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, 2005, 2006, 2008, 2009,
8 ;; 2010, 2011 MORIOKA Tomohiko
10 ;; This file is part of XEmacs.
12 ;; XEmacs is free software; you can redistribute it and/or modify it
13 ;; under the terms of the GNU General Public License as published by
14 ;; the Free Software Foundation; either version 2, or (at your option)
17 ;; XEmacs is distributed in the hope that it will be useful, but
18 ;; WITHOUT ANY WARRANTY; without even the implied warranty of
19 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
20 ;; General Public License for more details.
22 ;; You should have received a copy of the GNU General Public License
23 ;; along with XEmacs; see the file COPYING. If not, write to the
24 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
25 ;; Boston, MA 02111-1307, USA.
29 ;;; split off of mule.el and mostly moved to coding.el
33 (defun coding-system-force-on-output (coding-system register)
34 "Return the 'force-on-output property of CODING-SYSTEM for the specified REGISTER."
35 (check-type register integer)
36 (coding-system-property
39 (0 'force-g0-on-output)
40 (1 'force-g1-on-output)
41 (2 'force-g2-on-output)
42 (3 'force-g3-on-output)
43 (t (signal 'args-out-of-range (list register 0 3))))))
45 (defun coding-system-short (coding-system)
46 "Return the 'short property of CODING-SYSTEM."
47 (coding-system-property coding-system 'short))
49 (defun coding-system-no-ascii-eol (coding-system)
50 "Return the 'no-ascii-eol property of CODING-SYSTEM."
51 (coding-system-property coding-system 'no-ascii-eol))
53 (defun coding-system-no-ascii-cntl (coding-system)
54 "Return the 'no-ascii-cntl property of CODING-SYSTEM."
55 (coding-system-property coding-system 'no-ascii-cntl))
57 (defun coding-system-seven (coding-system)
58 "Return the 'seven property of CODING-SYSTEM."
59 (coding-system-property coding-system 'seven))
61 (defun coding-system-lock-shift (coding-system)
62 "Return the 'lock-shift property of CODING-SYSTEM."
63 (coding-system-property coding-system 'lock-shift))
65 ;;(defun coding-system-use-japanese-jisx0201-roman (coding-system)
66 ;; "Return the 'use-japanese-jisx0201-roman property of CODING-SYSTEM."
67 ;; (coding-system-property coding-system 'use-japanese-jisx0201-roman))
69 ;;(defun coding-system-use-japanese-jisx0208-1978 (coding-system)
70 ;; "Return the 'use-japanese-jisx0208-1978 property of CODING-SYSTEM."
71 ;; (coding-system-property coding-system 'use-japanese-jisx0208-2978))
73 (defun coding-system-no-iso6429 (coding-system)
74 "Return the 'no-iso6429 property of CODING-SYSTEM."
75 (coding-system-property coding-system 'no-iso6429))
77 (defun coding-system-ccl-encode (coding-system)
78 "Return the CCL 'encode property of CODING-SYSTEM."
79 (coding-system-property coding-system 'encode))
81 (defun coding-system-ccl-decode (coding-system)
82 "Return the CCL 'decode property of CODING-SYSTEM."
83 (coding-system-property coding-system 'decode))
86 ;;;; Definitions of predefined coding systems
90 "Coding-system used in X as Compound Text Encoding."
92 charset-g1 latin-iso8859-1
96 ;;; iso-8859-1 and ctext are aliases.
98 ;; (copy-coding-system 'ctext 'iso-8859-1)
100 'iso-8859-1 'no-conversion
101 "Coding-system used in X as Compound Text Encoding."
102 '(eol-type nil mnemonic "Noconv"))
105 'iso-2022-8bit-ss2 'iso2022
106 "ISO-2022 coding system using SS2 for 96-charset in 8-bit code."
108 charset-g1 latin-iso8859-1
109 charset-g2 t ;; unspecified but can be used later.
115 'iso-2022-7bit-ss2 'iso2022
116 "ISO-2022 coding system using SS2 for 96-charset in 7-bit code."
118 charset-g2 t ;; unspecified but can be used later.
