[444] | 1 | # |
---|
| 2 | # This file describes dependencies between encodings, CES, CCS, etc. |
---|
| 3 | # File relates only to UCS-based conversions and is needed for automatic |
---|
| 4 | # generation of C source files and C header files. |
---|
| 5 | # |
---|
| 6 | # This configuration file consists of sections, each section consists of |
---|
| 7 | # entries. |
---|
| 8 | # |
---|
| 9 | # Use only normalized names. |
---|
| 10 | # |
---|
| 11 | |
---|
| 12 | # |
---|
| 13 | # The first section named "ENCODINGS" describes: |
---|
| 14 | # 1. CES converter corresponding for each enoding; |
---|
| 15 | # 2. Each encoding's aliases; |
---|
| 16 | # 3. CCS tables corresponding for each enoding. |
---|
| 17 | # |
---|
| 18 | SECTION ENCODINGS |
---|
| 19 | |
---|
| 20 | # ISO-10646-UCS-2. Big Endian, NBSP is always interpreted as NBSP (BOM isn't supported). |
---|
| 21 | ENTRY |
---|
| 22 | ENCODING: ucs_2 |
---|
| 23 | CES: ucs_2 |
---|
| 24 | ALIASES: ucs2 iso_10646_ucs_2 iso10646_ucs_2 iso_10646_ucs2 iso10646_ucs2 iso10646ucs2 csUnicode |
---|
| 25 | ENTRY END |
---|
| 26 | |
---|
| 27 | # Big Endian version of ISO-10646-UCS-2 (in fact, equivalent to ucs_2). |
---|
| 28 | # Big Endian, NBSP is always interpreted as NBSP (BOM isn't supported). |
---|
| 29 | ENTRY |
---|
| 30 | ENCODING: ucs_2be |
---|
| 31 | CES: ucs_2 |
---|
| 32 | ALIASES: ucs2be |
---|
| 33 | ENTRY END |
---|
| 34 | |
---|
| 35 | # Little Endian version of ISO-10646-UCS-2. |
---|
| 36 | # Little Endian, NBSP is always interpreted as NBSP (BOM isn't supported). |
---|
| 37 | ENTRY |
---|
| 38 | ENCODING: ucs_2le |
---|
| 39 | CES: ucs_2 |
---|
| 40 | ALIASES: ucs2le |
---|
| 41 | ENTRY END |
---|
| 42 | |
---|
| 43 | # ISO-10646-UCS-2 in system byte order. |
---|
| 44 | # NBSP is always interpreted as NBSP (BOM isn't supported). |
---|
| 45 | # NOTE: Dont delete and rename this since it is used as widechar's |
---|
| 46 | # encoding when sizeof(wchar_t) == 2 |
---|
| 47 | ENTRY |
---|
| 48 | ENCODING: ucs_2_internal |
---|
| 49 | CES: ucs_2_internal |
---|
| 50 | ALIASES: ucs2_internal ucs_2internal ucs2internal |
---|
| 51 | ENTRY END |
---|
| 52 | |
---|
| 53 | # ISO-10646-UCS-4. Big Endian, NBSP is always interpreted as NBSP (BOM isn't supported). |
---|
| 54 | ENTRY |
---|
| 55 | ENCODING: ucs_4 |
---|
| 56 | CES: ucs_4 |
---|
| 57 | ALIASES: ucs4 iso_10646_ucs_4 iso10646_ucs_4 iso_10646_ucs4 iso10646_ucs4 iso10646ucs4 |
---|
| 58 | ENTRY END |
---|
| 59 | |
---|
| 60 | # Big Endian version of ISO-10646-UCS-4 (in fact, equivalent to ucs_4). |
