home *** CD-ROM | disk | FTP | other *** search
/ Source Code 1994 March / Source_Code_CD-ROM_Walnut_Creek_March_1994.iso / compsrcs / misc / volume36 / translit / part09 < prev    next >
Encoding:
Text File  |  1993-03-21  |  58.6 KB  |  1,142 lines
  1. Newsgroups: comp.sources.misc
  2. From: jkl@osc.edu (Jan Labanowski)
  3. Subject: v36i031:  translit - transliterate foreign alphabets, Part09/10
  4. Message-ID: <1993Mar19.224622.12487@sparky.imd.sterling.com>
  5. X-Md4-Signature: c1d18917b7254ecd6c57514d32d390e8
  6. Date: Fri, 19 Mar 1993 22:46:22 GMT
  7. Approved: kent@sparky.imd.sterling.com
  8.  
  9. Submitted-by: jkl@osc.edu (Jan Labanowski)
  10. Posting-number: Volume 36, Issue 31
  11. Archive-name: translit/part09
  12. Environment: UNIX, MS-DOS, VMS
  13.  
  14.  
  15. #! /bin/sh
  16. # This is a shell archive.  Remove anything before this line, then feed it
  17. # into a shell via "sh file" or similar.  To overwrite existing files,
  18. # type "sh file -c".
  19. # Contents:  gos-alt.rus koi7-8.rus koi7nl-8.rus koi8-7.rus koi8-lc.rus
  20. #   koi8-phg.rus koi8-php.rus phg-koi8.rus php-koi8.rus
  21. # Wrapped by kent@sparky on Fri Mar 19 16:00:15 1993
  22. PATH=/bin:/usr/bin:/usr/ucb:/usr/local/bin:/usr/lbin ; export PATH
  23. echo If this archive is complete, you will see the following message:
  24. echo '          "shar: End of archive 9 (of 10)."'
  25. if test -f 'gos-alt.rus' -a "${1}" != "-c" ; then 
  26.   echo shar: Will not clobber existing file \"'gos-alt.rus'\"
  27. else
  28.   echo shar: Extracting \"'gos-alt.rus'\" \(5932 characters\)
  29.   sed "s/^X//" >'gos-alt.rus' <<'END_OF_FILE'
  30. X# Jan Labanowski, jkl@osc.edu, Dec. 30, 1992
  31. X# File gos_alt.rus
  32. X
  33. X# This is a transliteration data file for converting GOSTSCII 84
  34. X# (approx. ISO-8859-5?) to ALT (Bryabrins alternativnyj variant)
  35. X
  36. X# To be used with translit.c program by Jan Labanowski
  37. X
  38. X   1            file version number
  39. X
  40. X   "    "      # string delimiters
  41. X   [    ]      # list delimites
  42. X   {    }      # regular expression delimiters
  43. X
  44. X
  45. X#starting sequence
  46. X""
  47. X
  48. X
  49. X#ending sequence
  50. X""
  51. X
  52. X   0     # number of input SHIFT sequences, only one set of input characters
  53. X
  54. X   0     # number of output SHIFT sequences, only one set of output characters
  55. X  
  56. X# conversion table
  57. X# inp_set_numb  inp_seq        out_set_numb  out_seq
  58. X      0          "\0xA1"          0         "\0xf0"  # capital Yo
  59. X      0          "\0xF1"          0         "\0xf1"  # small yo
  60. X      0          "\0xB0"          0         "\0x80"  # capital A               
  61. X      0          "\0xB1"          0         "\0x81"  # capital Be              
  62. X      0          "\0xB2"          0         "\0x82"  # capital Ve              
  63. X      0          "\0xB3"          0         "\0x83"  # capital Ghe             
  64. X      0          "\0xB4"          0         "\0x84"  # capital De              
  65. X      0          "\0xB5"          0         "\0x85"  # capital Ie              
  66. X      0          "\0xB6"          0         "\0x86"  # capital Zhe             
  67. X      0          "\0xB7"          0         "\0x87"  # capital Ze              
  68. X      0          "\0xB8"          0         "\0x88"  # capital I               
  69. X      0          "\0xB9"          0         "\0x89"  # capital short I         
  70. X      0          "\0xBA"          0         "\0x8a"  # capital Ka              
  71. X      0          "\0xBB"          0         "\0x8b"  # capital El              
  72. X      0          "\0xBC"          0         "\0x8c"  # capital Em              
  73. X      0          "\0xBD"          0         "\0x8d"  # capital En              
  74. X      0          "\0xBE"          0         "\0x8e"  # capital O               
  75. X      0          "\0xBF"          0         "\0x8f"  # capital Pe              
  76. X      0          "\0xC0"          0         "\0x90"  # capital Er              
  77. X      0          "\0xC1"          0         "\0x91"  # capital Es              
  78. X      0          "\0xC2"          0         "\0x92"  # capital Te              
  79. X      0          "\0xC3"          0         "\0x93"  # capital U               
  80. X      0          "\0xC4"          0         "\0x94"  # capital Ef              
  81. X      0          "\0xC5"          0         "\0x95"  # capital Kha             
  82. X      0          "\0xC6"          0         "\0x96"  # capital Tse             
  83. X      0          "\0xC7"          0         "\0x97"  # capital Che             
  84. X      0          "\0xC8"          0         "\0x98"  # capital Sha             
  85. X      0          "\0xC9"          0         "\0x99"  # capital Shcha           
  86. X      0          "\0xCA"          0         "\0x9a"  # capital hard sign (Ier) 
  87. X      0          "\0xCB"          0         "\0x9b"  # capital Y (Iery)        
  88. X      0          "\0xCC"          0         "\0x9c"  # capital soft sign Ierik 
  89. X      0          "\0xCD"          0         "\0x9d"  # capital reverse round E 
  90. X      0          "\0xCE"          0         "\0x9e"  # capital Yu              
  91. X      0          "\0xCF"          0         "\0x9f"  # capital Ya              
  92. X      0          "\0xD0"          0         "\0xa0"  # small a                 
  93. X      0          "\0xD1"          0         "\0xa1"  # small be                
  94. X      0          "\0xD2"          0         "\0xa2"  # small ve                
  95. X      0          "\0xD3"          0         "\0xa3"  # small ghe               
  96. X      0          "\0xD4"          0         "\0xa4"  # small de                
  97. X      0          "\0xD5"          0         "\0xa5"  # small ie                
  98. X      0          "\0xD6"          0         "\0xa6"  # small zhe               
  99. X      0          "\0xD7"          0         "\0xa7"  # small z                 
  100. X      0          "\0xD8"          0         "\0xa8"  # small i                 
  101. X      0          "\0xD9"          0         "\0xa9"  # small short i           
  102. X      0          "\0xDA"          0         "\0xaa"  # small ka                
  103. X      0          "\0xDB"          0         "\0xab"  # small el                
  104. X      0          "\0xDC"          0         "\0xac"  # small em                
  105. X      0          "\0xDD"          0         "\0xad"  # small en                
  106. X      0          "\0xDE"          0         "\0xae"  # small o                 
  107. X      0          "\0xDF"          0         "\0xaf"  # small pe                
  108. X      0          "\0xE0"          0         "\0xe0"  # small er                
  109. X      0          "\0xE1"          0         "\0xe1"  # small es                
  110. X      0          "\0xE2"          0         "\0xe2"  # small te                
  111. X      0          "\0xE3"          0         "\0xe3"  # small u                 
  112. X      0          "\0xE4"          0         "\0xe4"  # small ef                
  113. X      0          "\0xE5"          0         "\0xe5"  # small kha               
  114. X      0          "\0xE6"          0         "\0xe6"  # small tse               
  115. X      0          "\0xE7"          0         "\0xe7"  # small che               
  116. X      0          "\0xE8"          0         "\0xe8"  # small sha               
  117. X      0          "\0xE9"          0         "\0xe9"  # small shcha             
  118. X      0          "\0xEA"          0         "\0xea"  # small hard sign (ier)   
  119. X      0          "\0xEB"          0         "\0xeb"  # small y (iery)          
  120. X      0          "\0xEC"          0         "\0xec"  # small soft sign (ierik) 
  121. X      0          "\0xED"          0         "\0xed"  # small reverse rounded e 
  122. X      0          "\0xEE"          0         "\0xee"  # small yu                
  123. X      0          "\0xEF"          0         "\0xef"  # small ya                
  124. END_OF_FILE
  125.   if test 5932 -ne `wc -c <'gos-alt.rus'`; then
  126.     echo shar: \"'gos-alt.rus'\" unpacked with wrong size!
