Commit | Line | Data |
---|---|---|
08c19a27 KH |
1 | ;;; mule-conf.el --- configure multilingual environment |
2 | ||
08c19a27 | 3 | ;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN. |
fa526c4a | 4 | ;; Licensed to the Free Software Foundation. |
08c19a27 KH |
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 | |
2aa72de7 | 124 | [1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case" "VISCII1.1 lower-case"]) |
08c19a27 | 125 | (define-charset nil 'vietnamese-viscii-upper |
2aa72de7 | 126 | [1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case" "VISCII1.1 upper-case"]) |
08c19a27 KH |
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 | |
2aa72de7 | 133 | [1 94 1 0 ?2 0 "Arabic digit" "Arabic digit" "Arabic digit"]) |
08c19a27 | 134 | (define-charset nil 'arabic-1-column |
2aa72de7 | 135 | [1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column" "Arabic 1-column"]) |
08c19a27 | 136 | (define-charset nil 'arabic-2-column |
2aa72de7 | 137 | [1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column" "Arabic 2-column"]) |
08c19a27 KH |
138 | |
139 | ;; Ethiopic characters (Amahric and Tigrigna). | |
140 | (define-charset nil 'ethiopic | |
d2382a1d | 141 | [2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters" "Ethiopic characters"]) |
08c19a27 KH |
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 | |
2aa72de7 | 176 | [2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column" |
08c19a27 KH |
177 | "Indian charset for 2-column width glyphs"]) |
178 | ;; Actual Glyph for 1-column width. | |
179 | (define-charset nil 'indian-1-column | |
2aa72de7 | 180 | [2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column" |
49733613 | 181 | "Indian charset for 2-column width glyphs"]) |
08c19a27 KH |
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 | ||
2aa72de7 KH |
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 | ||
85f789f7 KH |
194 | ;; Tell C code charset ID's of several charsets. |
195 | (setup-special-charsets) | |
08c19a27 | 196 | |
85f789f7 | 197 | \f |
d2a1ee18 KH |
198 | ;; These are tables for translating characters on decoding and |
199 | ;; encoding. | |
200 | (define-character-translation-table | |
40e98681 KH |
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 | ||
d2a1ee18 KH |
206 | (setq standard-character-translation-table-for-decode |
207 | (get 'oldjis-newjis-jisroman-ascii 'character-translation-table)) | |
08c19a27 | 208 | |
d2a1ee18 | 209 | (setq standard-character-translation-table-for-encode nil) |
08c19a27 KH |
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 | |
3fcbab9a KH |
218 | (vector nil ?= "Do no conversion" |
219 | (list 'coding-category 'coding-category-binary | |
220 | 'alias-coding-systems '(no-conversion)) | |
221 | nil)) | |
08c19a27 | 222 | (put 'no-conversion 'eol-type 0) |
3fcbab9a KH |
223 | (put 'coding-category-binary 'coding-systems '(no-conversion)) |
224 | (setq coding-system-list '(no-conversion)) | |
225 | (setq coding-system-alist '(("no-conversion"))) | |
08c19a27 | 226 | |
8da035d0 RS |
227 | (define-coding-system-alias 'binary 'no-conversion) |
228 | ||
426591c3 | 229 | (put 'undecided 'coding-system |
76810f60 | 230 | (vector t ?- "No conversion on encoding, automatic conversion on decoding" |
3fcbab9a KH |
231 | (list 'alias-coding-systems '(undecided)) |
232 | nil)) | |
233 | (setq coding-system-list (cons 'undecided coding-system-list)) | |
234 | (setq coding-system-alist (cons '("undecided") coding-system-alist)) | |
426591c3 | 235 | (put 'undecided 'eol-type |
3fcbab9a | 236 | (make-subsidiary-coding-system 'undecided)) |
08c19a27 KH |
237 | |
238 | ;; Coding systems not specific to each language environment. | |
239 | ||
240 | (make-coding-system | |
426591c3 | 241 | 'emacs-mule 0 ?= |
fec0e02d | 242 | "Emacs internal format used in buffer and string" |
40e98681 KH |
243 | nil |
244 | '((safe-charsets . t))) | |
08c19a27 | 245 | |
2cb30410 KH |
246 | (make-coding-system |
247 | 'raw-text 5 ?t | |
fec0e02d | 248 | "Raw text, which means text contains random 8-bit codes." |
40e98681 KH |
249 | nil |
250 | '((safe-charsets . t))) | |
2cb30410 | 251 | |
08c19a27 | 252 | (make-coding-system |
4951a271 KH |
253 | 'iso-2022-7bit 2 ?J |
254 | "ISO 2022 based 7-bit encoding using only G0" | |
08c19a27 | 255 | '((ascii t) nil nil nil |
fec0e02d | 256 | short ascii-eol ascii-cntl seven) |
40e98681 | 257 | '((safe-charsets . t))) |
08c19a27 KH |
258 | |
259 | (make-coding-system | |
2792ce16 | 260 | 'iso-2022-7bit-ss2 2 ?$ |
4951a271 KH |
261 | "ISO 2022 based 7-bit encoding using SS2 for 96-charset" |
262 | '((ascii t) nil t nil | |
fec0e02d | 263 | short ascii-eol ascii-cntl seven nil single-shift) |
