lisp/international/mule-conf.el

   1 ;;; mule-conf.el --- configure multilingual environment -*- no-byte-compile: t -*-
   2
   3 ;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN.
   4 ;; Licensed to the Free Software Foundation.
   5
   6 ;; Keywords: mule, multilingual, character set, coding system
   7
   8 ;; This file is part of GNU Emacs.
   9
  10 ;; GNU Emacs is free software; you can redistribute it and/or modify
  11 ;; it under the terms of the GNU General Public License as published by
  12 ;; the Free Software Foundation; either version 2, or (at your option)
  13 ;; any later version.
  14
  15 ;; GNU Emacs is distributed in the hope that it will be useful,
  16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  18 ;; GNU General Public License for more details.
  19
  20 ;; You should have received a copy of the GNU General Public License
  21 ;; along with GNU Emacs; see the file COPYING.  If not, write to the
  22 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  23 ;; Boston, MA 02111-1307, USA.
  24
  25 ;;; Commentary:
  26
  27 ;; Don't byte-compile this file.
  28
  29 ;;; Code:
  30
  31 ;;; Definitions of character sets.
  32
  33 ;; Basic (official) character sets.  These character sets are treated
  34 ;; efficiently with respect to buffer memory.
  35
  36 ;; Syntax:
  37 ;; (define-charset CHARSET-ID CHARSET
  38 ;;   [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
  39 ;;     SHORT-NAME LONG-NAME DESCRIPTION ])
  40 ;; ASCII charset is defined in src/charset.c as below.
  41 ;; (define-charset 0 ascii
  42 ;;    [1 94 1 0 ?B 0 "ASCII" "ASCII" "ASCII (ISO646 IRV)"])
  43
  44 ;; 1-byte charsets.  Valid range of CHARSET-ID is 128..143.
  45
  46 ;; CHARSET-ID 128 is not used.
  47
  48 (define-charset 129 'latin-iso8859-1
  49   [1 96 1 0 ?A 1 "RHP of Latin-1" "RHP of Latin-1 (ISO 8859-1): ISO-IR-100"
  50      "Right-Hand Part of Latin Alphabet 1 (ISO/IEC 8859-1): ISO-IR-100."])
  51 (define-charset 130 'latin-iso8859-2
  52   [1 96 1 0 ?B 1 "RHP of Latin-2" "RHP of Latin-2 (ISO 8859-2): ISO-IR-101"
  53      "Right-Hand Part of Latin Alphabet 2 (ISO/IEC 8859-2): ISO-IR-101."])
  54 (define-charset 131 'latin-iso8859-3
  55   [1 96 1 0 ?C 1 "RHP of Latin-3" "RHP of Latin-3 (ISO 8859-3): ISO-IR-109"
  56      "Right-Hand Part of Latin Alphabet 3 (ISO/IEC 8859-3): ISO-IR-109."])
  57 (define-charset 132 'latin-iso8859-4
  58   [1 96 1 0 ?D 1 "RHP of Latin-4" "RHP of Latin-4 (ISO 8859-4): ISO-IR-110"
  59      "Right-Hand Part of Latin Alphabet 4 (ISO/IEC 8859-4): ISO-IR-110."])
  60 (define-charset 133 'thai-tis620
  61   [1 96 1 0 ?T 1 "RHP of TIS620" "RHP of Thai (TIS620): ISO-IR-166"
  62      "Right-Hand Part of TIS620.2533 (Thai): ISO-IR-166."])
  63 (define-charset 134 'greek-iso8859-7
  64   [1 96 1 0 ?F 1 "RHP of ISO8859/7" "RHP of Greek (ISO 8859-7): ISO-IR-126"
  65      "Right-Hand Part of Latin/Greek Alphabet (ISO/IEC 8859-7): ISO-IR-126."])
  66 (define-charset 135 'arabic-iso8859-6
  67   [1 96 1 1 ?G 1 "RHP of ISO8859/6" "RHP of Arabic (ISO 8859-6): ISO-IR-127"
  68      "Right-Hand Part of Latin/Arabic Alphabet (ISO/IEC 8859-6): ISO-IR-127."])
