| 1 | ;;; mule-conf.el --- configure multilingual environment |
| 2 | |
| 3 | ;; Copyright (C) 1997-2011 Free Software Foundation, Inc. |
| 4 | ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011 |
| 5 | ;; National Institute of Advanced Industrial Science and Technology (AIST) |
| 6 | ;; Registration Number H14PRO021 |
| 7 | ;; Copyright (C) 2003 |
| 8 | ;; National Institute of Advanced Industrial Science and Technology (AIST) |
| 9 | ;; Registration Number H13PRO009 |
| 10 | |
| 11 | ;; Keywords: i18n, mule, multilingual, character set, coding system |
| 12 | |
| 13 | ;; This file is part of GNU Emacs. |
| 14 | |
| 15 | ;; GNU Emacs is free software: you can redistribute it and/or modify |
| 16 | ;; it under the terms of the GNU General Public License as published by |
| 17 | ;; the Free Software Foundation, either version 3 of the License, or |
| 18 | ;; (at your option) any later version. |
| 19 | |
| 20 | ;; GNU Emacs is distributed in the hope that it will be useful, |
| 21 | ;; but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 22 | ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 23 | ;; GNU General Public License for more details. |
| 24 | |
| 25 | ;; You should have received a copy of the GNU General Public License |
| 26 | ;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. |
| 27 | |
| 28 | ;;; Commentary: |
| 29 | |
| 30 | ;; This file defines the Emacs charsets and some basic coding systems. |
| 31 | ;; Other coding systems are defined in the files in directory |
| 32 | ;; lisp/language. |
| 33 | |
| 34 | ;;; Code: |
| 35 | |
| 36 | ;;; Remarks |
| 37 | |
| 38 | ;; The ISO-IR registry is at http://www.itscj.ipsj.or.jp/ISO-IR/. |
| 39 | ;; Standards docs equivalent to iso-2022 and iso-8859 are at |
| 40 | ;; http://www.ecma.ch/. |
| 41 | |
| 42 | ;; FWIW, http://www.microsoft.com/globaldev/ lists the following for |
| 43 | ;; MS Windows, which are presumably the only charsets we really need |
| 44 | ;; to worry about on such systems: |
| 45 | ;; `OEM codepages': 437, 720, 737, 775, 850, 852, 855, 857, 858, 862, 866 |
| 46 | ;; `Windows codepages': 1250, 1251, 1252, 1253, 1254, 1255, 1256, 1257, |
| 47 | ;; 1258, 874, 932, 936, 949, 950 |
| 48 | |
| 49 | ;;; Definitions of character sets. |
| 50 | |
| 51 | ;; The charsets `ascii', `unicode' and `eight-bit' are already defined |
| 52 | ;; in charset.c as below: |
| 53 | ;; |
| 54 | ;; (define-charset 'ascii |
| 55 | ;; "" |
| 56 | ;; :dimension 1 |
| 57 | ;; :code-space [0 127] |
| 58 | ;; :iso-final-char ?B |
| 59 | ;; :ascii-compatible-p t |
| 60 | ;; :emacs-mule-id 0 |
| 61 | ;; :code-offset 0) |
| 62 | ;; |
| 63 | ;; (define-charset 'unicode |
| 64 | ;; "" |
| 65 | ;; :dimension 3 |
| 66 | ;; :code-space [0 255 0 255 0 16] |
| 67 | ;; :ascii-compatible-p t |
| 68 | ;; :code-offset 0) |
| 69 | ;; |
| 70 | ;; (define-charset 'emacs |
| 71 | ;; "" |
| 72 | ;; :dimension 3 |
| 73 | ;; :code-space [0 255 0 255 0 63] |
| 74 | ;; :ascii-compatible-p t |
| 75 | ;; :supplementary-p t |
| 76 | ;; :code-offset 0) |
| 77 | ;; |
| 78 | ;; (define-charset 'eight-bit |
| 79 | ;; "" |
| 80 | ;; :dimension 1 |
| 81 | ;; :code-space [128 255] |
| 82 | ;; :code-offset #x3FFF80) |
| 83 | ;; |
| 84 | ;; We now set :docstring, :short-name, and :long-name properties. |
| 85 | |
| 86 | (put-charset-property |
| 87 | 'ascii :docstring "ASCII (ISO646 IRV)") |
| 88 | (put-charset-property |
| 89 | 'ascii :short-name "ASCII") |
| 90 | (put-charset-property |
| 91 | 'ascii :long-name "ASCII (ISO646 IRV)") |
| 92 | (put-charset-property |
| 93 | 'iso-8859-1 :docstring "Latin-1 (ISO/IEC 8859-1)") |
| 94 | (put-charset-property |
| 95 | 'iso-8859-1 :short-name "Latin-1") |
| 96 | (put-charset-property |
| 97 | 'iso-8859-1 :long-name "Latin-1") |
| 98 | (put-charset-property |
| 99 | 'unicode :docstring "Unicode (ISO10646)") |
| 100 | (put-charset-property |
| 101 | 'unicode :short-name "Unicode") |
| 102 | (put-charset-property |
| 103 | 'unicode :long-name "Unicode (ISO10646)") |
| 104 | (put-charset-property |
| 105 | 'emacs :docstring "Full Emacs charset (excluding eight bit chars)") |
| 106 | (put-charset-property |
| 107 | 'emacs :short-name "Emacs") |
| 108 | (put-charset-property |
| 109 | 'emacs :long-name "Emacs") |
| 110 | |
| 111 | (put-charset-property 'eight-bit :docstring "Raw bytes 128-255") |
| 112 | (put-charset-property 'eight-bit :short-name "Raw bytes") |
| 113 | |
| 114 | (define-charset-alias 'ucs 'unicode) |
| 115 | |
| 116 | (define-charset 'latin-iso8859-1 |
| 117 | "Right-Hand Part of ISO/IEC 8859/1 (Latin-1): ISO-IR-100" |
| 118 | :short-name "RHP of Latin-1" |
| 119 | :long-name "RHP of ISO/IEC 8859/1 (Latin-1): ISO-IR-100" |
| 120 | :iso-final-char ?A |
| 121 | :emacs-mule-id 129 |
| 122 | :code-space [32 127] |
| 123 | :code-offset 160) |
| 124 | |
| 125 | ;; Name perhaps not ideal, but is XEmacs-compatible. |
| 126 | (define-charset 'control-1 |
| 127 | "8-bit control code (0x80..0x9F)" |
| 128 | :short-name "8-bit control code" |
| 129 | :code-space [128 159] |
| 130 | :code-offset 128) |
| 131 | |
| 132 | (define-charset 'eight-bit-control |
| 133 | "Raw bytes in the range 0x80..0x9F (usually produced from invalid encodings)" |
| 134 | :short-name "Raw bytes 0x80..0x9F" |
| 135 | :supplementary-p t |
| 136 | :code-space [128 159] |
| 137 | :code-offset #x3FFF80) ; see character.h |
| 138 | |
| 139 | (define-charset 'eight-bit-graphic |
| 140 | "Raw bytes in the range 0xA0..0xFF (usually produced from invalid encodings)" |
| 141 | :short-name "Raw bytes 0xA0..0xFF" |
| 142 | :supplementary-p t |
| 143 | :code-space [160 255] |
| 144 | :code-offset #x3FFFA0) ; see character.h |
| 145 | |
| 146 | (defmacro define-iso-single-byte-charset (symbol iso-symbol name nickname |
| 147 | iso-ir iso-final |
| 148 | emacs-mule-id map) |
| 149 | `(progn |
| 150 | (define-charset ,symbol |
| 151 | ,name |
| 152 | :short-name ,nickname |
| 153 | :long-name ,name |
| 154 | :ascii-compatible-p t |
| 155 | :code-space [0 255] |
| 156 | :map ,map) |
| 157 | (if ,iso-symbol |
| 158 | (define-charset ,iso-symbol |
| 159 | (if ,iso-ir |
| 160 | (format "Right-Hand Part of %s (%s): ISO-IR-%d" |
| 161 | ,name ,nickname ,iso-ir) |
| 162 | (format "Right-Hand Part of %s (%s)" ,name ,nickname)) |
| 163 | :short-name (format "RHP of %s" ,name) |
| 164 | :long-name (format "RHP of %s (%s)" ,name ,nickname) |
| 165 | :iso-final-char ,iso-final |
| 166 | :emacs-mule-id ,emacs-mule-id |
| 167 | :code-space [32 127] |
| 168 | :subset (list ,symbol 160 255 -128))))) |
| 169 | |
| 170 | (define-iso-single-byte-charset 'iso-8859-2 'latin-iso8859-2 |
| 171 | "ISO/IEC 8859/2" "Latin-2" 101 ?B 130 "8859-2") |
| 172 | |
| 173 | (define-iso-single-byte-charset 'iso-8859-3 'latin-iso8859-3 |
| 174 | "ISO/IEC 8859/3" "Latin-3" 109 ?C 131 "8859-3") |
| 175 | |
| 176 | (define-iso-single-byte-charset 'iso-8859-4 'latin-iso8859-4 |
| 177 | "ISO/IEC 8859/4" "Latin-4" 110 ?D 132 "8859-4") |
| 178 | |
| 179 | (define-iso-single-byte-charset 'iso-8859-5 'cyrillic-iso8859-5 |
| 180 | "ISO/IEC 8859/5" "Latin/Cyrillic" 144 ?L 140 "8859-5") |
| 181 | |
| 182 | (define-iso-single-byte-charset 'iso-8859-6 'arabic-iso8859-6 |
| 183 | "ISO/IEC 8859/6" "Latin/Arabic" 127 ?G 135 "8859-6") |
