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 ;; effectively in the aspect of memory in a buffer.
  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 "Latin-1" "ISO8859-1 (Latin-1)" "ISO8859-1 (Latin-1)"])
  46 (define-charset 130 'latin-iso8859-2
  47   [1 96 1 0 ?B 1 "Latin-2" "ISO8859-2 (Latin-2)" "ISO8859-2 (Latin-2)"])
  48 (define-charset 131 'latin-iso8859-3
  49   [1 96 1 0 ?C 1 "Latin-3" "ISO8859-3 (Latin-3)" "ISO8859-3 (Latin-3)"])
  50 (define-charset 132 'latin-iso8859-4
  51   [1 96 1 0 ?D 1 "Latin-4" "ISO8859-4 (Latin-4)" "ISO8859-4 (Latin-4)"])
  52 (define-charset 133 'thai-tis620
  53   [1 96 1 0 ?T 1 "TIS620" "TIS620 (Thai)" "TIS620.2529 (Thai)"])
  54 (define-charset 134 'greek-iso8859-7
  55   [1 96 1 0 ?F 1 "ISO8859-7" "ISO8859-7 (Greek)" "ISO8859-7 (Greek)"])
  56 (define-charset 135 'arabic-iso8859-6
  57   [1 96 1 1 ?G 1 "ISO8859-6" "ISO8859-6 (Arabic)" "ISO8859-6 (Arabic)"])
  58 (define-charset 136 'hebrew-iso8859-8
  59   [1 96 1 1 ?H 1 "ISO8859-8" "ISO8859-8 (Hebrew)" "ISO8859-8 (Hebrew)"])
  60 (define-charset 137 'katakana-jisx0201
  61   [1 94 1 0 ?I 1 "JISX0201 Kana" "JISX0201.1976 (Japanese Kana)"
  62      "JISX0201.1976 Japanese Kana"])
  63 (define-charset 138 'latin-jisx0201
  64   [1 94 1 0 ?J 0 "JISX0201 Roman" "JISX0201.1976 (Japanese Roman)"
  65      "JISX0201.1976 Japanese Roman"])
  66 (define-charset 140 'cyrillic-iso8859-5
  67   [1 96 1 0 ?L 1 "ISO8859-5" "ISO8859-5 (Cyrillic)"
  68      "ISO8859-5 (Cyrillic)"])
  69 (define-charset 141 'latin-iso8859-9
  70   [1 96 1 0 ?M 1 "Latin-5" "ISO8859-9 (Latin-5)" "ISO8859-9 (Latin-5)"])
  71 (define-charset 144 'japanese-jisx0208-1978
  72   [2 94 2 0 ?@ 0 "JISX0208.1978" "JISX0208.1978 (Japanese)"
  73      "JISX0208.1978 Japanese Kanji (so called \"old JIS\")"])
  74 (define-charset 145 'chinese-gb2312
  75   [2 94 2 0 ?A 0 "GB2312" "GB2312" "GB2312 Chinese simplified"])
  76 (define-charset 146 'japanese-jisx0208
  77   [2 94 2 0 ?B 0 "JISX0208" "JISX0208.1983/1990 (Japanese)"
  78      "JISX0208.1983/1990 Japanese Kanji"])
  79 (define-charset 147 'korean-ksc5601
  80   [2 94 2 0 ?C 0 "KSC5601" "KSC5601 (Korean)"
  81      "KSC5601 Korean Hangul and Hanja"])
  82 (define-charset 148 'japanese-jisx0212
  83   [2 94 2 0 ?D 0 "JISX0212" "JISX0212 (Japanese)"
  84      "JISX0212 Japanese supplement"])
  85 (define-charset 149 'chinese-cns11643-1
  86   [2 94 2 0 ?G 0 "CNS11643-1" "CNS11643-1 (Chinese traditional)"
  87      "CNS11643 Plane 1 Chinese traditional"])
  88 (define-charset 150 'chinese-cns11643-2
  89   [2 94 2 0 ?H 0 "CNS11643-2" "CNS11643-2 (Chinese traditional)"
  90      "CNS11643 Plane 2 Chinese traditional"])
  91 (define-charset 152 'chinese-big5-1
  92   [2 94 2 0 ?0 0 "Big5" "Big5 (Level-1)"
  93      "Big5 Level-1 Chinese traditional"])
  94 (define-charset 153 'chinese-big5-2
  95   [2 94 2 0 ?1 0 "Big5" "Big5 (Level-2)"
  96      "Big5 Level-2 Chinese traditional"])
  97
  98 ;; Additional (private) character sets.  These character sets are
  99 ;; treated less effectively in the aspect of memory in a buffer.