  69 (define-charset 136 'hebrew-iso8859-8
  70   [1 96 1 1 ?H 1 "RHP of ISO8859/8" "RHP of Hebrew (ISO 8859-8): ISO-IR-138"
  71      "Right-Hand Part of Latin/Hebrew Alphabet (ISO/IEC 8859-8): ISO-IR-138."])
  72 (define-charset 137 'katakana-jisx0201
  73   [1 94 1 0 ?I 1 "JISX0201 Katakana" "Japanese Katakana (JISX0201.1976)"
  74      "Katakana Part of JISX0201.1976."])
  75 (define-charset 138 'latin-jisx0201
  76   [1 94 1 0 ?J 0 "JISX0201 Roman" "Japanese Roman (JISX0201.1976)"
  77      "Roman Part of JISX0201.1976."])
  78
  79 ;; CHARSET-ID is not used 139.
  80
  81 (define-charset 140 'cyrillic-iso8859-5
  82   [1 96 1 0 ?L 1 "RHP of ISO8859/5" "RHP of Cyrillic (ISO 8859-5): ISO-IR-144"
  83      "Right-Hand Part of Latin/Cyrillic Alphabet (ISO/IEC 8859-5): ISO-IR-144."])
  84 (define-charset 141 'latin-iso8859-9
  85   [1 96 1 0 ?M 1 "RHP of Latin-5" "RHP of Latin-5 (ISO 8859-9): ISO-IR-148"
  86      "Right-Hand Part of Latin Alphabet 5 (ISO/IEC 8859-9): ISO-IR-148."])
  87 (define-charset 142 'latin-iso8859-15
  88   [1 96 1 0 ?b 1 "RHP of Latin-9" "RHP of Latin-9 (ISO 8859-15): ISO-IR-203"
  89      "Right-Hand Part of Latin Alphabet 9 (ISO/IEC 8859-15): ISO-IR-203."])
  90 (define-charset 143 'latin-iso8859-14
  91   [1 96 1 0 ?_ 1 "RHP of Latin-8" "RHP of Latin-8 (ISO 8859-14): ISO-IR-199"
  92      "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14): ISO-IR-199."])
  93
  94 ;; 2-byte charsets.  Valid range of CHARSET-ID is 144..153.
  95
  96 (define-charset 144 'japanese-jisx0208-1978
  97   [2 94 2 0 ?@ 0 "JISX0208.1978" "JISX0208.1978 (Japanese): ISO-IR-42"
  98      "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42."])
  99 (define-charset 145 'chinese-gb2312
 100   [2 94 2 0 ?A 0 "GB2312" "GB2312: ISO-IR-58"
 101      "GB2312 Chinese simplified: ISO-IR-58."])
 102 (define-charset 146 'japanese-jisx0208
 103   [2 94 2 0 ?B 0 "JISX0208" "JISX0208.1983/1990 (Japanese): ISO-IR-87"
 104      "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87."])
 105 (define-charset 147 'korean-ksc5601
 106   [2 94 2 0 ?C 0 "KSC5601" "KSC5601 (Korean): ISO-IR-149"
 107      "KSC5601 Korean Hangul and Hanja: ISO-IR-149."])
 108 (define-charset 148 'japanese-jisx0212
 109   [2 94 2 0 ?D 0 "JISX0212" "JISX0212 (Japanese): ISO-IR-159"
 110      "JISX0212 Japanese supplement: ISO-IR-159."])
 111 (define-charset 149 'chinese-cns11643-1
 112   [2 94 2 0 ?G 0 "CNS11643-1" "CNS11643-1 (Chinese traditional): ISO-IR-171"
 113      "CNS11643 Plane 1 Chinese traditional: ISO-IR-171."])
 114 (define-charset 150 'chinese-cns11643-2
 115   [2 94 2 0 ?H 0 "CNS11643-2" "CNS11643-2 (Chinese traditional): ISO-IR-172"
 116      "CNS11643 Plane 2 Chinese traditional: ISO-IR-172."])