---|
| 61 | # Big Endian, NBSP is always interpreted as NBSP (BOM isn't supported). |
---|
| 62 | ENTRY |
---|
| 63 | ENCODING: ucs_4be |
---|
| 64 | CES: ucs_4 |
---|
| 65 | ALIASES: ucs4be |
---|
| 66 | ENTRY END |
---|
| 67 | |
---|
| 68 | # Little Endian version of ISO-10646-UCS-4. |
---|
| 69 | # Little Endian, NBSP is always interpreted as NBSP (BOM isn't supported). |
---|
| 70 | ENTRY |
---|
| 71 | ENCODING: ucs_4le |
---|
| 72 | CES: ucs_4 |
---|
| 73 | ALIASES: ucs4le |
---|
| 74 | ENTRY END |
---|
| 75 | |
---|
| 76 | # ISO-10646-UCS-4 in system byte order. |
---|
| 77 | # NBSP is always interpreted as NBSP (BOM isn't supported). |
---|
| 78 | # NOTE: Dont delete and rename this since it is used as widechar's |
---|
| 79 | # encoding when sizeof(wchar_t) == 4 |
---|
| 80 | ENTRY |
---|
| 81 | ENCODING: ucs_4_internal |
---|
| 82 | CES: ucs_4_internal |
---|
| 83 | ALIASES: ucs4_internal ucs_4internal ucs4internal |
---|
| 84 | ENTRY END |
---|
| 85 | |
---|
| 86 | # RFC 3629 UTF-8 |
---|
| 87 | ENTRY |
---|
| 88 | ENCODING: utf_8 |
---|
| 89 | CES: utf_8 |
---|
| 90 | ALIASES: utf8 |
---|
| 91 | ENTRY END |
---|
| 92 | |
---|
| 93 | # RFC 2781 UTF-16. The very first NBSP code in stream is interpreted as BOM. |
---|
| 94 | ENTRY |
---|
| 95 | ENCODING: utf_16 |
---|
| 96 | CES: utf_16 |
---|
| 97 | ALIASES: utf16 |
---|
| 98 | ENTRY END |
---|
| 99 | |
---|
| 100 | # Big Endian version of RFC 2781 UTF-16. |
---|
| 101 | # NBSP is always interpreted as NBSP (BOM isn't supported). |
---|
| 102 | ENTRY |
---|
| 103 | ENCODING: utf_16be |
---|
| 104 | CES: utf_16 |
---|
| 105 | ALIASES: utf16be |
---|
| 106 | ENTRY END |
---|
| 107 | |
---|
| 108 | # Little Endian version of RFC 2781 UTF-16. |
---|
| 109 | # NBSP is always interpreted as NBSP (BOM isn't supported). |
---|
| 110 | ENTRY |
---|
| 111 | ENCODING: utf_16le |
---|
| 112 | CES: utf_16 |
---|
| 113 | ALIASES: utf16le |
---|
| 114 | ENTRY END |
---|
| 115 | |
---|
| 116 | # 7-bit ASCII. |
---|
| 117 | ENTRY |
---|
| 118 | ENCODING: us_ascii |
---|
| 119 | CES: us_ascii |
---|
| 120 | ALIASES: ansi_x3.4_1968 ansi_x3.4_1986 iso_646.irv:1991 ascii iso646_us us ibm367 cp367 csascii |
---|
| 121 | ENTRY END |
---|
| 122 | |
---|
| 123 | # RFC 1489 Cyrillic |
---|
| 124 | ENTRY |
---|
| 125 | ENCODING: koi8_r |
---|
| 126 | CES: table |
---|
| 127 | CCS: koi8_r |
---|
| 128 | ALIASES: cskoi8r koi8r koi8 |
---|
| 129 | ENTRY END |
---|
| 130 | |
---|
| 131 | # Obsoleted Ukrainian |
---|
| 132 | ENTRY |
---|
| 133 | ENCODING: koi8_ru |
---|
