code.delx.au - gnu-emacs/blob - lisp/international/mule-conf.el

   1 ;;; mule-conf.el --- configure multilingual environment -*- no-byte-compile: t -*-
   2
   3 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003,
   4 ;;   2004, 2005, 2006, 2007, 2008  Free Software Foundation, Inc.
   5 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008
   6 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   7 ;;   Registration Number H14PRO021
   8
   9 ;; Keywords: mule, multilingual, character set, coding system
  10
  11 ;; This file is part of GNU Emacs.
  12
  13 ;; GNU Emacs is free software; you can redistribute it and/or modify
  14 ;; it under the terms of the GNU General Public License as published by
  15 ;; the Free Software Foundation; either version 3, or (at your option)
  16 ;; any later version.
  17
  18 ;; GNU Emacs is distributed in the hope that it will be useful,
  19 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  20 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  21 ;; GNU General Public License for more details.
  22
  23 ;; You should have received a copy of the GNU General Public License
  24 ;; along with GNU Emacs; see the file COPYING.  If not, write to the
  25 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  26 ;; Boston, MA 02110-1301, USA.
  27
  28 ;;; Commentary:
  29
  30 ;; Don't byte-compile this file.
  31
  32 ;;; Code:
  33
  34 ;;; Definitions of character sets.
  35
  36 ;; Basic (official) character sets.  These character sets are treated
  37 ;; efficiently with respect to buffer memory.
  38
  39 ;; Syntax:
  40 ;; (define-charset CHARSET-ID CHARSET
  41 ;;   [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
  42 ;;     SHORT-NAME LONG-NAME DESCRIPTION ])
  43 ;; ASCII charset is defined in src/charset.c as below.
  44 ;; (define-charset 0 ascii
  45 ;;    [1 94 1 0 ?B 0 "ASCII" "ASCII" "ASCII (ISO646 IRV)"])
  46
  47 ;; 1-byte charsets.  Valid range of CHARSET-ID is 128..143.
  48
  49 ;; CHARSET-ID 128 is not used.
  50
  51 (define-charset 129 'latin-iso8859-1
  52   [1 96 1 0 ?A 1 "RHP of Latin-1" "RHP of Latin-1 (ISO 8859-1): ISO-IR-100"
  53      "Right-Hand Part of Latin Alphabet 1 (ISO/IEC 8859-1): ISO-IR-100."])
  54 (define-charset 130 'latin-iso8859-2
  55   [1 96 1 0 ?B 1 "RHP of Latin-2" "RHP of Latin-2 (ISO 8859-2): ISO-IR-101"
  56      "Right-Hand Part of Latin Alphabet 2 (ISO/IEC 8859-2): ISO-IR-101."])
  57 (define-charset 131 'latin-iso8859-3
  58   [1 96 1 0 ?C 1 "RHP of Latin-3" "RHP of Latin-3 (ISO 8859-3): ISO-IR-109"
  59      "Right-Hand Part of Latin Alphabet 3 (ISO/IEC 8859-3): ISO-IR-109."])
  60 (define-charset 132 'latin-iso8859-4
  61   [1 96 1 0 ?D 1 "RHP of Latin-4" "RHP of Latin-4 (ISO 8859-4): ISO-IR-110"
  62      "Right-Hand Part of Latin Alphabet 4 (ISO/IEC 8859-4): ISO-IR-110."])
  63 (define-charset 133 'thai-tis620
  64   [1 96 1 0 ?T 1 "RHP of TIS620" "RHP of Thai (TIS620): ISO-IR-166"
  65      "Right-Hand Part of TIS620.2533 (Thai): ISO-IR-166."])
  66 (define-charset 134 'greek-iso8859-7
  67   [1 96 1 0 ?F 1 "RHP of ISO8859/7" "RHP of Greek (ISO 8859-7): ISO-IR-126"
  68      "Right-Hand Part of Latin/Greek Alphabet (ISO/IEC 8859-7): ISO-IR-126."])
  69 (define-charset 135 'arabic-iso8859-6
  70   [1 96 1 1 ?G 1 "RHP of ISO8859/6" "RHP of Arabic (ISO 8859-6): ISO-IR-127"
  71      "Right-Hand Part of Latin/Arabic Alphabet (ISO/IEC 8859-6): ISO-IR-127."])
