA +V c > U+0686 ; Ottoman ç +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+062C U+0651 ;;SHADDA +c > U+062C +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +U+FDF2 > U+0644 U+0644 U+0647 ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-voc.tec new file mode 100644 index 00000000000..2ba125e3b92 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-turk-voc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-uighur.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-uighur.map new file mode 100644 index 00000000000..a1025dc974c --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-uighur.map @@ -0,0 +1,271 @@ +LHSName "ArabTeX-Uighur" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define LLAH U+006C U+006C U+005F U+0061 U+0068 + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) + + +; special ligatures +;; 1. Standard ArabTeX input +(a|A) l Z LLAH > U+0627 U+0644 U+0644 U+0647 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+0644 U+0644 U+0647 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+0644 U+0644 U+0647 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL)' +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE)' +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels + +a / # _ > U+0626 U+0627 +a > U+0627 +(CO a|U+00E4) / # _ > U+0626 U+0647 U+200C +(CO a|U+00E4) > U+0647 U+200C +o / # _ > U+0626 U+0648 ; +o > U+0648 ; +(CO o|U+00F6) / # _ > U+0626 U+06C6 +(CO o|U+00F6) > U+06C6 +i / # _ # > U+0626 U+0649 +i / # _ > U+0626 U+066E +i / _ # > U+0649 +i > U+066E +e / # _ > U+0626 U+06D0 +e > U+06D0 +u / # _ > U+0626 U+06C7 ; +u > U+06C7 ; +(CO u|U+00FC) / # _ > U+0626 U+06C8 ; +(CO u|U+00FC) > U+06C8 ; +l Q a > U+0644 U+064E U+0627 ; +l a > U+0644 U+0627 ; + +P z P z > U+0638 U+0651 ;;SHADDA +P z > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;pashto ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Y Y > U+0649 U+0651 ;;SHADDA +Y > U+0649 +w w > U+06CB U+0651 ;;SHADDA +w > U+06CB +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +V t V t > U+0679 U+0651 ; urdu ;;SHADDA +V t > U+0679 +UL t UL t > U+062B U+0651 ;;SHADDA +UL t > U+062B +P t P t > U+0637 U+0651 ;;SHADDA +P t > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +P s P s > U+0635 U+0651 ;;SHADDA +P s > U+0635 +V s V s > U+069A U+0651 ;Pashto ;;SHADDA +V s > U+069A ;Pashto +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+0692 U+0651 ;Kurdish ;;SHADDA ; missing in ArabTeX <<< +C r > U+0692 +P r P r > U+0695 U+0651 ;Kurdish ;;SHADDA +P r > U+0695 +V r V r > U+0691 U+0651 ;Urdu ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ; urdu ;;SHADDA +P n > U+06BA ; +V n V n > U+06BC U+0651 ; Pashto +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +C l C l > U+06B5 U+0651 ;kurdish ;;SHADDA +C l > U+06B5 +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ; pashto urdu ;;SHADDA +P k > U+06A9 +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +P h P h > U+062D U+0651 ;;SHADDA +P h > U+062D +V h V h > U+06C1 U+0651 +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +C g C g > U+063A U+0651 ;;SHADDA +C g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;pashto ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+0688 U+0651 ;urdu ;;SHADDA +V d > U+0688 ;urdu +C d C d > U+06EE ; not defined in ArabTeX U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +UL