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

   1 ;;; mule-conf.el --- configure multilingual environment
   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 (define-charset 129 'latin-iso8859-1
  45   [1 96 1 0 ?A 1 "RHP of Latin-1" "RHP of Latin-1 (ISO 8859-1): ISO-IR-100"
  46      "Right-Hand Part of Latin Alphabet 1 (ISO/IEC 8859-1): ISO-IR-100"])
  47 (define-charset 130 'latin-iso8859-2
  48   [1 96 1 0 ?B 1 "RHP of Latin-2" "RHP of Latin-2 (ISO 8859-2): ISO-IR-101"
  49      "Right-Hand Part of Latin Alphabet 2 (ISO/IEC 8859-2): ISO-IR-101"])
  50 (define-charset 131 'latin-iso8859-3
  51   [1 96 1 0 ?C 1 "RHP of Latin-3" "RHP of Latin-3 (ISO 8859-3): ISO-IR-109"
  52      "Right-Hand Part of Latin Alphabet 3 (ISO/IEC 8859-3): ISO-IR-109"])
  53 (define-charset 132 'latin-iso8859-4
  54   [1 96 1 0 ?D 1 "RHP of Latin-4" "RHP of Latin-4 (ISO 8859-4): ISO-IR-110"
  55      "Right-Hand Part of Latin Alphabet 4 (ISO/IEC 8859-4): ISO-IR-110"])
  56 (define-charset 133 'thai-tis620
  57   [1 96 1 0 ?T 1 "RHP of TIS620" "RHP of Thai (TIS620): ISO-IR-166"
  58      "Right-Hand Part of TIS620.2533 (Thai): ISO-IR-166"])
  59 (define-charset 134 'greek-iso8859-7
  60   [1 96 1 0 ?F 1 "RHP of ISO8859/7" "RHP of Greek (ISO 8859-7): ISO-IR-126"
  61      "Right-Hand Part of Latin/Greek Alphabet (ISO/IEC 8859-7): ISO-IR-126"])
  62 (define-charset 135 'arabic-iso8859-6
  63   [1 96 1 1 ?G 1 "RHP of ISO8859/6" "RHP of Arabic (ISO 8859-6): ISO-IR-127"
  64      "Right-Hand Part of Latin/Alabic Alphabet (ISO/IEC 8859-6): ISO-IR-127"])
  65 (define-charset 136 'hebrew-iso8859-8
  66   [1 96 1 1 ?H 1 "RHP of ISO8859/8" "RHP of Hebrew (ISO 8859-8): ISO-IR-138"
  67      "Right-Hand Part of Latin/Hebrew Alphabet (ISO/IEC 8859-8): ISO-IR-138"])
  68 (define-charset 137 'katakana-jisx0201
  69   [1 94 1 0 ?I 1 "JISX0201 Katakana" "Japanese Katakana (JISX0201.1976)"
  70      "Katakana Part of JISX0201.1976"])
  71 (define-charset 138 'latin-jisx0201
  72   [1 94 1 0 ?J 0 "JISX0201 Roman" "Japanese Roman (JISX0201.1976)"
  73      "Roman Part of JISX0201.1976"])
  74 (define-charset 140 'cyrillic-iso8859-5
  75   [1 96 1 0 ?L 1 "RHP of ISO8859/5" "RHP of Cyrillic (ISO 8859-5): ISO-IR-144"
  76      "Right-Hand Part of Latin/Cyrillic Alphabet (ISO/IEC 8859-5): ISO-IR-144"])
  77 (define-charset 141 'latin-iso8859-9
  78   [1 96 1 0 ?M 1 "RHP of Latin-5" "RHP of Latin-5 (ISO 8859-9): ISO-IR-148"
  79      "Right-Hand Part of Latin Alphabet 5 (ISO/IEC 8859-9): ISO-IR-148"])
  80 (define-charset 142 'latin-iso8859-15
  81   [1 96 1 0 ?b 1 "RHP of Latin-9" "RHP of Latin-9 (ISO 8859-15): ISO-IR-203"
  82      "Right-Hand Part of Latin Alphabet 9 (ISO/IEC 8859-15): ISO-IR-203"])
  83 (define-charset 143 'latin-iso8859-14
  84   [1 96 1 0 ?_ 1 "RHP of Latin-8" "RHP of Latin-8 (ISO 8859-14)"