  72 (define-charset 136 'hebrew-iso8859-8
  73   [1 96 1 1 ?H 1 "RHP of ISO8859/8" "RHP of Hebrew (ISO 8859-8): ISO-IR-138"
  74      "Right-Hand Part of Latin/Hebrew Alphabet (ISO/IEC 8859-8): ISO-IR-138."])
  75 (define-charset 137 'katakana-jisx0201
  76   [1 94 1 0 ?I 1 "JISX0201 Katakana" "Japanese Katakana (JISX0201.1976)"
  77      "Katakana Part of JISX0201.1976."])
  78 (define-charset 138 'latin-jisx0201
  79   [1 94 1 0 ?J 0 "JISX0201 Roman" "Japanese Roman (JISX0201.1976)"
  80      "Roman Part of JISX0201.1976."])
  81
  82 ;; CHARSET-ID is not used 139.
  83
  84 (define-charset 140 'cyrillic-iso8859-5
  85   [1 96 1 0 ?L 1 "RHP of ISO8859/5" "RHP of Cyrillic (ISO 8859-5): ISO-IR-144"
  86      "Right-Hand Part of Latin/Cyrillic Alphabet (ISO/IEC 8859-5): ISO-IR-144."])
  87 (define-charset 141 'latin-iso8859-9
  88   [1 96 1 0 ?M 1 "RHP of Latin-5" "RHP of Latin-5 (ISO 8859-9): ISO-IR-148"
  89      "Right-Hand Part of Latin Alphabet 5 (ISO/IEC 8859-9): ISO-IR-148."])
  90 (define-charset 142 'latin-iso8859-15
  91   [1 96 1 0 ?b 1 "RHP of Latin-9" "RHP of Latin-9 (ISO 8859-15): ISO-IR-203"
  92      "Right-Hand Part of Latin Alphabet 9 (ISO/IEC 8859-15): ISO-IR-203."])
  93 (define-charset 143 'latin-iso8859-14
  94   [1 96 1 0 ?_ 1 "RHP of Latin-8" "RHP of Latin-8 (ISO 8859-14): ISO-IR-199"
  95      "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14): ISO-IR-199."])
  96
  97 ;; 2-byte charsets.  Valid range of CHARSET-ID is 144..153.
  98
  99 (define-charset 144 'japanese-jisx0208-1978
 100   [2 94 2 0 ?@ 0 "JISX0208.1978" "JISX0208.1978 (Japanese): ISO-IR-42"
 101      "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42."])
 102 (define-charset 145 'chinese-gb2312
 103   [2 94 2 0 ?A 0 "GB2312" "GB2312: ISO-IR-58"
 104      "GB2312 Chinese simplified: ISO-IR-58."])
 105 (define-charset 146 'japanese-jisx0208
 106   [2 94 2 0 ?B 0 "JISX0208" "JISX0208.1983/1990 (Japanese): ISO-IR-87"
 107      "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87."])
 108 (define-charset 147 'korean-ksc5601
 109   [2 94 2 0 ?C 0 "KSC5601" "KSC5601 (Korean): ISO-IR-149"
 110      "KSC5601 Korean Hangul and Hanja: ISO-IR-149."])
 111 (define-charset 148 'japanese-jisx0212
 112   [2 94 2 0 ?D 0 "JISX0212" "JISX0212 (Japanese): ISO-IR-159"
 113      "JISX0212 Japanese supplement: ISO-IR-159."])
 114 (define-charset 149 'chinese-cns11643-1
 115   [2 94 2 0 ?G 0 "CNS11643-1" "CNS11643-1 (Chinese traditional): ISO-IR-171"
 116      "CNS11643 Plane 1 Chinese traditional: ISO-IR-171."])
 117 (define-charset 150 'chinese-cns11643-2
 118   [2 94 2 0 ?H 0 "CNS11643-2" "CNS11643-2 (Chinese traditional): ISO-IR-172"
 119      "CNS11643 Plane 2 Chinese traditional: ISO-IR-172."])