| 184 | |
| 185 | (define-iso-single-byte-charset 'iso-8859-7 'greek-iso8859-7 |
| 186 | "ISO/IEC 8859/7" "Latin/Greek" 126 ?F 134 "8859-7") |
| 187 | |
| 188 | (define-iso-single-byte-charset 'iso-8859-8 'hebrew-iso8859-8 |
| 189 | "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H 136 "8859-8") |
| 190 | |
| 191 | (define-iso-single-byte-charset 'iso-8859-9 'latin-iso8859-9 |
| 192 | "ISO/IEC 8859/9" "Latin-5" 148 ?M 141 "8859-9") |
| 193 | |
| 194 | (define-iso-single-byte-charset 'iso-8859-10 'latin-iso8859-10 |
| 195 | "ISO/IEC 8859/10" "Latin-6" 157 ?V nil "8859-10") |
| 196 | |
| 197 | ;; http://www.nectec.or.th/it-standards/iso8859-11/ |
| 198 | ;; http://www.cwi.nl/~dik/english/codes/8859.html says this is tis-620 |
| 199 | ;; plus nbsp |
| 200 | (define-iso-single-byte-charset 'iso-8859-11 'thai-iso8859-11 |
| 201 | "ISO/IEC 8859/11" "Latin/Thai" 166 ?T nil "8859-11") |
| 202 | |
| 203 | ;; 8859-12 doesn't (yet?) exist. |
| 204 | |
| 205 | (define-iso-single-byte-charset 'iso-8859-13 'latin-iso8859-13 |
| 206 | "ISO/IEC 8859/13" "Latin-7" 179 ?Y nil "8859-13") |
| 207 | |
| 208 | (define-iso-single-byte-charset 'iso-8859-14 'latin-iso8859-14 |
| 209 | "ISO/IEC 8859/14" "Latin-8" 199 ?_ 143 "8859-14") |
| 210 | |
| 211 | (define-iso-single-byte-charset 'iso-8859-15 'latin-iso8859-15 |
| 212 | "ISO/IEC 8859/15" "Latin-9" 203 ?b 142 "8859-15") |
| 213 | |
| 214 | (define-iso-single-byte-charset 'iso-8859-16 'latin-iso8859-16 |
| 215 | "ISO/IEC 8859/16" "Latin-10" 226 ?f nil "8859-16") |
| 216 | |
| 217 | ;; No point in keeping it around. |
| 218 | (fmakunbound 'define-iso-single-byte-charset) |
| 219 | |
| 220 | ;; Can this be shared with 8859-11? |
| 221 | ;; N.b. not all of these are defined in Unicode. |
| 222 | (define-charset 'thai-tis620 |
| 223 | "TIS620.2533" |
| 224 | :short-name "TIS620.2533" |
| 225 | :iso-final-char ?T |
| 226 | :emacs-mule-id 133 |
| 227 | :code-space [32 127] |
| 228 | :code-offset #x0E00) |
| 229 | |
| 230 | ;; Fixme: doc for this, c.f. above |
| 231 | (define-charset 'tis620-2533 |
| 232 | "TIS620.2533" |
| 233 | :short-name "TIS620.2533" |
| 234 | :ascii-compatible-p t |
| 235 | :code-space [0 255] |
| 236 | :superset '(ascii eight-bit-control (thai-tis620 . 128))) |
| 237 | |
| 238 | (define-charset 'jisx0201 |
| 239 | "JISX0201" |
| 240 | :short-name "JISX0201" |
| 241 | :code-space [0 #xDF] |
| 242 | :map "JISX0201") |
| 243 | |
| 244 | (define-charset 'latin-jisx0201 |
| 245 | "Roman Part of JISX0201.1976" |
| 246 | :short-name "JISX0201 Roman" |
| 247 | :long-name "Japanese Roman (JISX0201.1976)" |
| 248 | :iso-final-char ?J |
| 249 | :emacs-mule-id 138 |
| 250 | :supplementary-p t |
| 251 | :code-space [33 126] |
| 252 | :subset '(jisx0201 33 126 0)) |
| 253 | |
| 254 | (define-charset 'katakana-jisx0201 |
| 255 | "Katakana Part of JISX0201.1976" |
| 256 | :short-name "JISX0201 Katakana" |
| 257 | :long-name "Japanese Katakana (JISX0201.1976)" |
| 258 | :iso-final-char ?I |
| 259 | :emacs-mule-id 137 |
| 260 | :supplementary-p t |
| 261 | :code-space [33 126] |
| 262 | :subset '(jisx0201 161 254 -128)) |
| 263 | |
| 264 | (define-charset 'chinese-gb2312 |
| 265 | "GB2312 Chinese simplified: ISO-IR-58" |
| 266 | :short-name "GB2312" |
| 267 | :long-name "GB2312: ISO-IR-58" |
| 268 | :iso-final-char ?A |
| 269 | :emacs-mule-id 145 |
| 270 | :code-space [33 126 33 126] |
| 271 | :code-offset #x110000 |
| 272 | :unify-map "GB2312") |
| 273 | |
| 274 | (define-charset 'chinese-gbk |
| 275 | "GBK Chinese simplified." |
| 276 | :short-name "GBK" |
| 277 | :code-space [#x40 #xFE #x81 #xFE] |
| 278 | :code-offset #x160000 |
| 279 | :unify-map "GBK") |
| 280 | (define-charset-alias 'cp936 'chinese-gbk) |
| 281 | (define-charset-alias 'windows-936 'chinese-gbk) |
| 282 | |
| 283 | (define-charset 'chinese-cns11643-1 |
| 284 | "CNS11643 Plane 1 Chinese traditional: ISO-IR-171" |
| 285 | :short-name "CNS11643-1" |
| 286 | :long-name "CNS11643-1 (Chinese traditional): ISO-IR-171" |
| 287 | :iso-final-char ?G |
| 288 | :emacs-mule-id 149 |
| 289 | :code-space [33 126 33 126] |
| 290 | :code-offset #x114000 |
| 291 | :unify-map "CNS-1") |
| 292 | |
| 293 | (define-charset 'chinese-cns11643-2 |
| 294 | "CNS11643 Plane 2 Chinese traditional: ISO-IR-172" |
| 295 | :short-name "CNS11643-2" |
| 296 | :long-name "CNS11643-2 (Chinese traditional): ISO-IR-172" |
| 297 | :iso-final-char ?H |
| 298 | :emacs-mule-id 150 |
| 299 | :code-space [33 126 33 126] |
| 300 | :code-offset #x118000 |
| 301 | :unify-map "CNS-2") |
| 302 | |
| 303 | (define-charset 'chinese-cns11643-3 |
| 304 | "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183" |
| 305 | :short-name "CNS11643-3" |
| 306 | :long-name "CNS11643-3 (Chinese traditional): ISO-IR-183" |
| 307 | :iso-final-char ?I |
| 308 | :code-space [33 126 33 126] |
| 309 | :emacs-mule-id 246 |
| 310 | :code-offset #x11C000 |
| 311 | :unify-map "CNS-3") |
| 312 | |
| 313 | (define-charset 'chinese-cns11643-4 |
| 314 | "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184" |
| 315 | :short-name "CNS11643-4" |
| 316 | :long-name "CNS11643-4 (Chinese traditional): ISO-IR-184" |
| 317 | :iso-final-char ?J |
| 318 | :emacs-mule-id 247 |
| 319 | :code-space [33 126 33 126] |
| 320 | :code-offset #x120000 |
| 321 | :unify-map "CNS-4") |
| 322 | |
| 323 | (define-charset 'chinese-cns11643-5 |
| 324 | "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185" |
| 325 | :short-name "CNS11643-5" |
| 326 | :long-name "CNS11643-5 (Chinese traditional): ISO-IR-185" |
| 327 | :iso-final-char ?K |
| 328 | :emacs-mule-id 248 |
| 329 | :code-space [33 126 33 126] |
| 330 | :code-offset #x124000 |
| 331 | :unify-map "CNS-5") |
| 332 | |
| 333 | (define-charset 'chinese-cns11643-6 |
| 334 | "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186" |
| 335 | :short-name "CNS11643-6" |
| 336 | :long-name "CNS11643-6 (Chinese traditional): ISO-IR-186" |
| 337 | :iso-final-char ?L |
| 338 | :emacs-mule-id 249 |
| 339 | :code-space [33 126 33 126] |
| 340 | :code-offset #x128000 |
| 341 | :unify-map "CNS-6") |
| 342 | |
| 343 | (define-charset 'chinese-cns11643-7 |
| 344 | "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187" |
| 345 | :short-name "CNS11643-7" |
| 346 | :long-name "CNS11643-7 (Chinese traditional): ISO-IR-187" |
| 347 | :iso-final-char ?M |
| 348 | :emacs-mule-id 250 |
| 349 | :code-space [33 126 33 126] |
| 350 | :code-offset #x12C000 |
| 351 | :unify-map "CNS-7") |
| 352 | |
| 353 | (define-charset 'big5 |
| 354 | "Big5 (Chinese traditional)" |
| 355 | :short-name "Big5" |
| 356 | :code-space [#x40 #xFE #xA1 #xFE] |
| 357 | :code-offset #x130000 |
| 358 | :unify-map "BIG5") |
| 359 | ;; Fixme: AKA cp950 according to |
| 360 | ;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>. Is |
| 361 | ;; that correct? |
| 362 | |
| 363 | (define-charset 'chinese-big5-1 |
| 364 | "Frequently used part (A141-C67E) of Big5 (Chinese traditional)" |
| 365 | :short-name "Big5 (Level-1)" |
| 366 | :long-name "Big5 (Level-1) A141-C67F" |
| 367 | :iso-final-char ?0 |
| 368 | :emacs-mule-id 152 |
| 369 | :supplementary-p t |
| 370 | :code-space [#x21 #x7E #x21 #x7E] |
| 371 | :code-offset #x135000 |
| 372 | :unify-map "BIG5-1") |
| 373 | |
| 374 | (define-charset 'chinese-big5-2 |