| 134 | CES: table |
---|
| 135 | CCS: koi8_ru |
---|
| 136 | ALIASES: koi8ru |
---|
| 137 | ENTRY END |
---|
| 138 | |
---|
| 139 | # RFC 2319 Ukrainian |
---|
| 140 | ENTRY |
---|
| 141 | ENCODING: koi8_u |
---|
| 142 | CES: table |
---|
| 143 | CCS: koi8_u |
---|
| 144 | ALIASES: koi8u |
---|
| 145 | ENTRY END |
---|
| 146 | |
---|
| 147 | # KOI8 Unified |
---|
| 148 | ENTRY |
---|
| 149 | ENCODING: koi8_uni |
---|
| 150 | CES: table |
---|
| 151 | CCS: koi8_uni |
---|
| 152 | ALIASES: koi8uni |
---|
| 153 | ENTRY END |
---|
| 154 | |
---|
| 155 | # ISO IR 111/ECMA Cyrillic. |
---|
| 156 | ENTRY |
---|
| 157 | ENCODING: iso_ir_111 |
---|
| 158 | CES: table |
---|
| 159 | CCS: iso_ir_111 |
---|
| 160 | ALIASES: ecma_cyrillic koi8_e koi8e csiso111ecmacyrillic |
---|
| 161 | ENTRY END |
---|
| 162 | |
---|
| 163 | # ISO 8859-1:1987 - Latin 1, West European |
---|
| 164 | ENTRY |
---|
| 165 | ENCODING: iso_8859_1 |
---|
| 166 | CES: table |
---|
| 167 | CCS: iso_8859_1 |
---|
| 168 | ALIASES: iso8859_1 iso88591 iso_8859_1:1987 iso_ir_100 latin1 l1 ibm819 cp819 csisolatin1 |
---|
| 169 | ENTRY END |
---|
| 170 | |
---|
| 171 | # ISO 8859-2:1987 - Latin 2, East European |
---|
| 172 | ENTRY |
---|
| 173 | ENCODING: iso_8859_2 |
---|
| 174 | CES: table |
---|
| 175 | CCS: iso_8859_2 |
---|
| 176 | ALIASES: iso8859_2 iso88592 iso_8859_2:1987 iso_ir_101 latin2 l2 csisolatin2 |
---|
| 177 | ENTRY END |
---|
| 178 | |
---|
| 179 | # ISO 8859-3:1988 - Latin 3, South European |
---|
| 180 | ENTRY |
---|
| 181 | ENCODING: iso_8859_3 |
---|
| 182 | CES: table |
---|
| 183 | CCS: iso_8859_3 |
---|
| 184 | ALIASES: iso_8859_3:1988 iso_ir_109 iso8859_3 latin3 l3 csisolatin3 iso88593 |
---|
| 185 | ENTRY END |
---|
| 186 | |
---|
| 187 | # ISO 8859-4:1988 - Latin 4, North European |
---|
| 188 | ENTRY |
---|
| 189 | ENCODING: iso_8859_4 |
---|
| 190 | CES: table |
---|
| 191 | CCS: iso_8859_4 |
---|
| 192 | ALIASES: iso8859_4 iso88594 iso_8859_4:1988 iso_ir_110 latin4 l4 csisolatin4 |
---|
| 193 | ENTRY END |
---|
| 194 | |
---|
| 195 | # ISO 8859-5:1988 - Cyrillic |
---|
| 196 | ENTRY |
---|
| 197 | ENCODING: iso_8859_5 |
---|
| 198 | CES: table |
---|
| 199 | CCS: iso_8859_5 |
---|
| 200 | ALIASES: iso8859_5 iso88595 iso_8859_5:1988 iso_ir_144 cyrillic csisolatincyrillic |
---|
| 201 | ENTRY END |
---|
| 202 | |
---|
| 203 | # ISO i8859-6:1987 - Arabic |
---|
| 204 | ENTRY |
---|
| 205 | ENCODING: iso_8859_6 |
---|
| 206 | CES: table |
---|
| 207 | CCS: iso_8859_6 |
---|
| 208 | ALIASES: iso_8859_6:1987 iso_ir_127 iso8859_6 ecma_114 asmo_708 arabic csisolatinarabic iso88596 |
