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) 1997,1999,2000,2002,2003,2004,2005 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 '=jis-x0208-1978 '=jis-x0208@1978)
29 (define-charset-alias 'japanese-jisx0208-1978 '=jis-x0208@1978)
30 (define-charset-alias 'chinese-gb2312 '=gb2312)
31 (define-charset-alias '=jis-x0208-1983 '=jis-x0208@1983)
32 (define-charset-alias 'japanese-jisx0208 '=jis-x0208@1983)
33 (define-charset-alias 'korean-ksc5601 '=ks-x1001)
34 (define-charset-alias 'japanese-jisx0212 '=jis-x0212)
35 (define-charset-alias 'chinese-cns11643-1 '=cns11643-1)
36 (define-charset-alias 'chinese-cns11643-2 '=cns11643-2)
37 (define-charset-alias 'chinese-gb12345 '=gb12345)
38 (define-charset-alias 'chinese-big5 '=big5)
41 (make-charset 'sisheng "PinYin-ZhuYin"
42 '(registry "sisheng_cwnn\\|OMRON_UDC_ZH"
50 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
51 (make-charset 'lao "Lao script"
52 '(registry "MuleLao-1"
58 ;; IPA (International Phonetic Alphabet)
59 (make-charset 'ipa "International Phonetic Alphabet"
67 (make-charset 'ethiopic "Ethiopic"
75 ;; ISO-IR-165 (CCITT Extended GB)
76 ;; It is based on CCITT Recommendation T.101, includes GB 2312-80 +
77 ;; GB 8565-88 table A4 + 293 characters.
78 (if (featurep 'utf-2000)
80 (make-charset '=iso-ir165
81 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
89 (define-charset-alias 'chinese-isoir165 '=iso-ir165))
90 (make-charset 'chinese-isoir165
91 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
99 ;; CNS11643 Plane3 thru Plane7
100 ;; These represent more and more obscure Chinese characters.
101 ;; By the time you get to Plane 7, we're talking about characters
102 ;; that appear once in some ancient manuscript and whose meaning
106 ((make-chinese-cns11643-charset
107 (name iso-ir plane final)
109 name (concat "CNS 11643 Plane " plane " (Chinese traditional)")
112 ,(concat "CNS11643[.-]\\(.*[.-]\\)?" plane "$")
118 (make-chinese-cns11643-charset '=cns11643-3 183 "3" ?I)
119 (make-chinese-cns11643-charset '=cns11643-4 184 "4" ?J)
120 (make-chinese-cns11643-charset '=cns11643-5 185 "5" ?K)
121 (make-chinese-cns11643-charset '=cns11643-6 186 "6" ?L)
122 (make-chinese-cns11643-charset '=cns11643-7 187 "7" ?M)
123 (define-charset-alias 'chinese-cns11643-3 '=cns11643-3)
124 (define-charset-alias 'chinese-cns11643-4 '=cns11643-4)
125 (define-charset-alias 'chinese-cns11643-5 '=cns11643-5)
126 (define-charset-alias 'chinese-cns11643-6 '=cns11643-6)
127 (define-charset-alias 'chinese-cns11643-7 '=cns11643-7)
131 (if (featurep 'utf-2000)
135 "JIS X 0213:2000 Plain 1"
137 registry "jisx0213\\(\\.2000\\)-1"
140 mother =jis-x0208@1990
145 "JIS X 0213:2000 Plain 2"
147 registry "jisx0213\\(\\.2000\\)-2"
152 (define-charset-alias 'japanese-jisx0213-1 '=jis-x0213-1-2000)
153 (define-charset-alias 'japanese-jisx0213-2 '=jis-x0213-2-2000)
157 "JIS X 0213:2000 Plain 1"
158 '(registry "jisx0213\\(\\.2000\\)-1"
165 "JIS X 0213:2000 Plain 2"
166 '(registry "jisx0213\\(\\.2000\\)-2"
173 (when (featurep 'utf-2000)
174 (define-charset-alias 'ucs '=ucs)
175 (define-charset-alias '=jis-x0208-1990 '=jis-x0208@1990)
176 (define-charset-alias 'japanese-jisx0208-1990 '=jis-x0208@1990)
179 "JIS X 0208 based on the unification rule of 1997 edition."
180 '(registry "jisx0208\\.1990"
188 "The first impression of JIS X 0208:1978."