| 375 | "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)" |
| 376 | :short-name "Big5 (Level-2)" |
| 377 | :long-name "Big5 (Level-2) C940-FEFE" |
| 378 | :iso-final-char ?1 |
| 379 | :emacs-mule-id 153 |
| 380 | :supplementary-p t |
| 381 | :code-space [#x21 #x7E #x21 #x7E] |
| 382 | :code-offset #x137800 |
| 383 | :unify-map "BIG5-2") |
| 384 | |
| 385 | (define-charset 'japanese-jisx0208 |
| 386 | "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87" |
| 387 | :short-name "JISX0208" |
| 388 | :long-name "JISX0208.1983/1990 (Japanese): ISO-IR-87" |
| 389 | :iso-final-char ?B |
| 390 | :emacs-mule-id 146 |
| 391 | :code-space [33 126 33 126] |
| 392 | :code-offset #x140000 |
| 393 | :unify-map "JISX0208") |
| 394 | |
| 395 | (define-charset 'japanese-jisx0208-1978 |
| 396 | "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42" |
| 397 | :short-name "JISX0208.1978" |
| 398 | :long-name "JISX0208.1978 (JISC6226.1978): ISO-IR-42" |
| 399 | :iso-final-char ?@ |
| 400 | :emacs-mule-id 144 |
| 401 | :code-space [33 126 33 126] |
| 402 | :code-offset #x144000 |
| 403 | :unify-map "JISC6226") |
| 404 | |
| 405 | (define-charset 'japanese-jisx0212 |
| 406 | "JISX0212 Japanese supplement: ISO-IR-159" |
| 407 | :short-name "JISX0212" |
| 408 | :long-name "JISX0212 (Japanese): ISO-IR-159" |
| 409 | :iso-final-char ?D |
| 410 | :emacs-mule-id 148 |
| 411 | :code-space [33 126 33 126] |
| 412 | :code-offset #x148000 |
| 413 | :unify-map "JISX0212") |
| 414 | |
| 415 | ;; Note that jisx0213 contains characters not in Unicode (3.2?). It's |
| 416 | ;; arguable whether it should have a unify-map. |
| 417 | (define-charset 'japanese-jisx0213-1 |
| 418 | "JISX0213.2000 Plane 1 (Japanese)" |
| 419 | :short-name "JISX0213-1" |
| 420 | :iso-final-char ?O |
| 421 | :emacs-mule-id 151 |
| 422 | :unify-map "JISX2131" |
| 423 | :code-space [33 126 33 126] |
| 424 | :code-offset #x14C000) |
| 425 | |
| 426 | (define-charset 'japanese-jisx0213-2 |
| 427 | "JISX0213.2000 Plane 2 (Japanese)" |
| 428 | :short-name "JISX0213-2" |
| 429 | :iso-final-char ?P |
| 430 | :emacs-mule-id 254 |
| 431 | :unify-map "JISX2132" |
| 432 | :code-space [33 126 33 126] |
| 433 | :code-offset #x150000) |
| 434 | |
| 435 | (define-charset 'japanese-jisx0213-a |
| 436 | "JISX0213.2004 adds these characters to JISX0213.2000." |
| 437 | :short-name "JISX0213A" |
| 438 | :dimension 2 |
| 439 | :code-space [33 126 33 126] |
| 440 | :supplementary-p t |
| 441 | :map "JISX213A") |
| 442 | |
| 443 | (define-charset 'japanese-jisx0213.2004-1 |
| 444 | "JISX0213.2004 Plane1 (Japanese)" |
| 445 | :short-name "JISX0213.2004-1" |
| 446 | :dimension 2 |
| 447 | :code-space [33 126 33 126] |
| 448 | :iso-final-char ?Q |
| 449 | :superset '(japanese-jisx0213-a japanese-jisx0213-1)) |
| 450 | |
| 451 | (define-charset 'katakana-sjis |
| 452 | "Katakana part of Shift-JIS" |
| 453 | :dimension 1 |
| 454 | :code-space [#xA1 #xDF] |
| 455 | :subset '(jisx0201 #xA1 #xDF 0) |
| 456 | :supplementary-p t) |
| 457 | |
| 458 | (define-charset 'cp932-2-byte |
| 459 | "2-byte part of CP932" |
| 460 | :dimension 2 |
| 461 | :map "CP932-2BYTE" |
| 462 | :code-space [#x40 #xFC #x81 #xFC] |
| 463 | :supplementary-p t) |
| 464 | |
| 465 | (define-charset 'cp932 |
| 466 | "CP932 (Microsoft shift-jis)" |
| 467 | :code-space [#x00 #xFF #x00 #xFE] |
| 468 | :short-name "CP932" |
| 469 | :superset '(ascii katakana-sjis cp932-2-byte)) |
| 470 | |
| 471 | (define-charset 'korean-ksc5601 |
| 472 | "KSC5601 Korean Hangul and Hanja: ISO-IR-149" |
| 473 | :short-name "KSC5601" |
| 474 | :long-name "KSC5601 (Korean): ISO-IR-149" |
| 475 | :iso-final-char ?C |
| 476 | :emacs-mule-id 147 |
| 477 | :code-space [33 126 33 126] |
| 478 | :code-offset #x279f94 ; ... #x27c217 |
| 479 | :unify-map "KSC5601") |
| 480 | |
| 481 | (define-charset 'big5-hkscs |
| 482 | "Big5-HKSCS (Chinese traditional, Hong Kong supplement)" |
| 483 | :short-name "Big5" |
| 484 | :code-space [#x40 #xFE #xA1 #xFE] |
| 485 | :code-offset #x27c218 ; ... #x280839 |
| 486 | :unify-map "BIG5-HKSCS") |
| 487 | |
| 488 | (define-charset 'cp949-2-byte |
| 489 | "2-byte part of CP949" |
| 490 | :dimension 2 |
| 491 | :map "CP949-2BYTE" |
| 492 | :code-space [#x41 #xFE #x81 #xFD] |
| 493 | :supplementary-p t) |
| 494 | |
| 495 | (define-charset 'cp949 |
| 496 | "CP949 (Korean)" |
| 497 | :short-name "CP949" |
| 498 | :long-name "CP949 (Korean)" |
| 499 | :code-space [#x00 #xFE #x00 #xFD] |
| 500 | :superset '(ascii cp949-2-byte)) |
| 501 | |
| 502 | (define-charset 'chinese-sisheng |
| 503 | "SiSheng characters for PinYin/ZhuYin" |
| 504 | :short-name "SiSheng" |
| 505 | :long-name "SiSheng (PinYin/ZhuYin)" |
| 506 | :iso-final-char ?0 |
| 507 | :emacs-mule-id 160 |
| 508 | :code-space [33 126] |
| 509 | :unify-map "MULE-sisheng" |
| 510 | :supplementary-p t |
| 511 | :code-offset #x200000) |
| 512 | |
| 513 | ;; A subset of the 1989 version of IPA. It consists of the consonant |
| 514 | ;; signs used in English, French, German and Italian, and all vowels |
| 515 | ;; signs in the table. [says old MULE doc] |
| 516 | (define-charset 'ipa |
| 517 | "IPA (International Phonetic Association)" |
| 518 | :short-name "IPA" |
| 519 | :iso-final-char ?0 |
| 520 | :emacs-mule-id 161 |
| 521 | :unify-map "MULE-ipa" |
| 522 | :code-space [32 127] |
| 523 | :supplementary-p t |
| 524 | :code-offset #x200080) |
| 525 | |
| 526 | (define-charset 'viscii |
| 527 | "VISCII1.1" |
| 528 | :short-name "VISCII" |
| 529 | :long-name "VISCII 1.1" |
| 530 | :code-space [0 255] |
| 531 | :map "VISCII") |
| 532 | |
| 533 | (define-charset 'vietnamese-viscii-lower |
| 534 | "VISCII1.1 lower-case" |
| 535 | :short-name "VISCII lower" |
| 536 | :long-name "VISCII lower-case" |
| 537 | :iso-final-char ?1 |
| 538 | :emacs-mule-id 162 |
| 539 | :code-space [32 127] |
| 540 | :code-offset #x200200 |
| 541 | :supplementary-p t |
| 542 | :unify-map "MULE-lviscii") |
| 543 | |
| 544 | (define-charset 'vietnamese-viscii-upper |
| 545 | "VISCII1.1 upper-case" |
| 546 | :short-name "VISCII upper" |
| 547 | :long-name "VISCII upper-case" |
| 548 | :iso-final-char ?2 |
| 549 | :emacs-mule-id 163 |
| 550 | :code-space [32 127] |
| 551 | :code-offset #x200280 |
| 552 | :supplementary-p t |
| 553 | :unify-map "MULE-uviscii") |
| 554 | |
| 555 | (define-charset 'vscii |
| 556 | "VSCII1.1 (TCVN-5712 VN1)" |
| 557 | :short-name "VSCII" |
| 558 | :code-space [0 255] |
| 559 | :map "VSCII") |
| 560 | |
| 561 | (define-charset-alias 'tcvn-5712 'vscii) |
| 562 | |
| 563 | ;; Fixme: see note in tcvn.map about combining characters |
| 564 | (define-charset 'vscii-2 |
| 565 | "VSCII-2 (TCVN-5712 VN2)" |
| 566 | :code-space [0 255] |
| 567 | :map "VSCII-2") |
| 568 | |
| 569 | (define-charset 'koi8-r |
| 570 | "KOI8-R" |
| 571 | :short-name "KOI8-R" |
| 572 | :ascii-compatible-p t |
| 573 | :code-space [0 255] |
| 574 | :map "KOI8-R") |
| 575 | |
| 576 | (define-charset-alias 'koi8 'koi8-r) |
| 577 | |
| 578 | (define-charset 'alternativnyj |
| 579 | "ALTERNATIVNYJ" |
| 580 | :short-name "alternativnyj" |
| 581 | :ascii-compatible-p t |
| 582 | :code-space [0 255] |
| 583 | :map "ALTERNATIVNYJ") |
| 584 | |
| 585 | (define-charset 'cp866 |
| 586 | "CP866" |
| 587 | :short-name "cp866" |
