KOI8-U.TXT 11 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310
  1. #
  2. # Name: KOI8-U (RFC2319) to Unicode
  3. # Unicode version: 5.1
  4. # Table version: 1.0
  5. # Table format: Format A
  6. # Date: 13 October 2008
  7. # Authors: Philippe Verdy <verdy_p AT wanadoo.fr>,
  8. # Helmut Richter <richter@lrz.de>
  9. #
  10. # Copyright (c) 1991-2008 Unicode, Inc. All Rights reserved.
  11. #
  12. # This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
  13. # No claims are made as to fitness for any particular purpose. No
  14. # warranties of any kind are expressed or implied. The recipient
  15. # agrees to determine applicability of information provided. If this
  16. # file has been provided on optical media by Unicode, Inc., the sole
  17. # remedy for any claim will be exchange of defective media within 90
  18. # days of receipt.
  19. #
  20. # Unicode, Inc. hereby grants the right to freely use the information
  21. # supplied in this file in the creation of products supporting the
  22. # Unicode Standard, and to make copies of this file in any form for
  23. # internal or external distribution as long as this notice remains
  24. # attached.
  25. #
  26. # General notes:
  27. #
  28. # This table contains the data the Unicode Consortium has on how
  29. # KOI8-U characters map into Unicode. The underlying document is the
  30. # mapping described in RFC 2319. No statements are made as to whether
  31. # this mapping is the same as the mapping defined as "Code Page 878"
  32. # with some vendors.
  33. #
  34. # The KOI8-U (RFC2319) encoding is a variant based on KOI8-R (RFC1489),
  35. # where the support for four additional Cyrillic letters was added (both small
  36. # and capital letters), replacing 8 box-drawing characters. It is still widely
  37. # used to encode texts in Ukrainian, Byelorussian and Bulgarian.
  38. #
  39. # Format: Three tab-separated columns
  40. # Column #1 is the KOI8-U code (in hex as 0xXX)
  41. # Column #2 is the Unicode (in hex as 0xXXXX)
  42. # Column #3 the Unicode name (follows a comment sign, '#')
  43. #
  44. # The entries are in KOI8-U order.
  45. #
  46. # Version history
  47. # 1.0 version: created.
  48. #
  49. # Updated versions of this file may be found in:
  50. # <http://www.unicode.org/Public/MAPPINGS/>
  51. #
  52. # Any comments or problems, contact the Unicode Consortium at:
  53. # <http://www.unicode.org/reporting.html>
  54. #
  55. 0x00 0x0000 # NULL
  56. 0x01 0x0001 # START OF HEADING
  57. 0x02 0x0002 # START OF TEXT
  58. 0x03 0x0003 # END OF TEXT
  59. 0x04 0x0004 # END OF TRANSMISSION
  60. 0x05 0x0005 # ENQUIRY
  61. 0x06 0x0006 # ACKNOWLEDGE
  62. 0x07 0x0007 # BELL
  63. 0x08 0x0008 # BACKSPACE
  64. 0x09 0x0009 # HORIZONTAL TABULATION
  65. 0x0A 0x000A # LINE FEED
  66. 0x0B 0x000B # VERTICAL TABULATION
  67. 0x0C 0x000C # FORM FEED
  68. 0x0D 0x000D # CARRIAGE RETURN
  69. 0x0E 0x000E # SHIFT OUT
  70. 0x0F 0x000F # SHIFT IN
  71. 0x10 0x0010 # DATA LINK ESCAPE
  72. 0x11 0x0011 # DEVICE CONTROL ONE
  73. 0x12 0x0012 # DEVICE CONTROL TWO
  74. 0x13 0x0013 # DEVICE CONTROL THREE
  75. 0x14 0x0014 # DEVICE CONTROL FOUR
  76. 0x15 0x0015 # NEGATIVE ACKNOWLEDGE
  77. 0x16 0x0016 # SYNCHRONOUS IDLE
  78. 0x17 0x0017 # END OF TRANSMISSION BLOCK
  79. 0x18 0x0018 # CANCEL
  80. 0x19 0x0019 # END OF MEDIUM
  81. 0x1A 0x001A # SUBSTITUTE
  82. 0x1B 0x001B # ESCAPE
  83. 0x1C 0x001C # FILE SEPARATOR
  84. 0x1D 0x001D # GROUP SEPARATOR
  85. 0x1E 0x001E # RECORD SEPARATOR
