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 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"
187 (make-charset '=big5-cdp
188 "Big5 with CDP extension"
189 '(long-name "Big5-CDP"
195 registry "big5\\.cdp-0"
199 (define-charset-alias 'chinese-big5-cdp '=big5-cdp)
210 min-code ,(lsh #x6100 16)
211 max-code ,(+ (lsh #x6100 16) 67547)
212 code-offset ,(lsh #x6100 16)))
213 (define-charset-alias 'ideograph-gt '=gt)
215 "Ideographic components of GT"
216 `(long-name "GT components"
223 min-code ,(lsh #x6110 16)
224 max-code ,(+ (lsh #x6110 16) 17090)
225 code-offset ,(lsh #x6110 16)))
226 (define-charset-alias 'ideograph-gt-k '=gt-k)
230 (intern (format "=gt-pj-%d" i))
231 (format "GT 2000 (pseudo JIS encoding) part %d" i)
232 `(long-name ,(format "GT PJ %d" i)
238 registry ,(format "\\(GTpj-%d\\|jisx0208\\.GT-%d\\)$" i i)))
239 (define-charset-alias
240 (intern (format "ideograph-gt-pj-%d" i))
241 (intern (format "=gt-pj-%d" i)))
245 "Ideographic parts of GT (pseudo JIS encoding) part 1"
252 registry "\\(GTKpj-1\\|jisx0208\\.GTK-1\\)$"))
253 (define-charset-alias 'ideograph-gt-pj-k1 '=gt-pj-k1)
256 "Ideographic parts of GT (pseudo JIS encoding) part 2"
263 registry "\\(GTKpj-2\\|jisx0208\\.GTK-2\\)$"))
264 (define-charset-alias 'ideograph-gt-pj-k2 '=gt-pj-k2)
266 (make-charset '=daikanwa
267 "Daikanwa dictionary (revised version 2)"
268 `(long-name "Daikanwa"
274 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
276 max-code ,(+ #xE00000 50100)
277 code-offset #xE00000))
278 (define-charset-alias 'ideograph-daikanwa '=daikanwa)
280 (make-charset '=daikanwa@rev1
281 "Daikanwa dictionary (revised version)"
282 `(long-name "Daikanwa Rev."
288 registry "Daikanwa\\(\\.[0-9]+\\)?-2"
291 (define-charset-alias 'ideograph-daikanwa-2 '=daikanwa@rev1)
292 (define-charset-alias '=daikanwa-rev1 '=daikanwa@rev1)
294 (make-charset '=daikanwa@rev2
295 "Daikanwa dictionary (revised version 2)"
296 `(long-name "Daikanwa"
302 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
307 ;; max-code ,(+ #xE00000 50100)
308 ;; code-offset #xE00000
310 (define-charset-alias '=daikanwa-rev2 '=daikanwa@rev2)
312 (make-charset '=big5-pua
313 "Big5 with private used area"
314 '(long-name "Big5-PUA"
321 registry "Big5\\.ETEN"))
322 (define-charset-alias 'chinese-big5-pua '=big5-pua)
323 (make-charset '=big5-eten
325 '(long-name "Big5-ETEN"
334 registry "Big5\\.ETEN"))
335 (define-charset-alias 'chinese-big5-eten '=big5-eten)
336 (make-charset 'chinese-big5-eten-a
337 "Big5 ETEN (#xF9D6 .. #xF9FE)"
338 '(long-name "Big5-ETEN-a"
347 registry "Big5\\.ETEN"))
348 (make-charset 'chinese-big5-eten-b
349 "Big5 ETEN (#xC6A1 .. #xC8FE)"
350 '(long-name "Big5-ETEN-b"
359 registry "Big5\\.ETEN"))
362 (hzk-min (+ (lsh #x6200 16) 65536))
363 (hzk-max (+ hzk-min 65535)))
366 (intern (format "=hanziku-%d" i))
367 (format "HANZIKU (pseudo BIG5 encoding) part %d" i)
368 `(long-name ,(format "HANZIKU-%d" i)
374 registry ,(format "hanziku-%d$" i i)
377 code-offset ,hzk-min))
378 (define-charset-alias
379 (intern (format "ideograph-hanziku-%d" i))
380 (intern (format "=hanziku-%d" i)))
381 (setq hzk-min (1+ hzk-max)
382 hzk-max (+ hzk-min 65535))
385 (make-charset '=cbeta "CBETA private characters"
386 '(long-name "CBETA PUA"
396 (define-charset-alias 'ideograph-cbeta '=cbeta)
398 (make-charset '=jef-china3
399 "JEF + CHINA3 private characters"
400 '(long-name "JEF + CHINA3"
406 registry "china3jef-0"
409 code-offset #xE80000))
410 (define-charset-alias 'china3-jef '=jef-china3)
412 (make-charset '=ruimoku-v6
