summaryrefslogtreecommitdiff
path: root/support/translit/koi8-lc.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-lc.rus
Initial commit
Diffstat (limited to 'support/translit/koi8-lc.rus')
-rw-r--r--support/translit/koi8-lc.rus109
1 files changed, 109 insertions, 0 deletions
diff --git a/support/translit/koi8-lc.rus b/support/translit/koi8-lc.rus
new file mode 100644
index 0000000000..bb02650961
--- /dev/null
+++ b/support/translit/koi8-lc.rus
@@ -0,0 +1,109 @@
+# Jan Labanowski, jkl@osc.edu, Jan. 10, 1992
+# File koi8-lc.dat
+
+# This is a transliteration data file for converting from KOI-8 as used
+# by RELCOM (GOST 19768-74) to approximate Library of Congress (phonetic)
+# transliteration. I personally think, that LC transliteration is a bad one.
+# It is not possible to exactly represent Library of Congress transliteration
+# since it uses the accented letters which are not present in the ASCII
+# character set. Several changes are made to the letter of LC.
+# The English text has to be embraced in braces {}, while
+# the Russian one, is outside the braces.
+# To be used with translit.c program by Jan Labanowski. For a format of
+# this file consult translit documentation.
+
+ 1 file version number
+
+ " " # string delimiters
+ [ ] # list delimites
+ { } # regular expression delimiters
+
+
+
+#starting sequence for LaTeX
+""
+
+#ending sequence
+""
+
+ 0 # number of input SHIFT sequences, only one set of input characters
+
+ 2 # number of output SHIFT sequences, two sets of input characters
+
+# SHIFT-OUT SHIFT-IN
+ "" "" #cyrillic enclosed in {\cyr ... }
+ "{" "}" #shift sequences for Latin
+
+# conversion table
+# inp_set inp_seq out_set out_seq
+
+# Latin(ASCII) embrace it in {}
+ 0 ["'A-Za-z] 2 ["'A-Za-z]
+
+# Cyrillic letters
+ 0 "\0xA3" 1 "jo" # small jo
+ 0 "\0xB3" 1 "JO" # capital Jo
+ 0 "\0xE1" 1 "A"
+ 0 "\0xE2" 1 "B"
+ 0 "\0xF7" 1 "V"
+ 0 "\0xE7" 1 "G"
+ 0 "\0xE4" 1 "D"
+ 0 "\0xE5" 1 "E"
+ 0 "\0xF6" 1 "ZH"
+ 0 "\0xFA" 1 "Z"
+ 0 "\0xE9" 1 "I"
+ 0 "\0xEA" 1 "J" # I kratkoje
+ 0 "\0xEB" 1 "K"
+ 0 "\0xEC" 1 "L"
+ 0 "\0xED" 1 "M"
+ 0 "\0xEE" 1 "N"
+ 0 "\0xEF" 1 "O"
+ 0 "\0xF0" 1 "P"
+ 0 "\0xF2" 1 "R"
+ 0 "\0xF3" 1 "S"
+ 0 "\0xF4" 1 "T"
+ 0 "\0xF5" 1 "U"
+ 0 "\0xE6" 1 "F"
+ 0 "\0xE8" 1 "KH"
+ 0 "\0xE3" 1 "C"
+ 0 "\0xFE" 1 "Ch"
+ 0 "\0xFB" 1 "Sh"
+ 0 "\0xFD" 1 "Shch"
+ 0 "\0xFF" 1 "\0x22" # Tverdyj znak
+ 0 "\0xF9" 1 "Y"
+ 0 "\0xF8" 1 "'" # Myagkij znak
+ 0 "\0xFC" 1 "EH" # E oborotnoe
+ 0 "\0xE0" 1 "JU"
+ 0 "\0xF1" 1 "JA"
+ 0 "\0xC1" 1 "a"
+ 0 "\0xC2" 1 "b"
+ 0 "\0xD7" 1 "v"
+ 0 "\0xC7" 1 "g"
+ 0 "\0xC4" 1 "d"
+ 0 "\0xC5" 1 "e"
+ 0 "\0xD6" 1 "zh"
+ 0 "\0xDA" 1 "z"
+ 0 "\0xC9" 1 "i"
+ 0 "\0xCA" 1 "j"
+ 0 "\0xCB" 1 "k"
+ 0 "\0xCC" 1 "l"
+ 0 "\0xCD" 1 "m"
+ 0 "\0xCE" 1 "n"
+ 0 "\0xCF" 1 "o"
+ 0 "\0xD0" 1 "p"
+ 0 "\0xD2" 1 "r"
+ 0 "\0xD3" 1 "s"
+ 0 "\0xD4" 1 "t"
+ 0 "\0xD5" 1 "u"
+ 0 "\0xC6" 1 "f"
+ 0 "\0xC8" 1 "kh"
+ 0 "\0xC3" 1 "c"
+ 0 "\0xDE" 1 "ch"
+ 0 "\0xDB" 1 "sh"
+ 0 "\0xDD" 1 "shch"
+ 0 "\0xDF" 1 "\0x22"
+ 0 "\0xD9" 1 "y"
+ 0 "\0xD8" 1 "'"
+ 0 "\0xDC" 1 "eh" # e oborotnoe
+ 0 "\0xC0" 1 "ju"
+ 0 "\0xD1" 1 "ja"