---|
| 209 | ENTRY END |
---|
| 210 | |
---|
| 211 | # ISO 8859-7:1987 - Greek |
---|
| 212 | ENTRY |
---|
| 213 | ENCODING: iso_8859_7 |
---|
| 214 | CES: table |
---|
| 215 | CCS: iso_8859_7 |
---|
| 216 | ALIASES: iso_8859_7:1987 iso_ir_126 iso8859_7 elot_928 ecma_118 greek greek8 csisolatingreek iso88597 |
---|
| 217 | ENTRY END |
---|
| 218 | |
---|
| 219 | # ISO 8859-8:1988 - Hebrew |
---|
| 220 | ENTRY |
---|
| 221 | ENCODING: iso_8859_8 |
---|
| 222 | CES: table |
---|
| 223 | CCS: iso_8859_8 |
---|
| 224 | ALIASES: iso_8859_8:1988 iso_ir_138 iso8859_8 hebrew csisolatinhebrew iso88598 |
---|
| 225 | ENTRY END |
---|
| 226 | |
---|
| 227 | # ISO 8859-9:1989 - Latin 5, Turkish |
---|
| 228 | ENTRY |
---|
| 229 | ENCODING: iso_8859_9 |
---|
| 230 | CES: table |
---|
| 231 | CCS: iso_8859_9 |
---|
| 232 | ALIASES: iso_8859_9:1989 iso_ir_148 iso8859_9 latin5 l5 csisolatin5 iso88599 |
---|
| 233 | ENTRY END |
---|
| 234 | |
---|
| 235 | # ISO 8859-10:1992 - Latin 6, Nordic |
---|
| 236 | ENTRY |
---|
| 237 | ENCODING: iso_8859_10 |
---|
| 238 | CES: table |
---|
| 239 | CCS: iso_8859_10 |
---|
| 240 | ALIASES: iso_8859_10:1992 iso_ir_157 iso885910 latin6 l6 csisolatin6 iso8859_10 |
---|
| 241 | ENTRY END |
---|
| 242 | |
---|
| 243 | # ISO 8859-11 - Thai |
---|
| 244 | ENTRY |
---|
| 245 | ENCODING: iso_8859_11 |
---|
| 246 | CES: table |
---|
| 247 | CCS: iso_8859_11 |
---|
| 248 | ALIASES: iso8859_11 iso885911 |
---|
| 249 | ENTRY END |
---|
| 250 | |
---|
| 251 | # ISO 8859-13:1998 - Latin 7, Baltic Rim |
---|
| 252 | ENTRY |
---|
| 253 | ENCODING: iso_8859_13 |
---|
| 254 | CES: table |
---|
| 255 | CCS: iso_8859_13 |
---|
| 256 | ALIASES: iso_8859_13:1998 iso8859_13 iso885913 |
---|
| 257 | ENTRY END |
---|
| 258 | |
---|
| 259 | # ISO 8859-14:1998 - Latin 8, Celtic |
---|
| 260 | ENTRY |
---|
| 261 | ENCODING: iso_8859_14 |
---|
| 262 | CES: table |
---|
| 263 | CCS: iso_8859_14 |
---|
| 264 | ALIASES: iso_8859_14:1998 iso885914 iso8859_14 |
---|
| 265 | ENTRY END |
---|
| 266 | |
---|
| 267 | # ISO 8859-15:1998 - Latin 9, West Europe, successor of Latin 1 |
---|
| 268 | ENTRY |
---|
| 269 | ENCODING: iso_8859_15 |
---|
| 270 | CES: table |
---|
| 271 | CCS: iso_8859_15 |
---|
| 272 | ALIASES: iso885915 iso_8859_15:1998 iso8859_15 |
---|
| 273 | ENTRY END |
---|
| 274 | |
---|
| 275 | # Win-1250 |
---|
| 276 | ENTRY |
---|
| 277 | ENCODING: win_1250 |
---|
| 278 | CES: table |
---|
| 279 | CCS: win_1250 |
---|
| 280 | ALIASES: cp1250 |
---|
| 281 | ENTRY END |