d UL d > U+0630 U+0651 ;;SHADDA +UL d > U+0630 +P d P d > U+0636 U+0651 ;;SHADDA +P d > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;pashto ;;SHADDA +V c > U+0685 +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +c c > U+0681 U+0651 +c > U+0681 ; ح with hamza above +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H > U+0626 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / . _ . > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... +U+005B / . _ . > U+200D U+005B U+200D ; ... (but of course this screws up contextual analysis, so quoting of hamzas etc may be necessary) +Q > ; +N > ; +C > ;^ +Z > ;- +BAR > ;| + + diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-uighur.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-uighur.tec new file mode 100644 index 00000000000..54df2963345 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-uighur.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-fullvoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-fullvoc.map new file mode 100644 index 00000000000..e5b13384734 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-fullvoc.map @@ -0,0 +1,495 @@ +LHSName "ArabTeX-urdu-fullvocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +H E > U+06D3 ;; hamza + yeh barree +E / _ # > U+06D2 +E > y +a e / _ # > a U+06D2 +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +A / BEG _ > HA ;; ADD MORE ? <<< +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +U+0048 > U+06C3 +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +H H > U+06C1 U+0651 ;;SHADDA +H > U+06C1 +h h > U+06BE U+0651 ;;SHADDA +h > U+06BE ; urdu +;; fix letter+h letter+h > letter+h shadda in URDU <<< +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+0688 U+0651 ;;SHADDA +V d > U+0688 ;urdu +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +CO CO d CO CO d > U+0690 U+0651 ;;SHADDA +CO CO d > U+0690 ; old urdu: not in ArabTeX +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| +P P > U+06D4 ; urdu full stop << check + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +[CONS]=k1 / _ Z? [CONS] ^U+0651 > @k1 U+0652 ; hack: 2nd consonant has no shadda +U+064E (U+064A|U+0648)=hc / _ (^[VWLX]|#) > U+064E @hc U+0652 ; ay and aw diphtongs +U+0627 / # _ U+0644 > U+0627 U+064E ; otherwise initial alif takes fatha +[CONS]=k1 / _ ([CONS]|#) > @k1 U+0652 ; consonant + (consonant or final) +;; [CONS]=k1 / _ # > @k1 U+0652 ; final consonant +U+FDF2 > U+0644 U+0644 U+0647 ; +Q > ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-fullvoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-fullvoc.tec new file mode 100644 index 00000000000..596a5571ecc Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-fullvoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-novoc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-novoc.map new file mode 100644 index 00000000000..f4b1fb4a420 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-novoc.map @@ -0,0 +1,480 @@ +LHSName "ArabTeX-urdu-novowels" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +[AVWL] > ; strip off vowels when writing UTF-8 Arabic with novoc mode +CO O > U+06FC ; +H E > U+06D3 ;; hamza + yeh barree +E / _ # > U+06D2 +E > y +a e / _ # > a U+06D2 +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0627 ; +[VWL]=v1 / BEG _ > A @v1 +A / BEG _ > HA ;; ADD MORE ? <<< +Q?