124 ;; (copy-coding-system 'iso-2022-7bit-ss2 'iso-2022-jp-2)
126 'iso-2022-jp-2 'iso2022
127 "ISO-2022 coding system using SS2 for 96-charset in 7-bit code."
130 charset-g2 t ;; unspecified but can be used later.
135 (if (featurep 'utf-2000)
136 (list* 'ccs-priority-list
138 =jis-x0208@1983 =jis-x0208@1978
144 'iso-2022-7bit 'iso2022
145 "ISO 2022 based 7-bit encoding using only G0"
151 ;; compatibility for old XEmacsen
152 (copy-coding-system 'iso-2022-7bit 'iso-2022-7)
156 "ISO-2022 eight-bit coding system. No single-shift or locking-shift."
158 charset-g1 latin-iso8859-1
164 'escape-quoted 'iso2022
165 "ISO-2022 eight-bit coding system with escape quoting; used for .ELC files."
167 charset-g1 latin-iso8859-1
174 'iso-2022-lock 'iso2022
175 "ISO-2022 coding system using Locking-Shift for 96-charset."
177 charset-g1 t ;; unspecified but can be used later.
183 (when (featurep 'utf-2000)
184 (setq coded-charset-entity-reference-alist
185 '(((=adobe-japan1-base . isolated) "I-AJ1-" 5 d)
186 ((=adobe-japan1-6 . isolated) "I-AJ1-" 5 d)
187 ((=gt . isolated) "I-GT-" 5 d)
188 ((=ruimoku-v6 . isolated) "I-RUI6-" 4 X)
189 ((chinese-big5-cdp . isolated) "I-CDP-" 4 X)
190 ((=gt-k . isolated) "I-GT-K" 5 d)
191 ((ideograph-cbeta . isolated) "I-CB" 5 d)
192 ((ideograph-hanziku-1 . isolated) "I-HZK01-" 4 X)
193 ((ideograph-hanziku-2 . isolated) "I-HZK02-" 4 X)
194 ((ideograph-hanziku-3 . isolated) "I-HZK03-" 4 X)
195 ((ideograph-hanziku-4 . isolated) "I-HZK04-" 4 X)
196 ((ideograph-hanziku-5 . isolated) "I-HZK05-" 4 X)
197 ((ideograph-hanziku-6 . isolated) "I-HZK06-" 4 X)
198 ((ideograph-hanziku-7 . isolated) "I-HZK07-" 4 X)
199 ((ideograph-hanziku-8 . isolated) "I-HZK08-" 4 X)
200 ((ideograph-hanziku-9 . isolated) "I-HZK09-" 4 X)
201 ((ideograph-hanziku-10 . isolated) "I-HZK10-" 4 X)
202 ((ideograph-hanziku-11 . isolated) "I-HZK11-" 4 X)
203 ((ideograph-hanziku-12 . isolated) "I-HZK12-" 4 X)
204 ((=jis-x0208@1990 . isolated) "I-J90-" 4 X)
205 ((=jis-x0208@1983 . isolated) "I-J83-" 4 X)
206 ((=jis-x0213-1@2000 . isolated) "I-JX1-" 4 X)
207 ((=jis-x0213-2 . isolated) "I-JX2-" 4 X)
208 ((=jis-x0213-1@2004 . isolated) "I-JX3-" 4 X)
209 ((=jis-x0212 . isolated) "I-JSP-" 4 X)
210 ((=jis-x0208@1978 . isolated) "I-J78-" 4 X)
211 ((chinese-gb2312 . isolated) "I-G0-" 4 X)
212 ((chinese-cns11643-1 . isolated) "I-C1-" 4 X)
213 ((chinese-cns11643-2 . isolated) "I-C2-" 4 X)
214 ((chinese-cns11643-3 . isolated) "I-C3-" 4 X)
215 ((chinese-cns11643-4 . isolated) "I-C4-" 4 X)
216 ((chinese-cns11643-5 . isolated) "I-C5-" 4 X)
217 ((chinese-cns11643-6 . isolated) "I-C6-" 4 X)
218 ((chinese-cns11643-7 . isolated) "I-C7-" 4 X)
219 ((korean-ksc5601 . isolated) "I-K0-" 4 X)
220 ((=iso-ir165 . isolated) "I-EGB-" 4 X)
221 ((ideograph-daikanwa . isolated) "I-M-" 5 d)
222 ((chinese-big5 . isolated) "I-B-" 4 X)
223 ((latin-iso8859-1 . isolated) "I-LATIN1-" 2 X)
224 ((latin-iso8859-2 . isolated) "I-LATIN2-" 2 X)
225 ((latin-iso8859-3 . isolated) "I-LATIN3-" 2 X)
226 ((latin-iso8859-4 . isolated) "I-LATIN4-" 2 X)
227 ((cyrillic-iso8859-5 . isolated) "I-CYRILLIC-" 2 X)
228 ((greek-iso8859-7 . isolated) "I-GREEK-" 2 X)
229 ((hebrew-iso8859-8 . isolated) "I-HEBREW-" 2 X)
230 ((latin-iso8859-9 . isolated) "I-LATIN5-" 2 X)
231 ((latin-jisx0201 . isolated) "I-LATINJ-" 2 X)
232 ((katakana-jisx0201 . isolated) "I-KATAKANA-" 2 X)
233 ((latin-tcvn5712 . isolated) "I-VSCII2-" 2 X)
234 ;; ((latin-viscii . isolated) "I-VISCII-" 2 X)
235 ((latin-viscii-upper . isolated) "I-MULE-VIET-U-" 2 X)
236 ((latin-viscii-lower . isolated) "I-MULE-VIET-L-" 2 X)
237 ((thai-tis620 . isolated) "I-THAI-" 2 X)
238 ((lao . isolated) "I-MULE-LAO-" 2 X)
239 ((arabic-1-column . isolated) "I-MULE-ARB1-" 2 X)
240 ((arabic-2-column . isolated) "I-MULE-ARB2-" 2 X)
241 ((arabic-digit . isolated) "I-MULE-ARBD-" 2 X)
242 ((ipa . isolated) "I-MULE-IPA-" 2 X)
243 ((china3-jef . isolated) "I-JC3-" 4 X)
244 ( =adobe-japan1-6 "AJ1-" 5 d)
245 ( =adobe-japan1-base "I-AJ1-" 5 d)
247 ( =zinbun-oracle "ZOB-" 4 d)
248 ( =ruimoku-v6 "RUI6-" 4 X)
249 ( =big5-cdp "CDP-" 4 X)
250 ( =daikanwa "M-" 5 d)
251 ( =daikanwa@rev1 "r1M-" 5 d)
253 ( ideograph-cbeta "CB" 5 d)
254 ( ideograph-hanziku-1 "HZK01-" 4 X)
255 ( ideograph-hanziku-2 "HZK02-" 4 X)
256 ( ideograph-hanziku-3 "HZK03-" 4 X)
257 ( ideograph-hanziku-4 "HZK04-" 4 X)
258 ( ideograph-hanziku-5 "HZK05-" 4 X)
259 ( ideograph-hanziku-6 "HZK06-" 4 X)
260 ( ideograph-hanziku-7 "HZK07-" 4 X)
261 ( ideograph-hanziku-8 "HZK08-" 4 X)
262 ( ideograph-hanziku-9 "HZK09-" 4 X)
263 ( ideograph-hanziku-10 "HZK10-" 4 X)
264 ( ideograph-hanziku-11 "HZK11-" 4 X)
265 ( ideograph-hanziku-12 "HZK12-" 4 X)
266 ((ideograph-hanziku-1 . isolated) "I-HZK1-" 4 X)
267 ( ideograph-hanziku-1 "HZK1-" 4 X)
268 ((ideograph-hanziku-2 . isolated) "I-HZK2-" 4 X)
269 ( ideograph-hanziku-2 "HZK2-" 4 X)
270 ( =jis-x0208@1990 "J90-" 4 X)
271 ( =jis-x0208@1983 "J83-" 4 X)
272 ( =jis-x0213-1@2000 "JX1-" 4 X)
273 ( =jis-x0213-2 "JX2-" 4 X)
274 ( =jis-x0213-1@2004 "JX3-" 4 X)
275 ( =jis-x0212 "JSP-" 4 X)
