summaryrefslogtreecommitdiff
path: root/support/translit/koi8-7.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/koi8-7.rus
Initial commit
Diffstat (limited to 'support/translit/koi8-7.rus')
-rw-r--r--support/translit/koi8-7.rus120
1 files changed, 120 insertions, 0 deletions
diff --git a/support/translit/koi8-7.rus b/support/translit/koi8-7.rus
new file mode 100644
index 0000000000..8a5c737ea0
--- /dev/null
+++ b/support/translit/koi8-7.rus
@@ -0,0 +1,120 @@
+# Jan Labanowski, jkl@osc.edu, Jan 10, 1993
+# File koi8_7.rus
+
+# This is a transliteration data file for converting from KOI8 (RELCOM,
+# GOST 19768-74) to KOI7. The KOI7 character codes for Russian letters
+# overlap with Latin letters. To mark what is in Russian and what in English,
+# The SHIFT-OUT and SHIFT-IN characters are used. The SHIFT-OUT and SHIFT-IN
+# switch between Latin and Russian character set. The SHIFT-OUT switches
+# to Russian letters.
+# The SHIFT-OUT character is CTRL-N (\14 = \0x0E = \0o16).
+# The SHIFT-IN character is CTRL-O (\15 = \0x0F = \0o17). It switches back to
+# Latin characters. You might want to read comments in file koi7_8.rus
+#
+
+# 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, only one set of output characters
+
+ 2 # number of output SHIFT sequences, only one set of input characters
+ "" "" # Latin characters
+ "\0x0E" "\0x0F" # Russian letters ^N...^O
+# "{{" "}}" # Russian letters {{...}}
+
+
+# conversion table
+# ASCII characters (set 1) no-change
+# Russian letters could be given as a range like:
+# 0 [\0xA3\0xB3\0xFF\0xC0-\0xFE] 2 [#$"@-~]
+# but then we would miss the nice table for the humans
+
+
+# inp_set_numb inp_seq out_set_numb out_seq
+
+# This line is given here so the appropriate SHIFT-OUT/IN sequences are
+# sent to output. Note that it does not include control characters, spaces
+# digits, punctuation, etc., which can appear in both sets (at least this
+# is my understanding).
+
+ 0 [#$"@-~] 1 [#$"@-~] #Pass ASCII, no change
+
+# Russian letters
+ 0 "\0xA3" 2 "#" #small yo
+ 0 "\0xB3" 2 "$" #capital YO
+ 0 "\0xE1" 2 "a" #capital A
+ 0 "\0xE2" 2 "b" #capital Be
+ 0 "\0xF7" 2 "w" #capital Ve
+ 0 "\0xE7" 2 "g" #capital Ghe
+ 0 "\0xE4" 2 "d" #capital De
+ 0 "\0xE5" 2 "e" #capital Ie
+ 0 "\0xF6" 2 "v" #capital Zhe
+ 0 "\0xFA" 2 "z" #capital Ze
+ 0 "\0xE9" 2 "i" #capital I
+ 0 "\0xEA" 2 "j" #capital short I
+ 0 "\0xEB" 2 "k" #capital Ka
+ 0 "\0xEC" 2 "l" #capital El
+ 0 "\0xED" 2 "m" #capital Em
+ 0 "\0xEE" 2 "n" #capital En
+ 0 "\0xEF" 2 "o" #capital O
+ 0 "\0xF0" 2 "p" #capital Pe
+ 0 "\0xF2" 2 "r" #capital Er
+ 0 "\0xF3" 2 "s" #capital Es
+ 0 "\0xF4" 2 "t" #capital Te
+ 0 "\0xF5" 2 "u" #capital U
+ 0 "\0xE6" 2 "f" #capital Ef
+ 0 "\0xE8" 2 "h" #capital Kha
+ 0 "\0xE3" 2 "c" #capital Tse
+ 0 "\0xFE" 2 "~" #capital Che
+ 0 "\0xFB" 2 "{" #capital Sha
+ 0 "\0xFD" 2 "}" #capital Shcha
+ 0 "\0xFF" 2 "\0x22" #capital hard sign (Ier)
+ 0 "\0xF9" 2 "y" #capital Y (Iery)
+ 0 "\0xF8" 2 "x" #capit soft sign(Ierik)
+ 0 "\0xFC" 2 "|" #capit reverse rounded E
+ 0 "\0xE0" 2 "`" #capital Yu
+ 0 "\0xF1" 2 "q" #capital Ya
+ 0 "\0xC1" 2 "A" #small a
+ 0 "\0xC2" 2 "B" #small be
+ 0 "\0xD7" 2 "W" #small ve
+ 0 "\0xC7" 2 "G" #small ghe
+ 0 "\0xC4" 2 "D" #small de
+ 0 "\0xC5" 2 "E" #small ie
+ 0 "\0xD6" 2 "V" #small zhe
+ 0 "\0xDA" 2 "Z" #small z
+ 0 "\0xC9" 2 "I" #small i
+ 0 "\0xCA" 2 "J" #small short i
+ 0 "\0xCB" 2 "K" #small ka
+ 0 "\0xCC" 2 "L" #small el
+ 0 "\0xCD" 2 "M" #small em
+ 0 "\0xCE" 2 "N" #small en
+ 0 "\0xCF" 2 "O" #small o
+ 0 "\0xD0" 2 "P" #small pe
+ 0 "\0xD2" 2 "R" #small er
+ 0 "\0xD3" 2 "S" #small es
+ 0 "\0xD4" 2 "T" #small te
+ 0 "\0xD5" 2 "U" #small u
+ 0 "\0xC6" 2 "F" #small ef
+ 0 "\0xC8" 2 "H" #small kha
+ 0 "\0xC3" 2 "C" #small tse
+ 0 "\0xDE" 2 "^" #small che
+ 0 "\0xDB" 2 "[" #small sha
+ 0 "\0xDD" 2 "]" #small shcha
+ 0 "\0xDF" 2 "_" #small hard sign (ier)
+ 0 "\0xD9" 2 "Y" #small y (iery)
+ 0 "\0xD8" 2 "X" #small soft sign (ierik)
+ 0 "\0xDC" 2 "\" #small rev rounded e
+ 0 "\0xC0" 2 "@" #small yu
+ 0 "\0xD1" 2 "Q" #small ya