---|
| 282 | |
---|
| 283 | # Win-1251 - Cyrillic |
---|
| 284 | ENTRY |
---|
| 285 | ENCODING: win_1251 |
---|
| 286 | CES: table |
---|
| 287 | CCS: win_1251 |
---|
| 288 | ALIASES: cp1251 |
---|
| 289 | ENTRY END |
---|
| 290 | |
---|
| 291 | # Win-1252 - Latin 1 |
---|
| 292 | ENTRY |
---|
| 293 | ENCODING: win_1252 |
---|
| 294 | CES: table |
---|
| 295 | CCS: win_1252 |
---|
| 296 | ALIASES: cp1252 |
---|
| 297 | ENTRY END |
---|
| 298 | |
---|
| 299 | # Win-1253 - Greek |
---|
| 300 | ENTRY |
---|
| 301 | ENCODING: win_1253 |
---|
| 302 | CES: table |
---|
| 303 | CCS: win_1253 |
---|
| 304 | ALIASES: cp1253 |
---|
| 305 | ENTRY END |
---|
| 306 | |
---|
| 307 | # Win-1254 - Turkish |
---|
| 308 | ENTRY |
---|
| 309 | ENCODING: win_1254 |
---|
| 310 | CES: table |
---|
| 311 | CCS: win_1254 |
---|
| 312 | ALIASES: cp1254 |
---|
| 313 | ENTRY END |
---|
| 314 | |
---|
| 315 | # Win-1255 - Hebrew |
---|
| 316 | ENTRY |
---|
| 317 | ENCODING: win_1255 |
---|
| 318 | CES: table |
---|
| 319 | CCS: win_1255 |
---|
| 320 | ALIASES: cp1255 |
---|
| 321 | ENTRY END |
---|
| 322 | |
---|
| 323 | # Win-1256 - Arabic |
---|
| 324 | ENTRY |
---|
| 325 | ENCODING: win_1256 |
---|
| 326 | CES: table |
---|
| 327 | CCS: win_1256 |
---|
| 328 | ALIASES: cp1256 |
---|
| 329 | ENTRY END |
---|
| 330 | |
---|
| 331 | # Win-1257 - Baltic |
---|
| 332 | ENTRY |
---|
| 333 | ENCODING: win_1257 |
---|
| 334 | CES: table |
---|
| 335 | CCS: win_1257 |
---|
| 336 | ALIASES: cp1257 |
---|
| 337 | ENTRY END |
---|
| 338 | |
---|
| 339 | # Win-1258 - Vietnamese7 that supports Cyrillic |
---|
| 340 | ENTRY |
---|
| 341 | ENCODING: win_1258 |
---|
| 342 | CES: table |
---|
| 343 | CCS: win_1258 |
---|
| 344 | ALIASES: cp1258 |
---|
| 345 | ENTRY END |
---|
| 346 | |
---|
| 347 | # big5 - an encoding for Traditional Chinese |
---|
| 348 | ENTRY |
---|
| 349 | ENCODING: big5 |
---|
| 350 | CES: table_pcs |
---|
| 351 | CCS: big5 |
---|
| 352 | ALIASES: csbig5 big_five bigfive cn_big5 cp950 |
---|
| 353 | ENTRY END |
---|
| 354 | |
---|
| 355 | # IBM 775 - an updated version of CP 437 that supports balitic languages. |
---|
| 356 | ENTRY |
---|
| 357 | ENCODING: cp775 |
---|
| 358 | CES: table |
---|
| 359 | CCS: cp775 |
---|
| 360 | ALIASES: ibm775 cspc775baltic |
---|
| 361 | ENTRY END |
---|
| 362 | |
---|
| 363 | # IBM 850 - an updated version of CP 437 where several Latin 1 characters have been |
---|
| 364 | # added instead of some less-often used characters like line-drawing and greek ones. |
---|
| 365 | ENTRY |
---|
| 366 | ENCODING: cp850 |