 120 (define-charset 151 'japanese-jisx0213-1
 121   [2 94 2 0 ?O 0 "JISX0213-1" "JISX0213-1" "JISX0213 Plane 1 (Japanese)"])
 122 (define-charset 152 'chinese-big5-1
 123   [2 94 2 0 ?0 0 "Big5 (Level-1)" "Big5 (Level-1) A141-C67F"
 124      "Frequently used part (A141-C67F) of Big5 (Chinese traditional)."])
 125 (define-charset 153 'chinese-big5-2
 126   [2 94 2 0 ?1 0 "Big5 (Level-2)" "Big5 (Level-2) C940-FEFE"
 127      "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)."])
 128
 129 ;; Additional (private) character sets.  These character sets are
 130 ;; treated less space-efficiently in the buffer.
 131
 132 ;; Syntax:
 133 ;; (define-charset CHARSET-ID CHARSET
 134 ;;   [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
 135 ;;     SHORT-NAME LONG-NAME DESCRIPTION ])
 136
 137 ;; ISO-2022 allows a use of character sets not registered in ISO with
 138 ;; final characters `0' (0x30) through `?' (0x3F).  Among them, Emacs
 139 ;; reserves `0' through `9' to support several private character sets.
 140 ;; The remaining final characters `:' through `?' are for users.
 141
 142 ;; 1-byte 1-column charsets.  Valid range of CHARSET-ID is 160..223.
 143
 144 (define-charset 160 'chinese-sisheng
 145   [1 94 1 0 ?0 0 "SiSheng" "SiSheng (PinYin/ZhuYin)"
 146      "Sisheng characters (vowels with tone marks) for Pinyin/Zhuyin."])
 147
 148 ;; IPA characters for phonetic symbols.
 149 (define-charset 161 'ipa
 150   [1 96 1 0 ?0 1 "IPA" "IPA"
 151      "IPA (International Phonetic Association) characters."])
 152
 153 ;; Vietnamese VISCII.  VISCII is 1-byte character set which contains
 154 ;; more than 96 characters.  Since Emacs can't handle it as one
 155 ;; character set, it is divided into two: lower case letters and upper
 156 ;; case letters.
 157 (define-charset 162 'vietnamese-viscii-lower
 158   [1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case"
 159      "Vietnamese VISCII1.1 lower-case characters."])
 160 (define-charset 163 'vietnamese-viscii-upper
 161   [1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case"
 162      "Vietnamese VISCII1.1 upper-case characters."])
 163
 164 ;; For Arabic, we need three different types of character sets.
 165 ;; Digits are of direction left-to-right and of width 1-column.
 166 ;; Others are of direction right-to-left and of width 1-column or
 167 ;; 2-column.
 168 (define-charset 164 'arabic-digit
 169   [1 94 1 0 ?2 0 "Arabic digit" "Arabic digit"
 170      "Arabic digits."])
 171 (define-charset 165 'arabic-1-column
 172   [1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column"
 173      "Arabic 1-column width glyphs."])
 174
 175 ;; ASCII with right-to-left direction.
 176 (define-charset 166 'ascii-right-to-left
 177   [1 94 1 1 ?B 0 "rev ASCII" "ASCII with right-to-left direction"
 178      "ASCII (left half of ISO 8859-1) with right-to-left direction."])
 179
 180 ;; Lao script.
 181 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
 182 (define-charset 167 'lao
 183   [1 94 1 0 ?1 0 "Lao" "Lao"
 184      "Lao characters (U+0E80..U+0EDF)."])
 185
 186 ;; CHARSET-IDs 168..223 are not used.
 187
 188 ;; 1-byte 2-column charsets.  Valid range of CHARSET-ID is 224..239.
 189
 190 (define-charset 224 'arabic-2-column
 191   [1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column"
 192      "Arabic 2-column glyphs."])
 193
 194 ;; Indian scripts.  Symbolic charset for data exchange.  Glyphs are
 195 ;; not assigned.  They are automatically converted to each Indian
 196 ;; script which IS-13194 supports.