  127.   fi
  128.   # end of 'gos-alt.rus'
  129. fi
  130. if test -f 'koi7-8.rus' -a "${1}" != "-c" ; then 
  131.   echo shar: Will not clobber existing file \"'koi7-8.rus'\"
  132. else
  133.   echo shar: Extracting \"'koi7-8.rus'\" \(8116 characters\)
  134.   sed "s/^X//" >'koi7-8.rus' <<'END_OF_FILE'
  135. X# Jan Labanowski, jkl@osc.edu, Dec. 30, 1992
  136. X# File koi7_8.rus
  137. X
  138. X# This is a transliteration data file for converting from KOI7 to
  139. X# KOI8 (RELCOM-GOST 19768-74). The KOI7 character codes for Russian letters
  140. X# overlap with Latin letters. To mark what is in Russian and what in English,
  141. X# The SHIFT-OUT and SHIFT-IN characters are used: The SHIFT-OUT and SHIFT-IN 
  142. X# switch between Latin and Russian character set. The SHIFT-OUT switches
  143. X# to Russian letters. If the sequence of Russian characters does not start
  144. X# with the SHIFT-OUT character, it will be treated as English text!
  145. X# The SHIFT-OUT character is CTRL-N (\14 = \0x0E = \0o16).
  146. X# The SHIFT-IN character is CTRL-O (\15 = \0x0F = \0o17). It switches back to
  147. X# Latin characters. 
  148. X# If the SHIFT-OUT character is not present, whole file is assumed to be
  149. X# written in Latin alphabet.
  150. X# On the practical side: The KOI7 characters are frequently obtained
  151. X# from KOI8 character set as a result of transmission through the network.
  152. X# In most cases, the electronic-mail strips the 8th bit of KOI8 character
  153. X# set changing it to KOI7. The problem is that in this case, there is no
  154. X# SHIFT-IN and SHIFT-OUT codes to signal which characters are Latin and
  155. X# which are Russian. In this case, buy using the editor, YOU HAVE TO ENCLOSE
  156. X# RUSSIAN TEXT inside the appropriate SHIFT-OUT and SHIFT-IN sequence.
  157. X# To obtain a true KOI7 file, these should be CTRL-N and CTRL-O, respectively.
  158. X# However, It is sometimes difficult to obtain this control characters within
  159. X# an editor. In this case, you may use your own character, but they should
  160. X# not apear elsewhere in the text. Unfortunately, most "good" characters
  161. X# are taken. I think that it is better to use a two-character sequence in
  162. X# this situation. You are free to use your own, but I would suggest that you
  163. X# stick with {{ (as SHIFT-OUT) and }} as SHIFT-IN (they correspoind to:
  164. X# sh-sh and shch-shch in KOI7). Of course, if they appear in your KOI7
  165. X# text you need to use something else. To use these characters, you need to
  166. X# make following changes in the section of this file where input SHIFT-OUT/IN
  167. X# sequences are read in:
  168. X# 1) uncomment (i.e., delete # character in the first column):
  169. X#  #   "{{"    ""    ""    ""    "}}"      ""         # Russian letters {{...}}
  170. X# 2) comment (i.e., put # in the first column)
  171. X#  "\0x0E"  ""    ""    ""    "\0x0F"   ""         # Russian letters ^N...^O
  172. X
  173. X
  174. X# To be used with translit.c program by Jan Labanowski
  175. X
  176. X   1            file version number
  177. X
  178. X   "    "      # string delimiters
  179. X   [    ]      # list delimites
  180. X   {    }      # regular expression delimiters
  181. X
  182. X
  183. X#starting sequence
  184. X""
  185. X
  186. X
  187. X#ending sequence
  188. X""
  189. X
  190. X   2     # number of input SHIFT sequences, only one set of input characters
  191. X   ""      ""    ""    ""    ""        ""         # Latin characters
  192. X   "\0x0E"  ""    ""    ""    "\0x0F"   ""         # Russian letters ^N...^O
  193. X#   "{{"     ""    ""    ""    "}}"      ""         # Russian letters {{...}}
  194. X
  195. X   0     # number of output SHIFT sequences, only one set of output characters
  196. X  
  197. X# conversion table
  198. X#   ASCII characters (set 1) no-change
  199. X#   Russian letters have to be entered explicitly (we could use a simple
  200. X#   range like:
  201. X#   2  [#$"@-~]  0   [\0xA3\0xB3\0xFF\0xC0-\0xFE]
  202. X#  but then we would miss the nice table for the humans).
  203. X
  204. X# inp_set_numb  inp_seq        out_set_numb  out_seq
  205. X      1    [\0x21-\0x7F]          0  [\0x21-\0x7F]     #Pass  ASCII, no change
  206. X
  207. X# Leave the " as a quote if it is at the beginning or end of the word
  208. X# Change it to hard sign only if it is inside the word
  209. X2 {([][\0x7d{A-Za-z\|~@'/])\0x22([][\0x7d{A-Za-z\|~@'/])}
  210. X                                 -1        {\1\0xFF\2} # hard sign
  211. X      2           "#"             0          "\0xA3"   #small yo
  212. X      2           "$"             0          "\0xB3"   #capital YO
  213. X      2           "a"             0          "\0xE1"   #capital  A
  214. X      2           "b"             0          "\0xE2"   #capital  Be
  215. X      2           "w"             0          "\0xF7"   #capital  Ve
  216. X      2           "g"             0          "\0xE7"   #capital  Ghe
  217. X      2           "d"             0          "\0xE4"   #capital  De
  218. X      2           "e"             0          "\0xE5"   #capital  Ie
  219. X      2           "v"             0          "\0xF6"   #capital  Zhe
  220. X      2           "z"             0          "\0xFA"   #capital  Ze
  221. X      2           "i"             0          "\0xE9"   #capital  I
  222. X      2           "j"             0          "\0xEA"   #capital  short I
  223. X      2           "k"             0          "\0xEB"   #capital  Ka
  224. X      2           "l"             0          "\0xEC"   #capital  El
  225. X      2           "m"             0          "\0xED"   #capital  Em
  226. X      2           "n"             0          "\0xEE"   #capital  En
  227. X      2           "o"             0          "\0xEF"   #capital  O
  228. X      2           "p"             0          "\0xF0"   #capital  Pe
  229. X      2           "r"             0          "\0xF2"   #capital  Er
  230. X      2           "s"             0          "\0xF3"   #capital  Es
  231. X      2           "t"             0          "\0xF4"   #capital  Te
  232. X      2           "u"             0          "\0xF5"   #capital  U
  233. X      2           "f"             0          "\0xE6"   #capital  Ef
  234. X      2           "h"             0          "\0xE8"   #capital  Kha
  235. X      2           "c"             0          "\0xE3"   #capital  Tse
  236. X      2           "~"             0          "\0xFE"   #capital  Che
  237. X      2           "{"             0          "\0xFB"   #capital  Sha
  238. X      2           "}"             0          "\0xFD"   #capital  Shcha
  239. X      2           "y"             0          "\0xF9"   #capital  Y (Iery)
  240. X      2           "x"             0          "\0xF8"   #capit soft sign(Ierik)
  241. X      2           "|"             0          "\0xFC"   #capit reverse rounded E
  242. X      2           "`"             0          "\0xE0"   #capital  Yu
  243. X      2           "q"             0          "\0xF1"   #capital  Ya
  244. X      2           "A"             0          "\0xC1"   #small  a
  245. X      2           "B"             0          "\0xC2"   #small  be
  246. X      2           "W"             0          "\0xD7"   #small  ve
  247. X      2           "G"             0          "\0xC7"   #small  ghe
  248. X      2           "D"             0          "\0xC4"   #small  de
  249. X      2           "E"             0          "\0xC5"   #small  ie
  250. X      2           "V"             0          "\0xD6"   #small  zhe
  251. X      2           "Z"             0          "\0xDA"   #small  z
  252. X      2           "I"             0          "\0xC9"   #small  i
  253. X      2           "J"             0          "\0xCA"   #small  short i
  254. X      2           "K"             0          "\0xCB"   #small  ka
  255. X      2           "L"             0          "\0xCC"   #small  el
  256. X      2           "M"             0          "\0xCD"   #small  em
  257. X      2           "N"             0          "\0xCE"   #small  en
  258. X      2           "O"             0          "\0xCF"   #small  o
  259. X      2           "P"             0          "\0xD0"   #small  pe
  260. X      2           "R"             0          "\0xD2"   #small  er
  261. X      2           "S"             0          "\0xD3"   #small  es
  262. X      2           "T"             0          "\0xD4"   #small  te
  263. X      2           "U"             0          "\0xD5"   #small  u
  264. X      2           "F"             0          "\0xC6"   #small  ef
  265. X      2           "H"             0          "\0xC8"   #small  kha
  266. X      2           "C"             0          "\0xC3"   #small  tse
  267. X      2           "^"             0          "\0xDE"   #small  che
  268. X      2           "["             0          "\0xDB"   #small  sha
  269. X      2           "]"             0          "\0xDD"   #small  shcha
  270. X      2           "_"             0          "\0xDF"   #small hard sign (ier)
  271. X      2           "Y"             0          "\0xD9"   #small  y (iery)
  272. X      2           "X"             0          "\0xD8"   #small soft sign (ierik)
  273. X      2           "\"             0          "\0xDC"   #small  rev rounded e
  274. X      2           "@"             0          "\0xC0"   #small  yu
  275. X      2           "Q"             0          "\0xD1"   #small  ya
  276. END_OF_FILE
  277.   if test 8116 -ne `wc -c <'koi7-8.rus'`; then
  278.     echo shar: \"'koi7-8.rus'\" unpacked with wrong size!