 117 (define-charset 151 'japanese-jisx0213-1
 118   [2 94 2 0 ?O 0 "JISX0213-1" "JISX0213-1" "JISX0213 Plane 1 (Japanese)"])
 119 (define-charset 152 'chinese-big5-1
 120   [2 94 2 0 ?0 0 "Big5 (Level-1)" "Big5 (Level-1) A141-C67F"
 121      "Frequently used part (A141-C67F) of Big5 (Chinese traditional)."])
 122 (define-charset 153 'chinese-big5-2
 123   [2 94 2 0 ?1 0 "Big5 (Level-2)" "Big5 (Level-2) C940-FEFE"
 124      "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)."])
 125
 126 ;; Additional (private) character sets.  These character sets are
 127 ;; treated less space-efficiently in the buffer.
 128
 129 ;; Syntax:
 130 ;; (define-charset CHARSET-ID CHARSET
 131 ;;   [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
 132 ;;     SHORT-NAME LONG-NAME DESCRIPTION ])
 133
 134 ;; ISO-2022 allows a use of character sets not registered in ISO with
 135 ;; final characters `0' (0x30) through `?' (0x3F).  Among them, Emacs
 136 ;; reserves `0' through `9' to support several private character sets.
 137 ;; The remaining final characters `:' through `?' are for users.
 138
 139 ;; 1-byte 1-column charsets.  Valid range of CHARSET-ID is 160..223.
 140
 141 (define-charset 160 'chinese-sisheng
 142   [1 94 1 0 ?0 0 "SiSheng" "SiSheng (PinYin/ZhuYin)"
 143      "Sisheng characters (vowels with tone marks) for Pinyin/Zhuyin."])
 144
 145 ;; IPA characters for phonetic symbols.
 146 (define-charset 161 'ipa
 147   [1 96 1 0 ?0 1 "IPA" "IPA"
 148      "IPA (International Phonetic Association) characters."])
 149
 150 ;; Vietnamese VISCII.  VISCII is 1-byte character set which contains
 151 ;; more than 96 characters.  Since Emacs can't handle it as one
 152 ;; character set, it is divided into two: lower case letters and upper
 153 ;; case letters.
 154 (define-charset 162 'vietnamese-viscii-lower
 155   [1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case"
 156      "Vietnamese VISCII1.1 lower-case characters."])
 157 (define-charset 163 'vietnamese-viscii-upper
 158   [1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case"
 159      "Vietnamese VISCII1.1 upper-case characters."])
 160
 161 ;; For Arabic, we need three different types of character sets.
 162 ;; Digits are of direction left-to-right and of width 1-column.
 163 ;; Others are of direction right-to-left and of width 1-column or
 164 ;; 2-column.
 165 (define-charset 164 'arabic-digit
 166   [1 94 1 0 ?2 0 "Arabic digit" "Arabic digit"
 167      "Arabic digits."])
 168 (define-charset 165 'arabic-1-column
 169   [1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column"
 170      "Arabic 1-column width glyphs."])
 171
 172 ;; ASCII with right-to-left direction.
 173 (define-charset 166 'ascii-right-to-left
 174   [1 94 1 1 ?B 0 "rev ASCII" "ASCII with right-to-left direction"
 175      "ASCII (left half of ISO 8859-1) with right-to-left direction."])
 176
 177 ;; Lao script.
 178 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
 179 (define-charset 167 'lao
 180   [1 94 1 0 ?1 0 "Lao" "Lao"
 181      "Lao characters (U+0E80..U+0EDF)."])
 182
 183 ;; CHARSET-IDs 168..223 are not used.
 184
 185 ;; 1-byte 2-column charsets.  Valid range of CHARSET-ID is 224..239.
 186
 187 (define-charset 224 'arabic-2-column
 188   [1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column"
 189      "Arabic 2-column glyphs."])
 190
 191 ;; Indian scripts.  Symbolic charset for data exchange.  Glyphs are
 192 ;; not assigned.  They are automatically converted to each Indian
 193 ;; script which IS-13194 supports.