  86. 0x1F 0x001F # UNIT SEPARATOR
  87. 0x20 0x0020 # SPACE
  88. 0x21 0x0021 # EXCLAMATION MARK
  89. 0x22 0x0022 # QUOTATION MARK
  90. 0x23 0x0023 # NUMBER SIGN
  91. 0x24 0x0024 # DOLLAR SIGN
  92. 0x25 0x0025 # PERCENT SIGN
  93. 0x26 0x0026 # AMPERSAND
  94. 0x27 0x0027 # APOSTROPHE
  95. 0x28 0x0028 # LEFT PARENTHESIS
  96. 0x29 0x0029 # RIGHT PARENTHESIS
  97. 0x2A 0x002A # ASTERISK
  98. 0x2B 0x002B # PLUS SIGN
  99. 0x2C 0x002C # COMMA
  100. 0x2D 0x002D # HYPHEN-MINUS
  101. 0x2E 0x002E # FULL STOP
  102. 0x2F 0x002F # SOLIDUS
  103. 0x30 0x0030 # DIGIT ZERO
  104. 0x31 0x0031 # DIGIT ONE
  105. 0x32 0x0032 # DIGIT TWO
  106. 0x33 0x0033 # DIGIT THREE
  107. 0x34 0x0034 # DIGIT FOUR
  108. 0x35 0x0035 # DIGIT FIVE
  109. 0x36 0x0036 # DIGIT SIX
  110. 0x37 0x0037 # DIGIT SEVEN
  111. 0x38 0x0038 # DIGIT EIGHT
  112. 0x39 0x0039 # DIGIT NINE
  113. 0x3A 0x003A # COLON
  114. 0x3B 0x003B # SEMICOLON
  115. 0x3C 0x003C # LESS-THAN SIGN
  116. 0x3D 0x003D # EQUALS SIGN
  117. 0x3E 0x003E # GREATER-THAN SIGN
  118. 0x3F 0x003F # QUESTION MARK
  119. 0x40 0x0040 # COMMERCIAL AT
  120. 0x41 0x0041 # LATIN CAPITAL LETTER A
  121. 0x42 0x0042 # LATIN CAPITAL LETTER B
  122. 0x43 0x0043 # LATIN CAPITAL LETTER C
  123. 0x44 0x0044 # LATIN CAPITAL LETTER D
  124. 0x45 0x0045 # LATIN CAPITAL LETTER E
  125. 0x46 0x0046 # LATIN CAPITAL LETTER F
  126. 0x47 0x0047 # LATIN CAPITAL LETTER G
  127. 0x48 0x0048 # LATIN CAPITAL LETTER H
  128. 0x49 0x0049 # LATIN CAPITAL LETTER I
  129. 0x4A 0x004A # LATIN CAPITAL LETTER J
  130. 0x4B 0x004B # LATIN CAPITAL LETTER K
  131. 0x4C 0x004C # LATIN CAPITAL LETTER L
  132. 0x4D 0x004D # LATIN CAPITAL LETTER M
  133. 0x4E 0x004E # LATIN CAPITAL LETTER N
  134. 0x4F 0x004F # LATIN CAPITAL LETTER O
  135. 0x50 0x0050 # LATIN CAPITAL LETTER P
  136. 0x51 0x0051 # LATIN CAPITAL LETTER Q
  137. 0x52 0x0052 # LATIN CAPITAL LETTER R
  138. 0x53 0x0053 # LATIN CAPITAL LETTER S
  139. 0x54 0x0054 # LATIN CAPITAL LETTER T
  140. 0x55 0x0055 # LATIN CAPITAL LETTER U
  141. 0x56 0x0056 # LATIN CAPITAL LETTER V
  142. 0x57 0x0057 # LATIN CAPITAL LETTER W
  143. 0x58 0x0058 # LATIN CAPITAL LETTER X
  144. 0x59 0x0059 # LATIN CAPITAL LETTER Y
  145. 0x5A 0x005A # LATIN CAPITAL LETTER Z
  146. 0x5B 0x005B # LEFT SQUARE BRACKET
  147. 0x5C 0x005C # REVERSE SOLIDUS
  148. 0x5D 0x005D # RIGHT SQUARE BRACKET
  149. 0x5E 0x005E # CIRCUMFLEX ACCENT
  150. 0x5F 0x005F # LOW LINE
  151. 0x60 0x0060 # GRAVE ACCENT
  152. 0x61 0x0061 # LATIN SMALL LETTER A
  153. 0x62 0x0062 # LATIN SMALL LETTER B
  154. 0x63 0x0063 # LATIN SMALL LETTER C
  155. 0x64 0x0064 # LATIN SMALL LETTER D
  156. 0x65 0x0065 # LATIN SMALL LETTER E
  157. 0x66 0x0066 # LATIN SMALL LETTER F
  158. 0x67 0x0067 # LATIN SMALL LETTER G
  159. 0x68 0x0068 # LATIN SMALL LETTER H
  160. 0x69 0x0069 # LATIN SMALL LETTER I
  161. 0x6A 0x006A # LATIN SMALL LETTER J
  162. 0x6B 0x006B # LATIN SMALL LETTER K
  163. 0x6C 0x006C # LATIN SMALL LETTER L
  164. 0x6D 0x006D # LATIN SMALL LETTER M
  165. 0x6E 0x006E # LATIN SMALL LETTER N
  166. 0x6F 0x006F # LATIN SMALL LETTER O
  167. 0x70 0x0070 # LATIN SMALL LETTER P
  168. 0x71 0x0071 # LATIN SMALL LETTER Q
  169. 0x72 0x0072 # LATIN SMALL LETTER R
  170. 0x73 0x0073 # LATIN SMALL LETTER S
  171. 0x74 0x0074 # LATIN SMALL LETTER T
  172. 0x75 0x0075 # LATIN SMALL LETTER U
  173. 0x76 0x0076 # LATIN SMALL LETTER V
  174. 0x77 0x0077 # LATIN SMALL LETTER W
  175. 0x78 0x0078 # LATIN SMALL LETTER X
  176. 0x79 0x0079 # LATIN SMALL LETTER Y
