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)
32 (define-charset-alias 'chinese-big5 '=big5)
35 (make-charset 'sisheng "PinYin-ZhuYin"
36 '(registry "sisheng_cwnn\\|OMRON_UDC_ZH"
44 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
45 (make-charset 'lao "Lao script"
46 '(registry "MuleLao-1"
52 ;; IPA (International Phonetic Alphabet)
53 (make-charset 'ipa "International Phonetic Alphabet"
61 (make-charset 'ethiopic "Ethiopic"
69 ;; ISO-IR-165 (CCITT Extended GB)
70 ;; It is based on CCITT Recommendation T.101, includes GB 2312-80 +
71 ;; GB 8565-88 table A4 + 293 characters.
72 (make-charset '=iso-ir165
73 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
80 (define-charset-alias 'chinese-isoir165 '=iso-ir165)
82 ;; CNS11643 Plane3 thru Plane7
83 ;; These represent more and more obscure Chinese characters.
84 ;; By the time you get to Plane 7, we're talking about characters
85 ;; that appear once in some ancient manuscript and whose meaning
89 ((make-chinese-cns11643-charset
90 (name iso-ir plane final)
92 name (concat "CNS 11643 Plane " plane " (Chinese traditional)")
95 ,(concat "CNS11643[.-]\\(.*[.-]\\)?" plane "$")
101 (make-chinese-cns11643-charset 'chinese-cns11643-3 183 "3" ?I)
102 (make-chinese-cns11643-charset 'chinese-cns11643-4 184 "4" ?J)
103 (make-chinese-cns11643-charset 'chinese-cns11643-5 185 "5" ?K)
104 (make-chinese-cns11643-charset 'chinese-cns11643-6 186 "6" ?L)
105 (make-chinese-cns11643-charset 'chinese-cns11643-7 187 "7" ?M)
109 (if (featurep 'utf-2000)
113 "JIS X 0213:2000 Plain 1"
115 registry "jisx0213\\(\\.2000\\)-1"
118 mother =jis-x0208-1990
123 "JIS X 0213:2000 Plain 2"
125 registry "jisx0213\\(\\.2000\\)-2"
130 (define-charset-alias 'japanese-jisx0213-1 '=jis-x0213-1-2000)
131 (define-charset-alias 'japanese-jisx0213-2 '=jis-x0213-2-2000)
135 "JIS X 0213:2000 Plain 1"
136 '(registry "jisx0213\\(\\.2000\\)-1"
143 "JIS X 0213:2000 Plain 2"
144 '(registry "jisx0213\\(\\.2000\\)-2"
151 (when (featurep 'utf-2000)
152 (define-charset-alias 'ucs '=ucs)
153 (define-charset-alias 'japanese-jisx0208-1990 '=jis-x0208-1990)
154 (make-charset '=ucs@gb
156 `(long-name "ISO/IEC 10646 for GB"
163 (define-charset-alias 'ucs-gb '=ucs@gb)
164 (make-charset '=ucs@cns
166 `(long-name "ISO/IEC 10646 for CNS 11643"
173 (define-charset-alias 'ucs-cns '=ucs@cns)
174 (make-charset '=ucs@jis
176 `(long-name "ISO/IEC 10646 for JIS X0208/0212/0213"
183 (define-charset-alias 'ucs-jis '=ucs@jis)
184 (make-charset '=ucs@jis-1990
186 `(long-name "ISO/IEC 10646 for JIS X 0208/0212:1990"
193 (define-charset-alias '=ucs-jis-1990 '=ucs@jis-1990)
194 (make-charset '=ucs@jis-2000
196 `(long-name "ISO/IEC 10646 for JIS X 0213:2000"
203 (define-charset-alias '=ucs-jis-2000 '=ucs@jis-2000)
204 (make-charset '=ucs@ks
206 `(long-name "ISO/IEC 10646 for Korean Standards"
213 (define-charset-alias 'ucs-ks '=ucs@ks)
214 (make-charset '=ucs@big5
216 `(long-name "ISO/IEC 10646 for Big5"
223 (define-charset-alias 'ucs-big5 '=ucs@big5)
225 (make-charset 'ideograph-daikanwa
227 `(long-name "Daikanwa dictionary (revised version 2)"
233 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
235 max-code ,(+ #xE00000 50100)
236 code-offset #xE00000))
238 (make-charset '=daikanwa-rev1
240 `(long-name "Daikanwa dictionary (revised version)"
246 registry "Daikanwa\\(\\.[0-9]+\\)?-2"))
247 (define-charset-alias 'ideograph-daikanwa-2 '=daikanwa-rev1)
249 (make-charset '=daikanwa-rev2
251 `(long-name "Daikanwa dictionary (revised version 2)"
257 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
259 max-code ,(+ #xE00000 50100)
260 code-offset #xE00000))
262 (make-charset '=big5-pua
264 `(long-name "Big5 with private used area"
271 registry "Big5\\.ETEN"))
272 (define-charset-alias 'chinese-big5-pua '=big5-pua)
273 (make-charset '=big5-eten
275 `(long-name "Big5 ETEN"
284 registry "Big5\\.ETEN"))
285 (define-charset-alias 'chinese-big5-eten '=big5-eten)
286 (make-charset 'chinese-big5-eten-a
288 `(long-name "Big5 ETEN (#xF9D6 .. #xF9FE)"
297 registry "Big5\\.ETEN"))
298 (make-charset 'chinese-big5-eten-b
300 `(long-name "Big5 ETEN (#xC6A1 .. #xC8FE)"
309 registry "Big5\\.ETEN"))
310 (make-charset '=big5-cdp
312 `(long-name "Big5 with CDP extension"
318 registry "big5\\.cdp-0"
322 (define-charset-alias 'chinese-big5-cdp '=big5-cdp)
324 (hzk-min (+ (lsh #x6200 16) 65536))
325 (hzk-max (+ hzk-min 65535)))
328 (intern (format "=hanziku-%d" i))
329 (format "HANZIKU-%d" i)
330 `(long-name ,(format "HANZIKU (pseudo BIG5 encoding) part %d" i)
336 registry ,(format "hanziku-%d$" i i)
339 code-offset ,hzk-min))
340 (define-charset-alias
341 (intern (format "ideograph-hanziku-%d" i))
342 (intern (format "=hanziku-%d" i)))
343 (setq hzk-min (1+ hzk-max)
344 hzk-max (+ hzk-min 65535))
349 `(long-name "GT 2000"
356 min-code ,(lsh #x6100 16)
357 max-code ,(+ (lsh #x6100 16) 67547)
358 code-offset ,(lsh #x6100 16)))
359 (define-charset-alias 'ideograph-gt '=gt)
362 `(long-name "Ideographic parts of GT"
369 min-code ,(lsh #x6110 16)
370 max-code ,(+ (lsh #x6110 16) 17090)
371 code-offset ,(lsh #x6110 16)))
372 (define-charset-alias 'ideograph-gt-k '=gt-k)
376 (intern (format "=gt-pj-%d" i))
377 (format "GT PJ %d" i)
378 `(long-name ,(format "GT 2000 (pseudo JIS encoding) part %d" i)
384 registry ,(format "\\(GTpj-%d\\|jisx0208\\.GT-%d\\)$" i i)))
385 (define-charset-alias
386 (intern (format "ideograph-gt-pj-%d" i))
387 (intern (format "=gt-pj-%d" i)))
392 `(long-name "Ideographic parts of GT (pseudo JIS encoding) part 1"
398 registry "\\(GTKpj-1\\|jisx0208\\.GTK-1\\)$"))
399 (define-charset-alias 'ideograph-gt-pj-k1 '=gt-pj-k1)
403 `(long-name "Ideographic parts of GT (pseudo JIS encoding) part 2"
409 registry "\\(GTKpj-2\\|jisx0208\\.GTK-2\\)$"))
410 (define-charset-alias 'ideograph-gt-pj-k2 '=gt-pj-k2)
411 (make-charset '=cbeta "CBETA PUA"
412 '(long-name "CBETA private characters"
422 (define-charset-alias 'ideograph-cbeta '=cbeta)
423 (make-charset '=jef-china3
425 `(long-name "JEF + CHINA3 private characters"
431 registry "china3jef-0"
434 code-offset #xE80000))
435 (define-charset-alias 'china3-jef '=jef-china3)
438 ;;; mule-conf.el ends here