 194
 195 (define-charset 225 'indian-is13194
 196   [1 94 2 0 ?5 1 "IS 13194" "Indian IS 13194"
 197      "Generic Indian character set for data exchange with IS 13194."])
 198
 199 ;; CHARSET-IDs 226..239 are not used.
 200
 201 (define-charset 240  'indian-glyph
 202   [2 96 1 0 ?4 0 "Indian glyph" "Indian glyph"
 203      "Glyphs for Indian characters."])
 204 ;; 240 used to be [2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column"]
 205
 206 ;; 2-byte 1-column charsets.  Valid range of CHARSET-ID is 240..244.
 207
 208 ;; Actual Glyph for 1-column width.
 209 (define-charset 241 'tibetan-1-column
 210   [2 94 1 0 ?8 0 "Tibetan 1-col" "Tibetan 1 column"
 211      "Tibetan 1-column glyphs."])
 212
 213 ;; Subsets of Unicode.
 214
 215 (define-charset 242 'mule-unicode-2500-33ff
 216   [2 96 1 0 ?2 0 "Unicode subset 2" "Unicode subset (U+2500..U+33FF)"
 217      "Unicode characters of the range U+2500..U+33FF."])
 218
 219 (define-charset 243 'mule-unicode-e000-ffff
 220   [2 96 1 0 ?3 0 "Unicode subset 3" "Unicode subset (U+E000+FFFF)"
 221      "Unicode characters of the range U+E000..U+FFFF."])
 222
 223 (define-charset 244 'mule-unicode-0100-24ff
 224   [2 96 1 0 ?1 0 "Unicode subset" "Unicode subset (U+0100..U+24FF)"
 225      "Unicode characters of the range U+0100..U+24FF."])
 226
 227 ;; 2-byte 2-column charsets.  Valid range of CHARSET-ID is 245..254.
 228
 229 ;; Ethiopic characters (Amharic and Tigrigna).
 230 (define-charset 245 'ethiopic
 231   [2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters"
 232      "Ethiopic characters."])
 233
 234 ;; Chinese CNS11643 Plane3 thru Plane7.  Although these are official
 235 ;; character sets, the use is rare and don't have to be treated
 236 ;; space-efficiently in the buffer.
 237 (define-charset 246 'chinese-cns11643-3
 238   [2 94 2 0 ?I 0 "CNS11643-3" "CNS11643-3 (Chinese traditional): ISO-IR-183"
 239      "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183."])
 240 (define-charset 247 'chinese-cns11643-4
 241   [2 94 2 0 ?J 0 "CNS11643-4" "CNS11643-4 (Chinese traditional): ISO-IR-184"
 242      "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184."])
 243 (define-charset 248 'chinese-cns11643-5
 244   [2 94 2 0 ?K 0 "CNS11643-5" "CNS11643-5 (Chinese traditional): ISO-IR-185"
 245      "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185."])
 246 (define-charset 249 'chinese-cns11643-6
 247   [2 94 2 0 ?L 0 "CNS11643-6" "CNS11643-6 (Chinese traditional): ISO-IR-186"
 248      "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186."])
 249 (define-charset 250 'chinese-cns11643-7
 250   [2 94 2 0 ?M 0 "CNS11643-7" "CNS11643-7 (Chinese traditional): ISO-IR-187"
 251      "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187."])
 252
 253 ;; Actual Glyph for 2-column width.
 254 (define-charset 251 'indian-2-column
 255   [2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column"
 256      "Indian character set for 2-column width glyphs."])
 257   ;; old indian-1-column characters will be translated to indian-2-column.
 258 (declare-equiv-charset 2 94 ?6 'indian-2-column)
 259
 260 ;; Tibetan script.
 261 (define-charset 252 'tibetan
 262   [2 94 2 0 ?7 0 "Tibetan 2-col" "Tibetan 2 column"
 263      "Tibetan 2-column width glyphs."])
 264
 265 ;; CHARSET-ID 253 is not used.
 266
 267 ;; JISX0213 Plane 2
 268 (define-charset 254 'japanese-jisx0213-2
 269   [2 94 2 0 ?P 0 "JISX0213-2" "JISX0213-2"
 270      "JISX0213 Plane 2 (Japanese)."])