  177. 0x7A 0x007A # LATIN SMALL LETTER Z
  178. 0x7B 0x007B # LEFT CURLY BRACKET
  179. 0x7C 0x007C # VERTICAL LINE
  180. 0x7D 0x007D # RIGHT CURLY BRACKET
  181. 0x7E 0x007E # TILDE
  182. 0x7F 0x007F # DELETE
  183. 0x80 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL
  184. 0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL
  185. 0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT
  186. 0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT
  187. 0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT
  188. 0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT
  189. 0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
  190. 0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT
  191. 0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
  192. 0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL
  193. 0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
  194. 0x8B 0x2580 # UPPER HALF BLOCK
  195. 0x8C 0x2584 # LOWER HALF BLOCK
  196. 0x8D 0x2588 # FULL BLOCK
  197. 0x8E 0x258C # LEFT HALF BLOCK
  198. 0x8F 0x2590 # RIGHT HALF BLOCK
  199. 0x90 0x2591 # LIGHT SHADE
  200. 0x91 0x2592 # MEDIUM SHADE
  201. 0x92 0x2593 # DARK SHADE
  202. 0x93 0x2320 # TOP HALF INTEGRAL
  203. 0x94 0x25A0 # BLACK SQUARE
  204. 0x95 0x2219 # BULLET OPERATOR
  205. 0x96 0x221A # SQUARE ROOT
  206. 0x97 0x2248 # ALMOST EQUAL TO
  207. 0x98 0x2264 # LESS-THAN OR EQUAL TO
  208. 0x99 0x2265 # GREATER-THAN OR EQUAL TO
  209. 0x9A 0x00A0 # NO-BREAK SPACE
  210. 0x9B 0x2321 # BOTTOM HALF INTEGRAL
  211. 0x9C 0x00B0 # DEGREE SIGN
  212. 0x9D 0x00B2 # SUPERSCRIPT TWO
  213. 0x9E 0x00B7 # MIDDLE DOT
  214. 0x9F 0x00F7 # DIVISION SIGN
  215. 0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL
  216. 0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL
  217. 0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
  218. 0xA3 0x0451 # CYRILLIC SMALL LETTER IO
  219. 0xA4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE
  220. 0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT
  221. 0xA6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
  222. 0xA7 0x0457 # CYRILLIC SMALL LETTER YI (UKRAINIAN)
  223. 0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT
  224. 0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
  225. 0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
  226. 0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT
  227. 0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
  228. 0xAD 0x0491 # CYRILLIC SMALL LETTER GHE WITH UPTURN
  229. 0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT
  230. 0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
  231. 0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
  232. 0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
  233. 0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
  234. 0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO
  235. 0xB4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE
  236. 0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
  237. 0xB6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
  238. 0xB7 0x0407 # CYRILLIC CAPITAL LETTER YI (UKRAINIAN)
  239. 0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
  240. 0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
  241. 0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
  242. 0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
  243. 0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