40e98681 | 264 | '((safe-charsets . t))) |
4951a271 KH |
265 | |
266 | (make-coding-system | |
2792ce16 | 267 | 'iso-2022-7bit-lock 2 ?& |
4951a271 KH |
268 | "ISO-2022 coding system using Locking-Shift for 96-charset" |
269 | '((ascii t) t nil nil | |
fec0e02d | 270 | nil ascii-eol ascii-cntl seven locking-shift) |
40e98681 | 271 | '((safe-charsets . t))) |
4951a271 | 272 | |
2e21aa27 | 273 | (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock) |
08c19a27 KH |
274 | |
275 | (make-coding-system | |
4951a271 | 276 | 'iso-2022-7bit-lock-ss2 2 ?i |
d0c5d809 | 277 | "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN" |
08c19a27 KH |
278 | '((ascii t) |
279 | (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 t) | |
280 | (nil chinese-cns11643-2) | |
281 | (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5 | |
282 | chinese-cns11643-6 chinese-cns11643-7) | |
d0c5d809 | 283 | short ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil |
fec0e02d | 284 | init-bol) |
40e98681 KH |
285 | '((safe-charsets ascii japanesejisx0208 japanese-jisx0208-1978 latin-jisx0201 |
286 | korean-ksc5601 chinese-gb2312 chinese-cns11643-1 | |
287 | chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4 | |
288 | chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7))) | |
08c19a27 | 289 | |
2e21aa27 | 290 | (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2) |
08c19a27 KH |
291 | |
292 | (make-coding-system | |
4951a271 KH |
293 | 'iso-2022-8bit-ss2 2 ?@ |
294 | "ISO 2022 based 8-bit encoding using SS2 for 96-charset" | |
08c19a27 | 295 | '((ascii t) nil t nil |
fec0e02d | 296 | nil ascii-eol ascii-cntl nil nil single-shift) |
40e98681 | 297 | '((safe-charsets . t))) |
08c19a27 | 298 | |
f6eb8ace KH |
299 | (make-coding-system |
300 | 'iso-safe 2 ?- | |
301 | "Convert all characters but ASCII to `?'." | |
302 | '(ascii nil nil nil | |
fec0e02d | 303 | nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil t) |
40e98681 | 304 | '((safe-charsets ascii))) |
f6eb8ace KH |
305 | |
306 | ;; Use iso-safe for terminal output if some other coding system is | |
307 | ;; specified explicitely. | |
308 | (set-safe-terminal-coding-system-internal 'iso-safe) | |
309 | ||
08c19a27 KH |
310 | ;; The other coding-systems are defined in each language specific |
311 | ;; section of languages.el. | |
312 | ||
678dc7ec RS |
313 | ;; Normally, set coding system to `undecided' before reading a file. |
314 | ;; Compiled Emacs Lisp files (*.elc) are not decoded at all, | |
315 | ;; but we regard them as containing multibyte characters. | |
316 | ;; Tar files are not decoded at all, but we treat them as raw bytes. | |
08c19a27 | 317 | |
4951a271 | 318 | (setq file-coding-system-alist |
678dc7ec | 319 | '(("\\.elc$" . (emacs-mule . emacs-mule)) |
c63f7d2a | 320 | ("\\(\\`\\|/\\)loaddefs.el$" . (no-conversion . no-conversion)) |
9f993a10 | 321 | ("\\.tar$" . (no-conversion . no-conversion)) |
4951a271 | 322 | ("" . (undecided . nil)))) |
08c19a27 KH |
323 | |
324 | \f | |
325 | ;;; Setting coding categories and their priorities. | |
326 | ||
327 | ;; This setting is just to read an Emacs Lisp source files which | |
328 | ;; contain multilingual text while dumping Emacs. More appropriate | |
2792ce16 | 329 | ;; values are set by the command `set-language-environment' for each |
08c19a27 KH |
330 | ;; language environment. |
331 | ||
29742cb5 KH |
332 | (setq coding-category-emacs-mule 'emacs-mule |
333 | coding-category-sjis 'japanese-shift-jis | |
334 | coding-category-iso-7 'iso-2022-7bit | |
40e98681 | 335 | coding-category-iso-7-tight 'iso-2022-jp |
29742cb5 KH |
336 | coding-category-iso-8-1 'iso-latin-1 |
337 | coding-category-iso-8-2 'japanese-iso-8bit | |
338 | coding-category-iso-7-else 'iso-2022-7bit-lock | |
339 | coding-category-iso-8-else 'iso-2022-8bit-ss2 | |
340 | coding-category-big5 'chinese-big5 | |
2cb30410 | 341 | coding-category-raw-text 'raw-text |
29742cb5 | 342 | coding-category-binary 'no-conversion) |
08c19a27 KH |
343 | |
344 | (set-coding-priority | |
40e98681 KH |
345 | '(coding-category-iso-7-tight |
346 | coding-category-iso-7 | |
08c19a27 | 347 | coding-category-iso-8-1 |
69b73c8a | 348 | coding-category-iso-8-2 |
29742cb5 | 349 | coding-category-iso-7-else |
2cb30410 | 350 | coding-category-iso-8-else |
e4e6cfa0 | 351 | coding-category-emacs-mule |
2cb30410 | 352 | coding-category-raw-text |
08c19a27 KH |
353 | coding-category-sjis |
354 | coding-category-big5 | |
e4e6cfa0 | 355 | coding-category-binary)) |
08c19a27 | 356 | |
c1b628eb KH |
357 | \f |
358 | ;;; Miscellaneous settings. | |
359 | (aset latin-extra-code-table ?\222 t) | |
360 | ||
08c19a27 | 361 | ;;; mule-conf.el ends here |