 271
 272 ;; Tell C code charset ID's of several charsets.
 273 (setup-special-charsets)
 274
 275 \f
 276 ;; These are tables for translating characters on decoding and
 277 ;; encoding.
 278 (define-translation-table
 279   'oldjis-newjis-jisroman-ascii
 280   (list (cons (make-char 'japanese-jisx0208-1978)
 281               (make-char 'japanese-jisx0208))
 282         (cons (make-char 'latin-jisx0201) (make-char 'ascii))))
 283 (aset (get 'oldjis-newjis-jisroman-ascii 'translation-table)
 284       (make-char 'latin-jisx0201 92) (make-char 'latin-jisx0201 92))
 285 (aset (get 'oldjis-newjis-jisroman-ascii 'translation-table)
 286       (make-char 'latin-jisx0201 126) (make-char 'latin-jisx0201 126))
 287
 288 (setq standard-translation-table-for-decode
 289       (get 'oldjis-newjis-jisroman-ascii 'translation-table))
 290
 291 (setq standard-translation-table-for-encode nil)
 292
 293 (defvar translation-table-for-input nil
 294   "If non-nil, a char table used to translate characters from input methods.
 295 \(Currently only used by Quail.)")
 296 \f
 297 ;;; Make fundamental coding systems.
 298
 299 ;; Miscellaneous coding systems which can't be made by
 300 ;; `make-coding-system'.
 301
 302 (put 'no-conversion 'coding-system
 303      (vector nil ?= "Do no conversion.
 304
 305 When you visit a file with this coding, the file is read into a
 306 unibyte buffer as is, thus each byte of a file is treated as a
 307 character."
 308              (list 'coding-category 'coding-category-binary
 309                    'alias-coding-systems '(no-conversion)
 310                    'safe-charsets t 'safe-chars t)
 311              nil))
 312 (put 'no-conversion 'eol-type 0)
 313 (put 'coding-category-binary 'coding-systems '(no-conversion))
 314 (setq coding-system-list '(no-conversion))
 315 (setq coding-system-alist '(("no-conversion")))
 316 (define-coding-system-internal 'no-conversion)
 317
 318 (define-coding-system-alias 'binary 'no-conversion)
 319
 320 (put 'undecided 'coding-system
 321      (vector t ?- "No conversion on encoding, automatic conversion on decoding"
 322              (list 'alias-coding-systems '(undecided)
 323                    'safe-charsets '(ascii))
 324              nil))
 325 (setq coding-system-list (cons 'undecided coding-system-list))
 326 (setq coding-system-alist (cons '("undecided") coding-system-alist))
 327 (put 'undecided 'eol-type
 328      (make-subsidiary-coding-system 'undecided))
 329
 330 (define-coding-system-alias 'unix 'undecided-unix)
 331 (define-coding-system-alias 'dos 'undecided-dos)
 332 (define-coding-system-alias 'mac 'undecided-mac)
 333
 334 ;; Coding systems not specific to each language environment.
 335
 336 (make-coding-system
 337  'emacs-mule 0 ?=
 338  "Emacs internal format used in buffer and string.
 339
 340 Encoding text with this coding system produces the actual byte
 341 sequence of the text in buffers and strings.  An exception is made for
 342 eight-bit-control characters.  Each of them is encoded into a single
 343 byte."
 344  nil
 345  '((safe-charsets . t)
 346    (composition . t)))
 347
 348 (make-coding-system
 349  'raw-text 5 ?t
 350  "Raw text, which means text contains random 8-bit codes.
 351 Encoding text with this coding system produces the actual byte
 352 sequence of the text in buffers and strings.  An exception is made for
 353 eight-bit-control characters.  Each of them is encoded into a single
 354 byte.
 355
 356 When you visit a file with this coding, the file is read into a
 357 unibyte buffer as is (except for EOL format), thus each byte of a file
 358 is treated as a character."