 197
 198 (define-charset 225 'indian-is13194
 199   [1 94 2 0 ?5 1 "IS 13194" "Indian IS 13194"
 200      "Generic Indian character set for data exchange with IS 13194."])
 201
 202 ;; CHARSET-IDs 226..239 are not used.
 203
 204 (define-charset 240  'indian-glyph
 205   [2 96 1 0 ?4 0 "Indian glyph" "Indian glyph"
 206      "Glyphs for Indian characters."])
 207 ;; 240 used to be [2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column"]
 208
 209 ;; 2-byte 1-column charsets.  Valid range of CHARSET-ID is 240..244.
 210
 211 ;; Actual Glyph for 1-column width.
 212 (define-charset 241 'tibetan-1-column
 213   [2 94 1 0 ?8 0 "Tibetan 1-col" "Tibetan 1 column"
 214      "Tibetan 1-column glyphs."])
 215
 216 ;; Subsets of Unicode.
 217
 218 (define-charset 242 'mule-unicode-2500-33ff
 219   [2 96 1 0 ?2 0 "Unicode subset 2" "Unicode subset (U+2500..U+33FF)"
 220      "Unicode characters of the range U+2500..U+33FF."])
 221
 222 (define-charset 243 'mule-unicode-e000-ffff
 223   [2 96 1 0 ?3 0 "Unicode subset 3" "Unicode subset (U+E000+FFFF)"
 224      "Unicode characters of the range U+E000..U+FFFF."])
 225
 226 (define-charset 244 'mule-unicode-0100-24ff
 227   [2 96 1 0 ?1 0 "Unicode subset" "Unicode subset (U+0100..U+24FF)"
 228      "Unicode characters of the range U+0100..U+24FF."])
 229
 230 ;; 2-byte 2-column charsets.  Valid range of CHARSET-ID is 245..254.
 231
 232 ;; Ethiopic characters (Amharic and Tigrigna).
 233 (define-charset 245 'ethiopic
 234   [2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters"
 235      "Ethiopic characters."])
 236
 237 ;; Chinese CNS11643 Plane3 thru Plane7.  Although these are official
 238 ;; character sets, the use is rare and don't have to be treated
 239 ;; space-efficiently in the buffer.
 240 (define-charset 246 'chinese-cns11643-3
 241   [2 94 2 0 ?I 0 "CNS11643-3" "CNS11643-3 (Chinese traditional): ISO-IR-183"
 242      "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183."])
 243 (define-charset 247 'chinese-cns11643-4
 244   [2 94 2 0 ?J 0 "CNS11643-4" "CNS11643-4 (Chinese traditional): ISO-IR-184"
 245      "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184."])
 246 (define-charset 248 'chinese-cns11643-5
 247   [2 94 2 0 ?K 0 "CNS11643-5" "CNS11643-5 (Chinese traditional): ISO-IR-185"
 248      "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185."])
 249 (define-charset 249 'chinese-cns11643-6
 250   [2 94 2 0 ?L 0 "CNS11643-6" "CNS11643-6 (Chinese traditional): ISO-IR-186"
 251      "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186."])
 252 (define-charset 250 'chinese-cns11643-7
 253   [2 94 2 0 ?M 0 "CNS11643-7" "CNS11643-7 (Chinese traditional): ISO-IR-187"
 254      "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187."])
 255
 256 ;; Actual Glyph for 2-column width.
 257 (define-charset 251 'indian-2-column
 258   [2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column"
 259      "Indian character set for 2-column width glyphs."])
 260   ;; old indian-1-column characters will be translated to indian-2-column.
 261 (declare-equiv-charset 2 94 ?6 'indian-2-column)
 262
 263 ;; Tibetan script.
 264 (define-charset 252 'tibetan
 265   [2 94 2 0 ?7 0 "Tibetan 2-col" "Tibetan 2 column"
 266      "Tibetan 2-column width glyphs."])
 267
 268 ;; CHARSET-ID 253 is not used.
 269
 270 ;; JISX0213 Plane 2
 271 (define-charset 254 'japanese-jisx0213-2
 272   [2 94 2 0 ?P 0 "JISX0213-2" "JISX0213-2"
 273      "JISX0213 Plane 2 (Japanese)."])