 100
 101 ;; Syntax:
 102 ;; (define-charset nil CHARSET
 103 ;;   [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
 104 ;;     SHORT-NAME LONG-NAME DESCRIPTION ])
 105
 106 ;; ISO-2022 allows a use of character sets not registered in ISO with
 107 ;; final characters `0' (0x30) through `?' (0x3F).  Among them, Emacs
 108 ;; reserves `0' through `9' to support several private character sets.
 109 ;; The remaining final characters `:' through `?' are for users.
 110
 111 (define-charset nil 'chinese-sisheng
 112   [1 94 1 0 ?0 0 "SiSheng" "SiSheng (PinYin/ZhuYin)"
 113      "SiSheng characters for PinYin/ZhuYin"])
 114
 115 ;; IPA characters for phonetic symbols.
 116 (define-charset nil 'ipa
 117   [1 96 1 0 ?0 1 "IPA" "IPA" "IPA (International Phonetic Association)"])
 118
 119 ;; Vietnamese VISCII.  VISCII is 1-byte character set which contains
 120 ;; more than 96 characters.  Since Emacs can't handle it as one
 121 ;; character set, it is divided into two: lower case letters and upper
 122 ;; case letters.
 123 (define-charset nil 'vietnamese-viscii-lower
 124   [1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case" "VISCII1.1 lower-case"])
 125 (define-charset nil 'vietnamese-viscii-upper
 126   [1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case" "VISCII1.1 upper-case"])
 127
 128 ;; For Arabic, we need three different types of character sets.
 129 ;; Digits are of direction left-to-right and of width 1-column.
 130 ;; Others are of direction right-to-left and of width 1-column or
 131 ;; 2-column.
 132 (define-charset nil 'arabic-digit
 133   [1 94 1 0 ?2 0 "Arabic digit" "Arabic digit" "Arabic digit"])
 134 (define-charset nil 'arabic-1-column
 135   [1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column" "Arabic 1-column"])
 136 (define-charset nil 'arabic-2-column
 137   [1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column" "Arabic 2-column"])
 138
 139 ;; Ethiopic characters (Amahric and Tigrigna).
 140 (define-charset nil 'ethiopic
 141   [2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters" "Ethiopic characters"])
 142
 143 ;; Chinese CNS11643 Plane3 thru Plane7.  Although these are official
 144 ;; character sets, the use is rare and don't have to be treated
 145 ;; effectively in the aspect of memory in a buffer.
 146 (define-charset nil 'chinese-cns11643-3
 147   [2 94 2 0 ?I 0 "CNS11643-3" "CNS11643-3 (Chinese traditional)"
 148      "CNS11643 Plane 3 Chinese Traditional"])
 149 (define-charset nil 'chinese-cns11643-4
 150   [2 94 2 0 ?J 0 "CNS11643-4" "CNS11643-4 (Chinese traditional)"
 151      "CNS11643 Plane 4 Chinese Traditional"])
 152 (define-charset nil 'chinese-cns11643-5
 153   [2 94 2 0 ?K 0 "CNS11643-5" "CNS11643-5 (Chinese traditional)"
 154      "CNS11643 Plane 5 Chinese Traditional"])
 155 (define-charset nil 'chinese-cns11643-6
 156   [2 94 2 0 ?L 0 "CNS11643-6" "CNS11643-6 (Chinese traditional)"
 157      "CNS11643 Plane 6 Chinese Traditional"])
 158 (define-charset nil 'chinese-cns11643-7
 159   [2 94 2 0 ?M 0 "CNS11643-7" "CNS11643-7 (Chinese traditional)"
 160      "CNS11643 Plane 7 Chinese Traditional"])
 161
 162 ;; ASCII with right-to-left direction.