  85      "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14)"])
  86 (define-charset 144 'japanese-jisx0208-1978
  87   [2 94 2 0 ?@ 0 "JISX0208.1978" "JISX0208.1978 (Japanese): ISO-IR-42"
  88      "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42"])
  89 (define-charset 145 'chinese-gb2312
  90   [2 94 2 0 ?A 0 "GB2312" "GB2312: ISO-IR-58"
  91      "GB2312 Chinese simplified: ISO-IR-58"])
  92 (define-charset 146 'japanese-jisx0208
  93   [2 94 2 0 ?B 0 "JISX0208" "JISX0208.1983/1990 (Japanese): ISO-IR-87"
  94      "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87"])
  95 (define-charset 147 'korean-ksc5601
  96   [2 94 2 0 ?C 0 "KSC5601" "KSC5601 (Korean): ISO-IR-149"
  97      "KSC5601 Korean Hangul and Hanja: ISO-IR-149"])
  98 (define-charset 148 'japanese-jisx0212
  99   [2 94 2 0 ?D 0 "JISX0212" "JISX0212 (Japanese): ISO-IR-159"
 100      "JISX0212 Japanese supplement: ISO-IR-159"])
 101 (define-charset 149 'chinese-cns11643-1
 102   [2 94 2 0 ?G 0 "CNS11643-1" "CNS11643-1 (Chinese traditional): ISO-IR-171"
 103      "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"])
 104 (define-charset 150 'chinese-cns11643-2
 105   [2 94 2 0 ?H 0 "CNS11643-2" "CNS11643-2 (Chinese traditional): ISO-IR-172"
 106      "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"])
 107 (define-charset 152 'chinese-big5-1
 108   [2 94 2 0 ?0 0 "Big5 (Level-1)" "Big5 (Level-1) A141-C67F"
 109      "Frequentry used part (A141-C67F) of Big5 (Chinese traditional)"])
 110 (define-charset 153 'chinese-big5-2
 111   [2 94 2 0 ?1 0 "Big5 (Level-2)" "Big5 (Level-2) C940-FEFE"
 112      "Less frequentry used part (C940-FEFE) of Big5 (Chinese traditional)"])
 113
 114 ;; Additional (private) character sets.  These character sets are
 115 ;; treated less space-efficiently in the buffer.
 116
 117 ;; Syntax:
 118 ;; (define-charset nil CHARSET
 119 ;;   [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
 120 ;;     SHORT-NAME LONG-NAME DESCRIPTION ])
 121
 122 ;; ISO-2022 allows a use of character sets not registered in ISO with
 123 ;; final characters `0' (0x30) through `?' (0x3F).  Among them, Emacs
 124 ;; reserves `0' through `9' to support several private character sets.
 125 ;; The remaining final characters `:' through `?' are for users.
 126
 127 (define-charset nil 'chinese-sisheng
 128   [1 94 1 0 ?0 0 "SiSheng" "SiSheng (PinYin/ZhuYin)"
 129      "SiSheng characters for PinYin/ZhuYin"])
 130
 131 ;; IPA characters for phonetic symbols.
 132 (define-charset nil 'ipa
 133   [1 96 1 0 ?0 1 "IPA" "IPA" "IPA (International Phonetic Association)"])
 134
 135 ;; Vietnamese VISCII.  VISCII is 1-byte character set which contains
 136 ;; more than 96 characters.  Since Emacs can't handle it as one
 137 ;; character set, it is divided into two: lower case letters and upper
 138 ;; case letters.
