1 ;;; mule-coding.el --- Coding-system functions for Mule.
3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
4 ;; Licensed to the Free Software Foundation.
5 ;; Copyright (C) 1995 Amdahl Corporation.
6 ;; Copyright (C) 1995 Sun Microsystems.
7 ;; Copyright (C) 1997,1999,2002,2003,2004 MORIOKA Tomohiko
9 ;; This file is part of XEmacs.
11 ;; XEmacs is free software; you can redistribute it and/or modify it
12 ;; under the terms of the GNU General Public License as published by
13 ;; the Free Software Foundation; either version 2, or (at your option)
16 ;; XEmacs is distributed in the hope that it will be useful, but
17 ;; WITHOUT ANY WARRANTY; without even the implied warranty of
18 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
19 ;; General Public License for more details.
21 ;; You should have received a copy of the GNU General Public License
22 ;; along with XEmacs; see the file COPYING. If not, write to the
23 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
24 ;; Boston, MA 02111-1307, USA.
28 ;;; split off of mule.el and mostly moved to coding.el
32 (defun coding-system-force-on-output (coding-system register)
33 "Return the 'force-on-output property of CODING-SYSTEM for the specified REGISTER."
34 (check-type register integer)
35 (coding-system-property
38 (0 'force-g0-on-output)
39 (1 'force-g1-on-output)
40 (2 'force-g2-on-output)
41 (3 'force-g3-on-output)
42 (t (signal 'args-out-of-range (list register 0 3))))))
44 (defun coding-system-short (coding-system)
45 "Return the 'short property of CODING-SYSTEM."
46 (coding-system-property coding-system 'short))
48 (defun coding-system-no-ascii-eol (coding-system)
49 "Return the 'no-ascii-eol property of CODING-SYSTEM."
50 (coding-system-property coding-system 'no-ascii-eol))
52 (defun coding-system-no-ascii-cntl (coding-system)
53 "Return the 'no-ascii-cntl property of CODING-SYSTEM."
54 (coding-system-property coding-system 'no-ascii-cntl))
56 (defun coding-system-seven (coding-system)
57 "Return the 'seven property of CODING-SYSTEM."
58 (coding-system-property coding-system 'seven))
60 (defun coding-system-lock-shift (coding-system)
61 "Return the 'lock-shift property of CODING-SYSTEM."
62 (coding-system-property coding-system 'lock-shift))
64 ;;(defun coding-system-use-japanese-jisx0201-roman (coding-system)
65 ;; "Return the 'use-japanese-jisx0201-roman property of CODING-SYSTEM."
66 ;; (coding-system-property coding-system 'use-japanese-jisx0201-roman))
68 ;;(defun coding-system-use-japanese-jisx0208-1978 (coding-system)
69 ;; "Return the 'use-japanese-jisx0208-1978 property of CODING-SYSTEM."
70 ;; (coding-system-property coding-system 'use-japanese-jisx0208-2978))
72 (defun coding-system-no-iso6429 (coding-system)
73 "Return the 'no-iso6429 property of CODING-SYSTEM."
74 (coding-system-property coding-system 'no-iso6429))
76 (defun coding-system-ccl-encode (coding-system)
77 "Return the CCL 'encode property of CODING-SYSTEM."
78 (coding-system-property coding-system 'encode))
80 (defun coding-system-ccl-decode (coding-system)
81 "Return the CCL 'decode property of CODING-SYSTEM."
82 (coding-system-property coding-system 'decode))
85 ;;;; Definitions of predefined coding systems
89 "Coding-system used in X as Compound Text Encoding."
91 charset-g1 latin-iso8859-1
95 ;;; iso-8859-1 and ctext are aliases.
97 ;; (copy-coding-system 'ctext 'iso-8859-1)
99 'iso-8859-1 'no-conversion
100 "Coding-system used in X as Compound Text Encoding."
101 '(eol-type nil mnemonic "Noconv"))
104 'iso-2022-8bit-ss2 'iso2022
105 "ISO-2022 coding system using SS2 for 96-charset in 8-bit code."
107 charset-g1 latin-iso8859-1
108 charset-g2 t ;; unspecified but can be used later.
114 'iso-2022-7bit-ss2 'iso2022
115 "ISO-2022 coding system using SS2 for 96-charset in 7-bit code."
117 charset-g2 t ;; unspecified but can be used later.