  279.   fi
  280.   # end of 'koi7-8.rus'
  281. fi
  282. if test -f 'koi7nl-8.rus' -a "${1}" != "-c" ; then 
  283.   echo shar: Will not clobber existing file \"'koi7nl-8.rus'\"
  284. else
  285.   echo shar: Extracting \"'koi7nl-8.rus'\" \(5350 characters\)
  286.   sed "s/^X//" >'koi7nl-8.rus' <<'END_OF_FILE'
  287. X# Jan Labanowski, jkl@osc.edu, Dec. 30, 1992
  288. X# File koi7nl_8.rus
  289. X
  290. X# This is a transliteration data file for converting from KOI7 to
  291. X# KOI8 (RELCOM-GOST 19768-74). The KOI7 character codes for Russian letters
  292. X# overlap with Latin letters.  This file assumes that there are no Latin
  293. X# letters in the file (i.e., file is entirely in Russian).
  294. X
  295. X# To be used with translit.c program by Jan Labanowski
  296. X
  297. X   1            file version number
  298. X
  299. X   "    "      # string delimiters
  300. X   [    ]      # list delimites
  301. X   {    }      # regular expression delimiters
  302. X
  303. X
  304. X#starting sequence
  305. X""
  306. X
  307. X
  308. X#ending sequence
  309. X""
  310. X
  311. X   0     # number of input SHIFT sequences, only one set of input characters
  312. X   0     # number of output SHIFT sequences, only one set of output characters
  313. X  
  314. X# conversion table
  315. X
  316. X# inp_set_numb  inp_seq        out_set_numb  out_seq
  317. X      0           "#"             0          "\0xA3"   #small yo
  318. X      0           "$"             0          "\0xB3"   #capital YO
  319. X      0           "a"             0          "\0xE1"   #capital  A
  320. X      0           "b"             0          "\0xE2"   #capital  Be
  321. X      0           "w"             0          "\0xF7"   #capital  Ve
  322. X      0           "g"             0          "\0xE7"   #capital  Ghe
  323. X      0           "d"             0          "\0xE4"   #capital  De
  324. X      0           "e"             0          "\0xE5"   #capital  Ie
  325. X      0           "v"             0          "\0xF6"   #capital  Zhe
  326. X      0           "z"             0          "\0xFA"   #capital  Ze
  327. X      0           "i"             0          "\0xE9"   #capital  I
  328. X      0           "j"             0          "\0xEA"   #capital  short I
  329. X      0           "k"             0          "\0xEB"   #capital  Ka
  330. X      0           "l"             0          "\0xEC"   #capital  El
  331. X      0           "m"             0          "\0xED"   #capital  Em
  332. X      0           "n"             0          "\0xEE"   #capital  En
  333. X      0           "o"             0          "\0xEF"   #capital  O
  334. X      0           "p"             0          "\0xF0"   #capital  Pe
  335. X      0           "r"             0          "\0xF2"   #capital  Er
  336. X      0           "s"             0          "\0xF3"   #capital  Es
  337. X      0           "t"             0          "\0xF4"   #capital  Te
  338. X      0           "u"             0          "\0xF5"   #capital  U
  339. X      0           "f"             0          "\0xE6"   #capital  Ef
  340. X      0           "h"             0          "\0xE8"   #capital  Kha
  341. X      0           "c"             0          "\0xE3"   #capital  Tse
  342. X      0           "~"             0          "\0xFE"   #capital  Che
  343. X      0           "{"             0          "\0xFB"   #capital  Sha
  344. X      0           "}"             0          "\0xFD"   #capital  Shcha
  345. X      0           "\0x22"         0          "\0xFF"   #capital hard sign (Ier)
  346. X      0           "y"             0          "\0xF9"   #capital  Y (Iery)
  347. X      0           "x"             0          "\0xF8"   #capit soft sign(Ierik)
  348. X      0           "|"             0          "\0xFC"   #capit reverse rounded E
  349. X      0           "`"             0          "\0xE0"   #capital  Yu
  350. X      0           "q"             0          "\0xF1"   #capital  Ya
  351. X      0           "A"             0          "\0xC1"   #small  a
  352. X      0           "B"             0          "\0xC2"   #small  be
  353. X      0           "W"             0          "\0xD7"   #small  ve
  354. X      0           "G"             0          "\0xC7"   #small  ghe
  355. X      0           "D"             0          "\0xC4"   #small  de
  356. X      0           "E"             0          "\0xC5"   #small  ie
  357. X      0           "V"             0          "\0xD6"   #small  zhe
  358. X      0           "Z"             0          "\0xDA"   #small  z
  359. X      0           "I"             0          "\0xC9"   #small  i
  360. X      0           "J"             0          "\0xCA"   #small  short i
  361. X      0           "K"             0          "\0xCB"   #small  ka
  362. X      0           "L"             0          "\0xCC"   #small  el
  363. X      0           "M"             0          "\0xCD"   #small  em
  364. X      0           "N"             0          "\0xCE"   #small  en
  365. X      0           "O"             0          "\0xCF"   #small  o
  366. X      0           "P"             0          "\0xD0"   #small  pe
  367. X      0           "R"             0          "\0xD2"   #small  er
  368. X      0           "S"             0          "\0xD3"   #small  es
  369. X      0           "T"             0          "\0xD4"   #small  te
  370. X      0           "U"             0          "\0xD5"   #small  u
  371. X      0           "F"             0          "\0xC6"   #small  ef
  372. X      0           "H"             0          "\0xC8"   #small  kha
  373. X      0           "C"             0          "\0xC3"   #small  tse
  374. X      0           "^"             0          "\0xDE"   #small  che
  375. X      0           "["             0          "\0xDB"   #small  sha
  376. X      0           "]"             0          "\0xDD"   #small  shcha
  377. X      0           "_"             0          "\0xDF"   #small hard sign (ier)
  378. X      0           "Y"             0          "\0xD9"   #small  y (iery)
  379. X      0           "X"             0          "\0xD8"   #small soft sign (ierik)
  380. X      0           "\"             0          "\0xDC"   #small  rev rounded e
  381. X      0           "@"             0          "\0xC0"   #small  yu
  382. X      0           "Q"             0          "\0xD1"   #small  ya
  383. END_OF_FILE
  384.   if test 5350 -ne `wc -c <'koi7nl-8.rus'`; then
  385.     echo shar: \"'koi7nl-8.rus'\" unpacked with wrong size!