| 588 | :ascii-compatible-p t |
| 589 | :code-space [0 255] |
| 590 | :map "IBM866") |
| 591 | (define-charset-alias 'ibm866 'cp866) |
| 592 | |
| 593 | (define-charset 'koi8-u |
| 594 | "KOI8-U" |
| 595 | :short-name "KOI8-U" |
| 596 | :ascii-compatible-p t |
| 597 | :code-space [0 255] |
| 598 | :map "KOI8-U") |
| 599 | |
| 600 | (define-charset 'koi8-t |
| 601 | "KOI8-T" |
| 602 | :short-name "KOI8-T" |
| 603 | :ascii-compatible-p t |
| 604 | :code-space [0 255] |
| 605 | :map "KOI8-T") |
| 606 | |
| 607 | (define-charset 'georgian-ps |
| 608 | "GEORGIAN-PS" |
| 609 | :short-name "GEORGIAN-PS" |
| 610 | :ascii-compatible-p t |
| 611 | :code-space [0 255] |
| 612 | :map "KA-PS") |
| 613 | |
| 614 | (define-charset 'georgian-academy |
| 615 | "GEORGIAN-ACADEMY" |
| 616 | :short-name "GEORGIAN-ACADEMY" |
| 617 | :ascii-compatible-p t |
| 618 | :code-space [0 255] |
| 619 | :map "KA-ACADEMY") |
| 620 | |
| 621 | (define-charset 'windows-1250 |
| 622 | "WINDOWS-1250 (Central Europe)" |
| 623 | :short-name "WINDOWS-1250" |
| 624 | :ascii-compatible-p t |
| 625 | :code-space [0 255] |
| 626 | :map "CP1250") |
| 627 | (define-charset-alias 'cp1250 'windows-1250) |
| 628 | |
| 629 | (define-charset 'windows-1251 |
| 630 | "WINDOWS-1251 (Cyrillic)" |
| 631 | :short-name "WINDOWS-1251" |
| 632 | :ascii-compatible-p t |
| 633 | :code-space [0 255] |
| 634 | :map "CP1251") |
| 635 | (define-charset-alias 'cp1251 'windows-1251) |
| 636 | |
| 637 | (define-charset 'windows-1252 |
| 638 | "WINDOWS-1252 (Latin I)" |
| 639 | :short-name "WINDOWS-1252" |
| 640 | :ascii-compatible-p t |
| 641 | :code-space [0 255] |
| 642 | :map "CP1252") |
| 643 | (define-charset-alias 'cp1252 'windows-1252) |
| 644 | |
| 645 | (define-charset 'windows-1253 |
| 646 | "WINDOWS-1253 (Greek)" |
| 647 | :short-name "WINDOWS-1253" |
| 648 | :ascii-compatible-p t |
| 649 | :code-space [0 255] |
| 650 | :map "CP1253") |
| 651 | (define-charset-alias 'cp1253 'windows-1253) |
| 652 | |
| 653 | (define-charset 'windows-1254 |
| 654 | "WINDOWS-1254 (Turkish)" |
| 655 | :short-name "WINDOWS-1254" |
| 656 | :ascii-compatible-p t |
| 657 | :code-space [0 255] |
| 658 | :map "CP1254") |
| 659 | (define-charset-alias 'cp1254 'windows-1254) |
| 660 | |
| 661 | (define-charset 'windows-1255 |
| 662 | "WINDOWS-1255 (Hebrew)" |
| 663 | :short-name "WINDOWS-1255" |
| 664 | :ascii-compatible-p t |
| 665 | :code-space [0 255] |
| 666 | :map "CP1255") |
| 667 | (define-charset-alias 'cp1255 'windows-1255) |
| 668 | |
| 669 | (define-charset 'windows-1256 |
| 670 | "WINDOWS-1256 (Arabic)" |
| 671 | :short-name "WINDOWS-1256" |
| 672 | :ascii-compatible-p t |
| 673 | :code-space [0 255] |
| 674 | :map "CP1256") |
| 675 | (define-charset-alias 'cp1256 'windows-1256) |
| 676 | |
| 677 | (define-charset 'windows-1257 |
| 678 | "WINDOWS-1257 (Baltic)" |
| 679 | :short-name "WINDOWS-1257" |
| 680 | :ascii-compatible-p t |
| 681 | :code-space [0 255] |
| 682 | :map "CP1257") |
| 683 | (define-charset-alias 'cp1257 'windows-1257) |
| 684 | |
| 685 | (define-charset 'windows-1258 |
| 686 | "WINDOWS-1258 (Viet Nam)" |
| 687 | :short-name "WINDOWS-1258" |
| 688 | :ascii-compatible-p t |
| 689 | :code-space [0 255] |
| 690 | :map "CP1258") |
| 691 | (define-charset-alias 'cp1258 'windows-1258) |
| 692 | |
| 693 | (define-charset 'next |
| 694 | "NEXT" |
| 695 | :short-name "NEXT" |
| 696 | :ascii-compatible-p t |
| 697 | :code-space [0 255] |
| 698 | :map "NEXTSTEP") |
| 699 | |
| 700 | (define-charset 'cp1125 |
| 701 | "CP1125" |
| 702 | :short-name "CP1125" |
| 703 | :code-space [0 255] |
| 704 | :ascii-compatible-p t |
| 705 | :map "CP1125") |
| 706 | (define-charset-alias 'ruscii 'cp1125) |
| 707 | ;; Original name for cp1125, says Serhii Hlodin <hlodin@lutsk.bank.gov.ua> |
| 708 | (define-charset-alias 'cp866u 'cp1125) |
| 709 | |
| 710 | ;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html |
| 711 | ;; shows this as not ASCII compatible, with various graphics in |
| 712 | ;; 0x01-0x1F. |
| 713 | (define-charset 'cp437 |
| 714 | "CP437 (MS-DOS United States, Australia, New Zealand, South Africa)" |
| 715 | :short-name "CP437" |
| 716 | :code-space [0 255] |
| 717 | :ascii-compatible-p t |
| 718 | :map "IBM437") |
| 719 | |
| 720 | (define-charset 'cp720 |
| 721 | "CP720 (Arabic)" |
| 722 | :short-name "CP720" |
| 723 | :code-space [0 255] |
| 724 | :ascii-compatible-p t |
| 725 | :map "CP720") |
| 726 | |
| 727 | (define-charset 'cp737 |
| 728 | "CP737 (PC Greek)" |
| 729 | :short-name "CP737" |
| 730 | :code-space [0 255] |
| 731 | :ascii-compatible-p t |
| 732 | :map "CP737") |
| 733 | |
| 734 | (define-charset 'cp775 |
| 735 | "CP775 (PC Baltic)" |
| 736 | :short-name "CP775" |
| 737 | :code-space [0 255] |
| 738 | :ascii-compatible-p t |
| 739 | :map "CP775") |
| 740 | |
| 741 | (define-charset 'cp851 |
| 742 | "CP851 (Greek)" |
| 743 | :short-name "CP851" |
| 744 | :code-space [0 255] |
| 745 | :ascii-compatible-p t |
| 746 | :map "IBM851") |
| 747 | |
| 748 | (define-charset 'cp852 |
| 749 | "CP852 (MS-DOS Latin-2)" |
| 750 | :short-name "CP852" |
| 751 | :code-space [0 255] |
| 752 | :ascii-compatible-p t |
| 753 | :map "IBM852") |
| 754 | |
| 755 | (define-charset 'cp855 |
| 756 | "CP855 (IBM Cyrillic)" |
| 757 | :short-name "CP855" |
| 758 | :code-space [0 255] |
| 759 | :ascii-compatible-p t |
| 760 | :map "IBM855") |
| 761 | |
| 762 | (define-charset 'cp857 |
| 763 | "CP857 (IBM Turkish)" |
| 764 | :short-name "CP857" |
| 765 | :code-space [0 255] |
| 766 | :ascii-compatible-p t |
| 767 | :map "IBM857") |
| 768 | |
| 769 | (define-charset 'cp858 |
| 770 | "CP858 (Multilingual Latin I + Euro)" |
| 771 | :short-name "CP858" |
| 772 | :code-space [0 255] |
| 773 | :ascii-compatible-p t |
| 774 | :map "CP858") |
| 775 | (define-charset-alias 'cp00858 'cp858) ; IANA has IBM00858/CP00858 |
| 776 | |
| 777 | (define-charset 'cp860 |
| 778 | "CP860 (MS-DOS Portuguese)" |
| 779 | :short-name "CP860" |
| 780 | :code-space [0 255] |
| 781 | :ascii-compatible-p t |
| 782 | :map "IBM860") |
| 783 | |
| 784 | (define-charset 'cp861 |
| 785 | "CP861 (MS-DOS Icelandic)" |
| 786 | :short-name "CP861" |
| 787 | :code-space [0 255] |
| 788 | :ascii-compatible-p t |
| 789 | :map "IBM861") |
| 790 | |
| 791 | (define-charset 'cp862 |
| 792 | "CP862 (PC Hebrew)" |
| 793 | :short-name "CP862" |
| 794 | :code-space [0 255] |
| 795 | :ascii-compatible-p t |
| 796 | :map "IBM862") |
| 797 | |
| 798 | (define-charset 'cp863 |
| 799 | "CP863 (MS-DOS Canadian French)" |
| 800 | :short-name "CP863" |
| 801 | :code-space [0 255] |
| 802 | :ascii-compatible-p t |
| 803 | :map "IBM863") |
| 804 | |
| 805 | (define-charset 'cp864 |
| 806 | "CP864 (PC Arabic)" |
| 807 | :short-name "CP864" |
| 808 | :code-space [0 255] |
| 809 | :ascii-compatible-p t |
| 810 | :map "IBM864") |
| 811 | |
| 812 | (define-charset 'cp865 |
| 813 | "CP865 (MS-DOS Nordic)" |
| 814 | :short-name "CP865" |
| 815 | :code-space [0 255] |
| 816 | :ascii-compatible-p t |
| 817 | :map "IBM865") |
| 818 | |
| 819 | (define-charset 'cp869 |
| 820 | "CP869 (IBM Modern Greek)" |
| 821 | :short-name "CP869" |
| 822 | :code-space [0 255] |
| 823 | :ascii-compatible-p t |
| 824 | :map "IBM869") |
| 825 | |
| 826 | (define-charset 'cp874 |