 139 (define-charset nil 'vietnamese-viscii-lower
 140   [1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case" "VISCII1.1 lower-case"])
 141 (define-charset nil 'vietnamese-viscii-upper
 142   [1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case" "VISCII1.1 upper-case"])
 143
 144 ;; For Arabic, we need three different types of character sets.
 145 ;; Digits are of direction left-to-right and of width 1-column.
 146 ;; Others are of direction right-to-left and of width 1-column or
 147 ;; 2-column.
 148 (define-charset nil 'arabic-digit
 149   [1 94 1 0 ?2 0 "Arabic digit" "Arabic digit" "Arabic digit"])
 150 (define-charset nil 'arabic-1-column
 151   [1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column" "Arabic 1-column"])
 152 (define-charset nil 'arabic-2-column
 153   [1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column" "Arabic 2-column"])
 154
 155 ;; Ethiopic characters (Amahric and Tigrigna).
 156 (define-charset nil 'ethiopic
 157   [2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters" "Ethiopic characters"])
 158
 159 ;; Chinese CNS11643 Plane3 thru Plane7.  Although these are official
 160 ;; character sets, the use is rare and don't have to be treated
 161 ;; space-efficiently in the buffer.
 162 (define-charset nil 'chinese-cns11643-3
 163   [2 94 2 0 ?I 0 "CNS11643-3" "CNS11643-3 (Chinese traditional): ISO-IR-183"
 164      "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"])
 165 (define-charset nil 'chinese-cns11643-4
 166   [2 94 2 0 ?J 0 "CNS11643-4" "CNS11643-4 (Chinese traditional): ISO-IR-184"
 167      "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"])
 168 (define-charset nil 'chinese-cns11643-5
 169   [2 94 2 0 ?K 0 "CNS11643-5" "CNS11643-5 (Chinese traditional): ISO-IR-185"
 170      "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"])
 171 (define-charset nil 'chinese-cns11643-6
 172   [2 94 2 0 ?L 0 "CNS11643-6" "CNS11643-6 (Chinese traditional): ISO-IR-186"
 173      "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"])
 174 (define-charset nil 'chinese-cns11643-7
 175   [2 94 2 0 ?M 0 "CNS11643-7" "CNS11643-7 (Chinese traditional): ISO-IR-187"
 176      "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"])
 177
 178 ;; ASCII with right-to-left direction.
 179 (define-charset nil 'ascii-right-to-left
 180   [1 94 1 1 ?B 0 "rev ASCII" "ASCII with right-to-left direction"
 181      "ASCII (left half of ISO 8859-1) with right-to-left direction"])
 182
 183 ;; Indian scripts.  Symbolic charset for data exchange.  Glyphs are
 184 ;; not assigned.  They are automatically converted to each Indian
 185 ;; script which IS-13194 supports.
 186
 187 (define-charset nil 'indian-is13194
 188   [1 94 2 0 ?5 1 "IS 13194" "Indian IS 13194"
 189      "Generic Indian charset for data exchange with IS 13194"])
 190 ;; Actual Glyph for 2-column width.
 191 (define-charset nil 'indian-2-column
 192   [2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column"
 193      "Indian charset for 2-column width glyphs"])
 194 ;; Actual Glyph for 1-column width.
 195 (define-charset nil 'indian-1-column
 196   [2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column"
 197      "Indian charset for 2-column width glyphs"])
 198
 199 ;; Lao script.
 200 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
 201 (define-charset nil 'lao
 202   [1 94 1 0 ?1 0 "Lao" "Lao" "Lao characters (ISO10646 0E80..0EDF)"])
 203
 204 ;; Tibetan script.
 205 (define-charset nil 'tibetan
 206   [2 94 2 0 ?7 0 "Tibetan 2-col" "Tibetan 2 column" "Tibetan characters"])
 207 (define-charset nil 'tibetan-1-column
 208   [2 94 1 0 ?8 0 "Tibetan 1-col" "Tibetan 1 column" "Tibetan 1 column glyph"])
 209
 210 ;; Tell C code charset ID's of several charsets.
