summaryrefslogtreecommitdiff
path: root/support/translit/koi8-phg.rus
diff options
context:
space:
mode:
authorNorbert Preining <norbert@preining.info>2019-09-02 13:46:59 +0900
committerNorbert Preining <norbert@preining.info>2019-09-02 13:46:59 +0900
commite0c6872cf40896c7be36b11dcc744620f10adf1d (patch)
tree60335e10d2f4354b0674ec22d7b53f0f8abee672 /support/translit/koi8-phg.rus
Initial commit
Diffstat (limited to 'support/translit/koi8-phg.rus')
-rw-r--r--support/translit/koi8-phg.rus112
1 files changed, 112 insertions, 0 deletions
diff --git a/support/translit/koi8-phg.rus b/support/translit/koi8-phg.rus
new file mode 100644
index 0000000000..cf50f9cf1a
--- /dev/null
+++ b/support/translit/koi8-phg.rus
@@ -0,0 +1,112 @@
+
+# Jan Labanowski, jkl@osc.edu, Dec. 30, 1992
+# File koi8-phg.rus
+
+# This is a transliteration data file for converting from
+# KOI8 as used by RELCOM to transliteration defined in the GOST 16876-71
+# standard.
+# Since I never had a chance to look at the GOST 16876-71 document,
+# the actual table is based on the info which I read on some list
+# (I believe it was posted by Glenn Thobe on RUS-TEX)
+# To be used with translit.c program by Jan Labanowski
+
+ 1 file version number
+
+ " " # string delimiters
+ [ ] # list delimites
+ { } # regular expression delimiters
+
+
+#starting sequence
+""
+
+
+#ending sequence
+""
+
+ 0 # number of input SHIFT sequences
+
+ 2 # number of output SHIFT sequences, only one set of output characters
+ "" "" # russian outside brackets
+ "{" "}" # ascii, inside brackets
+
+# conversion table
+
+# Latin(ASCII) is embraced in {}
+ 0 [A-Za-z] 2 [A-Za-z]
+
+# White space and control characters
+ 0 [\0x01-\0x20] 0 [\0x01-\0x20] # spaces and controll
+# punctuation and digits
+ 0 [\0x21-\0x26\0x28-\0x3F\0x5B-\0x5F\0x7C\0x7e]
+ 0 [\0x21-\0x26\0x28-\0x3F\0x5B-\0x5F\0x7C\0x7e]
+
+
+# inp_set_numb inp_seq out_set_numb out_seq
+ 0 "\0xE1" 1 "A" # capital A
+ 0 "\0xE2" 1 "B" # capital Be
+ 0 "\0xF7" 1 "V" # capital Ve
+ 0 "\0xE7" 1 "G" # capital Ghe
+ 0 "\0xE4" 1 "D" # capital De
+ 0 "\0xE5" 1 "E" # capital Je
+ 0 "\0xB3" 1 "JO" # capital Yo
+ 0 "\0xF6" 1 "ZH" # capital Zhe
+ 0 "\0xFA" 1 "Z" # capital Ze
+ 0 "\0xE9" 1 "I" # capital I
+ 0 "\0xEA" 1 "JJ" # capital short I
+ 0 "\0xEB" 1 "K" # capital Ka
+ 0 "\0xEC" 1 "L" # capital El
+ 0 "\0xED" 1 "M" # capital Em
+ 0 "\0xEE" 1 "N" # capital En
+ 0 "\0xEF" 1 "O" # capital O
+ 0 "\0xF0" 1 "P" # capital Pe
+ 0 "\0xF2" 1 "R" # capital Er
+ 0 "\0xF3" 1 "S" # capital Es
+ 0 "\0xF4" 1 "T" # capital Te
+ 0 "\0xF5" 1 "U" # capital U
+ 0 "\0xE6" 1 "F" # capital Ef
+ 0 "\0xE8" 1 "Kh" # capital Kha
+ 0 "\0xE3" 1 "C" # capital Tse
+ 0 "\0xFE" 1 "CH" # capital Che
+ 0 "\0xFB" 1 "SH" # capital Sha
+ 0 "\0xFD" 1 "HH" # capital Shcha
+ 0 "\0xFF" 1 "``" # capital hard sign (Ier)
+ 0 "\0xF9" 1 "Y" # capital Y (Iery)
+ 0 "\0xF8" 1 "`" # capital soft sign Ierik
+ 0 "\0xFC" 1 "EH" # capital reverse round E
+ 0 "\0xE0" 1 "JU" # capital Yu
+ 0 "\0xF1" 1 "JA" # capital Ya
+
+ 0 "\0xC1" 1 "a" # small a
+ 0 "\0xC2" 1 "b" # small be
+ 0 "\0xD7" 1 "v" # small ve
+ 0 "\0xC7" 1 "g" # small ghe
+ 0 "\0xC4" 1 "d" # small de
+ 0 "\0xC5" 1 "e" # small je
+ 0 "\0xA3" 1 "jo" # small yo
+ 0 "\0xD6" 1 "zh" # small zhe
+ 0 "\0xDA" 1 "z" # small z
+ 0 "\0xC9" 1 "i" # small i
+ 0 "\0xCA" 1 "jj" # small short i
+ 0 "\0xCB" 1 "k" # small ka
+ 0 "\0xCC" 1 "l" # small el
+ 0 "\0xCD" 1 "m" # small em
+ 0 "\0xCE" 1 "n" # small en
+ 0 "\0xCF" 1 "o" # small o
+ 0 "\0xD0" 1 "p" # small pe
+ 0 "\0xD2" 1 "r" # small er
+ 0 "\0xD3" 1 "s" # small es
+ 0 "\0xD4" 1 "t" # small te
+ 0 "\0xD5" 1 "u" # small u
+ 0 "\0xC6" 1 "f" # small ef
+ 0 "\0xC8" 1 "kh" # small kha
+ 0 "\0xC3" 1 "c" # small tse
+ 0 "\0xDE" 1 "ch" # small che
+ 0 "\0xDB" 1 "sh" # small sha
+ 0 "\0xDD" 1 "hh" # small shcha
+ 0 "\0xDF" 1 "''" # small hard sign (ier)
+ 0 "\0xD9" 1 "y" # small y (iery)
+ 0 "\0xD8" 1 "'" # small soft sign (ierik)
+ 0 "\0xDC" 1 "eh" # small reverse rounded e
+ 0 "\0xC0" 1 "ju" # small yu
+ 0 "\0xD1" 1 "ja" # small ya