  386.   fi
  387.   # end of 'koi7nl-8.rus'
  388. fi
  389. if test -f 'koi8-7.rus' -a "${1}" != "-c" ; then 
  390.   echo shar: Will not clobber existing file \"'koi8-7.rus'\"
  391. else
  392.   echo shar: Extracting \"'koi8-7.rus'\" \(6368 characters\)
  393.   sed "s/^X//" >'koi8-7.rus' <<'END_OF_FILE'
  394. X# Jan Labanowski, jkl@osc.edu, Jan 10, 1993
  395. X# File koi8_7.rus
  396. X
  397. X# This is a transliteration data file for converting from  KOI8 (RELCOM,
  398. X# GOST 19768-74) to KOI7. The KOI7 character codes for Russian letters
  399. X# overlap with Latin letters. To mark what is in Russian and what in English,
  400. X# The SHIFT-OUT and SHIFT-IN characters are used. The SHIFT-OUT and SHIFT-IN 
  401. X# switch between Latin and Russian character set. The SHIFT-OUT switches
  402. X# to Russian letters. 
  403. X# The SHIFT-OUT character is CTRL-N (\14 = \0x0E = \0o16).
  404. X# The SHIFT-IN character is CTRL-O (\15 = \0x0F = \0o17). It switches back to
  405. X# Latin characters. You might want to read comments in file koi7_8.rus
  406. X#
  407. X
  408. X# To be used with translit.c program by Jan Labanowski
  409. X
  410. X   1            file version number
  411. X
  412. X   "    "      # string delimiters
  413. X   [    ]      # list delimites
  414. X   {    }      # regular expression delimiters
  415. X
  416. X
  417. X#starting sequence
  418. X""
  419. X
  420. X
  421. X#ending sequence
  422. X""
  423. X   0     # number of input SHIFT sequences, only one set of output characters
  424. X
  425. X   2     # number of output SHIFT sequences, only one set of input characters
  426. X   ""        ""         # Latin characters
  427. X   "\0x0E"   "\0x0F"    # Russian letters ^N...^O
  428. X#   "{{"      "}}"       # Russian letters {{...}}
  429. X
  430. X  
  431. X# conversion table
  432. X#   ASCII characters (set 1) no-change
  433. X#   Russian letters could be given as a range like:
  434. X#     0   [\0xA3\0xB3\0xFF\0xC0-\0xFE] 2  [#$"@-~]
  435. X#  but then we would miss the nice table for the humans
  436. X
  437. X
  438. X# inp_set_numb  inp_seq        out_set_numb  out_seq
  439. X
  440. X# This line is given here so the appropriate SHIFT-OUT/IN sequences are
  441. X# sent to output. Note that it does not include control characters, spaces
  442. X# digits, punctuation, etc.,  which can appear in both sets (at least this
  443. X# is my understanding).
  444. X
  445. X    0          [#$"@-~]          1      [#$"@-~]      #Pass  ASCII, no change
  446. X
  447. X# Russian letters
  448. X    0          "\0xA3"           2           "#"       #small yo
  449. X    0          "\0xB3"           2           "$"       #capital YO
  450. X    0          "\0xE1"           2           "a"       #capital  A
  451. X    0          "\0xE2"           2           "b"       #capital  Be
  452. X    0          "\0xF7"           2           "w"       #capital  Ve
  453. X    0          "\0xE7"           2           "g"       #capital  Ghe
  454. X    0          "\0xE4"           2           "d"       #capital  De
  455. X    0          "\0xE5"           2           "e"       #capital  Ie
  456. X    0          "\0xF6"           2           "v"       #capital  Zhe
  457. X    0          "\0xFA"           2           "z"       #capital  Ze
  458. X    0          "\0xE9"           2           "i"       #capital  I
  459. X    0          "\0xEA"           2           "j"       #capital  short I
  460. X    0          "\0xEB"           2           "k"       #capital  Ka
  461. X    0          "\0xEC"           2           "l"       #capital  El
  462. X    0          "\0xED"           2           "m"       #capital  Em
  463. X    0          "\0xEE"           2           "n"       #capital  En
  464. X    0          "\0xEF"           2           "o"       #capital  O
  465. X    0          "\0xF0"           2           "p"       #capital  Pe
  466. X    0          "\0xF2"           2           "r"       #capital  Er
  467. X    0          "\0xF3"           2           "s"       #capital  Es
  468. X    0          "\0xF4"           2           "t"       #capital  Te
  469. X    0          "\0xF5"           2           "u"       #capital  U
  470. X    0          "\0xE6"           2           "f"       #capital  Ef
  471. X    0          "\0xE8"           2           "h"       #capital  Kha
  472. X    0          "\0xE3"           2           "c"       #capital  Tse
  473. X    0          "\0xFE"           2           "~"       #capital  Che
  474. X    0          "\0xFB"           2           "{"       #capital  Sha
  475. X    0          "\0xFD"           2           "}"       #capital  Shcha
  476. X    0          "\0xFF"           2           "\0x22"   #capital hard sign (Ier)
  477. X    0          "\0xF9"           2           "y"       #capital  Y (Iery)
  478. X    0          "\0xF8"           2           "x"       #capit soft sign(Ierik)
  479. X    0          "\0xFC"           2           "|"       #capit reverse rounded E
  480. X    0          "\0xE0"           2           "`"       #capital  Yu
  481. X    0          "\0xF1"           2           "q"       #capital  Ya
  482. X    0          "\0xC1"           2           "A"       #small  a
  483. X    0          "\0xC2"           2           "B"       #small  be
  484. X    0          "\0xD7"           2           "W"       #small  ve
  485. X    0          "\0xC7"           2           "G"       #small  ghe
  486. X    0          "\0xC4"           2           "D"       #small  de
  487. X    0          "\0xC5"           2           "E"       #small  ie
  488. X    0          "\0xD6"           2           "V"       #small  zhe
  489. X    0          "\0xDA"           2           "Z"       #small  z
  490. X    0          "\0xC9"           2           "I"       #small  i
  491. X    0          "\0xCA"           2           "J"       #small  short i
  492. X    0          "\0xCB"           2           "K"       #small  ka
  493. X    0          "\0xCC"           2           "L"       #small  el
  494. X    0          "\0xCD"           2           "M"       #small  em
  495. X    0          "\0xCE"           2           "N"       #small  en
  496. X    0          "\0xCF"           2           "O"       #small  o
  497. X    0          "\0xD0"           2           "P"       #small  pe
  498. X    0          "\0xD2"           2           "R"       #small  er
  499. X    0          "\0xD3"           2           "S"       #small  es
  500. X    0          "\0xD4"           2           "T"       #small  te
  501. X    0          "\0xD5"           2           "U"       #small  u
  502. X    0          "\0xC6"           2           "F"       #small  ef
  503. X    0          "\0xC8"           2           "H"       #small  kha
  504. X    0          "\0xC3"           2           "C"       #small  tse
  505. X    0          "\0xDE"           2           "^"       #small  che
  506. X    0          "\0xDB"           2           "["       #small  sha
  507. X    0          "\0xDD"           2           "]"       #small  shcha
  508. X    0          "\0xDF"           2           "_"       #small hard sign (ier)
  509. X    0          "\0xD9"           2           "Y"       #small  y (iery)
  510. X    0          "\0xD8"           2           "X"       #small soft sign (ierik)
  511. X    0          "\0xDC"           2           "\"       #small  rev rounded e
  512. X    0          "\0xC0"           2           "@"       #small  yu
  513. X    0          "\0xD1"           2           "Q"       #small  ya
  514. END_OF_FILE
  515.   if test 6368 -ne `wc -c <'koi8-7.rus'`; then
  516.     echo shar: \"'koi8-7.rus'\" unpacked with wrong size!
  517.   fi
  518.   # end of 'koi8-7.rus'
  519. fi
  520. if test -f 'koi8-lc.rus' -a "${1}" != "-c" ; then 
  521.   echo shar: Will not clobber existing file \"'koi8-lc.rus'\"
  522. else
  523.   echo shar: Extracting \"'koi8-lc.rus'\" \(5463 characters\)
  524.   sed "s/^X//" >'koi8-lc.rus' <<'END_OF_FILE'