=q1 U / BEG _ > A @q1 u w ; -U +; Q?=q1 I / BEG _ > A @q1 i y ; -I ; but not when I is final FIXME!!! +Q?=q1 I / BEG _ > A @q1 i y ; except for Persian, coz of ezafe rules + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m Q i A Hy Q a +m Q i H a / _ (T|t) > m Q i A Hy +m i H Q a / _ (T|t) > m A Hy Q a +m i H a / _ (T|t) > m A Hy + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Y Y > U+0649 U+0651 ;;SHADDA +Y > U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +Q U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +Q U > U+064F U+0648 +[Uw] [Uw] > U+0648 U+0651 ;;SHADDA +[Uw] > U+0648 +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +Q u N > U+064C +u N > +Q u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 U+064B ;;SHADDA +T Q AN > U+0629 U+064B +T AN > U+0629 +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +I > U+064A +Q i N > U+064D +i N > ; +Q i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +U+0048 > U+06C3 +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +H H > U+06C1 U+0651 ;;SHADDA +H > U+06C1 +h h > U+06BE U+0651 ;;SHADDA +h > U+06BE ; urdu +;; fix letter+h letter+h > letter+h shadda in URDU <<< +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+0688 U+0651 ;;SHADDA +V d > U+0688 ;urdu +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +CO CO d CO CO d > U+0690 U+0651 ;;SHADDA +CO CO d > U+0690 ; old urdu: not in ArabTeX +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+0649 +UL a > U+0670 +UL u > ; +UL i > ; +Q AN / (A H|Ha) _ > U+064B +AN / (A H|Ha) _ > ; +Q AN > U+064B U+0627 +AN > U+0627 +Q a > U+064E +Q A > U+064E U+0627 +A > U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +[VWL] > ;stripoff vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +Z > ;- +BAR > ;| +P P > U+06D4 ; urdu full stop << check + +U+FDF2 > U+0644 U+0644 U+0647 ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-novoc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-novoc.tec new file mode 100644 index 00000000000..a7b5a04d586 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-novoc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-voc.map new file mode 100644 index 00000000000..74de2bc9794 --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-voc.map @@ -0,0 +1,490 @@ +LHSName "ArabTeX-urdu-vocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +H E > U+06D3 ;; hamza + yeh barree +E / _ # > U+06D2 +E > y +a e / _ # > a U+06D2 +a e > a y +a o > a w +(o|u)? O / # _ > U+0627 w +(o|u)? O > w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +I / _ # > i y + + +;; Persian ezafe (ALL BUT ARABIC AND UIGHUR) +U+0048 Z UL? (Q? (i|e))=vv / _ END > U+06C0 @vv U+200C ;H-i -> heh+hamza final; what about 06C2 in Urdu ?<<< +U+0048 Z Q?=qq (I|E)=vv / _ END > h U+0020 U+0627 @qq i @vv ; H-I +Q?=q1 (I|E) Z UL? Q?=q2 (i|e) / _ END > @q1 i U+0626 @q2 i U+200C ; ...I-e +Z Q?=qq I / (A|U) _ ENDZ > U+0626 @qq i y ; ...A-I or ...U-I +Z UL? (Q? (i|e))=vv / (A|U) _ END > U+0649 @vv ; ...A-i or ...U-i +Z Q?=q1 (e|i) / _ ENDZ > @q1 i ; ...-i +Z / U+0048 _ > U+0020 ; +b Q?=q1 (e|i) Q?