| 827 | "CP874 (IBM Thai)" |
| 828 | :short-name "CP874" |
| 829 | :code-space [0 255] |
| 830 | :ascii-compatible-p t |
| 831 | :map "IBM874") |
| 832 | |
| 833 | ;; For Arabic, we need three different types of character sets. |
| 834 | ;; Digits are of direction left-to-right and of width 1-column. |
| 835 | ;; Others are of direction right-to-left and of width 1-column or |
| 836 | ;; 2-column. |
| 837 | (define-charset 'arabic-digit |
| 838 | "Arabic digit" |
| 839 | :short-name "Arabic digit" |
| 840 | :iso-final-char ?2 |
| 841 | :emacs-mule-id 164 |
| 842 | :supplementary-p t |
| 843 | :code-space [34 42] |
| 844 | :code-offset #x0600) |
| 845 | |
| 846 | (define-charset 'arabic-1-column |
| 847 | "Arabic 1-column" |
| 848 | :short-name "Arabic 1-col" |
| 849 | :long-name "Arabic 1-column" |
| 850 | :iso-final-char ?3 |
| 851 | :emacs-mule-id 165 |
| 852 | :supplementary-p t |
| 853 | :code-space [33 126] |
| 854 | :code-offset #x200100) |
| 855 | |
| 856 | (define-charset 'arabic-2-column |
| 857 | "Arabic 2-column" |
| 858 | :short-name "Arabic 2-col" |
| 859 | :long-name "Arabic 2-column" |
| 860 | :iso-final-char ?4 |
| 861 | :emacs-mule-id 224 |
| 862 | :supplementary-p t |
| 863 | :code-space [33 126] |
| 864 | :code-offset #x200180) |
| 865 | |
| 866 | ;; Lao script. |
| 867 | ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF. |
| 868 | ;; Not all of them are defined in Unicode. |
| 869 | (define-charset 'lao |
| 870 | "Lao characters (ISO10646 0E81..0EDF)" |
| 871 | :short-name "Lao" |
| 872 | :iso-final-char ?1 |
| 873 | :emacs-mule-id 167 |
| 874 | :supplementary-p t |
| 875 | :code-space [33 126] |
| 876 | :code-offset #x0E81) |
| 877 | |
| 878 | (define-charset 'mule-lao |
| 879 | "Lao characters (ISO10646 0E81..0EDF)" |
| 880 | :short-name "Lao" |
| 881 | :code-space [0 255] |
| 882 | :supplementary-p t |
| 883 | :superset '(ascii eight-bit-control (lao . 128))) |
| 884 | |
| 885 | |
| 886 | ;; Indian scripts. Symbolic charset for data exchange. Glyphs are |
| 887 | ;; not assigned. They are automatically converted to each Indian |
| 888 | ;; script which IS-13194 supports. |
| 889 | |
| 890 | (define-charset 'indian-is13194 |
| 891 | "Generic Indian charset for data exchange with IS 13194" |
| 892 | :short-name "IS 13194" |
| 893 | :long-name "Indian IS 13194" |
| 894 | :iso-final-char ?5 |
| 895 | :emacs-mule-id 225 |
| 896 | :supplementary-p t |
| 897 | :code-space [33 126] |
| 898 | :code-offset #x180000) |
| 899 | |
| 900 | (let ((code-offset #x180100)) |
| 901 | (dolist (script '(devanagari sanskrit bengali tamil telugu assamese |
| 902 | oriya kannada malayalam gujarati punjabi)) |
| 903 | (define-charset (intern (format "%s-cdac" script)) |
| 904 | (format "Glyphs of %s script for CDAC font. Subset of `indian-glyph'." |
| 905 | (capitalize (symbol-name script))) |
| 906 | :short-name (format "CDAC %s glyphs" (capitalize (symbol-name script))) |
| 907 | :supplementary-p t |
| 908 | :code-space [0 255] |
| 909 | :code-offset code-offset) |
| 910 | (setq code-offset (+ code-offset #x100))) |
| 911 | |
| 912 | (dolist (script '(devanagari bengali punjabi gujarati |
| 913 | oriya tamil telugu kannada malayalam)) |
| 914 | (define-charset (intern (format "%s-akruti" script)) |
| 915 | (format "Glyphs of %s script for AKRUTI font. Subset of `indian-glyph'." |
| 916 | (capitalize (symbol-name script))) |
| 917 | :short-name (format "AKRUTI %s glyphs" (capitalize (symbol-name script))) |
| 918 | :supplementary-p t |
| 919 | :code-space [0 255] |
| 920 | :code-offset code-offset) |
| 921 | (setq code-offset (+ code-offset #x100)))) |
| 922 | |
| 923 | (define-charset 'indian-glyph |
| 924 | "Glyphs for Indian characters." |
| 925 | :short-name "Indian glyph" |
| 926 | :iso-final-char ?4 |
| 927 | :emacs-mule-id 240 |
| 928 | :supplementary-p t |
| 929 | :code-space [32 127 32 127] |
| 930 | :code-offset #x180100) |
| 931 | |
| 932 | ;; Actual Glyph for 1-column width. |
| 933 | (define-charset 'indian-1-column |
| 934 | "Indian charset for 1-column width glyphs." |
| 935 | :short-name "Indian 1-col" |
| 936 | :long-name "Indian 1 Column" |
| 937 | :iso-final-char ?6 |
| 938 | :emacs-mule-id 251 |
| 939 | :supplementary-p t |
| 940 | :code-space [33 126 33 126] |
| 941 | :code-offset #x184000) |
| 942 | |
| 943 | ;; Actual Glyph for 2-column width. |
| 944 | (define-charset 'indian-2-column |
| 945 | "Indian charset for 2-column width glyphs." |
| 946 | :short-name "Indian 2-col" |
| 947 | :long-name "Indian 2 Column" |
| 948 | :iso-final-char ?5 |
| 949 | :emacs-mule-id 251 |
| 950 | :supplementary-p t |
| 951 | :code-space [33 126 33 126] |
| 952 | :code-offset #x184000) |
| 953 | |
| 954 | (define-charset 'tibetan |
| 955 | "Tibetan characters" |
| 956 | :iso-final-char ?7 |
| 957 | :short-name "Tibetan 2-col" |
| 958 | :long-name "Tibetan 2 column" |
| 959 | :iso-final-char ?7 |
| 960 | :emacs-mule-id 252 |
| 961 | :unify-map "MULE-tibetan" |
| 962 | :supplementary-p t |
| 963 | :code-space [33 126 33 37] |
| 964 | :code-offset #x190000) |
| 965 | |
| 966 | (define-charset 'tibetan-1-column |
| 967 | "Tibetan 1 column glyph" |
| 968 | :short-name "Tibetan 1-col" |
| 969 | :long-name "Tibetan 1 column" |
| 970 | :iso-final-char ?8 |
| 971 | :emacs-mule-id 241 |
| 972 | :supplementary-p t |
| 973 | :code-space [33 126 33 37] |
| 974 | :code-offset #x190000) |
| 975 | |
| 976 | ;; Subsets of Unicode. |
| 977 | (define-charset 'mule-unicode-2500-33ff |
| 978 | "Unicode characters of the range U+2500..U+33FF." |
| 979 | :short-name "Unicode subset 2" |
| 980 | :long-name "Unicode subset (U+2500..U+33FF)" |
| 981 | :iso-final-char ?2 |
| 982 | :emacs-mule-id 242 |
| 983 | :supplementary-p t |
| 984 | :code-space [#x20 #x7f #x20 #x47] |
| 985 | :code-offset #x2500) |
| 986 | |
| 987 | (define-charset 'mule-unicode-e000-ffff |
| 988 | "Unicode characters of the range U+E000..U+FFFF." |
| 989 | :short-name "Unicode subset 3" |
| 990 | :long-name "Unicode subset (U+E000+FFFF)" |
| 991 | :iso-final-char ?3 |
| 992 | :emacs-mule-id 243 |
| 993 | :supplementary-p t |
| 994 | :code-space [#x20 #x7F #x20 #x75] |
| 995 | :code-offset #xE000 |
| 996 | :max-code 30015) ; U+FFFF |
| 997 | |
| 998 | (define-charset 'mule-unicode-0100-24ff |
| 999 | "Unicode characters of the range U+0100..U+24FF." |
| 1000 | :short-name "Unicode subset" |
| 1001 | :long-name "Unicode subset (U+0100..U+24FF)" |
| 1002 | :iso-final-char ?1 |
| 1003 | :emacs-mule-id 244 |
| 1004 | :supplementary-p t |
| 1005 | :code-space [#x20 #x7F #x20 #x7F] |
| 1006 | :code-offset #x100) |
| 1007 | |
| 1008 | (define-charset 'unicode-bmp |
| 1009 | "Unicode Basic Multilingual Plane (U+0000..U+FFFF)" |
| 1010 | :short-name "Unicode BMP" |
| 1011 | :code-space [0 255 0 255] |
| 1012 | :code-offset 0) |
| 1013 | |
| 1014 | (define-charset 'unicode-smp |
| 1015 | "Unicode Supplementary Multilingual Plane (U+10000..U+1FFFF)" |
| 1016 | :short-name "Unicode SMP " |
| 1017 | :code-space [0 255 0 255] |
| 1018 | :code-offset #x10000) |
| 1019 | |
| 1020 | (define-charset 'unicode-sip |
| 1021 | "Unicode Supplementary Ideographic Plane (U+20000..U+2FFFF)" |
| 1022 | :short-name "Unicode SIP" |
| 1023 | :code-space [0 255 0 255] |
| 1024 | :code-offset #x20000) |