189 '(registry "jisx0208\\.1978"
192 mother =jis-x0208@1978
196 (make-charset '=big5-cdp
197 "Big5 with CDP extension"
198 '(long-name "Big5-CDP"
204 registry "big5\\.cdp-0"
208 (define-charset-alias 'chinese-big5-cdp '=big5-cdp)
219 min-code ,(lsh #x6100 16)
220 max-code ,(+ (lsh #x6100 16) 67547)
221 code-offset ,(lsh #x6100 16)))
222 (define-charset-alias 'ideograph-gt '=gt)
224 "Ideographic components of GT"
225 `(long-name "GT components"
232 min-code ,(lsh #x6110 16)
233 max-code ,(+ (lsh #x6110 16) 17090)
234 code-offset ,(lsh #x6110 16)))
235 (define-charset-alias 'ideograph-gt-k '=gt-k)
239 (intern (format "=gt-pj-%d" i))
240 (format "GT 2000 (pseudo JIS encoding) part %d" i)
241 `(long-name ,(format "GT PJ %d" i)
247 registry ,(format "\\(GTpj-%d\\|jisx0208\\.GT-%d\\)$" i i)))
248 (define-charset-alias
249 (intern (format "ideograph-gt-pj-%d" i))
250 (intern (format "=gt-pj-%d" i)))
254 "Ideographic parts of GT (pseudo JIS encoding) part 1"
261 registry "\\(GTKpj-1\\|jisx0208\\.GTK-1\\)$"))
262 (define-charset-alias 'ideograph-gt-pj-k1 '=gt-pj-k1)
265 "Ideographic parts of GT (pseudo JIS encoding) part 2"
272 registry "\\(GTKpj-2\\|jisx0208\\.GTK-2\\)$"))
273 (define-charset-alias 'ideograph-gt-pj-k2 '=gt-pj-k2)
275 (make-charset '=daikanwa
276 "Daikanwa dictionary (revised version 2)"
277 `(long-name "Daikanwa"
283 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
285 max-code ,(+ #xE00000 50100)
286 code-offset #xE00000))
287 (define-charset-alias 'ideograph-daikanwa '=daikanwa)
289 (make-charset '=daikanwa@rev1
290 "Daikanwa dictionary (revised version)"
291 `(long-name "Daikanwa Rev."
297 registry "Daikanwa\\(\\.[0-9]+\\)?-2"
300 (define-charset-alias 'ideograph-daikanwa-2 '=daikanwa@rev1)
301 (define-charset-alias '=daikanwa-rev1 '=daikanwa@rev1)
303 (make-charset '=daikanwa@rev2
304 "Daikanwa dictionary (revised version 2)"
305 `(long-name "Daikanwa"
311 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
316 ;; max-code ,(+ #xE00000 50100)
317 ;; code-offset #xE00000
319 (define-charset-alias '=daikanwa-rev2 '=daikanwa@rev2)
321 (make-charset '=big5-pua
322 "Big5 with private used area"
323 '(long-name "Big5-PUA"
330 registry "Big5\\.ETEN"))
331 (define-charset-alias 'chinese-big5-pua '=big5-pua)
332 (make-charset '=big5-eten
334 '(long-name "Big5-ETEN"
343 registry "Big5\\.ETEN"))
344 (define-charset-alias 'chinese-big5-eten '=big5-eten)
345 (make-charset 'chinese-big5-eten-a
346 "Big5 ETEN (#xF9D6 .. #xF9FE)"
347 '(long-name "Big5-ETEN-a"
356 registry "Big5\\.ETEN"))
357 (make-charset 'chinese-big5-eten-b
358 "Big5 ETEN (#xC6A1 .. #xC8FE)"
359 '(long-name "Big5-ETEN-b"
368 registry "Big5\\.ETEN"))
371 (hzk-min (+ (lsh #x6200 16) 65536))
372 (hzk-max (+ hzk-min 65535)))
375 (intern (format "=hanziku-%d" i))
376 (format "HANZIKU (pseudo BIG5 encoding) part %d" i)
377 `(long-name ,(format "HANZIKU-%d" i)
383 registry ,(format "hanziku-%d$" i i)
386 code-offset ,hzk-min))
387 (define-charset-alias
388 (intern (format "ideograph-hanziku-%d" i))
389 (intern (format "=hanziku-%d" i)))
390 (setq hzk-min (1+ hzk-max)
391 hzk-max (+ hzk-min 65535))
394 (make-charset '=cbeta "CBETA private characters"
395 '(long-name "CBETA PUA"
405 (define-charset-alias 'ideograph-cbeta '=cbeta)
407 (make-charset '=zinbun-oracle
408 "Oracle Bones Script"
409 `(long-name "Oracle Bones Script in Zinbun, Kyoto Univ."