 211 (setup-special-charsets)
 212
 213 \f
 214 ;; These are tables for translating characters on decoding and
 215 ;; encoding.
 216 (define-translation-table
 217   'oldjis-newjis-jisroman-ascii
 218   (list (cons (make-char 'japanese-jisx0208-1978)
 219               (make-char 'japanese-jisx0208))
 220         (cons (make-char 'latin-jisx0201) (make-char 'ascii))))
 221
 222 (setq standard-translation-table-for-decode
 223       (get 'oldjis-newjis-jisroman-ascii 'translation-table))
 224
 225 (setq standard-translation-table-for-encode nil)
 226
 227 \f
 228 ;;; Make fundamental coding systems.
 229
 230 ;; Miscellaneous coding systems which can't be made by
 231 ;; `make-coding-system'.
 232
 233 (put 'no-conversion 'coding-system
 234      (vector nil ?= "Do no conversion"
 235              (list 'coding-category 'coding-category-binary
 236                    'alias-coding-systems '(no-conversion))
 237              nil))
 238 (put 'no-conversion 'eol-type 0)
 239 (put 'coding-category-binary 'coding-systems '(no-conversion))
 240 (setq coding-system-list '(no-conversion))
 241 (setq coding-system-alist '(("no-conversion")))
 242
 243 (define-coding-system-alias 'binary 'no-conversion)
 244
 245 (put 'undecided 'coding-system
 246      (vector t ?- "No conversion on encoding, automatic conversion on decoding"
 247              (list 'alias-coding-systems '(undecided)
 248                    'safe-charsets '(ascii))
 249              nil))
 250 (setq coding-system-list (cons 'undecided coding-system-list))
 251 (setq coding-system-alist (cons '("undecided") coding-system-alist))
 252 (put 'undecided 'eol-type
 253      (make-subsidiary-coding-system 'undecided))
 254
 255 (define-coding-system-alias 'dos 'undecided-dos)
 256 (define-coding-system-alias 'mac 'undecided-mac)
 257
 258 ;; Coding systems not specific to each language environment.
 259
 260 (make-coding-system
 261  'emacs-mule 0 ?=
 262  "Emacs internal format used in buffer and string"
 263  nil
 264  '((safe-charsets . t)))
 265
 266 (make-coding-system
 267  'raw-text 5 ?t
 268  "Raw text, which means text contains random 8-bit codes."
 269  nil
 270  '((safe-charsets . t)))
 271
 272 (make-coding-system
 273  'iso-2022-7bit 2 ?J
 274  "ISO 2022 based 7-bit encoding using only G0"
 275  '((ascii t) nil nil nil
 276    short ascii-eol ascii-cntl seven)
 277  '((safe-charsets . t)
 278    (composition . t)))
 279
 280 (make-coding-system
 281  'iso-2022-7bit-ss2 2 ?$
 282  "ISO 2022 based 7-bit encoding using SS2 for 96-charset"
 283  '((ascii t) nil t nil
 284    short ascii-eol ascii-cntl seven nil single-shift)
 285  '((safe-charsets . t)
 286    (composition . t)))
 287
 288 (make-coding-system
 289  'iso-2022-7bit-lock 2 ?&
 290  "ISO-2022 coding system using Locking-Shift for 96-charset"
 291  '((ascii t) t nil nil
 292    nil ascii-eol ascii-cntl seven locking-shift)
 293  '((safe-charsets . t)
 294    (composition . t)))
 295
 296 (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)
 297
 298 (make-coding-system
 299  'iso-2022-7bit-lock-ss2 2 ?i
 300  "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN"
 301  '((ascii t)
 302    (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 t)
 303    (nil chinese-cns11643-2)
 304    (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
 305         chinese-cns11643-6 chinese-cns11643-7)
 306    short ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
 307    init-bol)
 308  '((safe-charsets ascii japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
 309                   korean-ksc5601 chinese-gb2312 chinese-cns11643-1
 310                   chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4
 311                   chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7)
 312    (composition . t)))
 313
 314 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)
 315
 316 (make-coding-system
 317  'iso-2022-8bit-ss2 2 ?@
 318  "ISO 2022 based 8-bit encoding using SS2 for 96-charset"
 319  '((ascii t) nil t nil
 320    nil ascii-eol ascii-cntl nil nil single-shift)
 321  '((safe-charsets . t)
 322    (composition . t)))
 323
 324 (make-coding-system
 325  'x-ctext 2 ?x
 326  "Compound text based generic encoding for decoding unknown messages."