| 1025 | |
| 1026 | (define-charset 'unicode-ssp |
| 1027 | "Unicode Supplementary Special-purpose Plane (U+E0000..U+EFFFF)" |
| 1028 | :short-name "Unicode SSP" |
| 1029 | :code-space [0 255 0 255] |
| 1030 | :code-offset #xE0000) |
| 1031 | |
| 1032 | (define-charset 'ethiopic |
| 1033 | "Ethiopic characters for Amharic and Tigrigna." |
| 1034 | :short-name "Ethiopic" |
| 1035 | :long-name "Ethiopic characters" |
| 1036 | :iso-final-char ?3 |
| 1037 | :emacs-mule-id 245 |
| 1038 | :supplementary-p t |
| 1039 | :unify-map "MULE-ethiopic" |
| 1040 | :code-space [33 126 33 126] |
| 1041 | :code-offset #x1A0000) |
| 1042 | |
| 1043 | (define-charset 'mac-roman |
| 1044 | "Mac Roman charset" |
| 1045 | :short-name "Mac Roman" |
| 1046 | :ascii-compatible-p t |
| 1047 | :code-space [0 255] |
| 1048 | :map "MACINTOSH") |
| 1049 | |
| 1050 | ;; Fixme: modern EBCDIC variants, e.g. IBM00924? |
| 1051 | (define-charset 'ebcdic-us |
| 1052 | "US version of EBCDIC" |
| 1053 | :short-name "EBCDIC-US" |
| 1054 | :code-space [0 255] |
| 1055 | :mime-charset 'ebcdic-us |
| 1056 | :map "EBCDICUS") |
| 1057 | |
| 1058 | (define-charset 'ebcdic-uk |
| 1059 | "UK version of EBCDIC" |
| 1060 | :short-name "EBCDIC-UK" |
| 1061 | :code-space [0 255] |
| 1062 | :mime-charset 'ebcdic-uk |
| 1063 | :map "EBCDICUK") |
| 1064 | |
| 1065 | (define-charset 'ibm1047 |
| 1066 | ;; Says groff: |
| 1067 | "IBM1047, `EBCDIC Latin 1/Open Systems' used by OS/390 Unix." |
| 1068 | :short-name "IBM1047" |
| 1069 | :code-space [0 255] |
| 1070 | :mime-charset 'ibm1047 |
| 1071 | :map "IBM1047") |
| 1072 | (define-charset-alias 'cp1047 'ibm1047) |
| 1073 | |
| 1074 | (define-charset 'hp-roman8 |
| 1075 | "Encoding used by Hewlet-Packard printer software" |
| 1076 | :short-name "HP-ROMAN8" |
| 1077 | :ascii-compatible-p t |
| 1078 | :code-space [0 255] |
| 1079 | :map "HP-ROMAN8") |
| 1080 | |
| 1081 | ;; To make a coding system with this, a pre-write-conversion should |
| 1082 | ;; account for the commented-out multi-valued code points in |
| 1083 | ;; stdenc.map. |
| 1084 | (define-charset 'adobe-standard-encoding |
| 1085 | "Adobe `standard encoding' used in PostScript" |
| 1086 | :short-name "ADOBE-STANDARD-ENCODING" |
| 1087 | :code-space [#x20 255] |
| 1088 | :map "stdenc") |
| 1089 | |
| 1090 | (define-charset 'symbol |
| 1091 | "Adobe symbol encoding used in PostScript" |
| 1092 | :short-name "ADOBE-SYMBOL" |
| 1093 | :code-space [#x20 255] |
| 1094 | :map "symbol") |
| 1095 | |
| 1096 | (define-charset 'ibm850 |
| 1097 | "DOS codepage 850 (Latin-1)" |
| 1098 | :short-name "IBM850" |
| 1099 | :ascii-compatible-p t |
| 1100 | :code-space [0 255] |
| 1101 | :map "IBM850") |
| 1102 | (define-charset-alias 'cp850 'ibm850) |
| 1103 | |
| 1104 | (define-charset 'mik |
| 1105 | "Bulgarian DOS codepage" |
| 1106 | :short-name "MIK" |
| 1107 | :ascii-compatible-p t |
| 1108 | :code-space [0 255] |
| 1109 | :map "MIK") |
| 1110 | |
| 1111 | (define-charset 'ptcp154 |
| 1112 | "`Paratype' codepage (Asian Cyrillic)" |
| 1113 | :short-name "PT154" |
| 1114 | :ascii-compatible-p t |
| 1115 | :code-space [0 255] |
| 1116 | :mime-charset 'pt154 |
| 1117 | :map "PTCP154") |
| 1118 | (define-charset-alias 'pt154 'ptcp154) |
| 1119 | (define-charset-alias 'cp154 'ptcp154) |
| 1120 | |
| 1121 | (define-charset 'gb18030-2-byte |
| 1122 | "GB18030 2-byte (0x814E..0xFEFE)" |
| 1123 | :code-space [#x40 #xFE #x81 #xFE] |
| 1124 | :supplementary-p t |
| 1125 | :map "GB180302") |
| 1126 | |
| 1127 | (define-charset 'gb18030-4-byte-bmp |
| 1128 | "GB18030 4-byte for BMP (0x81308130-0x8431A439)" |
| 1129 | :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x81 #x84] |
| 1130 | :supplementary-p t |
| 1131 | :map "GB180304") |
| 1132 | |
| 1133 | (define-charset 'gb18030-4-byte-smp |
| 1134 | "GB18030 4-byte for SMP (0x90308130-0xE3329A35)" |
| 1135 | :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x90 #xE3] |
| 1136 | :min-code '(#x9030 . #x8130) |
| 1137 | :max-code '(#xE332 . #x9A35) |
| 1138 | :supplementary-p t |
| 1139 | :code-offset #x10000) |
| 1140 | |
| 1141 | (define-charset 'gb18030-4-byte-ext-1 |
| 1142 | "GB18030 4-byte (0x8431A530-0x8F39FE39)" |
| 1143 | :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x84 #x8F] |
| 1144 | :min-code '(#x8431 . #xA530) |
| 1145 | :max-code '(#x8F39 . #xFE39) |
| 1146 | :supplementary-p t |
| 1147 | :code-offset #x200000 ; ... #x22484B |
| 1148 | ) |
| 1149 | |
| 1150 | (define-charset 'gb18030-4-byte-ext-2 |
| 1151 | "GB18030 4-byte (0xE3329A36-0xFE39FE39)" |
| 1152 | :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #xE3 #xFE] |
| 1153 | :min-code '(#xE332 . #x9A36) |
| 1154 | :max-code '(#xFE39 . #xFE39) |
| 1155 | :supplementary-p t |
| 1156 | :code-offset #x22484C ; ... #x279f93 |
| 1157 | ) |
| 1158 | |
| 1159 | (define-charset 'gb18030 |
| 1160 | "GB18030" |
| 1161 | :code-space [#x00 #xFF #x00 #xFE #x00 #xFE #x00 #xFE] |
| 1162 | :min-code 0 |
| 1163 | :max-code '(#xFE39 . #xFE39) |
| 1164 | :superset '(ascii gb18030-2-byte |
| 1165 | gb18030-4-byte-bmp gb18030-4-byte-smp |
| 1166 | gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)) |
| 1167 | |
| 1168 | (define-charset 'chinese-cns11643-15 |
| 1169 | "CNS11643 Plane 15 Chinese Traditional" |
| 1170 | :short-name "CNS11643-15" |
| 1171 | :long-name "CNS11643-15 (Chinese traditional)" |
| 1172 | :code-space [33 126 33 126] |
| 1173 | :code-offset #x27A000) |
| 1174 | |
| 1175 | (unify-charset 'chinese-gb2312) |
| 1176 | (unify-charset 'chinese-gbk) |
| 1177 | (unify-charset 'chinese-cns11643-1) |
| 1178 | (unify-charset 'chinese-cns11643-2) |
| 1179 | (unify-charset 'chinese-cns11643-3) |
| 1180 | (unify-charset 'chinese-cns11643-4) |
| 1181 | (unify-charset 'chinese-cns11643-5) |
| 1182 | (unify-charset 'chinese-cns11643-6) |
| 1183 | (unify-charset 'chinese-cns11643-7) |
| 1184 | (unify-charset 'big5) |
| 1185 | (unify-charset 'chinese-big5-1) |
| 1186 | (unify-charset 'chinese-big5-2) |
| 1187 | (unify-charset 'big5-hkscs) |
| 1188 | (unify-charset 'korean-ksc5601) |
| 1189 | (unify-charset 'vietnamese-viscii-lower) |
| 1190 | (unify-charset 'vietnamese-viscii-upper) |
| 1191 | (unify-charset 'chinese-sisheng) |
| 1192 | (unify-charset 'ipa) |
| 1193 | (unify-charset 'tibetan) |
| 1194 | (unify-charset 'ethiopic) |
| 1195 | (unify-charset 'japanese-jisx0208-1978) |
| 1196 | (unify-charset 'japanese-jisx0208) |
| 1197 | (unify-charset 'japanese-jisx0212) |
| 1198 | (unify-charset 'japanese-jisx0213-1) |
| 1199 | (unify-charset 'japanese-jisx0213-2) |
| 1200 | |
| 1201 | \f |
| 1202 | ;; These are tables for translating characters on decoding and |
| 1203 | ;; encoding. |
| 1204 | ;; Fixme: these aren't used now -- should they be? |
| 1205 | (setq standard-translation-table-for-decode nil) |
| 1206 | |
| 1207 | (setq standard-translation-table-for-encode nil) |
| 1208 | \f |
| 1209 | ;;; Make fundamental coding systems. |
| 1210 | |
| 1211 | ;; The coding system `no-conversion' and `undecided' are already |
| 1212 | ;; defined in coding.c as below: |
| 1213 | ;; |
| 1214 | ;; (define-coding-system 'no-conversion |
| 1215 | ;; "..." |
| 1216 | ;; :coding-type 'raw-text |
| 1217 | ;; ...) |
| 1218 | ;; (define-coding-system 'undecided |
| 1219 | ;; "..." |
| 1220 | ;; :coding-type 'undecided |
| 1221 | ;; ...) |
| 1222 | |
| 1223 | (define-coding-system-alias 'binary 'no-conversion) |
| 1224 | (define-coding-system-alias 'unix 'undecided-unix) |
| 1225 | (define-coding-system-alias 'dos 'undecided-dos) |
| 1226 | (define-coding-system-alias 'mac 'undecided-mac) |
| 1227 | |
| 1228 | (define-coding-system 'raw-text |
| 1229 | "Raw text, which means text contains random 8-bit codes. |
| 1230 | Encoding text with this coding system produces the actual byte |
| 1231 | sequence of the text in buffers and strings. An exception is made for |
| 1232 | characters from the `eight-bit' character set. Each of them is encoded |
| 1233 | into a single byte. |
| 1234 | |
| 1235 | When you visit a file with this coding, the file is read into a |
| 1236 | unibyte buffer as is (except for EOL format), thus each byte of a file |
| 1237 | is treated as a character." |
| 1238 | :coding-type 'raw-text |
| 1239 | :for-unibyte t |
| 1240 | :mnemonic ?t) |
| 1241 | |
| 1242 | (define-coding-system 'no-conversion-multibyte |
| 1243 | "Like `no-conversion' but don't read a file into a unibyte buffer." |
| 1244 | :coding-type 'raw-text |
| 1245 | :eol-type 'unix |
| 1246 | :mnemonic ?=) |
| 1247 | |
| 1248 | (define-coding-system 'iso-latin-1 |
| 1249 | "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)." |
| 1250 | :coding-type 'charset |
| 1251 | :mnemonic ?1 |
| 1252 | :charset-list '(iso-8859-1) |
| 1253 | :mime-charset 'iso-8859-1) |
| 1254 | |
| 1255 | (define-coding-system-alias 'iso-8859-1 'iso-latin-1) |
| 1256 | (define-coding-system-alias 'latin-1 'iso-latin-1) |
| 1257 | |
| 1258 | ;; Coding systems not specific to each language environment. |
| 1259 | |
| 1260 | (define-coding-system 'emacs-mule |
| 1261 | "Emacs 21 internal format used in buffer and string." |
| 1262 | :coding-type 'emacs-mule |
| 1263 | :charset-list 'emacs-mule |
| 1264 | :mnemonic ?M) |
| 1265 | |
| 1266 | (define-coding-system 'utf-8 |
| 1267 | "UTF-8 (no signature (BOM))" |
| 1268 | :coding-type 'utf-8 |
| 1269 | :mnemonic ?U |
| 1270 | :charset-list '(unicode) |
| 1271 | :mime-charset 'utf-8) |
| 1272 | |
| 1273 | (define-coding-system 'utf-8-with-signature |
| 1274 | "UTF-8 (with signature (BOM))" |
| 1275 | :coding-type 'utf-8 |
| 1276 | :mnemonic ?U |
| 1277 | :charset-list '(unicode) |
| 1278 | :bom t) |
| 1279 | |
| 1280 | (define-coding-system 'utf-8-auto |
| 1281 | "UTF-8 (auto-detect signature (BOM))" |
| 1282 | :coding-type 'utf-8 |
| 1283 | :mnemonic ?U |
| 1284 | :charset-list '(unicode) |
| 1285 | :bom '(utf-8-with-signature . utf-8)) |
| 1286 | |
| 1287 | (define-coding-system-alias 'mule-utf-8 'utf-8) |
| 1288 | |
| 1289 | (define-coding-system 'utf-8-emacs |
| 1290 | "Support for all Emacs characters (including non-Unicode characters)." |
| 1291 | :coding-type 'utf-8 |
| 1292 | :mnemonic ?U |
| 1293 | :charset-list '(emacs)) |
| 1294 | |
| 1295 | ;; The encoding used internally. This encoding is meant to be able to save |
| 1296 | ;; any multibyte buffer without losing information. It can change between |
| 1297 | ;; Emacs releases, tho, so should only be used for internal files. |
| 1298 | (define-coding-system-alias 'emacs-internal 'utf-8-emacs-unix) |
| 1299 | |
| 1300 | (define-coding-system 'utf-16le |
| 1301 | "UTF-16LE (little endian, no signature (BOM))." |
| 1302 | :coding-type 'utf-16 |
| 1303 | :mnemonic ?U |
| 1304 | :charset-list '(unicode) |
| 1305 | :endian 'little |
| 1306 | :mime-text-unsuitable t |
| 1307 | :mime-charset 'utf-16le) |
| 1308 | |
| 1309 | (define-coding-system 'utf-16be |
| 1310 | "UTF-16BE (big endian, no signature (BOM))." |
| 1311 | :coding-type 'utf-16 |
| 1312 | :mnemonic ?U |
| 1313 | :charset-list '(unicode) |
| 1314 | :endian 'big |
| 1315 | :mime-text-unsuitable t |
| 1316 | :mime-charset 'utf-16be) |
| 1317 | |
| 1318 | (define-coding-system 'utf-16le-with-signature |
| 1319 | "UTF-16 (little endian, with signature (BOM))." |
| 1320 | :coding-type 'utf-16 |
| 1321 | :mnemonic ?U |
| 1322 | :charset-list '(unicode) |
| 1323 | :bom t |
| 1324 | :endian 'little |
| 1325 | :mime-text-unsuitable t |
| 1326 | :mime-charset 'utf-16) |
| 1327 | |
| 1328 | (define-coding-system 'utf-16be-with-signature |
| 1329 | "UTF-16 (big endian, with signature (BOM))." |
| 1330 | :coding-type 'utf-16 |
| 1331 | :mnemonic ?U |
| 1332 | :charset-list '(unicode) |
| 1333 | :bom t |
| 1334 | :endian 'big |
| 1335 | :mime-text-unsuitable t |
| 1336 | :mime-charset 'utf-16) |
| 1337 | |
| 1338 | (define-coding-system 'utf-16 |
| 1339 | "UTF-16 (detect endian on decoding, use big endian on encoding with BOM)." |
| 1340 | :coding-type 'utf-16 |
| 1341 | :mnemonic ?U |
| 1342 | :charset-list '(unicode) |
| 1343 | :bom '(utf-16le-with-signature . utf-16be-with-signature) |
| 1344 | :endian 'big |
| 1345 | :mime-text-unsuitable t |
| 1346 | :mime-charset 'utf-16) |
| 1347 | |
| 1348 | ;; Backwards compatibility (old names, also used by Mule-UCS). We |
| 1349 | ;; prefer the MIME names. |
| 1350 | (define-coding-system-alias 'utf-16-le 'utf-16le-with-signature) |
| 1351 | (define-coding-system-alias 'utf-16-be 'utf-16be-with-signature) |
| 1352 | |
| 1353 | |
| 1354 | (define-coding-system 'iso-2022-7bit |
| 1355 | "ISO 2022 based 7-bit encoding using only G0." |
| 1356 | :coding-type 'iso-2022 |
| 1357 | :mnemonic ?J |
| 1358 | :charset-list 'iso-2022 |
| 1359 | :designation [(ascii t) nil nil nil] |
| 1360 | :flags '(short ascii-at-eol ascii-at-cntl 7-bit designation composition)) |
| 1361 | |
| 1362 | (define-coding-system 'iso-2022-7bit-ss2 |
| 1363 | "ISO 2022 based 7-bit encoding using SS2 for 96-charset." |
| 1364 | :coding-type 'iso-2022 |
| 1365 | :mnemonic ?$ |
| 1366 | :charset-list 'iso-2022 |
| 1367 | :designation [(ascii 94) nil (nil 96) nil] |
| 1368 | :flags '(short ascii-at-eol ascii-at-cntl 7-bit |
| 1369 | designation single-shift composition)) |
| 1370 | |
| 1371 | (define-coding-system 'iso-2022-7bit-lock |
| 1372 | "ISO-2022 coding system using Locking-Shift for 96-charset." |
| 1373 | :coding-type 'iso-2022 |
| 1374 | :mnemonic ?& |
| 1375 | :charset-list 'iso-2022 |
| 1376 | :designation [(ascii 94) (nil 96) nil nil] |
| 1377 | :flags '(ascii-at-eol ascii-at-cntl 7-bit |
| 1378 | designation locking-shift composition)) |
| 1379 | |
| 1380 | (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock) |
| 1381 | |
| 1382 | (define-coding-system 'iso-2022-7bit-lock-ss2 |
| 1383 | "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN." |
| 1384 | :coding-type 'iso-2022 |
| 1385 | :mnemonic ?i |
| 1386 | :charset-list '(ascii |
| 1387 | japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201 |
| 1388 | korean-ksc5601 |
| 1389 | chinese-gb2312 |
| 1390 | chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3 |
| 1391 | chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6 |
| 1392 | chinese-cns11643-7) |
| 1393 | :designation [(ascii 94) |
| 1394 | (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 96) |
| 1395 | (nil chinese-cns11643-2) |
| 1396 | (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5 |
| 1397 | chinese-cns11643-6 chinese-cns11643-7)] |
| 1398 | :flags '(short ascii-at-eol ascii-at-cntl 7-bit locking-shift |