  244. 0xBD 0x0490 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN
  245. 0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
  246. 0xBF 0x00A9 # COPYRIGHT SIGN
  247. 0xC0 0x044E # CYRILLIC SMALL LETTER YU
  248. 0xC1 0x0430 # CYRILLIC SMALL LETTER A
  249. 0xC2 0x0431 # CYRILLIC SMALL LETTER BE
  250. 0xC3 0x0446 # CYRILLIC SMALL LETTER TSE
  251. 0xC4 0x0434 # CYRILLIC SMALL LETTER DE
  252. 0xC5 0x0435 # CYRILLIC SMALL LETTER IE
  253. 0xC6 0x0444 # CYRILLIC SMALL LETTER EF
  254. 0xC7 0x0433 # CYRILLIC SMALL LETTER GHE
  255. 0xC8 0x0445 # CYRILLIC SMALL LETTER HA
  256. 0xC9 0x0438 # CYRILLIC SMALL LETTER I
  257. 0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I
  258. 0xCB 0x043A # CYRILLIC SMALL LETTER KA
  259. 0xCC 0x043B # CYRILLIC SMALL LETTER EL
  260. 0xCD 0x043C # CYRILLIC SMALL LETTER EM
  261. 0xCE 0x043D # CYRILLIC SMALL LETTER EN
  262. 0xCF 0x043E # CYRILLIC SMALL LETTER O
  263. 0xD0 0x043F # CYRILLIC SMALL LETTER PE
  264. 0xD1 0x044F # CYRILLIC SMALL LETTER YA
  265. 0xD2 0x0440 # CYRILLIC SMALL LETTER ER
  266. 0xD3 0x0441 # CYRILLIC SMALL LETTER ES
  267. 0xD4 0x0442 # CYRILLIC SMALL LETTER TE
  268. 0xD5 0x0443 # CYRILLIC SMALL LETTER U
  269. 0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE
  270. 0xD7 0x0432 # CYRILLIC SMALL LETTER VE
  271. 0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN
  272. 0xD9 0x044B # CYRILLIC SMALL LETTER YERU
  273. 0xDA 0x0437 # CYRILLIC SMALL LETTER ZE
  274. 0xDB 0x0448 # CYRILLIC SMALL LETTER SHA
  275. 0xDC 0x044D # CYRILLIC SMALL LETTER E
  276. 0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA
  277. 0xDE 0x0447 # CYRILLIC SMALL LETTER CHE
  278. 0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN
  279. 0xE0 0x042E # CYRILLIC CAPITAL LETTER YU
  280. 0xE1 0x0410 # CYRILLIC CAPITAL LETTER A
  281. 0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE
  282. 0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE
  283. 0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE
  284. 0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE
  285. 0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF
  286. 0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE
  287. 0xE8 0x0425 # CYRILLIC CAPITAL LETTER HA
  288. 0xE9 0x0418 # CYRILLIC CAPITAL LETTER I
  289. 0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I
  290. 0xEB 0x041A # CYRILLIC CAPITAL LETTER KA
  291. 0xEC 0x041B # CYRILLIC CAPITAL LETTER EL
  292. 0xED 0x041C # CYRILLIC CAPITAL LETTER EM
  293. 0xEE 0x041D # CYRILLIC CAPITAL LETTER EN
  294. 0xEF 0x041E # CYRILLIC CAPITAL LETTER O
  295. 0xF0 0x041F # CYRILLIC CAPITAL LETTER PE
  296. 0xF1 0x042F # CYRILLIC CAPITAL LETTER YA
  297. 0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER
  298. 0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES
  299. 0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE
  300. 0xF5 0x0423 # CYRILLIC CAPITAL LETTER U
  301. 0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE
  302. 0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE
  303. 0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN
  304. 0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU
  305. 0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE
  306. 0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA
  307. 0xFC 0x042D # CYRILLIC CAPITAL LETTER E
  308. 0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA
  309. 0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE
  310. 0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN