1 ;;; mule-conf.el --- configure multilingual environment
3 ;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN.
4 ;; Licensed to the Free Software Foundation.
6 ;; Keywords: mule, multilingual, character set, coding system
8 ;; This file is part of GNU Emacs.
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)
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.
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.
27 ;; Don't byte-compile this file.
31 ;;; Definitions of character sets.
33 ;; Basic (official) character sets. These character sets are treated
34 ;; efficiently with respect to buffer memory.
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)"])
44 ;; 1-byte charsets. Valid range of CHARSET-ID is 128..143.
46 ;; CHARSET-ID 128 is not used.
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"])
79 ;; CHARSET-ID is not used 139.
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)"
92 "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14)"])
94 ;; 2-byte charsets. Valid range of CHARSET-ID is 144..153.
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)"])
126 ;; Additional (private) character sets. These character sets are
127 ;; treated less space-efficiently in the buffer.
130 ;; (define-charset CHARSET-ID CHARSET
131 ;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
132 ;; SHORT-NAME LONG-NAME DESCRIPTION ])
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.
139 ;; 1-byte 1-column charsets. Valid range of CHARSET-ID is 160..223.
141 (define-charset 160 'chinese-sisheng
142 [1 94 1 0 ?0 0 "SiSheng" "SiSheng (PinYin/ZhuYin)"
143 "SiSheng characters for PinYin/ZhuYin"])
145 ;; IPA characters for phonetic symbols.
146 (define-charset 161 'ipa
147 [1 96 1 0 ?0 1 "IPA" "IPA" "IPA (International Phonetic Association)"])
149 ;; Vietnamese VISCII. VISCII is 1-byte character set which contains
150 ;; more than 96 characters. Since Emacs can't handle it as one
151 ;; character set, it is divided into two: lower case letters and upper
153 (define-charset 162 'vietnamese-viscii-lower
154 [1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case" "VISCII1.1 lower-case"])
155 (define-charset 163 'vietnamese-viscii-upper
156 [1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case" "VISCII1.1 upper-case"])
158 ;; For Arabic, we need three different types of character sets.
159 ;; Digits are of direction left-to-right and of width 1-column.
160 ;; Others are of direction right-to-left and of width 1-column or
162 (define-charset 164 'arabic-digit
163 [1 94 1 0 ?2 0 "Arabic digit" "Arabic digit" "Arabic digit"])
164 (define-charset 165 'arabic-1-column
165 [1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column" "Arabic 1-column"])
167 ;; ASCII with right-to-left direction.
168 (define-charset 166 'ascii-right-to-left
169 [1 94 1 1 ?B 0 "rev ASCII" "ASCII with right-to-left direction"
170 "ASCII (left half of ISO 8859-1) with right-to-left direction"])
173 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
174 (define-charset 167 'lao
175 [1 94 1 0 ?1 0 "Lao" "Lao" "Lao characters (ISO10646 0E80..0EDF)"])
177 ;; CHARSET-IDs 168..223 are not used.
179 ;; 1-byte 2-column charsets. Valid range of CHARSET-ID is 224..239.
181 (define-charset 224 'arabic-2-column
182 [1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column" "Arabic 2-column"])
184 ;; Indian scripts. Symbolic charset for data exchange. Glyphs are
185 ;; not assigned. They are automatically converted to each Indian
186 ;; script which IS-13194 supports.
188 (define-charset 225 'indian-is13194
189 [1 94 2 0 ?5 1 "IS 13194" "Indian IS 13194"
190 "Generic Indian charset for data exchange with IS 13194"])
192 ;; CHARSET-IDs 226..239 are not used.
194 (define-charset 240 'indian-glyph
195 [2 96 1 0 ?4 0 "Indian glyph" "Indian glyph"
196 "Glyphs for Indian characters."])
197 ;; 240 used to be [2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column"]
199 ;; 2-byte 1-column charsets. Valid range of CHARSET-ID is 240..244.
201 ;; Actual Glyph for 1-column width.
202 (define-charset 241 'tibetan-1-column
203 [2 94 1 0 ?8 0 "Tibetan 1-col" "Tibetan 1 column" "Tibetan 1 column glyph"])
205 ;; Subsets of Unicode.
207 (define-charset 242 'mule-unicode-2500-33ff
208 [2 96 1 0 ?2 0 "Unicode subset 2" "Unicode subset (U+2500..U+33FF)"
209 "Unicode characters of the range U+2500..U+33FF."])
211 (define-charset 243 'mule-unicode-e000-ffff
212 [2 96 1 0 ?3 0 "Unicode subset 3" "Unicode subset (U+E000+FFFF)"
213 "Unicode characters of the range U+E000..U+FFFF."])
215 (define-charset 244 'mule-unicode-0100-24ff
216 [2 96 1 0 ?1 0 "Unicode subset" "Unicode subset (U+0100..U+24FF)"
217 "Unicode characters of the range U+0100..U+24FF."])