123 ;; (copy-coding-system 'iso-2022-7bit-ss2 'iso-2022-jp-2)
125 'iso-2022-jp-2 'iso2022
126 "ISO-2022 coding system using SS2 for 96-charset in 7-bit code."
128 charset-g2 t ;; unspecified but can be used later.
135 'iso-2022-7bit 'iso2022
136 "ISO 2022 based 7-bit encoding using only G0"
142 ;; compatibility for old XEmacsen
143 (copy-coding-system 'iso-2022-7bit 'iso-2022-7)
147 "ISO-2022 eight-bit coding system. No single-shift or locking-shift."
149 charset-g1 latin-iso8859-1
155 'escape-quoted 'iso2022
156 "ISO-2022 eight-bit coding system with escape quoting; used for .ELC files."
158 charset-g1 latin-iso8859-1
165 'iso-2022-lock 'iso2022
166 "ISO-2022 coding system using Locking-Shift for 96-charset."
168 charset-g1 t ;; unspecified but can be used later.
174 (when (featurep 'utf-2000)
175 (setq coded-charset-entity-reference-alist
176 '(((ideograph-gt . isolated) "I-GT-" 5 d)
177 ((=ruimoku-v6 . isolated) "I-RUI6-" 4 X)
178 ((chinese-big5-cdp . isolated) "I-CDP-" 4 X)
179 ((ideograph-gt-k . isolated) "I-GT-K" 5 d)
180 ((ideograph-cbeta . isolated) "I-CB" 5 d)
181 ((ideograph-hanziku-1 . isolated) "I-HZK01-" 4 X)
182 ((ideograph-hanziku-2 . isolated) "I-HZK02-" 4 X)
183 ((ideograph-hanziku-3 . isolated) "I-HZK03-" 4 X)
184 ((ideograph-hanziku-4 . isolated) "I-HZK04-" 4 X)
185 ((ideograph-hanziku-5 . isolated) "I-HZK05-" 4 X)
186 ((ideograph-hanziku-6 . isolated) "I-HZK06-" 4 X)
187 ((ideograph-hanziku-7 . isolated) "I-HZK07-" 4 X)
188 ((ideograph-hanziku-8 . isolated) "I-HZK08-" 4 X)
189 ((ideograph-hanziku-9 . isolated) "I-HZK09-" 4 X)
190 ((ideograph-hanziku-10 . isolated) "I-HZK10-" 4 X)
191 ((ideograph-hanziku-11 . isolated) "I-HZK11-" 4 X)
192 ((ideograph-hanziku-12 . isolated) "I-HZK12-" 4 X)
193 ((japanese-jisx0208-1990 . isolated) "I-J90-" 4 X)
194 ((japanese-jisx0208 . isolated) "I-J83-" 4 X)
195 ((japanese-jisx0213-1 . isolated) "I-JX1-" 4 X)
196 ((japanese-jisx0213-2 . isolated) "I-JX2-" 4 X)
197 ((japanese-jisx0212 . isolated) "I-JSP-" 4 X)
198 ((japanese-jisx0208-1978 . isolated) "I-J78-" 4 X)
199 ((chinese-gb2312 . isolated) "I-G0-" 4 X)
200 ((chinese-cns11643-1 . isolated) "I-C1-" 4 X)
201 ((chinese-cns11643-2 . isolated) "I-C2-" 4 X)
202 ((chinese-cns11643-3 . isolated) "I-C3-" 4 X)
203 ((chinese-cns11643-4 . isolated) "I-C4-" 4 X)
204 ((chinese-cns11643-5 . isolated) "I-C5-" 4 X)
205 ((chinese-cns11643-6 . isolated) "I-C6-" 4 X)
206 ((chinese-cns11643-7 . isolated) "I-C7-" 4 X)
207 ((korean-ksc5601 . isolated) "I-K0-" 4 X)
208 ((=iso-ir165 . isolated) "I-EGB-" 4 X)
209 ((ideograph-daikanwa . isolated) "I-M-" 5 d)
210 ((chinese-big5 . isolated) "I-B-" 4 X)
211 ((latin-iso8859-1 . isolated) "I-LATIN1-" 2 X)
212 ((latin-iso8859-2 . isolated) "I-LATIN2-" 2 X)
213 ((latin-iso8859-3 . isolated) "I-LATIN3-" 2 X)