  525. X# Jan Labanowski, jkl@osc.edu, Jan. 10, 1992
  526. X# File koi8-lc.dat
  527. X
  528. X# This is a transliteration data file for converting from KOI-8 as used
  529. X# by RELCOM (GOST 19768-74) to approximate Library of Congress (phonetic)
  530. X# transliteration. I personally think, that LC transliteration is a bad one.
  531. X# It is not possible to exactly represent Library of Congress transliteration
  532. X# since it uses the accented letters which are not present in the ASCII
  533. X# character set. Several changes are made to the letter of LC.
  534. X# The English text has to be embraced in braces {}, while
  535. X# the Russian one, is outside the braces.
  536. X# To be used with translit.c program by Jan Labanowski. For a format of
  537. X# this file consult translit documentation.
  538. X
  539. X   1            file version number
  540. X
  541. X   "    "      # string delimiters
  542. X   [    ]      # list delimites
  543. X   {    }      # regular expression delimiters
  544. X
  545. X
  546. X
  547. X#starting sequence for LaTeX
  548. X""
  549. X
  550. X#ending sequence
  551. X""
  552. X
  553. X   0     # number of input SHIFT sequences, only one set of input characters
  554. X
  555. X   2     # number of output SHIFT sequences, two sets of input characters
  556. X  
  557. X# SHIFT-OUT      SHIFT-IN
  558. X    ""             ""         #cyrillic enclosed in {\cyr ... }
  559. X    "{"            "}"        #shift sequences for Latin
  560. X
  561. X# conversion table
  562. X# inp_set     inp_seq           out_set    out_seq
  563. X
  564. X# Latin(ASCII) embrace it in {}
  565. X     0  ["'A-Za-z]                   2      ["'A-Za-z]
  566. X     
  567. X# Cyrillic letters  
  568. X     0         "\0xA3"              1       "jo"    # small jo
  569. X     0         "\0xB3"              1       "JO"    # capital Jo
  570. X     0         "\0xE1"              1       "A"             
  571. X     0         "\0xE2"              1       "B"             
  572. X     0         "\0xF7"              1       "V"             
  573. X     0         "\0xE7"              1        "G"             
  574. X     0         "\0xE4"              1       "D"             
  575. X     0         "\0xE5"              1       "E"             
  576. X     0         "\0xF6"              1       "ZH"            
  577. X     0         "\0xFA"              1       "Z"             
  578. X     0         "\0xE9"              1       "I"             
  579. X     0         "\0xEA"              1       "J"     # I kratkoje 
  580. X     0         "\0xEB"              1       "K"             
  581. X     0         "\0xEC"              1       "L"             
  582. X     0         "\0xED"              1       "M"             
  583. X     0         "\0xEE"              1       "N"             
  584. X     0         "\0xEF"              1       "O"             
  585. X     0         "\0xF0"              1       "P"             
  586. X     0         "\0xF2"              1       "R"             
  587. X     0         "\0xF3"              1       "S"             
  588. X     0         "\0xF4"              1       "T"             
  589. X     0         "\0xF5"              1       "U"             
  590. X     0         "\0xE6"              1       "F"             
  591. X     0         "\0xE8"              1       "KH"            
  592. X     0         "\0xE3"              1       "C"             
  593. X     0         "\0xFE"              1       "Ch"            
  594. X     0         "\0xFB"              1       "Sh"            
  595. X     0         "\0xFD"              1       "Shch"          
  596. X     0         "\0xFF"              1       "\0x22"   # Tverdyj znak 
  597. X     0         "\0xF9"              1       "Y"             
  598. X     0         "\0xF8"              1       "'"    # Myagkij znak 
  599. X     0         "\0xFC"              1       "EH"   # E oborotnoe
  600. X     0         "\0xE0"              1       "JU"            
  601. X     0         "\0xF1"              1       "JA"            
  602. X     0         "\0xC1"              1       "a"             
  603. X     0         "\0xC2"              1       "b"             
  604. X     0         "\0xD7"              1       "v"             
  605. X     0         "\0xC7"              1       "g"             
  606. X     0         "\0xC4"              1       "d"             
  607. X     0         "\0xC5"              1       "e"             
  608. X     0         "\0xD6"              1       "zh"            
  609. X     0         "\0xDA"              1       "z"             
  610. X     0         "\0xC9"              1       "i"             
  611. X     0         "\0xCA"              1       "j"             
  612. X     0         "\0xCB"              1       "k"             
  613. X     0         "\0xCC"              1       "l"             
  614. X     0         "\0xCD"              1       "m"             
  615. X     0         "\0xCE"              1       "n"             
  616. X     0         "\0xCF"              1       "o"             
  617. X     0         "\0xD0"              1       "p"             
  618. X     0         "\0xD2"              1       "r"             
  619. X     0         "\0xD3"              1       "s"             
  620. X     0         "\0xD4"              1       "t"             
  621. X     0         "\0xD5"              1       "u"             
  622. X     0         "\0xC6"              1       "f"             
  623. X     0         "\0xC8"              1       "kh"            
  624. X     0         "\0xC3"              1       "c"             
  625. X     0         "\0xDE"              1       "ch"            
  626. X     0         "\0xDB"              1       "sh"            
  627. X     0         "\0xDD"              1       "shch"          
  628. X     0         "\0xDF"              1       "\0x22"    
  629. X     0         "\0xD9"              1       "y"             
  630. X     0         "\0xD8"              1       "'"     
  631. X     0         "\0xDC"              1       "eh"       # e oborotnoe
  632. X     0         "\0xC0"              1       "ju"            
  633. X     0         "\0xD1"              1       "ja"            
  634. END_OF_FILE
  635.   if test 5463 -ne `wc -c <'koi8-lc.rus'`; then
  636.     echo shar: \"'koi8-lc.rus'\" unpacked with wrong size!
  637.   fi
  638.   # end of 'koi8-lc.rus'
  639. fi
  640. if test -f 'koi8-phg.rus' -a "${1}" != "-c" ; then 
  641.   echo shar: Will not clobber existing file \"'koi8-phg.rus'\"
  642. else
  643.   echo shar: Extracting \"'koi8-phg.rus'\" \(5726 characters\)
  644.   sed "s/^X//" >'koi8-phg.rus' <<'END_OF_FILE'
  645. X
  646. X# Jan Labanowski, jkl@osc.edu, Dec. 30, 1992
  647. X# File koi8-phg.rus
  648. X
  649. X# This is a transliteration data file for converting from
  650. X# KOI8 as used by RELCOM to transliteration defined in the GOST 16876-71
  651. X# standard.
  652. X# Since I never had a chance to look at the GOST 16876-71 document,
  653. X# the actual table is based on the info which I read on some list
  654. X# (I believe it was posted by Glenn Thobe on RUS-TEX)
  655. X# To be used with translit.c program by Jan Labanowski
  656. X
  657. X   1            file version number
  658. X
  659. X   "    "      # string delimiters
  660. X   [    ]      # list delimites
  661. X   {    }      # regular expression delimiters
  662. X
  663. X
  664. X#starting sequence
  665. X""
  666. X
  667. X
  668. X#ending sequence
  669. X""
  670. X
  671. X   0     # number of input SHIFT sequences
  672. X
  673. X   2     # number of output SHIFT sequences, only one set of output characters
  674. X   ""    ""            # russian outside brackets
  675. X   "{"   "}"           # ascii, inside brackets
  676. X  
  677. X# conversion table
  678. X
  679. X# Latin(ASCII) is embraced in {}
  680. X     0         [A-Za-z]        2  [A-Za-z]
  681. X
  682. X# White space and control characters
  683. X     0         [\0x01-\0x20]        0  [\0x01-\0x20]  # spaces and controll
  684. X# punctuation and digits
  685. X     0  [\0x21-\0x26\0x28-\0x3F\0x5B-\0x5F\0x7C\0x7e]
  686. X                               0 [\0x21-\0x26\0x28-\0x3F\0x5B-\0x5F\0x7C\0x7e]
  687. X
  688. X
  689. X# inp_set_numb  inp_seq        out_set_numb  out_seq
  690. X     0          "\0xE1"           1     "A"          # capital A
  691. X     0          "\0xE2"           1     "B"          # capital Be
  692. X     0          "\0xF7"           1     "V"          # capital Ve
  693. X     0          "\0xE7"           1     "G"          # capital Ghe
  694. X     0          "\0xE4"           1     "D"          # capital De
  695. X     0          "\0xE5"           1     "E"          # capital Je
  696. X     0          "\0xB3"           1     "JO"         # capital Yo
  697. X     0          "\0xF6"           1     "ZH"         # capital Zhe
  698. X     0          "\0xFA"           1     "Z"          # capital Ze
  699. X     0          "\0xE9"           1     "I"          # capital I
  700. X     0          "\0xEA"           1     "JJ"         # capital short I
  701. X     0          "\0xEB"           1     "K"          # capital Ka
  702. X     0          "\0xEC"           1     "L"          # capital El
  703. X     0          "\0xED"           1     "M"          # capital Em
  704. X     0          "\0xEE"           1     "N"          # capital En
  705. X     0          "\0xEF"           1     "O"          # capital O
  706. X     0          "\0xF0"           1     "P"          # capital Pe
  707. X     0          "\0xF2"           1     "R"          # capital Er
  708. X     0          "\0xF3"           1     "S"          # capital Es
  709. X     0          "\0xF4"           1     "T"          # capital Te
  710. X     0          "\0xF5"           1     "U"          # capital U
  711. X     0          "\0xE6"           1     "F"          # capital Ef
  712. X     0          "\0xE8"           1     "Kh"         # capital Kha
