1 ;;; mule-conf.el --- configure multilingual environment
3 ;; Copyright (C) 1995,1999 Electrotechnical Laboratory, JAPAN.
4 ;; Licensed to the Free Software Foundation.
5 ;; Copyright (C) 1997,1999,2000,2002,2003 MORIOKA Tomohiko
7 ;; Keywords: mule, multilingual, character set, coding system
9 ;; This file is part of XEmacs.
11 ;; XEmacs is free software; you can redistribute it and/or modify
12 ;; it 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,
17 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
18 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19 ;; GNU 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 (define-charset-alias 'japanese-jisx0208-1978 '=jis-x0208-1978)
29 (define-charset-alias 'japanese-jisx0208 '=jis-x0208-1983)
30 (define-charset-alias 'korean-ksc5601 '=ks-x1001)
31 (define-charset-alias 'japanese-jisx0212 '=jis-x0212)
34 (make-charset 'sisheng "PinYin-ZhuYin"
35 '(registry "sisheng_cwnn\\|OMRON_UDC_ZH"
43 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
44 (make-charset 'lao "Lao script"
45 '(registry "MuleLao-1"
51 ;; IPA (International Phonetic Alphabet)
52 (make-charset 'ipa "International Phonetic Alphabet"
60 (make-charset 'ethiopic "Ethiopic"
68 ;; ISO-IR-165 (CCITT Extended GB)
69 ;; It is based on CCITT Recommendation T.101, includes GB 2312-80 +
70 ;; GB 8565-88 table A4 + 293 characters.
71 (make-charset '=iso-ir165
72 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
79 (define-charset-alias 'chinese-isoir165 '=iso-ir165)
81 ;; CNS11643 Plane3 thru Plane7
82 ;; These represent more and more obscure Chinese characters.
83 ;; By the time you get to Plane 7, we're talking about characters
84 ;; that appear once in some ancient manuscript and whose meaning
88 ((make-chinese-cns11643-charset
89 (name iso-ir plane final)
91 name (concat "CNS 11643 Plane " plane " (Chinese traditional)")
94 ,(concat "CNS11643[.-]\\(.*[.-]\\)?" plane "$")
100 (make-chinese-cns11643-charset 'chinese-cns11643-3 183 "3" ?I)
101 (make-chinese-cns11643-charset 'chinese-cns11643-4 184 "4" ?J)
102 (make-chinese-cns11643-charset 'chinese-cns11643-5 185 "5" ?K)
103 (make-chinese-cns11643-charset 'chinese-cns11643-6 186 "6" ?L)
104 (make-chinese-cns11643-charset 'chinese-cns11643-7 187 "7" ?M)
108 (if (featurep 'utf-2000)
112 "JIS X 0213:2000 Plain 1"
114 registry "jisx0213\\(\\.2000\\)-1"
117 mother =jis-x0208-1990
122 "JIS X 0213:2000 Plain 2"
124 registry "jisx0213\\(\\.2000\\)-2"
129 (define-charset-alias 'japanese-jisx0213-1 '=jis-x0213-1-2000)
130 (define-charset-alias 'japanese-jisx0213-2 '=jis-x0213-2-2000)
134 "JIS X 0213:2000 Plain 1"
135 '(registry "jisx0213\\(\\.2000\\)-1"
142 "JIS X 0213:2000 Plain 2"
143 '(registry "jisx0213\\(\\.2000\\)-2"
150 (when (featurep 'utf-2000)
151 (define-charset-alias 'ucs '=ucs)
152 (define-charset-alias 'japanese-jisx0208-1990 '=jis-x0208-1990)
153 (make-charset '=ucs@gb
155 `(long-name "ISO/IEC 10646 for GB"
162 (define-charset-alias 'ucs-gb '=ucs@gb)
163 (make-charset '=ucs@cns
165 `(long-name "ISO/IEC 10646 for CNS 11643"
172 (define-charset-alias 'ucs-cns '=ucs@cns)
173 (make-charset '=ucs@jis
175 `(long-name "ISO/IEC 10646 for JIS X0208/0212/0213"
182 (define-charset-alias 'ucs-jis '=ucs@jis)
183 (make-charset '=ucs@jis-1990
185 `(long-name "ISO/IEC 10646 for JIS X 0208/0212:1990"
192 (define-charset-alias '=ucs-jis-1990 '=ucs@jis-1990)
193 (make-charset '=ucs@jis-2000
195 `(long-name "ISO/IEC 10646 for JIS X 0213:2000"