| 1399 | single-shift init-bol)) |
| 1400 | |
| 1401 | (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2) |
| 1402 | |
| 1403 | (define-coding-system 'iso-2022-8bit-ss2 |
| 1404 | "ISO 2022 based 8-bit encoding using SS2 for 96-charset." |
| 1405 | :coding-type 'iso-2022 |
| 1406 | :mnemonic ?@ |
| 1407 | :charset-list 'iso-2022 |
| 1408 | :designation [(ascii 94) nil (nil 96) nil] |
| 1409 | :flags '(ascii-at-eol ascii-at-cntl designation single-shift composition)) |
| 1410 | |
| 1411 | (define-coding-system 'compound-text |
| 1412 | "Compound text based generic encoding. |
| 1413 | This coding system is an extension of X's \"Compound Text Encoding\". |
| 1414 | It encodes many characters using the normal ISO-2022 designation sequences, |
| 1415 | but it doesn't support extended segments of CTEXT." |
| 1416 | :coding-type 'iso-2022 |
| 1417 | :mnemonic ?x |
| 1418 | :charset-list 'iso-2022 |
| 1419 | :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] |
| 1420 | :flags '(ascii-at-eol ascii-at-cntl long-form |
| 1421 | designation locking-shift single-shift composition) |
| 1422 | ;; Fixme: this isn't a valid MIME charset and has to be |
| 1423 | ;; special-cased elsewhere -- fx |
| 1424 | :mime-charset 'x-ctext) |
| 1425 | |
| 1426 | (define-coding-system-alias 'x-ctext 'compound-text) |
| 1427 | (define-coding-system-alias 'ctext 'compound-text) |
| 1428 | |
| 1429 | ;; Same as compound-text, but doesn't produce composition escape |
| 1430 | ;; sequences. Used in post-read and pre-write conversions of |
| 1431 | ;; compound-text-with-extensions, see mule.el. Note that this should |
| 1432 | ;; not have a mime-charset property, to prevent it from showing up |
| 1433 | ;; close to the beginning of coding systems ordered by priority. |
| 1434 | (define-coding-system 'ctext-no-compositions |
| 1435 | "Compound text based generic encoding. |
| 1436 | |
| 1437 | Like `compound-text', but does not produce escape sequences for compositions." |
| 1438 | :coding-type 'iso-2022 |
| 1439 | :mnemonic ?x |
| 1440 | :charset-list 'iso-2022 |
| 1441 | :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] |
| 1442 | :flags '(ascii-at-eol ascii-at-cntl |
| 1443 | designation locking-shift single-shift)) |
| 1444 | |
| 1445 | (define-coding-system 'compound-text-with-extensions |
| 1446 | "Compound text encoding with ICCCM Extended Segment extensions. |
| 1447 | |
| 1448 | See the variables `ctext-standard-encodings' and |
| 1449 | `ctext-non-standard-encodings-alist' for the detail about how |
| 1450 | extended segments are handled. |
| 1451 | |
| 1452 | This coding system should be used only for X selections. It is inappropriate |
| 1453 | for decoding and encoding files, process I/O, etc." |
| 1454 | :coding-type 'iso-2022 |
| 1455 | :mnemonic ?x |
| 1456 | :charset-list 'iso-2022 |
| 1457 | :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] |
| 1458 | :flags '(ascii-at-eol ascii-at-cntl long-form |
| 1459 | designation locking-shift single-shift) |
| 1460 | :post-read-conversion 'ctext-post-read-conversion |
| 1461 | :pre-write-conversion 'ctext-pre-write-conversion) |
| 1462 | |
| 1463 | (define-coding-system-alias |
| 1464 | 'x-ctext-with-extensions 'compound-text-with-extensions) |
| 1465 | (define-coding-system-alias |
| 1466 | 'ctext-with-extensions 'compound-text-with-extensions) |
| 1467 | |
| 1468 | (define-coding-system 'us-ascii |
| 1469 | "Encode ASCII as-is and encode non-ASCII characters to `?'." |
| 1470 | :coding-type 'charset |
| 1471 | :mnemonic ?- |
| 1472 | :charset-list '(ascii) |
| 1473 | :default-char ?? |
| 1474 | :mime-charset 'us-ascii) |
| 1475 | |
| 1476 | (define-coding-system-alias 'iso-safe 'us-ascii) |
| 1477 | |
| 1478 | (define-coding-system 'utf-7 |
| 1479 | "UTF-7 encoding of Unicode (RFC 2152)." |
| 1480 | :coding-type 'utf-8 |
| 1481 | :mnemonic ?U |
| 1482 | :mime-charset 'utf-7 |
| 1483 | :charset-list '(unicode) |
| 1484 | :pre-write-conversion 'utf-7-pre-write-conversion |
| 1485 | :post-read-conversion 'utf-7-post-read-conversion) |
| 1486 | |
| 1487 | (define-coding-system 'utf-7-imap |
| 1488 | "UTF-7 encoding of Unicode, IMAP version (RFC 2060)" |
| 1489 | :coding-type 'utf-8 |
| 1490 | :mnemonic ?u |
| 1491 | :charset-list '(unicode) |
| 1492 | :pre-write-conversion 'utf-7-imap-pre-write-conversion |
| 1493 | :post-read-conversion 'utf-7-imap-post-read-conversion) |
| 1494 | |
| 1495 | ;; Use us-ascii for terminal output if some other coding system is not |
| 1496 | ;; specified explicitly. |
| 1497 | (set-safe-terminal-coding-system-internal 'us-ascii) |
| 1498 | |
| 1499 | ;; The other coding-systems are defined in each language specific |
| 1500 | ;; files under lisp/language. |
| 1501 | |
| 1502 | ;; Normally, set coding system to `undecided' before reading a file. |
| 1503 | ;; Compiled Emacs Lisp files (*.elc) are not decoded at all, |
| 1504 | ;; but we regard them as containing multibyte characters. |
| 1505 | ;; Tar files are not decoded at all, but we treat them as raw bytes. |
| 1506 | |
| 1507 | (setq file-coding-system-alist |
| 1508 | (mapcar (lambda (arg) (cons (purecopy (car arg)) (cdr arg))) |
| 1509 | '(("\\.elc\\'" . utf-8-emacs) |
| 1510 | ("\\.utf\\(-8\\)?\\'" . utf-8) |
| 1511 | ("\\.xml\\'" . xml-find-file-coding-system) |
| 1512 | ;; We use raw-text for reading loaddefs.el so that if it |
| 1513 | ;; happens to have DOS or Mac EOLs, they are converted to |
| 1514 | ;; newlines. This is required to make the special treatment |
| 1515 | ;; of the "\ newline" combination in loaddefs.el, which marks |
| 1516 | ;; the beginning of a doc string, work. |
| 1517 | ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix)) |
| 1518 | ("\\.tar\\'" . (no-conversion . no-conversion)) |
| 1519 | ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system) |
| 1520 | ("\\.\\(tex\\|ltx\\|dtx\\|drv\\)\\'" . latexenc-find-file-coding-system) |
| 1521 | ("" . (undecided . nil))))) |
| 1522 | |
| 1523 | \f |
| 1524 | ;;; Setting coding categories and their priorities. |
| 1525 | |
| 1526 | ;; This setting is just to read an Emacs Lisp source files which |
| 1527 | ;; contain multilingual text while dumping Emacs. More appropriate |
| 1528 | ;; values are set by the command `set-language-environment' for each |
| 1529 | ;; language environment. |
| 1530 | |
| 1531 | (set-coding-system-priority |
| 1532 | 'iso-latin-1 |
| 1533 | 'utf-8 |
| 1534 | 'iso-2022-7bit |
| 1535 | ) |
| 1536 | |
| 1537 | \f |
| 1538 | ;;; Miscellaneous settings. |
| 1539 | |
| 1540 | ;; Make all multibyte characters self-insert. |
| 1541 | (set-char-table-range (nth 1 global-map) |
| 1542 | (cons 128 (max-char)) |
| 1543 | 'self-insert-command) |
| 1544 | |
| 1545 | (aset latin-extra-code-table ?\221 t) |
| 1546 | (aset latin-extra-code-table ?\222 t) |
| 1547 | (aset latin-extra-code-table ?\223 t) |
| 1548 | (aset latin-extra-code-table ?\224 t) |
| 1549 | (aset latin-extra-code-table ?\225 t) |
| 1550 | (aset latin-extra-code-table ?\226 t) |
| 1551 | |
| 1552 | ;; The old code-pages library is obsoleted by coding systems based on |
| 1553 | ;; the charsets defined in this file but might be required by user |
| 1554 | ;; code. |
| 1555 | (provide 'code-pages) |
| 1556 | |
| 1557 | ;;; mule-conf.el ends here |