 359  nil
 360  '((safe-charsets . t)))
 361
 362 (make-coding-system
 363  'iso-2022-7bit 2 ?J
 364  "ISO 2022 based 7-bit encoding using only G0"
 365  '((ascii t) nil nil nil
 366    short ascii-eol ascii-cntl seven)
 367  '((safe-charsets . t)
 368    (composition . t)))
 369
 370 (make-coding-system
 371  'iso-2022-7bit-ss2 2 ?$
 372  "ISO 2022 based 7-bit encoding using SS2 for 96-charset"
 373  '((ascii t) nil t nil
 374    short ascii-eol ascii-cntl seven nil single-shift)
 375  '((safe-charsets . t)
 376    (composition . t)))
 377
 378 (make-coding-system
 379  'iso-2022-7bit-lock 2 ?&
 380  "ISO-2022 coding system using Locking-Shift for 96-charset"
 381  '((ascii t) t nil nil
 382    nil ascii-eol ascii-cntl seven locking-shift)
 383  '((safe-charsets . t)
 384    (composition . t)))
 385
 386 (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)
 387
 388 (make-coding-system
 389  'iso-2022-7bit-lock-ss2 2 ?i
 390  "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN"
 391  '((ascii t)
 392    (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 t)
 393    (nil chinese-cns11643-2)
 394    (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
 395         chinese-cns11643-6 chinese-cns11643-7)
 396    short ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
 397    init-bol)
 398  '((safe-charsets ascii japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
 399                   korean-ksc5601 chinese-gb2312 chinese-cns11643-1
 400                   chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4
 401                   chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7)
 402    (composition . t)))
 403
 404 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)
 405
 406 (make-coding-system
 407  'iso-2022-8bit-ss2 2 ?@
 408  "ISO 2022 based 8-bit encoding using SS2 for 96-charset"
 409  '((ascii t) nil t nil
 410    nil ascii-eol ascii-cntl nil nil single-shift)
 411  '((safe-charsets . t)
 412    (composition . t)))
 413
 414 (make-coding-system
 415  'compound-text 2 ?x
 416  "Compound text based generic encoding for decoding unknown messages.
 417
 418 This coding system does not support extended segments."
 419  '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) t t
 420    nil ascii-eol ascii-cntl nil locking-shift single-shift nil nil nil
 421    init-bol nil nil)
 422  '((safe-charsets . t)
 423    (mime-charset . x-ctext)
 424    (composition . t)))
 425
 426 (define-coding-system-alias  'x-ctext 'compound-text)
 427 (define-coding-system-alias  'ctext 'compound-text)
 428
 429 ;; Same as compound-text, but doesn't produce composition escape
 430 ;; sequences.  Used in post-read and pre-write conversions of
 431 ;; compound-text-with-extensions, see mule.el.  Note that this should
 432 ;; not have a mime-charset property, to prevent it from showing up
 433 ;; close to the beginning of coding systems ordered by priority.
 434 (make-coding-system
 435  'ctext-no-compositions 2 ?x
 436  "Compound text based generic encoding for decoding unknown messages.
 437
 438 Like `compound-text', but does not produce escape sequences for compositions."
 439  '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) t t
 440    nil ascii-eol ascii-cntl nil locking-shift single-shift nil nil nil
 441    init-bol nil nil)
 442  '((safe-charsets . t)))
 443
 444 (make-coding-system
 445  'compound-text-with-extensions 5 ?x
 446  "Compound text encoding with extended segments.
 447
 448 This coding system should be used only for X selections.  It is inappropriate
 449 for decoding and encoding files, process I/O, etc."
 450  nil
 451  '((post-read-conversion . ctext-post-read-conversion)
 452    (pre-write-conversion . ctext-pre-write-conversion)))
 453
 454 (define-coding-system-alias
 455   'x-ctext-with-extensions 'compound-text-with-extensions)
 456 (define-coding-system-alias
 457   'ctext-with-extensions 'compound-text-with-extensions)
 458
 459 (make-coding-system
 460  'iso-safe 2 ?-
 461  "Encode ASCII asis and encode non-ASCII characters to `?'."