219 ;; 2-byte 2-column charsets. Valid range of CHARSET-ID is 245..254.
221 ;; Ethiopic characters (Amahric and Tigrigna).
222 (define-charset 245 'ethiopic
223 [2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters" "Ethiopic characters"])
225 ;; Chinese CNS11643 Plane3 thru Plane7. Although these are official
226 ;; character sets, the use is rare and don't have to be treated
227 ;; space-efficiently in the buffer.
228 (define-charset 246 'chinese-cns11643-3
229 [2 94 2 0 ?I 0 "CNS11643-3" "CNS11643-3 (Chinese traditional): ISO-IR-183"
230 "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"])
231 (define-charset 247 'chinese-cns11643-4
232 [2 94 2 0 ?J 0 "CNS11643-4" "CNS11643-4 (Chinese traditional): ISO-IR-184"
233 "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"])
234 (define-charset 248 'chinese-cns11643-5
235 [2 94 2 0 ?K 0 "CNS11643-5" "CNS11643-5 (Chinese traditional): ISO-IR-185"
236 "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"])
237 (define-charset 249 'chinese-cns11643-6
238 [2 94 2 0 ?L 0 "CNS11643-6" "CNS11643-6 (Chinese traditional): ISO-IR-186"
239 "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"])
240 (define-charset 250 'chinese-cns11643-7
241 [2 94 2 0 ?M 0 "CNS11643-7" "CNS11643-7 (Chinese traditional): ISO-IR-187"
242 "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"])
244 ;; Actual Glyph for 2-column width.
245 (define-charset 251 'indian-2-column
246 [2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column"
247 "Indian charset for 2-column width glyphs"])
248 ;; old indian-1-column characters will be translated to indian-2-column.
249 (declare-equiv-charset 2 94 ?6 'indian-2-column)
252 (define-charset 252 'tibetan
253 [2 94 2 0 ?7 0 "Tibetan 2-col" "Tibetan 2 column" "Tibetan characters"])
255 ;; CHARSET-ID 253 is not used.
258 (define-charset 254 'japanese-jisx0213-2
259 [2 94 2 0 ?P 0 "JISX0213-2" "JISX0213-2" "JISX0213 Plane 2 (Japanese)"])
261 ;; Tell C code charset ID's of several charsets.
262 (setup-special-charsets)
265 ;; These are tables for translating characters on decoding and
267 (define-translation-table
268 'oldjis-newjis-jisroman-ascii
269 (list (cons (make-char 'japanese-jisx0208-1978)
270 (make-char 'japanese-jisx0208))
271 (cons (make-char 'latin-jisx0201) (make-char 'ascii))))
272 (aset (get 'oldjis-newjis-jisroman-ascii 'translation-table)
273 (make-char 'latin-jisx0201 92) (make-char 'latin-jisx0201 92))
274 (aset (get 'oldjis-newjis-jisroman-ascii 'translation-table)
275 (make-char 'latin-jisx0201 126) (make-char 'latin-jisx0201 126))
277 (setq standard-translation-table-for-decode
278 (get 'oldjis-newjis-jisroman-ascii 'translation-table))
280 (setq standard-translation-table-for-encode nil)
283 ;;; Make fundamental coding systems.
285 ;; Miscellaneous coding systems which can't be made by
286 ;; `make-coding-system'.
288 (put 'no-conversion 'coding-system
289 (vector nil ?= "Do no conversion.
291 When you visit a file with this coding, the file is read into a
292 unibyte buffer as is, thus each byte of a file is treated as a
294 (list 'coding-category 'coding-category-binary
295 'alias-coding-systems '(no-conversion))
297 (put 'no-conversion 'eol-type 0)
298 (put 'coding-category-binary 'coding-systems '(no-conversion))
299 (setq coding-system-list '(no-conversion))
300 (setq coding-system-alist '(("no-conversion")))
301 (register-char-codings 'no-conversion t)
303 (define-coding-system-alias 'binary 'no-conversion)
305 (put 'undecided 'coding-system
306 (vector t ?- "No conversion on encoding, automatic conversion on decoding"
307 (list 'alias-coding-systems '(undecided)
308 'safe-charsets '(ascii))
310 (setq coding-system-list (cons 'undecided coding-system-list))
311 (setq coding-system-alist (cons '("undecided") coding-system-alist))
312 (put 'undecided 'eol-type
313 (make-subsidiary-coding-system 'undecided))
315 (define-coding-system-alias 'unix 'undecided-unix)
316 (define-coding-system-alias 'dos 'undecided-dos)
317 (define-coding-system-alias 'mac 'undecided-mac)
319 ;; Coding systems not specific to each language environment.
323 "Emacs internal format used in buffer and string.
325 Encoding text with this coding system produces the actual byte
326 sequence of the text in buffers and strings. An exception is made for
327 eight-bit-control characters. Each of them is encoded into a single
330 '((safe-charsets . t)))
334 "Raw text, which means text contains random 8-bit codes.