 274
 275 ;; Tell C code charset ID's of several charsets.
 276 (setup-special-charsets)
 277
 278 \f
 279 ;; These are tables for translating characters on decoding and
 280 ;; encoding.
 281 (define-translation-table
 282   'oldjis-newjis-jisroman-ascii
 283   (list (cons (make-char 'japanese-jisx0208-1978)
 284               (make-char 'japanese-jisx0208))
 285         (cons (make-char 'latin-jisx0201) (make-char 'ascii))))
 286 (aset (get 'oldjis-newjis-jisroman-ascii 'translation-table)
 287       (make-char 'latin-jisx0201 92) (make-char 'latin-jisx0201 92))
 288 (aset (get 'oldjis-newjis-jisroman-ascii 'translation-table)
 289       (make-char 'latin-jisx0201 126) (make-char 'latin-jisx0201 126))
 290
 291 (setq standard-translation-table-for-decode
 292       (get 'oldjis-newjis-jisroman-ascii 'translation-table))
 293
 294 (setq standard-translation-table-for-encode nil)
 295 \f
 296 ;;; Make fundamental coding systems.
 297
 298 ;; Miscellaneous coding systems which can't be made by
 299 ;; `make-coding-system'.
 300
 301 (put 'no-conversion 'coding-system
 302      (vector nil ?= "Do no conversion.
 303
 304 When you visit a file with this coding, the file is read into a
 305 unibyte buffer as is, thus each byte of a file is treated as a
 306 character."
 307              (list 'coding-category 'coding-category-binary
 308                    'alias-coding-systems '(no-conversion)
 309                    'safe-charsets t 'safe-chars t)
 310              nil))
 311 (put 'no-conversion 'eol-type 0)
 312 (put 'coding-category-binary 'coding-systems '(no-conversion))
 313 (setq coding-system-list '(no-conversion))
 314 (setq coding-system-alist '(("no-conversion")))
 315 (define-coding-system-internal 'no-conversion)
 316
 317 (define-coding-system-alias 'binary 'no-conversion)
 318
 319 (put 'undecided 'coding-system
 320      (vector t ?- "No conversion on encoding, automatic conversion on decoding"
 321              (list 'alias-coding-systems '(undecided)
 322                    'safe-charsets '(ascii))
 323              nil))
 324 (setq coding-system-list (cons 'undecided coding-system-list))
 325 (setq coding-system-alist (cons '("undecided") coding-system-alist))
 326 (put 'undecided 'eol-type
 327      (make-subsidiary-coding-system 'undecided))
 328
 329 (define-coding-system-alias 'unix 'undecided-unix)
 330 (define-coding-system-alias 'dos 'undecided-dos)
 331 (define-coding-system-alias 'mac 'undecided-mac)
 332
 333 ;; Coding systems not specific to each language environment.
 334
 335 (make-coding-system
 336  'emacs-mule 0 ?=
 337  "Emacs internal format used in buffer and string.
 338
 339 Encoding text with this coding system produces the actual byte
 340 sequence of the text in buffers and strings.  An exception is made for
 341 eight-bit-control characters.  Each of them is encoded into a single
 342 byte."
 343  nil
 344  '((safe-charsets . t)
 345    (composition . t)))
 346
 347 (make-coding-system
 348  'raw-text 5 ?t
 349  "Raw text, which means text contains random 8-bit codes.
 350 Encoding text with this coding system produces the actual byte
 351 sequence of the text in buffers and strings.  An exception is made for
 352 eight-bit-control characters.  Each of them is encoded into a single
 353 byte.
 354
 355 When you visit a file with this coding, the file is read into a
 356 unibyte buffer as is (except for EOL format), thus each byte of a file
 357 is treated as a character."