415 max-code ,(+ #xE70000 8192)
420 (make-charset '=jef-china3
421 "JEF + CHINA3 private characters"
422 '(long-name "JEF + CHINA3"
428 registry "china3jef-0"
431 code-offset #xE80000))
432 (define-charset-alias 'china3-jef '=jef-china3)
434 (make-charset '=ruimoku-v6
435 "private characters used in RUIMOKU Version.6"
444 min-code #xE90000 ; #xE000
445 max-code #xE908FF ; #xE8FF
446 code-offset ,(- #xE90000 #xE000)))
448 (make-charset '=ucs@iso
449 "ISO/IEC 10646 for its representative glyphs"
450 '(long-name "UCS for ISO"
457 (make-charset '=ucs@unicode
458 "Unicode for its representative glyphs"
459 '(long-name "UCS for Unicode"
466 (make-charset '=ucs@gb
467 "ISO/IEC 10646 for GB"
468 '(long-name "UCS for GB"
474 mother =ucs@unicode))
475 (define-charset-alias 'ucs-gb '=ucs@gb)
476 (make-charset '=ucs@gb/fw
477 "ISO/IEC 10646 for GB with fullwidth"
478 '(long-name "UCS for GB-fullwidth"
485 (make-charset '=ucs-bmp@gb
486 "ISO/IEC 10646 BMP for GB"
487 '(long-name "BMP for GB"
496 (make-charset '=ucs@cns
497 "ISO/IEC 10646 for CNS 11643"
498 '(long-name "UCS for CNS"
504 mother =ucs@unicode))
505 (define-charset-alias 'ucs-cns '=ucs@cns)
506 (make-charset '=ucs@cns/fw
507 "ISO/IEC 10646 for CNS 11643 with fullwidth"
508 '(long-name "UCS for CNS-fullwidth"
515 (make-charset '=ucs-bmp@cns
516 "ISO/IEC 10646 BMP for CNS"
517 '(long-name "BMP for CNS"
526 (make-charset '=ucs@jis
527 "ISO/IEC 10646 for JIS X0208/0212/0213"
528 '(long-name "UCS for JIS"
534 mother =ucs@unicode))
535 (define-charset-alias 'ucs-jis '=ucs@jis)
536 (make-charset '=ucs@jis/fw
537 "ISO/IEC 10646 for JIS X0208/0212/0213 with fullwidth"
538 '(long-name "UCS for JIS-fullwidth"
545 (make-charset '=ucs-bmp@jis
546 "ISO/IEC 10646 BMP for JIS"
547 '(long-name "BMP for JIS"
556 (make-charset '=ucs@jis/1990
557 "ISO/IEC 10646 for JIS X 0208/0212:1990"
558 '(long-name "UCS for JIS:1990"
565 (define-charset-alias '=ucs@jis-1990 '=ucs@jis/1990)
566 (define-charset-alias '=ucs-jis-1990 '=ucs@jis/1990)
567 (make-charset '=ucs@jis/2000
568 "ISO/IEC 10646 for JIS X 0213:2000"
569 '(long-name "UCS for JIS:2000"
576 (define-charset-alias '=ucs@jis-2000 '=ucs@jis/2000)
577 (define-charset-alias '=ucs-jis-2000 '=ucs@jis/2000)
578 (make-charset '=ucs@JP
579 "UCS for common glyphs used in Japan"
580 '(long-name "UCS for Japan"
586 mother =ucs@jis/2000))
587 (define-charset-alias '=ucs@jp '=ucs@JP)
588 (make-charset '=ucs@ks
589 "ISO/IEC 10646 for Korean Standards"
590 '(long-name "UCS for KS"
596 mother =ucs@unicode))
597 (define-charset-alias 'ucs-ks '=ucs@ks)
598 (make-charset '=ucs-bmp@ks
599 "ISO/IEC 10646 BMP for KS"
600 '(long-name "BMP for KS"
609 (make-charset '=ucs@big5
610 "ISO/IEC 10646 for Big5"
611 '(long-name "UCS for Big5"
617 mother =ucs@unicode))
618 (define-charset-alias 'ucs-big5 '=ucs@big5)
619 (make-charset '=ucs@big5/cns11643
620 "ISO/IEC 10646 for Big5 based on www.cns11643.gov.tw"
621 '(long-name "UCS for Big5@CNS11643"
628 (make-charset '=ucs@cns11643
629 "ISO/IEC 10646 for CNS based on www.cns11643.gov.tw"
630 '(long-name "UCS for CNS11643"
640 "CJK Radicals of UCS"
641 '(long-name "UCS-Radicals"
647 registry "-zhRadicals-.*-ucs-0"
649 min-code #x2E00 max-code #x2FFF))
651 '=ucs-radicals@unicode
652 "CJK Radicals of UCS"
653 '(long-name "UCS-Radicals"
659 registry "-zhRadicals-.*-ucs-0"
661 min-code #x2E00 max-code #x2FFF))
664 "Hangul Syllables of UCS"
665 '(long-name "UCS-Hangul-Syllables"
671 registry "-Hangul-.*-ucs-0"
673 min-code #xAC00 max-code #xD7AF))
676 "CJK Characters in BMP of UCS"
677 '(long-name "UCS-BMP-CJK"
683 registry "-zh-.*-ucs-0"
690 '=ucs-bmp-cjk@unicode
691 "CJK Characters in BMP of Unicode"
692 '(long-name "Unicode-BMP-CJK"
698 registry "-zh-.*-ucs-0"
700 min-code #x2E00 max-code #xA4CF))
703 "CJK Ideographs Extension B"
704 '(long-name "UCS CJK Ext-B"
710 registry "\\(iso10646\\|ucs02\\)-2$"
712 min-code #x20000 max-code #x2A6D6
713 code-offset #x20000))
716 "CJK Ideographs Extension B (ISO/IEC 10646-2)"
717 '(long-name "UCS CJK Ext-B"
723 registry "\\(iso10646\\|ucs02\\)-2$"
725 min-code #x20000 max-code #x2A6D6
726 code-offset #x20000))
729 ;;; mule-conf.el ends here