 163 (define-charset nil 'ascii-right-to-left
 164   [1 94 1 1 ?B 0 "rev ASCII" "ASCII with right-to-left direction"
 165      "ASCII (left half of ISO8859-1) with right-to-left direction"])
 166
 167 ;; Indian scripts.  Symbolic charset for data exchange.  Glyphs are
 168 ;; not assigned.  They are automatically converted to each Indian
 169 ;; script which IS-13194 supports.
 170
 171 (define-charset nil 'indian-is13194
 172   [1 94 2 0 ?5 1 "IS 13194" "Indian IS 13194"
 173      "Generic Indian charset for data exchange with IS 13194"])
 174 ;; Actual Glyph for 2-column width.
 175 (define-charset nil 'indian-2-column
 176   [2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column"
 177      "Indian charset for 2-column width glyphs"])
 178 ;; Actual Glyph for 1-column width.
 179 (define-charset nil 'indian-1-column
 180   [2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column"
 181      "Indian charset for 2-column width glyphs"])
 182
 183 ;; Lao script.
 184 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
 185 (define-charset nil 'lao
 186   [1 94 1 0 ?1 0 "Lao" "Lao" "Lao characters (ISO10646 0E80..0EDF)"])
 187
 188 ;; Tibetan script.
 189 (define-charset nil 'tibetan
 190   [2 94 2 0 ?7 0 "Tibetan 2-col" "Tibetan 2 column" "Tibetan characters"])
 191 (define-charset nil 'tibetan-1-column
 192   [2 94 1 0 ?8 0 "Tibetan 1-col" "Tibetan 1 column" "Tibetan 1 column glyph"])
 193
 194 ;; Tell C code charset ID's of several charsets.
 195 (setup-special-charsets)
 196
 197 \f
 198 ;; These are tables for translating characters on decoding and
 199 ;; encoding.
 200 (define-translation-table
 201   'oldjis-newjis-jisroman-ascii
 202   (list (cons (make-char 'japanese-jisx0208-1978)
 203               (make-char 'japanese-jisx0208))
 204         (cons (make-char 'latin-jisx0201) (make-char 'ascii))))
 205
 206 (setq standard-translation-table-for-decode
 207       (get 'oldjis-newjis-jisroman-ascii 'translation-table))
 208
 209 (setq standard-translation-table-for-encode nil)
 210
 211 \f
 212 ;;; Make fundamental coding systems.
 213
 214 ;; Miscellaneous coding systems which can't be made by
 215 ;; `make-coding-system'.
 216
 217 (put 'no-conversion 'coding-system
 218      (vector nil ?= "Do no conversion"
 219              (list 'coding-category 'coding-category-binary
 220                    'alias-coding-systems '(no-conversion))
 221              nil))
 222 (put 'no-conversion 'eol-type 0)
 223 (put 'coding-category-binary 'coding-systems '(no-conversion))
 224 (setq coding-system-list '(no-conversion))
 225 (setq coding-system-alist '(("no-conversion")))
 226
 227 (define-coding-system-alias 'binary 'no-conversion)
 228
 229 (put 'undecided 'coding-system
 230      (vector t ?- "No conversion on encoding, automatic conversion on decoding"
 231              (list 'alias-coding-systems '(undecided)
 232                    'safe-charsets '(ascii))
 233              nil))
 234 (setq coding-system-list (cons 'undecided coding-system-list))
 235 (setq coding-system-alist (cons '("undecided") coding-system-alist))
 236 (put 'undecided 'eol-type
 237      (make-subsidiary-coding-system 'undecided))
 238
 239 (define-coding-system-alias 'dos 'undecided-dos)
 240 (define-coding-system-alias 'mac 'undecided-mac)
 241
 242 ;; Coding systems not specific to each language environment.
 243
 244 (make-coding-system
 245  'emacs-mule 0 ?=
 246  "Emacs internal format used in buffer and string"
 247  nil
 248  '((safe-charsets . t)))
 249
 250 (make-coding-system
 251  'raw-text 5 ?t
 252  "Raw text, which means text contains random 8-bit codes."