276 ( =jis-x0208@1978 "J78-" 4 X)
277 ( chinese-cns11643-1 "C1-" 4 X)
278 ( chinese-cns11643-2 "C2-" 4 X)
279 ( chinese-cns11643-3 "C3-" 4 X)
280 ( chinese-cns11643-4 "C4-" 4 X)
281 ( chinese-cns11643-5 "C5-" 4 X)
282 ( chinese-cns11643-6 "C6-" 4 X)
283 ( chinese-cns11643-7 "C7-" 4 X)
284 ( korean-ksc5601 "K0-" 4 X)
285 ( chinese-gb2312 "G0-" 4 X)
286 ( =iso-ir165 "EGB-" 4 X)
287 ( latin-iso8859-1 "LATIN1-" 2 X)
288 ( latin-iso8859-2 "LATIN2-" 2 X)
289 ( latin-iso8859-3 "LATIN3-" 2 X)
290 ( latin-iso8859-4 "LATIN4-" 2 X)
291 ( cyrillic-iso8859-5 "CYRILLIC-" 2 X)
292 ( greek-iso8859-7 "GREEK-" 2 X)
293 ( hebrew-iso8859-8 "HEBREW-" 2 X)
294 ( latin-iso8859-9 "LATIN5-" 2 X)
295 ( latin-jisx0201 "LATINJ-" 2 X)
296 ( katakana-jisx0201 "KATAKANA-" 2 X)
297 ( latin-tcvn5712 "VSCII2-" 2 X)
298 ( latin-viscii "VISCII-" 2 X)
299 ( latin-viscii-upper "MULE-VIET-U-" 2 X)
300 ( latin-viscii-lower "MULE-VIET-L-" 2 X)
301 ( thai-tis620 "THAI-" 2 X)
302 ( lao "MULE-LAO-" 2 X)
303 ( ethiopic "MULE-ETHIO-" 4 X)
304 ( arabic-1-column "MULE-ARB1-" 2 X)
305 ( arabic-2-column "MULE-ARB2-" 2 X)
306 ( arabic-digit "MULE-ARBD-" 2 X)
307 ( ipa "MULE-IPA-" 2 X)
310 (=>>jis-x0208 "G-J0-" 4 X)
311 (=>>jis-x0213-1@2000 "G-JX1-" 4 X)
312 (=>>jis-x0213-2 "G-JX2-" 4 X)
313 (=>>jis-x0213-1@2004 "G-JX3-" 4 X)
314 (=>>jis-x0213-1@2000 "aJX1-" 4 X)
315 (=>>jis-x0213-2 "aJX2-" 4 X)
316 (=>>jis-x0213-1@2004 "aJX3-" 4 X)
317 (=>>jis-x0208@1978 "G-J78-" 4 X)
318 (=>>big5-cdp "G-CDP-" 4 X)
319 (=>>gt-k "G-GT-K" 5 d)
320 (=>>ruimoku-v6 "G-RUI6-" 4 X)
321 ( =>jis-x0208@usual "o-J0-" 4 X)
322 ( =>jis-x0208@1997 "J97-" 4 X)
323 ( =>jis-x0208@1997 "A-J0-" 4 X)
324 ( =>jis-x0213-1@2000 "A-JX1-" 4 X)
325 ( =>jis-x0213-2@usual "o-JX2-" 4 X)
326 ( =>jis-x0213-2 "A-JX2-" 4 X)
327 ( =>jis-x0213-1@2004 "A-JX3-" 4 X)
329 ( =>zinbun-oracle "A-ZOB-" 4 d)
330 (==>ucs@bucs "BUCS+" 4 X)
331 ( =>ucs@iso "A-IU+" 4 X)
332 ( =>ucs@unicode "A-UU+" 4 X)
333 ( =>ucs@jis "A-JU+" 4 X)
334 ( =>ucs@cns "A-CU+" 4 X)
335 ( =>ucs@JP "o-JU+" 4 X)
336 (=>>ucs@iso "G-IU+" 4 X)
337 (=>>ucs@unicode "G-UU+" 4 X)
338 (=>>ucs@jis "G-JU+" 4 X)
339 (=>>ucs@ks "G-KU+" 4 X)
340 (=>>ucs@cns "G-CU+" 4 X)
341 (=>>ucs@jis/2004 "G-J04U+" 4 X)
342 (=>>ucs@jis/2000 "G-J00U+" 4 X)
343 (=>>ucs@jis/1990 "G-J90U+" 4 X)
345 ( =ucs@unicode "UU+" 4 X)
346 ( =ucs@unicode "UU-" 8 X)
350 ( =ucs@jis "JU+" 4 X)
351 ( =ucs@jis "JU-" 8 X)
352 ( =ucs@cns "CU+" 4 X)
353 ( =ucs@cns "CU-" 8 X)
356 ( china3-jef "JC3-" 4 X)
357 ( chinese-big5 "B-" 4 X)
358 ( chinese-big5 "C0-" 4 X)