=q2 U / # _ > b @q1 i U+0627 @q2 u w ;; special case of prep be without hyphen + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +A / BEG _ > HA ;; ADD MORE ? <<< +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +;; y / _ # > U+0649 ; y final in persian,ottoman,urdu,pashto,kashmiri has no dots +y y > U+06CC U+0651 ;;SHADDA +y > U+06CC ; yeh in persian etc. > iso and final shapes have no dots +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +U+0048 > U+06C3 +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +H H > U+06C1 U+0651 ;;SHADDA +H > U+06C1 +h h > U+06BE U+0651 ;;SHADDA +h > U+06BE ; urdu +;; fix letter+h letter+h > letter+h shadda in URDU <<< +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+0688 U+0651 ;;SHADDA +V d > U+0688 ;urdu +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +CO CO d CO CO d > U+0690 U+0651 ;;SHADDA +CO CO d > U+0690 ; old urdu: not in ArabTeX +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+064F; +UL i > U+0650; +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArEasternDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| +P P > U+06D4 ; urdu full stop << check + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +U+FDF2 > U+0644 U+0644 U+0647 ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-voc.tec new file mode 100644 index 00000000000..93aef573b5e Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-urdu-voc.tec differ diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-voc.map b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-voc.map new file mode 100644 index 00000000000..989adb6228c --- /dev/null +++ b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-voc.map @@ -0,0 +1,472 @@ +LHSName "ArabTeX-vocalized" +RHSName "UNICODE" + +Define a U+0061 ;a +Define b U+0062 ;b +Define c U+0063 ;c +Define d U+0064 ;d +Define e U+0065 ;e +Define f U+0066 ;f +Define g U+0067 ;g +Define h U+0068 ;h +Define i U+0069 ;i +Define j U+006A ;j +Define k U+006B ;k +Define l U+006C ;l +Define m U+006D ;m +Define n U+006E ;n +Define o U+006F ;o +Define p U+0070 ;p +Define q U+0071 ;q +Define r U+0072 ;r +Define s U+0073 ;s +Define t U+0074 ;t +Define u U+0075 ;u +Define v U+0076 ;v +Define w U+0077 ;w +Define x U+0078 ;x +Define y U+0079 ;y +Define z U+007A ;z +Define A U+0041 ;A +Define B U+0042 ;B +Define E U+0045 ;E +Define G U+0047 ;G +Define I U+0049 ;I +Define N U+004E ;N +Define O U+004F ;O +Define T U+0054 ;T +Define U U+0055 ;U +Define W U+0057 ;W +Define Y U+0059 ;Y +Define C U+005E ;^ << CARET +Define UL U+005F ;_ << UNDERLINE +Define P U+002E ;. << DOT +Define V U+002C ;, << COMMA (_V_irgule) +Define CO U+003A ;: << COLON +Define SC U+003B ;; << SEMICOLON +Define Ain U+0060 ;` +Define H U+0027 ;' << HAMZA +Define Q U+0022 ;" << QUOTE +Define Z U+002D ;- << HYPHEN +Define BAR U+007C ;| +Define AN U+0061 U+004E ; aN +Define LLAH U+006C U+006C U+005F U+0061 U+0068 ; ll_ah +;Define NUL U+00A6; +Define Ha U+0623 +Define Hi U+0625 +Define Hy U+0626 +Define Hw U+0624 +Define Hh U+06C0 ;; = U+0647 U+0654 +Define HA U+0622 +Define HB U+0640 U+0654 +Define HBAR U+0621 ; '| + +pass(Unicode) + +U+E000 > ; eliminate special code for capitalization in transliterations + +pass(Unicode) + +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [AVWL] = (U+064B..U+0650); +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0047 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;a..z A E I O U B N T Y ^ . _ " "" ` +Class [BRACKETS] = (U+003C U+003E U+00AB U+00BB U+0028 U+0029 U+005B U+005D U+2018 U+2019 U+201C U+201D); < > () « » [ ] ‘ ’ “ ” +Class [PUNCT] = (V