 462  '(ascii nil nil nil
 463    nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil t)
 464  '((safe-charsets ascii)))
 465
 466 (define-coding-system-alias
 467   'us-ascii 'iso-safe)
 468
 469 (make-coding-system
 470  'iso-latin-1 2 ?1
 471  "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)."
 472  '(ascii latin-iso8859-1 nil nil
 473    nil nil nil nil nil nil nil nil nil nil nil t t)
 474  '((safe-charsets ascii latin-iso8859-1)
 475    (mime-charset . iso-8859-1)))
 476
 477 (define-coding-system-alias 'iso-8859-1 'iso-latin-1)
 478 (define-coding-system-alias 'latin-1 'iso-latin-1)
 479
 480 ;; Use iso-safe for terminal output if some other coding system is not
 481 ;; specified explicitly.
 482 (set-safe-terminal-coding-system-internal 'iso-safe)
 483
 484 ;; The other coding-systems are defined in each language specific
 485 ;; section of languages.el.
 486
 487 ;; Normally, set coding system to `undecided' before reading a file.
 488 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
 489 ;; but we regard them as containing multibyte characters.
 490 ;; Tar files are not decoded at all, but we treat them as raw bytes.
 491
 492 (setq file-coding-system-alist
 493       '(("\\.elc\\'" . (emacs-mule . emacs-mule))
 494         ("\\.utf\\(-8\\)?\\'" . utf-8)
 495         ;; We use raw-text for reading loaddefs.el so that if it
 496         ;; happens to have DOS or Mac EOLs, they are converted to
 497         ;; newlines.  This is required to make the special treatment
 498         ;; of the "\ newline" combination in loaddefs.el, which marks
 499         ;; the beginning of a doc string, work.
 500         ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix))
 501         ("\\.tar\\'" . (no-conversion . no-conversion))
 502         ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system)
 503         ("" . (undecided . nil))))
 504
 505 \f
 506 ;;; Setting coding categories and their priorities.
 507
 508 ;; This setting is just to read an Emacs Lisp source files which
 509 ;; contain multilingual text while dumping Emacs.  More appropriate
 510 ;; values are set by the command `set-language-environment' for each
 511 ;; language environment.
 512
 513 (setq coding-category-emacs-mule        'emacs-mule
 514       coding-category-sjis              'japanese-shift-jis
 515       coding-category-iso-7             'iso-2022-7bit
 516       coding-category-iso-7-tight       'iso-2022-jp
 517       coding-category-iso-8-1           'iso-latin-1
 518       coding-category-iso-8-2           'iso-latin-1
 519       coding-category-iso-7-else        'iso-2022-7bit-lock
 520       coding-category-iso-8-else        'iso-2022-8bit-ss2
 521       coding-category-ccl               nil
 522       coding-category-utf-8             'mule-utf-8
 523       coding-category-utf-16-be         'mule-utf-16be-with-signature
 524       coding-category-utf-16-le         'mule-utf-16le-with-signature
 525       coding-category-big5              'chinese-big5
 526       coding-category-raw-text          'raw-text
 527       coding-category-binary            'no-conversion)
 528
 529 (set-coding-priority
 530  '(coding-category-iso-8-1
 531    coding-category-iso-8-2
 532    coding-category-utf-8
 533    coding-category-utf-16-be
 534    coding-category-utf-16-le
 535    coding-category-iso-7-tight
 536    coding-category-iso-7
 537    coding-category-iso-7-else
 538    coding-category-iso-8-else
 539    coding-category-emacs-mule
 540    coding-category-raw-text
 541    coding-category-sjis
 542    coding-category-big5
 543    coding-category-ccl
 544    coding-category-binary
 545    ))
 546
 547 \f
 548 ;;; Miscellaneous settings.
 549 (aset latin-extra-code-table ?\221 t)
 550 (aset latin-extra-code-table ?\222 t)
 551 (aset latin-extra-code-table ?\223 t)
 552 (aset latin-extra-code-table ?\224 t)
 553 (aset latin-extra-code-table ?\225 t)
 554 (aset latin-extra-code-table ?\226 t)
 555
 556 (update-coding-systems-internal)
 557
 558 ;;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5
 559 ;;; mule-conf.el ends here