 327  '((ascii t) (latin-iso8859-1 t) t t
 328    nil ascii-eol ascii-cntl nil locking-shift single-shift nil nil nil
 329    init-bol nil nil)
 330  '((safe-charsets . t)
 331    (mime-charset . x-ctext)
 332    (composition . t)))
 333
 334 (make-coding-system
 335  'iso-safe 2 ?-
 336  "Convert all characters but ASCII to `?'."
 337  '(ascii nil nil nil
 338    nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil t)
 339  '((safe-charsets ascii)))
 340
 341 ;; Use iso-safe for terminal output if some other coding system is not
 342 ;; specified explicitly.
 343 (set-safe-terminal-coding-system-internal 'iso-safe)
 344
 345 ;; The other coding-systems are defined in each language specific
 346 ;; section of languages.el.
 347
 348 ;; Normally, set coding system to `undecided' before reading a file.
 349 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
 350 ;; but we regard them as containing multibyte characters.
 351 ;; Tar files are not decoded at all, but we treat them as raw bytes.
 352
 353 (setq file-coding-system-alist
 354       '(("\\.elc$" . (emacs-mule . emacs-mule))
 355         ("\\(\\`\\|/\\)loaddefs.el$" . (no-conversion . no-conversion))
 356         ("\\.tar$" . (no-conversion . no-conversion))
 357         ("" . (undecided . nil))))
 358
 359 \f
 360 ;;; Setting coding categories and their priorities.
 361
 362 ;; This setting is just to read an Emacs Lisp source files which
 363 ;; contain multilingual text while dumping Emacs.  More appropriate
 364 ;; values are set by the command `set-language-environment' for each
 365 ;; language environment.
 366
 367 (setq coding-category-emacs-mule        'emacs-mule
 368       coding-category-sjis              'japanese-shift-jis
 369       coding-category-iso-7             'iso-2022-7bit
 370       coding-category-iso-7-tight       'iso-2022-jp
 371       coding-category-iso-8-1           'iso-latin-1
 372       coding-category-iso-8-2           'iso-latin-1
 373       coding-category-iso-7-else        'iso-2022-7bit-lock
 374       coding-category-iso-8-else        'iso-2022-8bit-ss2
 375       coding-category-ccl               nil
 376       coding-category-utf-8             nil
 377       coding-category-utf-16-be         nil
 378       coding-category-utf-16-le         nil
 379       coding-category-big5              'chinese-big5
 380       coding-category-raw-text          'raw-text
 381       coding-category-binary            'no-conversion)
 382
 383 (set-coding-priority
 384  '(coding-category-iso-8-1
 385    coding-category-iso-8-2
 386    coding-category-iso-7-tight
 387    coding-category-iso-7
 388    coding-category-iso-7-else
 389    coding-category-iso-8-else
 390    coding-category-emacs-mule
 391    coding-category-raw-text
 392    coding-category-sjis
 393    coding-category-big5
 394    coding-category-ccl
 395    coding-category-binary
 396    coding-category-utf-16-be
 397    coding-category-utf-16-le
 398    coding-category-utf-8))
 399
 400 \f
 401 ;;; Miscellaneous settings.
 402 (aset latin-extra-code-table ?\222 t)
 403
 404 (update-coding-systems-internal)
 405
 406 ;;; mule-conf.el ends here