214 ((latin-iso8859-4 . isolated) "I-LATIN4-" 2 X)
215 ((cyrillic-iso8859-5 . isolated) "I-CYRILLIC-" 2 X)
216 ((greek-iso8859-7 . isolated) "I-GREEK-" 2 X)
217 ((hebrew-iso8859-8 . isolated) "I-HEBREW-" 2 X)
218 ((latin-iso8859-9 . isolated) "I-LATIN5-" 2 X)
219 ((latin-jisx0201 . isolated) "I-LATINJ-" 2 X)
220 ((katakana-jisx0201 . isolated) "I-KATAKANA-" 2 X)
221 ((latin-tcvn5712 . isolated) "I-VSCII2-" 2 X)
222 ;; ((latin-viscii . isolated) "I-VISCII-" 2 X)
223 ((latin-viscii-upper . isolated) "I-MULE-VIET-U-" 2 X)
224 ((latin-viscii-lower . isolated) "I-MULE-VIET-L-" 2 X)
225 ((thai-tis620 . isolated) "I-THAI-" 2 X)
226 ((lao . isolated) "I-MULE-LAO-" 2 X)
227 ((arabic-1-column . isolated) "I-MULE-ARB1-" 2 X)
228 ((arabic-2-column . isolated) "I-MULE-ARB2-" 2 X)
229 ((arabic-digit . isolated) "I-MULE-ARBD-" 2 X)
230 ((ipa . isolated) "I-MULE-IPA-" 2 X)
231 ((china3-jef . isolated) "I-JC3-" 4 X)
232 ( ideograph-gt "GT-" 5 d)
233 ( =ruimoku-v6 "RUI6-" 4 X)
234 ( chinese-big5-cdp "CDP-" 4 X)
235 ( ideograph-daikanwa "M-" 5 d)
236 ( ideograph-gt-k "GT-K" 5 d)
237 ( ideograph-cbeta "CB" 5 d)
238 ( ideograph-hanziku-1 "HZK01-" 4 X)
239 ( ideograph-hanziku-2 "HZK02-" 4 X)
240 ( ideograph-hanziku-3 "HZK03-" 4 X)
241 ( ideograph-hanziku-4 "HZK04-" 4 X)
242 ( ideograph-hanziku-5 "HZK05-" 4 X)
243 ( ideograph-hanziku-6 "HZK06-" 4 X)
244 ( ideograph-hanziku-7 "HZK07-" 4 X)
245 ( ideograph-hanziku-8 "HZK08-" 4 X)
246 ( ideograph-hanziku-9 "HZK09-" 4 X)
247 ( ideograph-hanziku-10 "HZK10-" 4 X)
248 ( ideograph-hanziku-11 "HZK11-" 4 X)
249 ( ideograph-hanziku-12 "HZK12-" 4 X)
250 ((ideograph-hanziku-1 . isolated) "I-HZK1-" 4 X)
251 ( ideograph-hanziku-1 "HZK1-" 4 X)
252 ((ideograph-hanziku-2 . isolated) "I-HZK2-" 4 X)
253 ( ideograph-hanziku-2 "HZK2-" 4 X)
254 ( japanese-jisx0208-1990 "J90-" 4 X)
255 ( japanese-jisx0208 "J83-" 4 X)
256 ( japanese-jisx0213-1 "JX1-" 4 X)
257 ( japanese-jisx0213-2 "JX2-" 4 X)
258 ( japanese-jisx0212 "JSP-" 4 X)
259 ( japanese-jisx0208-1978 "J78-" 4 X)
260 ( chinese-cns11643-1 "C1-" 4 X)
261 ( chinese-cns11643-2 "C2-" 4 X)
262 ( chinese-cns11643-3 "C3-" 4 X)
263 ( chinese-cns11643-4 "C4-" 4 X)
264 ( chinese-cns11643-5 "C5-" 4 X)
265 ( chinese-cns11643-6 "C6-" 4 X)
266 ( chinese-cns11643-7 "C7-" 4 X)
267 ( korean-ksc5601 "K0-" 4 X)
268 ( chinese-gb2312 "G0-" 4 X)
269 ( =iso-ir165 "EGB-" 4 X)
270 ( latin-iso8859-1 "LATIN1-" 2 X)
271 ( latin-iso8859-2 "LATIN2-" 2 X)
272 ( latin-iso8859-3 "LATIN3-" 2 X)
273 ( latin-iso8859-4 "LATIN4-" 2 X)
274 ( cyrillic-iso8859-5 "CYRILLIC-" 2 X)
275 ( greek-iso8859-7 "GREEK-" 2 X)
276 ( hebrew-iso8859-8 "HEBREW-" 2 X)
277 ( latin-iso8859-9 "LATIN5-" 2 X)
278 ( latin-jisx0201 "LATINJ-" 2 X)
279 ( katakana-jisx0201 "KATAKANA-" 2 X)
280 ( latin-tcvn5712 "VSCII2-" 2 X)
281 ( latin-viscii "VISCII-" 2 X)