 358  nil
 359  '((safe-charsets . t)))
 360
 361 (make-coding-system
 362  'iso-2022-7bit 2 ?J
 363  "ISO 2022 based 7-bit encoding using only G0"
 364  '((ascii t) nil nil nil
 365    short ascii-eol ascii-cntl seven)
 366  '((safe-charsets . t)
 367    (composition . t)))
 368
 369 (make-coding-system
 370  'iso-2022-7bit-ss2 2 ?$
 371  "ISO 2022 based 7-bit encoding using SS2 for 96-charset"
 372  '((ascii t) nil t nil
 373    short ascii-eol ascii-cntl seven nil single-shift)
 374  '((safe-charsets . t)
 375    (composition . t)))
 376
 377 (make-coding-system
 378  'iso-2022-7bit-lock 2 ?&
 379  "ISO-2022 coding system using Locking-Shift for 96-charset"
 380  '((ascii t) t nil nil
 381    nil ascii-eol ascii-cntl seven locking-shift)
 382  '((safe-charsets . t)
 383    (composition . t)))
 384
 385 (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)
 386
 387 (make-coding-system
 388  'iso-2022-7bit-lock-ss2 2 ?i
 389  "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN"
 390  '((ascii t)
 391    (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 t)
 392    (nil chinese-cns11643-2)
 393    (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
 394         chinese-cns11643-6 chinese-cns11643-7)
 395    short ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
 396    init-bol)
 397  '((safe-charsets ascii japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
 398                   korean-ksc5601 chinese-gb2312 chinese-cns11643-1
 399                   chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4
 400                   chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7)
 401    (composition . t)))
 402
 403 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)
 404
 405 (make-coding-system
 406  'iso-2022-8bit-ss2 2 ?@
 407  "ISO 2022 based 8-bit encoding using SS2 for 96-charset"
 408  '((ascii t) nil t nil
 409    nil ascii-eol ascii-cntl nil nil single-shift)
 410  '((safe-charsets . t)
 411    (composition . t)))
 412
 413 (make-coding-system
 414  'compound-text 2 ?x
 415  "Compound text based generic encoding for decoding unknown messages.
 416
 417 This coding system does not support extended segments."
 418  '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) t t
 419    nil ascii-eol ascii-cntl nil locking-shift single-shift nil nil nil
 420    init-bol nil nil)
 421  '((safe-charsets . t)
 422    (mime-charset . x-ctext)
 423    (composition . t)))
 424
 425 (define-coding-system-alias  'x-ctext 'compound-text)
 426 (define-coding-system-alias  'ctext 'compound-text)
 427
 428 ;; Same as compound-text, but doesn't produce composition escape
 429 ;; sequences.  Used in post-read and pre-write conversions of
 430 ;; compound-text-with-extensions, see mule.el.  Note that this should
 431 ;; not have a mime-charset property, to prevent it from showing up
 432 ;; close to the beginning of coding systems ordered by priority.
 433 (make-coding-system
 434  'ctext-no-compositions 2 ?x
 435  "Compound text based generic encoding for decoding unknown messages.
 436
 437 Like `compound-text', but does not produce escape sequences for compositions."
 438  '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) t t
 439    nil ascii-eol ascii-cntl nil locking-shift single-shift nil nil nil
 440    init-bol nil nil)
 441  '((safe-charsets . t)))
 442
 443 (make-coding-system
 444  'compound-text-with-extensions 2 ?x
 445  "Compound text encoding with extended segments.
 446
 447 See the variable `ctext-non-standard-encodings-alist' for the
 448 detail about how extended segments are handled.
 449
 450 This coding system should be used only for X selections.  It is inappropriate
 451 for decoding and encoding files, process I/O, etc."
 452  '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) t t
 453    nil ascii-eol ascii-cntl)
 454  '((post-read-conversion . ctext-post-read-conversion)
 455    (pre-write-conversion . ctext-pre-write-conversion)))
 456
 457 (define-coding-system-alias
 458   'x-ctext-with-extensions 'compound-text-with-extensions)
 459 (define-coding-system-alias
 460   'ctext-with-extensions 'compound-text-with-extensions)
 461
 462 (make-coding-system
 463  'iso-safe 2 ?-
 464  "Encode ASCII asis and encode non-ASCII characters to `?'."
 465  '(ascii nil nil nil
 466    nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil t)
 467  '((safe-charsets ascii)))
 468
 469 (define-coding-system-alias
 470   'us-ascii 'iso-safe)
 471
 472 (make-coding-system
 473  'iso-latin-1 2 ?1
 474  "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)."