413 "private characters used in RUIMOKU Version.6"
422 min-code #xE90000 ; #xE000
423 max-code #xE908FF ; #xE8FF
424 code-offset ,(- #xE90000 #xE000)))
426 (make-charset '=ucs@iso
427 "ISO/IEC 10646 for its representative glyphs"
428 '(long-name "UCS for ISO"
435 (make-charset '=ucs@unicode
436 "Unicode for its representative glyphs"
437 '(long-name "UCS for Unicode"
444 (make-charset '=ucs@gb
445 "ISO/IEC 10646 for GB"
446 '(long-name "UCS for GB"
452 mother =ucs@unicode))
453 (define-charset-alias 'ucs-gb '=ucs@gb)
454 (make-charset '=ucs@gb/fw
455 "ISO/IEC 10646 for GB with fullwidth"
456 '(long-name "UCS for GB-fullwidth"
463 (make-charset '=ucs@cns
464 "ISO/IEC 10646 for CNS 11643"
465 '(long-name "UCS for CNS"
471 mother =ucs@unicode))
472 (define-charset-alias 'ucs-cns '=ucs@cns)
473 (make-charset '=ucs@cns/fw
474 "ISO/IEC 10646 for CNS 11643 with fullwidth"
475 '(long-name "UCS for CNS-fullwidth"
482 (make-charset '=ucs@jis
483 "ISO/IEC 10646 for JIS X0208/0212/0213"
484 '(long-name "UCS for JIS"
490 mother =ucs@unicode))
491 (define-charset-alias 'ucs-jis '=ucs@jis)
492 (make-charset '=ucs@jis/fw
493 "ISO/IEC 10646 for JIS X0208/0212/0213 with fullwidth"
494 '(long-name "UCS for JIS-fullwidth"
501 (make-charset '=ucs@jis/1990
502 "ISO/IEC 10646 for JIS X 0208/0212:1990"
503 '(long-name "UCS for JIS:1990"
510 (define-charset-alias '=ucs@jis-1990 '=ucs@jis/1990)
511 (define-charset-alias '=ucs-jis-1990 '=ucs@jis/1990)
512 (make-charset '=ucs@jis/2000
513 "ISO/IEC 10646 for JIS X 0213:2000"
514 '(long-name "UCS for JIS:2000"
521 (define-charset-alias '=ucs@jis-2000 '=ucs@jis/2000)
522 (define-charset-alias '=ucs-jis-2000 '=ucs@jis/2000)
523 (make-charset '=ucs@JP
524 "UCS for common glyphs used in Japan"
525 '(long-name "UCS for Japan"
531 mother =ucs@jis/2000))
532 (define-charset-alias '=ucs@jp '=ucs@JP)
533 (make-charset '=ucs@ks
534 "ISO/IEC 10646 for Korean Standards"
535 '(long-name "UCS for KS"
541 mother =ucs@unicode))
542 (define-charset-alias 'ucs-ks '=ucs@ks)
543 (make-charset '=ucs@big5
544 "ISO/IEC 10646 for Big5"
545 '(long-name "UCS for Big5"
551 mother =ucs@unicode))
552 (define-charset-alias 'ucs-big5 '=ucs@big5)
553 (make-charset '=ucs@big5/cns11643
554 "ISO/IEC 10646 for Big5 based on www.cns11643.gov.tw"
555 '(long-name "UCS for Big5@CNS11643"
562 (make-charset '=ucs@cns11643
563 "ISO/IEC 10646 for CNS based on www.cns11643.gov.tw"
564 '(long-name "UCS for CNS11643"
574 "CJK Radicals of UCS"
575 '(long-name "UCS-Radicals"
581 registry "-zhRadicals-.*-ucs-0"
583 min-code #x2E00 max-code #x2FFF))
585 '=ucs-radicals@unicode
586 "CJK Radicals of UCS"
587 '(long-name "UCS-Radicals"
593 registry "-zhRadicals-.*-ucs-0"
595 min-code #x2E00 max-code #x2FFF))
598 "Hangul Syllables of UCS"
599 '(long-name "UCS-Hangul-Syllables"
605 registry "-Hangul-.*-ucs-0"
607 min-code #xAC00 max-code #xD7AF))
610 "CJK Characters in BMP of UCS"
611 '(long-name "UCS-BMP-CJK"
617 registry "-zh-.*-ucs-0"
619 min-code #x2E00 max-code #xA4CF))
621 '=ucs-bmp-cjk@unicode
622 "CJK Characters in BMP of Unicode"
623 '(long-name "Unicode-BMP-CJK"
629 registry "-zh-.*-ucs-0"
631 min-code #x2E00 max-code #xA4CF))
634 "CJK Ideographs Extension B"
635 '(long-name "UCS CJK Ext-B"
641 registry "\\(iso10646\\|ucs02\\)-2$"
643 min-code #x20000 max-code #x2A6D6
644 code-offset #x20000))
647 "CJK Ideographs Extension B (ISO/IEC 10646-2)"
648 '(long-name "UCS CJK Ext-B"
654 registry "\\(iso10646\\|ucs02\\)-2$"
656 min-code #x20000 max-code #x2A6D6
657 code-offset #x20000))
660 ;;; mule-conf.el ends here