202 (define-charset-alias '=ucs-jis-2000 '=ucs@jis-2000)
203 (make-charset '=ucs@ks
205 `(long-name "ISO/IEC 10646 for Korean Standards"
212 (define-charset-alias 'ucs-ks '=ucs@ks)
213 (make-charset '=ucs@big5
215 `(long-name "ISO/IEC 10646 for Big5"
222 (define-charset-alias 'ucs-big5 '=ucs@big5)
224 (make-charset 'ideograph-daikanwa
226 `(long-name "Daikanwa dictionary (revised version 2)"
232 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
234 max-code ,(+ #xE00000 50100)
235 code-offset #xE00000))
237 (make-charset '=daikanwa-rev1
239 `(long-name "Daikanwa dictionary (revised version)"
245 registry "Daikanwa\\(\\.[0-9]+\\)?-2"))
246 (define-charset-alias 'ideograph-daikanwa-2 '=daikanwa-rev1)
248 (make-charset '=daikanwa-rev2
250 `(long-name "Daikanwa dictionary (revised version 2)"
256 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
258 max-code ,(+ #xE00000 50100)
259 code-offset #xE00000))
261 (make-charset '=big5-pua
263 `(long-name "Big5 with private used area"
270 registry "Big5\\.ETEN"))
271 (define-charset-alias 'chinese-big5-pua '=big5-pua)
272 (make-charset '=big5-eten
274 `(long-name "Big5 ETEN"
283 registry "Big5\\.ETEN"))
284 (define-charset-alias 'chinese-big5-eten '=big5-eten)
285 (make-charset 'chinese-big5-eten-a
287 `(long-name "Big5 ETEN (#xF9D6 .. #xF9FE)"
296 registry "Big5\\.ETEN"))
297 (make-charset 'chinese-big5-eten-b
299 `(long-name "Big5 ETEN (#xC6A1 .. #xC8FE)"
308 registry "Big5\\.ETEN"))
309 (make-charset '=big5-cdp
311 `(long-name "Big5 with CDP extension"
317 registry "big5\\.cdp-0"
321 (define-charset-alias 'chinese-big5-cdp '=big5-cdp)
323 (hzk-min (+ (lsh #x6200 16) 65536))
324 (hzk-max (+ hzk-min 65535)))
327 (intern (format "=hanziku-%d" i))
328 (format "HANZIKU-%d" i)
329 `(long-name ,(format "HANZIKU (pseudo BIG5 encoding) part %d" i)
335 registry ,(format "hanziku-%d$" i i)
338 code-offset ,hzk-min))
339 (define-charset-alias
340 (intern (format "ideograph-hanziku-%d" i))
341 (intern (format "=hanziku-%d" i)))
342 (setq hzk-min (1+ hzk-max)
343 hzk-max (+ hzk-min 65535))
348 `(long-name "GT 2000"
355 min-code ,(lsh #x6100 16)
356 max-code ,(+ (lsh #x6100 16) 67547)
357 code-offset ,(lsh #x6100 16)))
358 (define-charset-alias 'ideograph-gt '=gt)
361 `(long-name "Ideographic parts of GT"
368 min-code ,(lsh #x6110 16)
369 max-code ,(+ (lsh #x6110 16) 17090)
370 code-offset ,(lsh #x6110 16)))
371 (define-charset-alias 'ideograph-gt-k '=gt-k)
375 (intern (format "=gt-pj-%d" i))
376 (format "GT PJ %d" i)
377 `(long-name ,(format "GT 2000 (pseudo JIS encoding) part %d" i)
383 registry ,(format "\\(GTpj-%d\\|jisx0208\\.GT-%d\\)$" i i)))
384 (define-charset-alias
385 (intern (format "ideograph-gt-pj-%d" i))
386 (intern (format "=gt-pj-%d" i)))
391 `(long-name "Ideographic parts of GT (pseudo JIS encoding) part 1"
397 registry "\\(GTKpj-1\\|jisx0208\\.GTK-1\\)$"))
398 (define-charset-alias 'ideograph-gt-pj-k1 '=gt-pj-k1)
402 `(long-name "Ideographic parts of GT (pseudo JIS encoding) part 2"
408 registry "\\(GTKpj-2\\|jisx0208\\.GTK-2\\)$"))
409 (define-charset-alias 'ideograph-gt-pj-k2 '=gt-pj-k2)
410 (make-charset '=cbeta "CBETA PUA"
411 '(long-name "CBETA private characters"
421 (define-charset-alias 'ideograph-cbeta '=cbeta)
422 (make-charset '=jef-china3
424 `(long-name "JEF + CHINA3 private characters"
430 registry "china3jef-0"
433 code-offset #xE80000))
434 (define-charset-alias 'china3-jef '=jef-china3)
437 ;;; mule-conf.el ends here