 475  '(ascii latin-iso8859-1 nil nil
 476    nil nil nil nil nil nil nil nil nil nil nil t t)
 477  '((safe-charsets ascii latin-iso8859-1)
 478    (mime-charset . iso-8859-1)))
 479
 480 (define-coding-system-alias 'iso-8859-1 'iso-latin-1)
 481 (define-coding-system-alias 'latin-1 'iso-latin-1)
 482
 483 ;; Use iso-safe for terminal output if some other coding system is not
 484 ;; specified explicitly.
 485 (set-safe-terminal-coding-system-internal 'iso-safe)
 486
 487 ;; The other coding-systems are defined in each language specific
 488 ;; section of languages.el.
 489
 490 ;; Normally, set coding system to `undecided' before reading a file.
 491 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
 492 ;; but we regard them as containing multibyte characters.
 493 ;; Tar files are not decoded at all, but we treat them as raw bytes.
 494
 495 (setq file-coding-system-alist
 496       '(("\\.elc\\'" . (emacs-mule . emacs-mule))
 497         ("\\.utf\\(-8\\)?\\'" . utf-8)
 498         ;; We use raw-text for reading loaddefs.el so that if it
 499         ;; happens to have DOS or Mac EOLs, they are converted to
 500         ;; newlines.  This is required to make the special treatment
 501         ;; of the "\ newline" combination in loaddefs.el, which marks
 502         ;; the beginning of a doc string, work.
 503         ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix))
 504         ("\\.tar\\'" . (no-conversion . no-conversion))
 505         ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system)
 506         ("\\.\\(tex\\|ltx\\|dtx\\|drv\\)\\'" . latexenc-find-file-coding-system)
 507         ("" . (undecided . nil))))
 508
 509 \f
 510 ;;; Setting coding categories and their priorities.
 511
 512 ;; This setting is just to read an Emacs Lisp source files which
 513 ;; contain multilingual text while dumping Emacs.  More appropriate
 514 ;; values are set by the command `set-language-environment' for each
 515 ;; language environment.
 516
 517 (setq coding-category-emacs-mule        'emacs-mule
 518       coding-category-sjis              'japanese-shift-jis
 519       coding-category-iso-7             'iso-2022-7bit
 520       coding-category-iso-7-tight       'iso-2022-jp
 521       coding-category-iso-8-1           'iso-latin-1
 522       coding-category-iso-8-2           'iso-latin-1
 523       coding-category-iso-7-else        'iso-2022-7bit-lock
 524       coding-category-iso-8-else        'iso-2022-8bit-ss2
 525       coding-category-ccl               nil
 526       coding-category-utf-8             'mule-utf-8
 527       coding-category-utf-16-be         'mule-utf-16be-with-signature
 528       coding-category-utf-16-le         'mule-utf-16le-with-signature
 529       coding-category-big5              'chinese-big5
 530       coding-category-raw-text          'raw-text
 531       coding-category-binary            'no-conversion)
 532
 533 (set-coding-priority
 534  '(coding-category-iso-8-1
 535    coding-category-iso-8-2
 536    coding-category-utf-8
 537    coding-category-utf-16-be
 538    coding-category-utf-16-le
 539    coding-category-iso-7-tight
 540    coding-category-iso-7
 541    coding-category-iso-7-else
 542    coding-category-iso-8-else
 543    coding-category-emacs-mule
 544    coding-category-raw-text
 545    coding-category-sjis
 546    coding-category-big5
 547    coding-category-ccl
 548    coding-category-binary
 549    ))
 550
 551 \f
 552 ;;; Miscellaneous settings.
 553 (aset latin-extra-code-table ?\221 t)
 554 (aset latin-extra-code-table ?\222 t)
 555 (aset latin-extra-code-table ?\223 t)
 556 (aset latin-extra-code-table ?\224 t)
 557 (aset latin-extra-code-table ?\225 t)
 558 (aset latin-extra-code-table ?\226 t)
 559
 560 (update-coding-systems-internal)
 561
 562 ;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5
 563 ;;; mule-conf.el ends here