---|
| 367 | CES: table |
---|
| 368 | CCS: cp850 |
---|
| 369 | ALIASES: ibm850 850 cspc850multilingual |
---|
| 370 | ENTRY END |
---|
| 371 | |
---|
| 372 | # IBM 852 - an updated version of CP 437 where several Latin 2 characters have been added |
---|
| 373 | # instead of some less-often used characters like line-drawing and greek ones. |
---|
| 374 | ENTRY |
---|
| 375 | ENCODING: cp852 |
---|
| 376 | CES: table |
---|
| 377 | CCS: cp852 |
---|
| 378 | ALIASES: ibm852 852 cspcp852 |
---|
| 379 | ENTRY END |
---|
| 380 | |
---|
| 381 | # IBM 855 - an updated version of CP 437 that supports Cyrillic. |
---|
| 382 | ENTRY |
---|
| 383 | ENCODING: cp855 |
---|
| 384 | CES: table |
---|
| 385 | CCS: cp855 |
---|
| 386 | ALIASES: ibm855 855 csibm855 |
---|
| 387 | ENTRY END |
---|
| 388 | |
---|
| 389 | # IBM 866 - an updated version of CP 855 which followes the more logical Russian alphabet |
---|
| 390 | # ordering of the alternativny variant that is preferred by many Russian users. |
---|
| 391 | ENTRY |
---|
| 392 | ENCODING: cp866 |
---|
| 393 | CES: table |
---|
| 394 | CCS: cp866 |
---|
| 395 | ALIASES: 866 IBM866 CSIBM866 |
---|
| 396 | ENTRY END |
---|
| 397 | |
---|
| 398 | # EUC-JP - The EUC for Japanese |
---|
| 399 | ENTRY |
---|
| 400 | ENCODING: euc_jp |
---|
| 401 | CES: euc |
---|
| 402 | CCS: jis_x0208_1990 jis_x0201_1976 jis_x0212_1990 |
---|
| 403 | ALIASES: eucjp |
---|
| 404 | ENTRY END |
---|
| 405 | |
---|
| 406 | # EUC-KR - The EUC for Korean |
---|
| 407 | ENTRY |
---|
| 408 | ENCODING: euc_kr |
---|
| 409 | CES: euc |
---|
| 410 | CCS: ksx1001 |
---|
| 411 | ALIASES: euckr |
---|
| 412 | ENTRY END |
---|
| 413 | |
---|
| 414 | # EUC-TW - The EUC for Traditional Chinese |
---|
| 415 | ENTRY |
---|
| 416 | ENCODING: euc_tw |
---|
| 417 | CES: euc |
---|
| 418 | CCS: cns11643_plane1 cns11643_plane2 cns11643_plane14 |
---|
| 419 | ALIASES: euctw |
---|
| 420 | ENTRY END |
---|
| 421 | |
---|
| 422 | SECTION END |
---|
| 423 | |
---|
| 424 | # |
---|
| 425 | # This section is named "CES_DEPENDENCIES" and describes dependencies |
---|
| 426 | # between CES converters (some CES converters may use another CES converters). |
---|
| 427 | # |
---|
| 428 | SECTION CES_DEPENDENCIES |
---|
| 429 | |
---|
| 430 | ENTRY |
---|
| 431 | CES: table_pcs |
---|
| 432 | USED_CES: table |
---|
| 433 | ENTRY END |
---|
| 434 | |
---|
| 435 | ENTRY |
---|
| 436 | CES: euc |
---|
| 437 | USED_CES: table us_ascii |
---|
| 438 | ENTRY END |
---|
| 439 | |
---|
| 440 | SECTION END |
---|
| 441 | |
---|