SC P CO) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) +Class [Uwu] = (U+0055 U+0077 U+0075) ;(U w u) +;Class [ae] = (U+0061 U+0065) ;(a e) +;Class [ou] = (U+0075 U+006F) ;(u o) +Class [Iyi] = (U+0069 U+0079 U+0049) +Class [UI] = (U+0049 U+0055) ; U I +Class [Digits] = (U+0030..U+0039) + +Define BEG (#|Z|[BRACKETS]) +Define END (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #) +Define ENDZ (#|[BRACKETS]|[PUNCT] U+0020|[PUNCT] #|Z) + +; special ligatures +;; 1. Standard ArabTeX input +;; FDF2 is just used as temporary holder, and is converted back to ligature lam lam hah later (to be taken care of by the font) +;; The BAR is used in the DMG transliteration to suppress the initial A +(a|A) BAR? l Z LLAH > U+0627 U+FDF2 ;; 'al-ll_ah' or 'Al-ll_ah' +LLAH > U+FDF2 ;; 'll_ah' -> 'l l h' +;; UPPERCASE mnemonics for various ligatures or special glyphs +U+004C U+004C U+0048 > U+FDF2 ;; 'LLH' -> 'l l h' +U+0046 U+0041 U+004C U+0049 U+004C U+004C U+0041 U+0048 > U+0641 U+064E U+0644 U+0650 U+0644 U+0647 ;; 'FALILLAH' +U+0041 U+004C U+004C U+0041 U+0048 > U+0627 U+0644 U+0644 U+0647 ; 'ALLAH' +U+004C U+004C U+0041 U+0048 > U+0644 U+0644 U+0647 ; 'LLAH' + +U+0053 U+004C U+004D > U+FDFA ; 'SLM' : .sallY al-ll_ah `alayhi wa-sallam +U+0028 U+0028 > U+FD3F ;; '((' : ornate right par +U+0029 U+0029 > U+FD3E ;; '))' : ornate left par +U+0052 U+0049 U+0059 U+0041 U+004C > U+FDFC ;; 'RIYAL' : Saudi currency sign +;; most fonts won't have the following ones: +U+0053 U+0041 U+004C U+004C U+0041 U+0053 U+0054 U+004F U+0050 > U+FDF0 ;; 'SALLASTOP' (.sallY with "ye-barree", Quranic stop sign) +U+0051 U+0041 U+004C U+0041 > U+FDF1 ;; 'QALA' : qalY with ye-barree, Quranic stop sign +U+0041 U+004B U+0042 U+0041 U+0052 > U+FDF3 ;; 'AKBAR' +U+004D U+0055 U+0048 U+0041 U+004D U+004D U+0041 U+0044 > U+FDF4 ;; 'MUHAMMAD' +U+0053 U+0041 U+004C U+0041 U+004D > U+FDF5 ;; 'SALAM' +U+0052 U+0041 U+0053 U+004F ? U+0055 U+004C > U+FDF6 ;; 'RASUL' (also unicode 'RASOUL') +U+0041 U+004C U+0041 U+0059 U+0048 (U+0049|U+0045) > U+FDF7 ;; 'ALAYHI' (also unicode 'ALAYHE') +U+0057 U+0041 U+0053 U+0041 U+004C U+004C U+0041 U+004D > U+FDF8 ;; 'WASALLAM' +U+0053 U+0041 U+004C U+004C U+0041 > U+FDF9 ;; 'SALLA' +U+004A U+0041 U+004C U+004C U+0041 > U+FDFB ;; 'JALLA' : "jalla jalAluhu" +U+0042 U+0041 U+0053 U+004D U+0041 U+004C U+0041 > U+FDFD ;; 'BASMALA' : very few fonts have this ligature afaik + +U+005E U+0053 U+004C U+0059 > U+06D6 ;; ^SLY +U+005E U+0051 U+004C U+0059 > U+06D7 ;; ^QLY +U+005E U+004D U+0049 U+004D > U+06D8 ;; ^MIM- +U+005E U+004C U+0041 > U+06D9 ;; ^LA +U+005E U+004A U+0049 U+004D > U+06DA ;; ^JIM +U+005E U+0044 U+004F U+0054 U+0053 > U+06DB ;; ^DOTS +U+005E U+0053 U+0049 U+004E > U+06DC ;; ^SIN +U+0048 U+0049 U+005A U+0042 > U+06DE ;; HIZB +U+0043 U+0049 U+0052 U+0043 U+005A U+0045 U+0052 U+004F > U+06DF ;; CIRCZERO +U+0052 U+0045 U+0043 U+0054 U+005A U+0045 U+0052 U+004F > U+06E0 ;; RECTZERO +U+005E U+004A U+0041 U+005A U+004D > U+06E1 ;; ^JAZM +U+005E U+004D U+0049 U+004D > U+06E2 ;; ^MIM +U+005F U+0053 U+0049 U+004E > U+06E3 ;; _SIN +U+005E U+004D U+0041 U+0044 U+0044 U+0041 > U+06E4 ;; ^MADDA +U+0057 U+0041 U+0057 > U+06E5 ;; WAW +U+0059 U+0045 U+0048 > U+06E6 ;; YEH +U+005E U+0059 U+0045 U+0048 > U+06E7 ;; ^YEH +U+005E U+004E U+0055 U+004E > U+06E8 ;; ^NUN +U+0053 U+0041 U+004A U+0044 U+0041 > U+06E9 ;; SAJDA +U+005F U+0053 U+0054 U+004F U+0050 > U+06EA ;; _STOP +U+005E U+0053 U+0054 U+004F U+0050 > U+06EB ;; ^STOP +U+005E U+0052 U+0053 U+0054 U+004F U+0050 > U+06EC ;; ^RSTOP +U+005F U+004D U+0049 U+004D > U+06ED ;; _MIM + +U+0044 U+004F U+0054 U+0053 > U+061E ;; DOTS (also possible by typing "::") + +;; This is to enclose digits within glyph U+06DD +U+005B U+005B ([Digits]+)=dig U+005D U+005D > U+06DD @dig ; [[digits]] + + +; vowels +u u > U +i i > I +a a > A +CO O > U+06FC ; +a e > a y +a o > a w +CO U > U+06C7 ; +e > i ;; but not pashto > U+0659 and kashmiri > y + U+0658 (U+06CE is kurdish) +o > u +E > I +O > U + + + +;; initial characters ... +a l Z / BEG _ > U+0627 l Z +H l Z / BEG _ > U+0627 l Z +;; wasla on initial alif : NEW! NOT TESTED! +H / BEG _ l l > U+0671 ; e.g. alla_dI -> 'lla_dI +[VWL]=v1 / BEG _ > U+0627 @v1 +A / BEG _ > U+0627 a +Q?=q1 U / BEG _ > U+0627 @q1 u w ; -U +; Q?=q1 I / BEG _ > U+0627 @q1 i y ; -I +Q?=q1 I / BEG _ > U+0627 @q1 i y + + +;; Words with anomalous orthography: + +; mi'aT -> ماية +;;; i H / m Q ? _ Q ? a ? (T|t) > i A Hy +m Q i H Q a / _ (T|t) > m U+0627 Hy +m Q i H a / _ (T|t) > m U+0627 Hy a +m i H Q a / _ (T|t) > m i U+0627 Hy +m i H a / _ (T|t) > m i U+0627 Hy a + + +;; contextual analysis of hamzas +;; THESE DO NOT APPLY FOR SINDHI + +; initial hamzas +H / (#|^[LTR]) _ Q? [Iyi] > Hi +H Q A / (#|^[LTR]) _ > HA ; alif madda +H / (#|^[LTR]) _ Q? [Uwu] > Ha +H / (#|^[LTR]) _ Q? a > Ha +Q H / (#|^[LTR]) _ > HB ; quoted isolated hamza at beginning of word + +; quoted hamzas in contextual mode, equivalent to verbatim mode +a Q H > Ha +i Q H > Hi +y Q H > Hy +w Q H > Hw +h Q H > Hh +A Q H > HA +B Q H > HB +BAR Q H > HBAR + +; hamza + fathatan +H / a _ Q? AN > Ha +;;H / [Iyi] _ Q? AN > Hy +H / _ Q? AN > Hy + +;final hamzas +H / A _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Uw] _ Q? [VWL]? N? (#|^[LTR]) > HBAR +H / [Iy] _ Q? (i N?|u N?)? (#|^[LTR]) > HBAR ; not AN ... +H / a _ Q? (#|^[LTR]) > Ha ; not AN... +H / a _ Q? (u|i) N? (#|^[LTR]) > Ha ; not AN... +H / i _ Q? [VWL]? N? (#|^[LTR]) > Hy +H / u _ Q? [VWL]? N? (#|^[LTR]) > Hw + +;;and more hamzas ... + +; n°1: kasra/ya +H / [LTR] _ Q? [Iyi] ^N > Hy +H / [Iyi] _ > Hy + +; n°2: damma/waw +H / [LTR] _ Q? (U|u) ^N > Hw +H / (U|u) _ Q? ^[Iyi] > Hw +H / U _ > HBAR + +; n°3: fatha/alif +H Q? A > HA +H / A _ Q? a > HBAR +H / ^[UI] _ Q? a > Ha +H / a _ Q? ^[UI] > Ha + + +pass(Unicode) + +Class [Digits] = (U+0030..U+0039) +Class [ArDigits] = (U+0660..U+0669) +Class [ArEasternDigits] = (U+06F0..U+06F9) +Class [VWL] = (U+0061 U+0065 U+0069 U+006F U+0075 ) ;(a e i o u) +Class [LTR] = (U+0061..U+007A U+0041 U+0045 U+0049 U+004F U+0055 U+0042 U+004E U+0054 U+0059 U+005E U+002E U+005F U+0022 U+0027 U+0060) ;(a..z A E I O U B N T Y ^ . _ " "" `) +Class [Iy] = (U+0049 U+0079) ;(I y) +Class [Uw] = (U+0055 U+0077) ;(U w) + + + + +;normal code + + +(P z|U+1E93) (P z|U+1E93) > U+0638 U+0651 ;;SHADDA +(P z|U+1E93) > U+0638 +C z C z > U+0698 U+0651 ;;SHADDA +C z > U+0698 +V z V z > U+0696 U+0651 ;;SHADDA +V z > U+0696 ;pashto +z z > U+0632 U+0651 ;;SHADDA +z > U+0632 +Q Y Y > U+0649 U+0651 ;;SHADDA +Q Y > U+0649 +Y Y > U+064E U+0649 U+0651 ;;SHADDA +Y > U+064E U+0649 +P I P I / _ # > U+0650 U+06CC U+0651 ;; SHADDA +P I / _ # > U+0650 U+06CC ;; workaround to have ya without dots in Arabic +y