282 ( latin-viscii-upper "MULE-VIET-U-" 2 X)
283 ( latin-viscii-lower "MULE-VIET-L-" 2 X)
284 ( thai-tis620 "THAI-" 2 X)
285 ( lao "MULE-LAO-" 2 X)
286 ( ethiopic "MULE-ETHIO-" 4 X)
287 ( arabic-1-column "MULE-ARB1-" 2 X)
288 ( arabic-2-column "MULE-ARB2-" 2 X)
289 ( arabic-digit "MULE-ARBD-" 2 X)
290 ( ipa "MULE-IPA-" 2 X)
291 ( china3-jef "JC3-" 4 X)
292 ( chinese-big5 "B-" 4 X)
293 ( chinese-big5 "C0-" 4 X)
294 ( =ucs@unicode "UU+" 4 X)
295 ( =ucs@unicode "UU-" 8 X)
300 ( =ucs@jis "JU+" 4 X)
301 ( =ucs@jis "JU-" 8 X)
302 ( =ucs@cns "CU+" 4 X)
303 ( =ucs@cns "CU-" 8 X)
306 ( =jis-x0208@1997 "J97-" 4 X)
311 "Coding-system of UTF-8 with entity-reference."
312 '(mnemonic "MTF8r" use-entity-reference t))
316 "Coding-system of UTF-8 using GB mapping."
324 "Coding-system of UTF-8 using GB mapping with entity-reference."
329 use-entity-reference t))
333 "Coding-system of UTF-8 using CNS mapping."
341 "Coding-system of UTF-8 using CNS mapping with entity-reference."
346 use-entity-reference t))
350 "Coding-system of UTF-8 using Big5 mapping."
353 charset-g1 =>ucs-big5
357 'utf-8-big5-er 'utf-8
358 "Coding-system of UTF-8 using Big5 mapping with entity-reference."
361 charset-g1 =>ucs-big5
363 use-entity-reference t))
367 "Coding-system of UTF-8 using JIS mapping."
369 charset-g0 =ucs@jis-2000
375 "Coding-system of UTF-8 using JIS mapping with entity-reference."
377 charset-g0 =ucs@jis-2000
380 use-entity-reference t))
384 "Coding-system of UTF-8 for common glyphs used in Japan."
392 "Coding-system of UTF-8 using =ucs@jp mapping with entity-reference."
397 use-entity-reference t))
401 "Coding-system of UTF-8 using KS mapping."
409 "Coding-system of UTF-8 using KS mapping with entity-reference."
414 use-entity-reference t))
416 (define-coding-system-alias 'utf-8 'utf-8-mcs)
417 (define-coding-system-alias 'utf-8-er 'utf-8-mcs-er)
421 'euc-jisx0213 'iso2022
422 "Coding-system of Japanese EUC based on JIS X 0213."
424 charset-g1 japanese-jisx0213-1
425 charset-g2 katakana-jisx0201
426 charset-g3 japanese-jisx0213-2
428 mnemonic "Ja/EUC0213"
431 ;; initialize the coding categories to something semi-reasonable
432 ;; so that the remaining Lisp files can contain extended characters.
433 ;; (They will be in ISO-7 format)
434 ;; #### This list needs to be synched with the ones in mule-cmds.el.
436 (if (featurep 'utf-2000)
437 (set-coding-priority-list '(iso-7
447 (set-coding-priority-list '(iso-7
459 (set-coding-category-system 'iso-7 'iso-2022-7)
460 (set-coding-category-system 'iso-8-designate 'ctext)
461 (set-coding-category-system 'iso-8-1 'ctext)
462 (set-coding-category-system 'iso-lock-shift 'iso-2022-lock)
463 (set-coding-category-system 'no-conversion 'no-conversion)
465 (setq-default buffer-file-coding-system 'iso-2022-8)
467 ;;; mule-coding.el ends here