335 Encoding text with this coding system produces the actual byte
336 sequence of the text in buffers and strings. An exception is made for
337 eight-bit-control characters. Each of them is encoded into a single
340 When you visit a file with this coding, the file is read into a
341 unibyte buffer as is (except for EOL format), thus each byte of a file
342 is treated as a character."
344 '((safe-charsets . t)))
348 "ISO 2022 based 7-bit encoding using only G0"
349 '((ascii t) nil nil nil
350 short ascii-eol ascii-cntl seven)
351 '((safe-charsets . t)
355 'iso-2022-7bit-ss2 2 ?$
356 "ISO 2022 based 7-bit encoding using SS2 for 96-charset"
357 '((ascii t) nil t nil
358 short ascii-eol ascii-cntl seven nil single-shift)
359 '((safe-charsets . t)
363 'iso-2022-7bit-lock 2 ?&
364 "ISO-2022 coding system using Locking-Shift for 96-charset"
365 '((ascii t) t nil nil
366 nil ascii-eol ascii-cntl seven locking-shift)
367 '((safe-charsets . t)
370 (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)
373 'iso-2022-7bit-lock-ss2 2 ?i
374 "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN"
376 (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 t)
377 (nil chinese-cns11643-2)
378 (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
379 chinese-cns11643-6 chinese-cns11643-7)
380 short ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
382 '((safe-charsets ascii japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
383 korean-ksc5601 chinese-gb2312 chinese-cns11643-1
384 chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4
385 chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7)
388 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)
391 'iso-2022-8bit-ss2 2 ?@
392 "ISO 2022 based 8-bit encoding using SS2 for 96-charset"
393 '((ascii t) nil t nil
394 nil ascii-eol ascii-cntl nil nil single-shift)
395 '((safe-charsets . t)
400 "Compound text based generic encoding for decoding unknown messages."
401 '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) t t
402 nil ascii-eol ascii-cntl nil locking-shift single-shift nil nil nil
404 '((safe-charsets . t)
405 (mime-charset . x-ctext)
408 (define-coding-system-alias 'x-ctext 'compound-text)
409 (define-coding-system-alias 'ctext 'compound-text)
413 "Convert all characters but ASCII to `?'."
415 nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil t)
416 '((safe-charsets ascii)))
418 ;; Use iso-safe for terminal output if some other coding system is not
419 ;; specified explicitly.
420 (set-safe-terminal-coding-system-internal 'iso-safe)
422 ;; The other coding-systems are defined in each language specific
423 ;; section of languages.el.
425 ;; Normally, set coding system to `undecided' before reading a file.
426 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
427 ;; but we regard them as containing multibyte characters.
428 ;; Tar files are not decoded at all, but we treat them as raw bytes.
430 (setq file-coding-system-alist
431 '(("\\.elc\\'" . (emacs-mule . emacs-mule))
432 ;; We use raw-text for reading loaddefs.el so that if it
433 ;; happens to have DOS or Mac EOLs, they are converted to
434 ;; newlines. This is required to make the special treatment
435 ;; of the "\ newline" combination in loaddefs.el, which marks
436 ;; the beginning of a doc string, work.
437 ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix))
438 ("\\.tar\\'" . (no-conversion . no-conversion))
439 ("" . (undecided . nil))))
442 ;;; Setting coding categories and their priorities.
444 ;; This setting is just to read an Emacs Lisp source files which
445 ;; contain multilingual text while dumping Emacs. More appropriate
446 ;; values are set by the command `set-language-environment' for each
447 ;; language environment.
449 (setq coding-category-emacs-mule 'emacs-mule
450 coding-category-sjis 'japanese-shift-jis
451 coding-category-iso-7 'iso-2022-7bit
452 coding-category-iso-7-tight 'iso-2022-jp
453 coding-category-iso-8-1 'iso-latin-1
454 coding-category-iso-8-2 'iso-latin-1
455 coding-category-iso-7-else 'iso-2022-7bit-lock
456 coding-category-iso-8-else 'iso-2022-8bit-ss2
457 coding-category-ccl nil
458 coding-category-utf-8 'mule-utf-8
459 coding-category-utf-16-be nil
460 coding-category-utf-16-le nil
461 coding-category-big5 'chinese-big5
462 coding-category-raw-text 'raw-text
463 coding-category-binary 'no-conversion)
466 '(coding-category-iso-8-1
467 coding-category-iso-8-2
468 coding-category-iso-7-tight
469 coding-category-iso-7
470 coding-category-iso-7-else
471 coding-category-iso-8-else
472 coding-category-emacs-mule
473 coding-category-raw-text
477 coding-category-binary
478 coding-category-utf-8
479 coding-category-utf-16-be
480 coding-category-utf-16-le))
483 ;;; Miscellaneous settings.
484 (aset latin-extra-code-table ?\222 t)
485 (aset latin-extra-code-table ?\223 t)
486 (aset latin-extra-code-table ?\224 t)
488 (update-coding-systems-internal)
490 ;;; mule-conf.el ends here