y > U+064A U+0651 ;;SHADDA +y > U+064A +v v > U+06A4 U+0651 ;;SHADDA +v > U+06A4 +W > U+0648 U+0627 ; waw + alif +C U > U+064F U+0648 U+0653; historical spelling : madda on waw +C w C w > U+06C9 U+0651 ;;SHADDA +C w > U+06C9 +CO w CO w > U+06CA U+0651 ;,SHADDA +CO w > U+06CA +U A / _ # > U+064F U+0648 U+0627 +Q U [Uw] > U+0648 U+0651 ;;SHADDA +Q U > U+0648 +U [Uw] > U+064F U+0648 U+0651 ;;SHADDA +U > U+064F U+0648 +w w > U+0648 U+0651 ;;SHADDA +w > U+0648 +Q u N? > +u N > U+064C +u > U+064F +V t V t > U+0679 U+0651 ;;SHADDA +V t > U+0679 ;urdu +UL (t|s) UL (t|s) > U+062B U+0651 ;;SHADDA +UL (t|s) > U+062B +(P t|U+1E6D) (P t|U+1E6D) > U+0637 U+0651 ;;SHADDA +(P t|U+1E6D) > U+0637 +t t > U+062A U+0651 ;;SHADDA +t > U+062A +T T Q AN > U+0629 U+0651 ;;SHADDA +T Q AN > U+0629 +T AN > U+0629 U+064B +T T > U+0629 U+0651 ;;SHADDA +T > U+0629 +C s C s > U+0634 U+0651 ;;SHADDA +C s > U+0634 +(P s|U+1E63) (P s|U+1E63) > U+0635 U+0651 ;;SHADDA +(P s|U+1E63) > U+0635 +V s V s > U+069A U+0651 ;;SHADDA +V s > U+069A ;Pashto +CO s CO s > U+069B U+0651 ;;SHADDA +CO s > U+069B ; sin with 3 dots below +s s > U+0633 U+0651 ;;SHADDA +s > U+0633 +C r C r > U+06EF U+0651 ;;SHADDA ; missing in ArabTeX <<< +C r > U+06EF +CO r CO r > U+0697 U+0651 ;;SHADDA ; missing in ArabTeX <<< +CO r > U+0697 ; Dargwa language, Dagestan +P r P r > U+0694 U+0651 ;;SHADDA +P r > U+0694 ; r with dot below; in Kurdish .r -> 0694 +V r V r > U+0691 U+0651 ;;SHADDA +V r > U+0691 ;Urdu +r r > U+0631 U+0651 ;;SHADDA +r > U+0631 +P q P q > U+066F U+0651 ;;SHADDA +P q > U+066F +q q > U+0642 U+0651 ;;SHADDA +q > U+0642 +p p > U+067E U+0651 ;;SHADDA +p > U+067E +CO n CO n > U+06B1 U+0651 ;;SHADDA +CO n > U+06B1 +C n C n > U+06AD U+0651 ;;SHADDA +C n > U+06AD +P n P n > U+06BA U+0651 ;;SHADDA +P n > U+06BA ; urdu +V n V n > U+06BC U+0651 ;;SHADDA +V n > U+06BC ; Pashto +n n > U+0646 U+0651 ;;SHADDA +n > U+0646 +m m > U+0645 U+0651 ;;SHADDA +m > U+0645 +P l P l > U+06B6 U+0651 ; +P l > U+06B6 ; ADDED <<< +C l C l > U+06B5 U+0651 ;;SHADDA +C l > U+06B5 ;kurdish +l l > U+0644 U+0651 ;;SHADDA +l > U+0644 +P k P k > U+06A9 U+0651 ;;SHADDA +P k > U+06A9 ; pashto urdu +UL k UL k > U+063A U+0651 ;;SHADDA +UL k > U+063A +k k > U+0643 U+0651 ;;SHADDA +k > U+0643 +C g C g > U+062C U+0651 ;;SHADDA +C g > U+062C +CO j CO j > U+0684 U+0651 ;;SHADDA +CO j > U+0684 +j j > U+062C U+0651 ;;SHADDA +j > U+062C +Q I > U+064A +I > U+0650 U+064A +C I > U+0650 U+064A U+0653 ; historical spelling : madda on ya +UL I > ; suggestion of O. Smrz (arabtex-plus project) URL = ### +Q i N? > ; +i N > U+064D +i > U+0650 +x x > U+062E U+0651 ;;SHADDA +x > U+062E +UL h UL h > U+062E U+0651 ;;SHADDA +UL h > U+062E +(P h|U+1E25) (P h|U+1E25) > U+062D U+0651 ;;SHADDA +(P h|U+1E25) > U+062D +V h V h > U+06C1 U+0651 ;;SHADDA +V h > U+06C1 +h h > U+0647 U+0651 ;;SHADDA +h > U+0647 +CO g CO g > U+06B3 U+0651 ;;SHADDA +CO g > U+06B3 +V g V g > U+06AC U+0651 ;;SHADDA +V g > U+06AC ; kaf with dot above +P g P g > U+063A U+0651 ;;SHADDA +P g > U+063A +g g > U+06AF U+0651 ;;SHADDA +g > U+06AF +G G > U+06AB U+0651 ;;SHADDA +G > U+06AB ;pashto +P f P f > U+06A1 U+0651 ;;SHADDA +P f > U+06A1 +f f > U+0641 U+0651 ;;SHADDA +f > U+0641 +V d V d > U+068A U+0651 ;;SHADDA +V d > U+068A +P V d P V d > U+068B U+0651 ;;SHADDA +P V d > U+068B ;; (like U+0688 with dot below, for Lahnda = Western