 253  nil
 254  '((safe-charsets . t)))
 255
 256 (make-coding-system
 257  'iso-2022-7bit 2 ?J
 258  "ISO 2022 based 7-bit encoding using only G0"
 259  '((ascii t) nil nil nil
 260    short ascii-eol ascii-cntl seven)
 261  '((safe-charsets . t)))
 262
 263 (make-coding-system
 264  'iso-2022-7bit-ss2 2 ?$
 265  "ISO 2022 based 7-bit encoding using SS2 for 96-charset"
 266  '((ascii t) nil t nil
 267    short ascii-eol ascii-cntl seven nil single-shift)
 268  '((safe-charsets . t)))
 269
 270 (make-coding-system
 271  'iso-2022-7bit-lock 2 ?&
 272  "ISO-2022 coding system using Locking-Shift for 96-charset"
 273  '((ascii t) t nil nil
 274    nil ascii-eol ascii-cntl seven locking-shift)
 275  '((safe-charsets . t)))
 276
 277 (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)
 278
 279 (make-coding-system
 280  'iso-2022-7bit-lock-ss2 2 ?i
 281  "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN"
 282  '((ascii t)
 283    (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 t)
 284    (nil chinese-cns11643-2)
 285    (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
 286         chinese-cns11643-6 chinese-cns11643-7)
 287    short ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
 288    init-bol)
 289  '((safe-charsets ascii japanesejisx0208 japanese-jisx0208-1978 latin-jisx0201
 290                   korean-ksc5601 chinese-gb2312 chinese-cns11643-1
 291                   chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4
 292                   chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7)))
 293
 294 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)
 295
 296 (make-coding-system
 297  'iso-2022-8bit-ss2 2 ?@
 298  "ISO 2022 based 8-bit encoding using SS2 for 96-charset"
 299  '((ascii t) nil t nil
 300    nil ascii-eol ascii-cntl nil nil single-shift)
 301  '((safe-charsets . t)))
 302
 303 (make-coding-system
 304  'iso-safe 2 ?-
 305  "Convert all characters but ASCII to `?'."
 306  '(ascii nil nil nil
 307    nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil t)
 308  '((safe-charsets ascii)))
 309
 310 ;; Use iso-safe for terminal output if some other coding system is not
 311 ;; specified explicitly.
 312 (set-safe-terminal-coding-system-internal 'iso-safe)
 313
 314 ;; The other coding-systems are defined in each language specific
 315 ;; section of languages.el.
 316
 317 ;; Normally, set coding system to `undecided' before reading a file.
 318 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
 319 ;; but we regard them as containing multibyte characters.
 320 ;; Tar files are not decoded at all, but we treat them as raw bytes.
 321
 322 (setq file-coding-system-alist
 323       '(("\\.elc$" . (emacs-mule . emacs-mule))
 324         ("\\(\\`\\|/\\)loaddefs.el$" . (no-conversion . no-conversion))
 325         ("\\.tar$" . (no-conversion . no-conversion))
 326         ("" . (undecided . nil))))
 327
 328 \f
 329 ;;; Setting coding categories and their priorities.
 330
 331 ;; This setting is just to read an Emacs Lisp source files which
 332 ;; contain multilingual text while dumping Emacs.  More appropriate
 333 ;; values are set by the command `set-language-environment' for each
 334 ;; language environment.
 335
 336 (setq coding-category-emacs-mule        'emacs-mule
 337       coding-category-sjis              'japanese-shift-jis
 338       coding-category-iso-7             'iso-2022-7bit
 339       coding-category-iso-7-tight       'iso-2022-jp
 340       coding-category-iso-8-1           'iso-latin-1
 341       coding-category-iso-8-2           'iso-latin-1
 342       coding-category-iso-7-else        'iso-2022-7bit-lock
 343       coding-category-iso-8-else        'iso-2022-8bit-ss2
 344       coding-category-ccl               nil
 345       coding-category-big5              'chinese-big5
 346       coding-category-raw-text          'raw-text
 347       coding-category-binary            'no-conversion)
 348
 349 (set-coding-priority
 350  '(coding-category-iso-8-1
 351    coding-category-iso-8-2
 352    coding-category-iso-7-tight
 353    coding-category-iso-7
 354    coding-category-iso-7-else
 355    coding-category-iso-8-else
 356    coding-category-emacs-mule
 357    coding-category-raw-text
 358    coding-category-sjis
 359    coding-category-big5
 360    coding-category-ccl
 361    coding-category-binary))
 362
 363 \f
 364 ;;; Miscellaneous settings.
 365 (aset latin-extra-code-table ?\222 t)
 366
 367 (update-coding-systems-internal)
 368
 369 ;;; mule-conf.el ends here