359 ( =>big5-cdp "A-CDP-" 4 X)
360 ( =>daikanwa "A-M-" 5 d)
361 ( =jis-x0208@1978/i1 "J78i1-" 4 X)
362 ( =shinjigen@rev "SJG2-" 4 d)
363 ( =shinjigen@1ed "SJG1-" 4 d)
368 "Coding-system of UTF-8 with entity-reference."
369 '(mnemonic "MTF8r" use-entity-reference t))
372 'utf-8-mcs-no-composition 'utf-8
373 "Coding-system of UTF-8 without composition."
374 '(mnemonic "MTF8-nc" disable-composition t))
378 "Coding-system of UTF-8 using GB mapping."
386 "Coding-system of UTF-8 using GB mapping with entity-reference."
391 use-entity-reference t))
395 "Coding-system of UTF-8 using CNS mapping."
403 "Coding-system of UTF-8 using CNS mapping with entity-reference."
408 use-entity-reference t))
412 "Coding-system of UTF-8 using Big5 mapping."
415 charset-g1 =>ucs-big5
419 'utf-8-big5-er 'utf-8
420 "Coding-system of UTF-8 using Big5 mapping with entity-reference."
423 charset-g1 =>ucs-big5
425 use-entity-reference t))
429 "Coding-system of UTF-8 using JIS mapping."
431 charset-g0 =ucs@jis-2000
437 "Coding-system of UTF-8 using JIS mapping with entity-reference."
439 charset-g0 =ucs@jis-2000
442 use-entity-reference t))
446 "Coding-system of UTF-8 for common glyphs used in Japan."
454 "Coding-system of UTF-8 using =ucs@jp mapping with entity-reference."
459 use-entity-reference t))
463 "Coding-system of UTF-8 using KS mapping."
471 "Coding-system of UTF-8 using KS mapping with entity-reference."
476 use-entity-reference t))
478 (define-coding-system-alias 'utf-8 'utf-8-mcs)
479 (define-coding-system-alias 'utf-8-er 'utf-8-mcs-er)
483 'euc-jisx0213 'iso2022
484 "Coding-system of Japanese EUC based on JIS X 0213."
486 charset-g1 japanese-jisx0213-1
487 charset-g2 katakana-jisx0201
488 charset-g3 japanese-jisx0213-2
490 mnemonic "Ja/EUC0213"
493 ;; initialize the coding categories to something semi-reasonable
494 ;; so that the remaining Lisp files can contain extended characters.
495 ;; (They will be in ISO-7 format)
496 ;; #### This list needs to be synched with the ones in mule-cmds.el.
498 (if (featurep 'utf-2000)
499 (set-coding-priority-list '(iso-7
509 (set-coding-priority-list '(iso-7
521 (set-coding-category-system 'iso-7 'iso-2022-7)
522 (set-coding-category-system 'iso-8-designate 'ctext)
523 (set-coding-category-system 'iso-8-1 'ctext)
524 (set-coding-category-system 'iso-lock-shift 'iso-2022-lock)
525 (set-coding-category-system 'no-conversion 'no-conversion)
527 (setq-default buffer-file-coding-system 'iso-2022-8)
529 ;;; mule-coding.el ends here