  713. X     0          "\0xE3"           1     "C"          # capital Tse
  714. X     0          "\0xFE"           1     "CH"         # capital Che
  715. X     0          "\0xFB"           1     "SH"         # capital Sha
  716. X     0          "\0xFD"           1     "HH"         # capital Shcha
  717. X     0          "\0xFF"           1     "``"         # capital hard sign (Ier)
  718. X     0          "\0xF9"           1     "Y"          # capital Y (Iery)
  719. X     0          "\0xF8"           1     "`"          # capital soft sign Ierik
  720. X     0          "\0xFC"           1     "EH"         # capital reverse round E
  721. X     0          "\0xE0"           1     "JU"         # capital Yu
  722. X     0          "\0xF1"           1     "JA"         # capital Ya
  723. X                       
  724. X     0          "\0xC1"           1     "a"          # small a
  725. X     0          "\0xC2"           1     "b"          # small be
  726. X     0          "\0xD7"           1     "v"          # small ve
  727. X     0          "\0xC7"           1     "g"          # small ghe
  728. X     0          "\0xC4"           1     "d"          # small de
  729. X     0          "\0xC5"           1     "e"          # small je
  730. X     0          "\0xA3"           1     "jo"         # small yo
  731. X     0          "\0xD6"           1     "zh"         # small zhe
  732. X     0          "\0xDA"           1     "z"          # small z
  733. X     0          "\0xC9"           1     "i"          # small i
  734. X     0          "\0xCA"           1     "jj"         # small short i
  735. X     0          "\0xCB"           1     "k"          # small ka
  736. X     0          "\0xCC"           1     "l"          # small el
  737. X     0          "\0xCD"           1     "m"          # small em
  738. X     0          "\0xCE"           1     "n"          # small en
  739. X     0          "\0xCF"           1     "o"          # small o
  740. X     0          "\0xD0"           1     "p"          # small pe
  741. X     0          "\0xD2"           1     "r"          # small er
  742. X     0          "\0xD3"           1     "s"          # small es
  743. X     0          "\0xD4"           1     "t"          # small te
  744. X     0          "\0xD5"           1     "u"          # small u
  745. X     0          "\0xC6"           1     "f"          # small ef
  746. X     0          "\0xC8"           1     "kh"         # small kha
  747. X     0          "\0xC3"           1     "c"          # small tse
  748. X     0          "\0xDE"           1     "ch"         # small che
  749. X     0          "\0xDB"           1     "sh"         # small sha
  750. X     0          "\0xDD"           1     "hh"         # small shcha
  751. X     0          "\0xDF"           1     "''"         # small hard sign (ier)
  752. X     0          "\0xD9"           1     "y"          # small y (iery)
  753. X     0          "\0xD8"           1     "'"          # small soft sign (ierik)
  754. X     0          "\0xDC"           1     "eh"         # small reverse rounded e
  755. X     0          "\0xC0"           1     "ju"         # small yu
  756. X     0          "\0xD1"           1     "ja"         # small ya
  757. END_OF_FILE
  758.   if test 5726 -ne `wc -c <'koi8-phg.rus'`; then
  759.     echo shar: \"'koi8-phg.rus'\" unpacked with wrong size!
  760.   fi
  761.   # end of 'koi8-phg.rus'
  762. fi
  763. if test -f 'koi8-php.rus' -a "${1}" != "-c" ; then 
  764.   echo shar: Will not clobber existing file \"'koi8-php.rus'\"
  765. else
  766.   echo shar: Extracting \"'koi8-php.rus'\" \(5502 characters\)
  767.   sed "s/^X//" >'koi8-php.rus' <<'END_OF_FILE'
  768. X# Jan Labanowski, jkl@osc.edu, Dec. 30, 1992
  769. X# File koi8-php.rus
  770. X
  771. X# This is a transliteration data file for converting from
  772. X# KOI8 as used by RELCOM to transliteration defined as Pokrovsky EuroTex-92
  773. X# (posted to RUSTEX by Joseph Romanovsky)
  774. X# standard.
  775. X# To be used with translit.c program by Jan Labanowski
  776. X
  777. X   1            file version number
  778. X
  779. X   "    "      # string delimiters
  780. X   [    ]      # list delimites
  781. X   {    }      # regular expression delimiters
  782. X
  783. X
  784. X#starting sequence
  785. X""
  786. X
  787. X
  788. X#ending sequence
  789. X""
  790. X
  791. X   0     # number of input SHIFT sequences
  792. X
  793. X   2     # number of output SHIFT sequences, only one set of output characters
  794. X   ""    ""            # russian outside brackets
  795. X   "{"   "}"           # ascii, inside brackets
  796. X  
  797. X# conversion table
  798. X
  799. X# Latin(ASCII) is embraced in {}
  800. X     0         [A-Za-z]        2  [A-Za-z]
  801. X
  802. X# White space and control characters
  803. X     0         [\0x01-\0x20]        0  [\0x01-\0x20]
  804. X
  805. X# punctuation and digits
  806. X 0 [\0x21-\0x3F\0x5B-\0x60\0x7B-\0x7E] 0 [\0x21-\0x3F\0x5B-\0x60\0x7B-\0x7E]
  807. X
  808. X# inp_set_numb  inp_seq        out_set_numb  out_seq
  809. X     0          "\0xE1"           1     "A"          # capital A
  810. X     0          "\0xE2"           1     "B"          # capital Be
  811. X     0          "\0xF7"           1     "V"          # capital Ve
  812. X     0          "\0xE7"           1     "G"          # capital Ghe
  813. X     0          "\0xE4"           1     "D"          # capital De
  814. X     0          "\0xE5"           1     "E"          # capital Je
  815. X     0          "\0xB3"           1     "Jo"         # capital Yo
  816. X     0          "\0xF6"           1     "Zh"         # capital Zhe
  817. X     0          "\0xFA"           1     "Z"          # capital Ze
  818. X     0          "\0xE9"           1     "I"          # capital I
  819. X     0          "\0xEA"           1     "Ji"         # capital short I
  820. X     0          "\0xEB"           1     "K"          # capital Ka
  821. X     0          "\0xEC"           1     "L"          # capital El
  822. X     0          "\0xED"           1     "M"          # capital Em
  823. X     0          "\0xEE"           1     "N"          # capital En
  824. X     0          "\0xEF"           1     "O"          # capital O
  825. X     0          "\0xF0"           1     "P"          # capital Pe
  826. X     0          "\0xF2"           1     "R"          # capital Er
  827. X     0          "\0xF3"           1     "S"          # capital Es
  828. X     0          "\0xF4"           1     "T"          # capital Te
  829. X     0          "\0xF5"           1     "U"          # capital U
  830. X     0          "\0xE6"           1     "F"          # capital Ef
  831. X     0          "\0xE8"           1     "Kh"         # capital Kha
  832. X     0          "\0xE3"           1     "C"          # capital Tse
  833. X     0          "\0xFE"           1     "Ch"         # capital Che
  834. X     0          "\0xFB"           1     "Sh"         # capital Sha
  835. X     0          "\0xFD"           1     "W"          # capital Shcha
  836. X     0          "\0xFF"           1     "X"         # capital hard sign (Ier)
  837. X     0          "\0xF9"           1     "Y"          # capital Y (Iery)
  838. X     0          "\0xF8"           1     "Q"          # capital soft sign Ierik
  839. X     0          "\0xFC"           1     "Eh"         # capital reverse round E
  840. X     0          "\0xE0"           1     "Ju"         # capital Yu
  841. X     0          "\0xF1"           1     "Ja"         # capital Ya
  842. X                       
  843. X     0          "\0xC1"           1     "a"          # small a
  844. X     0          "\0xC2"           1     "b"          # small be
  845. X     0          "\0xD7"           1     "v"          # small ve
  846. X     0          "\0xC7"           1     "g"          # small ghe
  847. X     0          "\0xC4"           1     "d"          # small de
  848. X     0          "\0xC5"           1     "e"          # small je
  849. X     0          "\0xA3"           1     "jo"         # small yo
  850. X     0          "\0xD6"           1     "zh"         # small zhe
  851. X     0          "\0xDA"           1     "z"          # small z
  852. X     0          "\0xC9"           1     "i"          # small i
  853. X     0          "\0xCA"           1     "ji"         # small short i
  854. X     0          "\0xCB"           1     "k"          # small ka
  855. X     0          "\0xCC"           1     "l"          # small el
  856. X     0          "\0xCD"           1     "m"          # small em
  857. X     0          "\0xCE"           1     "n"          # small en
  858. X     0          "\0xCF"           1     "o"          # small o
  859. X     0          "\0xD0"           1     "p"          # small pe
  860. X     0          "\0xD2"           1     "r"          # small er
  861. X     0          "\0xD3"           1     "s"          # small es
  862. X     0          "\0xD4"           1     "t"          # small te
  863. X     0          "\0xD5"           1     "u"          # small u
  864. X     0          "\0xC6"           1     "f"          # small ef
  865. X     0          "\0xC8"           1     "kh"         # small kha
  866. X     0          "\0xC3"           1     "c"          # small tse
  867. X     0          "\0xDE"           1     "ch"         # small che
  868. X     0          "\0xDB"           1     "sh"         # small sha
  869. X     0          "\0xDD"           1     "w"          # small shcha
  870. X     0          "\0xDF"           1     "x"          # small hard sign (ier)
  871. X     0          "\0xD9"           1     "y"          # small y (iery)
  872. X     0          "\0xD8"           1     "q"          # small soft sign (ierik)
  873. X     0          "\0xDC"           1     "eh"         # small reverse rounded e
  874. X     0          "\0xC0"           1     "ju"         # small yu
  875. X     0          "\0xD1"           1     "ja"         # small ya
  876. END_OF_FILE
  877.   if test 5502 -ne `wc -c <'koi8-php.rus'`; then
  878.     echo shar: \"'koi8-php.rus'\" unpacked with wrong size!