Punjabi) +C d C d > U+06EE U+0651 ;;SHADDA +C d > U+06EE ; not defined in ArabTeX +CO d CO d > U+068F U+0651 ;;SHADDA +CO d > U+068F +UL (d|z) UL (d|z) > U+0630 U+0651 ;;SHADDA +UL (d|z) > U+0630 +(P d|U+1E0D) (P d|U+1E0D) > U+0636 U+0651 ;;SHADDA +(P d|U+1E0D) > U+0636 +d d > U+062F U+0651 ;;SHADDA +d > U+062F +V c V c > U+0685 U+0651 ;;SHADDA +V c > U+0685 ;pashto +C c C c > U+0686 U+0651 ;;SHADDA +C c > U+0686 +P C c P C c > U+06BF U+0651 ;;SHADDA +P C c > U+06BF ;; cheh with dot above <<< +c c > U+0681 U+0651 ;;SHADDA +c > U+0681 ; ح with hamza above +CO c CO c > U+0682 U+0651 ;;SHADDA +CO c > U+0682 ; old pashto +CO b CO b > U+067B U+0651 ;;SHADDA +CO b > U+067B +P b P b > U+066E U+0651 ;;SHADDA +P b > U+066E +b b > U+0628 U+0651 ;;SHADDA +b > U+0628 +H A > U+0622 +C A > U+064E U+0622 ; historical spelling +UL A > U+064E U+0649 +UL a > U+0670 +UL u > U+0657 ; inverted damma +UL i > U+0656 ; subscript alif +Q AN / (A H|Ha) _ > ; +AN / (A H|Ha) _ > U+064B +Q AN > U+0627 +AN > U+064B U+0627 +Q a > +a > U+064E +Q A > U+0627 +A > U+064E U+0627 +Ain Ain > U+0639 U+0651 ;;SHADDA +Ain > U+0639 +H H > U+0621 U+0651 ;;SHADDA +H > U+0621 +U+002C / [Digits] _ [Digits] > U+002C ; comma in numerical context not an Arabic comma +Z Z / [Digits] _ [Digits] > U+2013 ; two hyphens in numerical context -> endash +(Z|U+005D|U+005B|U+0028|U+0029)=xx / [Digits] _ [Digits] > U+202D @xx U+202C ; hyphen or brackets in numerical context: surrounded by LRO & PDF marks +[Digits] > [ArDigits] +Z Z Z / # _ # > U+2014 +Z Z / # _ # > U+2013 +Z Z > U+0640 +B > U+0640 +Z / # _ > U+200D ; -x > force initial form with "zero-width joiner" +Z / _ # > U+200D ; x- > force final form +U+003C U+003C > U+00BB ;<< +U+003E U+003E > U+00AB ;>> +U+00AB > U+00BB +U+00BB > U+00AB +UL > U+0640 ;_ +U+003F > U+061F ;? +U+003B > U+061B ;; +U+003A U+003A > U+061E ;; '::' ligature 'DOTS' also defined above... +U+002C > U+060C ;, +U+005D / [LTR] _ [LTR] > U+200D U+005D U+200D ; keep shaping when inserting ...[...]... ... +U+005B / [LTR] _ [LTR] > U+200D U+005B U+200D ; (but of course this screws up contextual + ; analysis, so quoting of hamzas etc may be necessary +;U+005D > U+005B ;] these are automatically mirrored, following Unicode rules +;U+005B > U+005D ;[ +Q [VWL] > ;stripoff quoted vowels +Q > U+0652 +U+00B0 > U+0652 ; ° +N > ; +C > ;^ +BAR > ;| + +pass(Unicode) + +Class [CONS] = (U+0621 U+0623 U+0624 U+0626 U+0628 U+062A..U+063A U+0641..U+0647 U+066E U+066F U+0672 U+0675 U+0676 U+0678..U+06BF U+06EE U+06EF U+06FA..U+06FF U+0750..U+076D) ; to be improved: not sure that all glyphs listed (esp for Urdu,Sindhi,etc are really "consonants" in the sense that they can carry a sukun, not to mention that some of these languages may not have a sukun at all ;-) +Class [VWLX] = (U+0627 U+0648..U+065E U+0670) ; long vowels, vowel signs, shadda, sukun etc. +Class [VWL] = (U+0627 U+0648..U+0650 U+0670); +U+0627 [VWL]? / [VWL] Z _ > U+0627 ; e.g. fa-isti_hraj -> initial alif has no vowel +U+FDF2 > U+0644 U+0644 U+0647 ; +Z > ; diff --git a/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-voc.tec b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-voc.tec new file mode 100644 index 00000000000..9384beaaec7 Binary files /dev/null and b/Master/texmf-dist/fonts/misc/xetex/fontmapping/arabxetex/arabtex-voc.tec differ -- cgit v1.2.3