  879.   fi
  880.   # end of 'koi8-php.rus'
  881. fi
  882. if test -f 'phg-koi8.rus' -a "${1}" != "-c" ; then 
  883.   echo shar: Will not clobber existing file \"'phg-koi8.rus'\"
  884. else
  885.   echo shar: Extracting \"'phg-koi8.rus'\" \(5906 characters\)
  886.   sed "s/^X//" >'phg-koi8.rus' <<'END_OF_FILE'
  887. X
  888. X# Jan Labanowski, jkl@osc.edu, Dec. 30, 1992
  889. X# File phg-koi8.rus
  890. X
  891. X# This is a transliteration data file for converting from transliteration
  892. X# defined in the GOST 16876-71 standard to KOI8 as used by RELCOM.
  893. X# Since I never had a chance to look at the GOST 16876-71 document,
  894. X# the actual table is based on the info which I read on some list
  895. X# (I believe it was posted by Glenn Thobe on RUS-TEX)
  896. X# To be used with translit.c program by Jan Labanowski
  897. X
  898. X   1            file version number
  899. X
  900. X   "    "      # string delimiters
  901. X   [    ]      # list delimites
  902. X   {    }      # regular expression delimiters
  903. X
  904. X
  905. X#starting sequence
  906. X""
  907. X
  908. X
  909. X#ending sequence
  910. X""
  911. X
  912. X   2     # number of input SHIFT sequences
  913. X""  ""  ""  ""  ""  ""    # no SHIFT-OUT/IN for Russian letters
  914. X"{" ""  ""  ""  "}" ""    # Latin text in braces {}
  915. X
  916. X   0     # number of output SHIFT sequences, only one set of output characters
  917. X  
  918. X# conversion table
  919. X
  920. X# Latin(ASCII) is embraced in {}
  921. X     2         [\0x21-\0x79]        0  [\0x21-\0x79]
  922. X
  923. X# White space and control characters
  924. X     0         [\0x01-\0x20]        0  [\0x01-\0x20]
  925. X# punctuation and digits
  926. X     0  [\0x21-\0x26\0x28-\0x3F\0x5B-\0x5F\0x7C\0x7e]
  927. X                               0 [\0x21-\0x26\0x28-\0x3F\0x5B-\0x5F\0x7C\0x7e]
  928. X# inp_set_numb  inp_seq        out_set_numb  out_seq
  929. X     1         {K[Hh]}              0       "\0xE8"  # capital Kha
  930. X     1         {E[Hh]}              0       "\0xFC"  # capital reverse round E
  931. X     1         {J[Oo]}              0       "\0xB3"  # capital Yo
  932. X     1         {J[Ee]}              0       "\0xE5"  # capital Je
  933. X     1         {Z[Hh]}              0       "\0xF6"  # capital Zhe
  934. X     1         {J[Jj]}              0       "\0xEA"  # capital short I
  935. X     1         {S[Hh][Cc][Hh]}      0       "\0xFD"  # capital Shcha
  936. X     1         {C[Hh]}              0       "\0xFE"  # capital Che
  937. X     1         {S[Hh]}              0       "\0xFB"  # capital Sha
  938. X     1         {H[Hh]}              0       "\0xFD"  # capital Shcha
  939. X     1         "``"                 0       "\0xFF"  # capital hard sign (Ier)
  940. X     1         {J[Uu]}              0       "\0xE0"  # capital Yu
  941. X     1         {J[Aa]}              0       "\0xF1"  # capital Ya
  942. X     1         "kh"                 0       "\0xC8"  # small kha
  943. X     1         "eh"                 0       "\0xDC"  # small reverse rounded e
  944. X     1         "jo"                 0       "\0xA3"  # small yo
  945. X     1         "zh"                 0       "\0xD6"  # small zhe
  946. X     1         "jj"                 0       "\0xCA"  # small short i
  947. X     1         "shch"               0       "\0xDD"  # small shcha
  948. X     1         "ch"                 0       "\0xDE"  # small che
  949. X     1         "sh"                 0       "\0xDB"  # small sha
  950. X     1         "hh"                 0       "\0xDD"  # small shcha
  951. X     1         "''"                 0       "\0xDF"  # small hard sign (ier)
  952. X     1         "ju"                 0       "\0xC0"  # small yu
  953. X     1         "ja"                 0       "\0xD1"  # small ya
  954. X     1         "A"                  0       "\0xE1"  # capital A
  955. X     1         "B"                  0       "\0xE2"  # capital Be
  956. X     1         "V"                  0       "\0xF7"  # capital Ve
  957. X     1         "G"                  0       "\0xE7"  # capital Ghe
  958. X     1         "D"                  0       "\0xE4"  # capital De
  959. X     1         "E"                  0       "\0xE5"  # capital Je
  960. X     1         "Z"                  0       "\0xFA"  # capital Ze
  961. X     1         "I"                  0       "\0xE9"  # capital I
  962. X     1         "K"                  0       "\0xEB"  # capital Ka
  963. X     1         "L"                  0       "\0xEC"  # capital El
  964. X     1         "M"                  0       "\0xED"  # capital Em
  965. X     1         "N"                  0       "\0xEE"  # capital En
  966. X     1         "O"                  0       "\0xEF"  # capital O
  967. X     1         "P"                  0       "\0xF0"  # capital Pe
  968. X     1         "R"                  0       "\0xF2"  # capital Er
  969. X     1         "S"                  0       "\0xF3"  # capital Es
  970. X     1         "T"                  0       "\0xF4"  # capital Te
  971. X     1         "U"                  0       "\0xF5"  # capital U
  972. X     1         "F"                  0       "\0xE6"  # capital Ef
  973. X     1         "C"                  0       "\0xE3"  # capital Tse
  974. X     1         "Y"                  0       "\0xF9"  # capital Y (Iery)
  975. X     1         "`"                  0       "\0xF8"  # capital soft sign Ierik
  976. X
  977. X     1         "a"                  0       "\0xC1"  # small a
  978. X     1         "b"                  0       "\0xC2"  # small be
  979. X     1         "v"                  0       "\0xD7"  # small ve
  980. X     1         "g"                  0       "\0xC7"  # small ghe
  981. X     1         "d"                  0       "\0xC4"  # small de
  982. X     1         "e"                  0       "\0xC5"  # small je
  983. X     1         "z"                  0       "\0xDA"  # small z
  984. X     1         "i"                  0       "\0xC9"  # small i
  985. X     1         "k"                  0       "\0xCB"  # small ka
  986. X     1         "l"                  0       "\0xCC"  # small el
  987. X     1         "m"                  0       "\0xCD"  # small em
  988. X     1         "n"                  0       "\0xCE"  # small en
  989. X     1         "o"                  0       "\0xCF"  # small o
  990. X     1         "p"                  0       "\0xD0"  # small pe
  991. X     1         "r"                  0       "\0xD2"  # small er
  992. X     1         "s"                  0       "\0xD3"  # small es
  993. X     1         "t"                  0       "\0xD4"  # small te
  994. X     1         "u"                  0       "\0xD5"  # small u
  995. X     1         "f"                  0       "\0xC6"  # small ef
  996. X     1         "c"                  0       "\0xC3"  # small tse
  997. X     1         "y"                  0       "\0xD9"  # small y (iery)
  998. X     1         "'"                  0       "\0xD8"  # small soft sign (ierik)
  999. END_OF_FILE
  1000.   if test 5906 -ne `wc -c <'phg-koi8.rus'`; then
  1001.     echo shar: \"'phg-koi8.rus'\" unpacked with wrong size!
  1002.   fi
  1003.   # end of 'phg-koi8.rus'
  1004. fi
  1005. if test -f 'php-koi8.rus' -a "${1}" != "-c" ; then 
  1006.   echo shar: Will not clobber existing file \"'php-koi8.rus'\"
  1007. else
  1008.   echo shar: Extracting \"'php-koi8.rus'\" \(5732 characters\)
  1009.   sed "s/^X//" >'php-koi8.rus' <<'END_OF_FILE'
  1010. X# Jan Labanowski, jkl@osc.edu, Dec. 30, 1992
  1011. X# File php-koi8.rus
  1012. X
  1013. X# This is a transliteration data file for converting from transliteration
  1014. X# called Pokrovsky and announced at EuroTex92 (from the message to RUSTEX
  1015. X# by Joseph Romanovsky). to KOI8 as used by RELCOM.
  1016. X# To be used with translit.c program by Jan Labanowski
  1017. X
  1018. X   1            file version number
  1019. X
  1020. X   "    "      # string delimiters
  1021. X   [    ]      # list delimites
  1022. X   {    }      # regular expression delimiters
  1023. X
  1024. X
  1025. X#starting sequence
  1026. X""
  1027. X
  1028. X
  1029. X#ending sequence
  1030. X""
  1031. X
  1032. X   2     # number of input SHIFT sequences
  1033. X""  ""  ""  ""  ""  ""    # no SHIFT-OUT/IN for Russian letters
  1034. X"{" ""  ""  ""  "}" ""    # Latin text in braces {}
  1035. X
  1036. X   0     # number of output SHIFT sequences, only one set of output characters
  1037. X  
  1038. X# conversion table
  1039. X
  1040. X# Latin(ASCII) is embraced in {}
  1041. X     2         [A-Za-z]        0  [A-Za-z]
  1042. X
  1043. X# White space and control characters
  1044. X     0         [\0x01-\0x20]        0  [\0x01-\0x20]
  1045. X# punctuation and digits
  1046. X 0 [\0x21-\0x3F\0x5B-\0x60\0x7B-\0x7E] 0 [\0x21-\0x3F\0x5B-\0x60\0x7B-\0x7E]
  1047. X
  1048. X# inp_set_numb  inp_seq        out_set_numb  out_seq
  1049. X     1         {K[Hh]}              0       "\0xE8"  # capital Kha
  1050. X     1         {E[Hh]}              0       "\0xFC"  # capital reverse round E
  1051. X     1         {J[Oo]}              0       "\0xB3"  # capital Yo
  1052. X     1         {J[Ee]}              0       "\0xE5"  # capital Je
  1053. X     1         {Z[Hh]}              0       "\0xF6"  # capital Zhe
  1054. X     1         {J[Ii]}              0       "\0xEA"  # capital short I
  1055. X     1         {S[Hh][Cc][Hh]}      0       "\0xFD"  # capital Shcha (in case)
  1056. X     1         {C[Hh]}              0       "\0xFE"  # capital Che
  1057. X     1         {S[Hh]}              0       "\0xFB"  # capital Sha
  1058. X     1         {J[Uu]}              0       "\0xE0"  # capital Yu
  1059. X     1         {J[Aa]}              0       "\0xF1"  # capital Ya
  1060. X     1         "kh"                 0       "\0xC8"  # small kha
  1061. X     1         "eh"                 0       "\0xDC"  # small reverse rounded e
  1062. X     1         "jo"                 0       "\0xA3"  # small yo
  1063. X     1         "zh"                 0       "\0xD6"  # small zhe
  1064. X     1         "ji"                 0       "\0xCA"  # small short i
  1065. X     1         "shch"               0       "\0xDD"  # small shcha (in case)
  1066. X     1         "ch"                 0       "\0xDE"  # small che
  1067. X     1         "sh"                 0       "\0xDB"  # small sha
  1068. X     1         "ju"                 0       "\0xC0"  # small yu
  1069. X     1         "ja"                 0       "\0xD1"  # small ya
  1070. X     1         "A"                  0       "\0xE1"  # capital A
  1071. X     1         "B"                  0       "\0xE2"  # capital Be
  1072. X     1         "V"                  0       "\0xF7"  # capital Ve
  1073. X     1         "G"                  0       "\0xE7"  # capital Ghe
  1074. X     1         "D"                  0       "\0xE4"  # capital De
  1075. X     1         "E"                  0       "\0xE5"  # capital Je
  1076. X     1         "Z"                  0       "\0xFA"  # capital Ze
  1077. X     1         "I"                  0       "\0xE9"  # capital I
  1078. X     1         "K"                  0       "\0xEB"  # capital Ka
  1079. X     1         "L"                  0       "\0xEC"  # capital El
  1080. X     1         "M"                  0       "\0xED"  # capital Em
  1081. X     1         "N"                  0       "\0xEE"  # capital En
  1082. X     1         "O"                  0       "\0xEF"  # capital O
  1083. X     1         "P"                  0       "\0xF0"  # capital Pe
  1084. X     1         "R"                  0       "\0xF2"  # capital Er
  1085. X     1         "S"                  0       "\0xF3"  # capital Es
  1086. X     1         "T"                  0       "\0xF4"  # capital Te
  1087. X     1         "U"                  0       "\0xF5"  # capital U
  1088. X     1         "F"                  0       "\0xE6"  # capital Ef
  1089. X     1         "C"                  0       "\0xE3"  # capital Tse 
  1090. X     1         "W"                  0       "\0xFD"  # capital Shcha
  1091. X     1         "X"                  0       "\0xFF"  # capital hard sign (Ier)
  1092. X     1         "Y"                  0       "\0xF9"  # capital Y (Iery)
  1093. X     1         "Q"                  0       "\0xF8"  # capital soft sign Ierik
  1094. X
  1095. X     1         "a"                  0       "\0xC1"  # small a
  1096. X     1         "b"                  0       "\0xC2"  # small be
  1097. X     1         "v"                  0       "\0xD7"  # small ve
  1098. X     1         "g"                  0       "\0xC7"  # small ghe
  1099. X     1         "d"                  0       "\0xC4"  # small de
  1100. X     1         "e"                  0       "\0xC5"  # small je
  1101. X     1         "z"                  0       "\0xDA"  # small z
  1102. X     1         "i"                  0       "\0xC9"  # small i
  1103. X     1         "k"                  0       "\0xCB"  # small ka
  1104. X     1         "l"                  0       "\0xCC"  # small el
  1105. X     1         "m"                  0       "\0xCD"  # small em
  1106. X     1         "n"                  0       "\0xCE"  # small en
  1107. X     1         "o"                  0       "\0xCF"  # small o
  1108. X     1         "p"                  0       "\0xD0"  # small pe
  1109. X     1         "r"                  0       "\0xD2"  # small er
  1110. X     1         "s"                  0       "\0xD3"  # small es
  1111. X     1         "t"                  0       "\0xD4"  # small te
  1112. X     1         "u"                  0       "\0xD5"  # small u
  1113. X     1         "f"                  0       "\0xC6"  # small ef
  1114. X     1         "c"                  0       "\0xC3"  # small tse
  1115. X     1         "w"                  0       "\0xDD"  # small shcha
  1116. X     1         "x"                  0       "\0xDF"  # small hard sign (ier)
  1117. X     1         "y"                  0       "\0xD9"  # small y (iery)
  1118. X     1         "q"                  0       "\0xD8"  # small soft sign (ierik)
  1119. END_OF_FILE
  1120.   if test 5732 -ne `wc -c <'php-koi8.rus'`; then
  1121.     echo shar: \"'php-koi8.rus'\" unpacked with wrong size!
  1122.   fi
  1123.   # end of 'php-koi8.rus'
  1124. fi
  1125. echo shar: End of archive 9 \(of 10\).
  1126. cp /dev/null ark9isdone
  1127. MISSING=""
  1128. for I in 1 2 3 4 5 6 7 8 9 10 ; do
  1129.     if test ! -f ark${I}isdone ; then
  1130.     MISSING="${MISSING} ${I}"
  1131.     fi
  1132. done
  1133. if test "${MISSING}" = "" ; then
  1134.     echo You have unpacked all 10 archives.
  1135.     rm -f ark[1-9]isdone ark[1-9][0-9]isdone
  1136. else
  1137.     echo You still must unpack the following archives:
  1138.     echo "        " ${MISSING}
  1139. fi
  1140. exit 0
  1141. exit 0 # Just in case...
  1142.