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) 1997,1999,2000,2002,2003,2004,2005,2006,2008 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.
32 "JIS X 0208:1978, unchanged part."
33 '(registry "jisx0208\\.1978"
42 "JIS X 0208:1978, 1st - 3rd impressions."
43 '(registry "jisx0208\\.1978"
46 mother =jis-x0208@1978
52 "JIS X 0208:1978, 1st impression."
54 registry "jisx0208\\.1978"
57 mother =jis-x0208@1978/-4pr
62 "JIS X 0208:1978, 4th impression or later."
63 '(registry "jisx0208\\.1978"
66 mother =jis-x0208@1978
70 (define-charset-alias '=jis-x0208@1978/i1 '=jis-x0208@1978/1pr)
71 (define-charset-alias '=jis-x0208@1978/i-4 '=jis-x0208@1978/-4pr)
72 (define-charset-alias '=jis-x0208@1978/i4- '=jis-x0208@1978/4-pr)
77 "JIS X0208:1978 Japanese Kanji (so called \"old JIS\")."
79 registry "jisx0208\\.1978"
87 (define-charset-alias '=jis-x0208-1978 '=jis-x0208@1978)
88 (define-charset-alias 'japanese-jisx0208-1978 '=jis-x0208@1978)
89 (define-charset-alias 'chinese-gb2312 '=gb2312)
90 (define-charset-alias '=jis-x0208-1983 '=jis-x0208@1983)
91 (define-charset-alias 'japanese-jisx0208 '=jis-x0208@1983)
92 (define-charset-alias 'korean-ksc5601 '=ks-x1001)
93 (define-charset-alias 'japanese-jisx0212 '=jis-x0212)
94 (define-charset-alias 'chinese-cns11643-1 '=cns11643-1)
95 (define-charset-alias 'chinese-cns11643-2 '=cns11643-2)
96 (define-charset-alias 'chinese-gb12345 '=gb12345)
97 (define-charset-alias 'chinese-big5 '=big5)
100 (make-charset 'sisheng "PinYin-ZhuYin"
101 '(registry "sisheng_cwnn\\|OMRON_UDC_ZH"
109 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
110 (make-charset 'lao "Lao script"
111 '(registry "MuleLao-1"
117 ;; IPA (International Phonetic Alphabet)
118 (make-charset 'ipa "International Phonetic Alphabet"
126 (make-charset 'ethiopic "Ethiopic"
134 ;; ISO-IR-165 (CCITT Extended GB)
135 ;; It is based on CCITT Recommendation T.101, includes GB 2312-80 +
136 ;; GB 8565-88 table A4 + 293 characters.
137 (if (featurep 'utf-2000)
139 (make-charset '=iso-ir165
140 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
148 (define-charset-alias 'chinese-isoir165 '=iso-ir165))
149 (make-charset 'chinese-isoir165
150 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
158 ;; CNS11643 Plane3 thru Plane7
159 ;; These represent more and more obscure Chinese characters.
160 ;; By the time you get to Plane 7, we're talking about characters
161 ;; that appear once in some ancient manuscript and whose meaning
165 ((make-chinese-cns11643-charset
166 (name iso-ir plane final)
168 name (concat "CNS 11643 Plane " plane " (Chinese traditional)")
171 ,(concat "CNS11643[.-]\\(.*[.-]\\)?" plane "$")
177 (make-chinese-cns11643-charset '=cns11643-3 183 "3" ?I)
178 (make-chinese-cns11643-charset '=cns11643-4 184 "4" ?J)
179 (make-chinese-cns11643-charset '=cns11643-5 185 "5" ?K)
180 (make-chinese-cns11643-charset '=cns11643-6 186 "6" ?L)
181 (make-chinese-cns11643-charset '=cns11643-7 187 "7" ?M)
182 (define-charset-alias 'chinese-cns11643-3 '=cns11643-3)
183 (define-charset-alias 'chinese-cns11643-4 '=cns11643-4)
184 (define-charset-alias 'chinese-cns11643-5 '=cns11643-5)
185 (define-charset-alias 'chinese-cns11643-6 '=cns11643-6)
186 (define-charset-alias 'chinese-cns11643-7 '=cns11643-7)
191 ((featurep 'utf-2000)
194 "JIS X 0213 Plain 1 (unchanged part)"
195 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
204 "JIS X 0213:2000 Plain 1"
206 registry "jisx0213\\(\\.2000\\)-1"
216 registry "jisx0213\\(\\.\\(2000\\|2004\\)\\)?-2"
224 "JIS X 0213:2004 Plain 1"
226 registry "jisx0213\\(\\.2004\\)-1"
233 (define-charset-alias 'japanese-jisx0213-1 '=jis-x0213-1@2000)
234 (define-charset-alias 'japanese-jisx0213-2 '=jis-x0213-2)
235 (define-charset-alias '=jis-x0213-1-2000 '=jis-x0213-1@2000)
236 (define-charset-alias '=jis-x0213-2-2000 '=jis-x0213-2)
241 "JIS X 0213:2000 Plain 1"
242 '(registry "jisx0213\\(\\.2000\\)-1"
249 "JIS X 0213:2000 Plain 2"
250 '(registry "jisx0213\\(\\.2000\\)-2"
257 (when (featurep 'utf-2000)
258 (define-charset-alias 'ucs '=ucs)
259 (define-charset-alias '=jis-x0208-1990 '=jis-x0208@1990)
260 (define-charset-alias 'japanese-jisx0208-1990 '=jis-x0208@1990)
263 "JIS X 0208 based on the unification rule of 1997 edition."
264 '(registry "jisx0208\\.1990"
271 (make-charset '=big5-cdp
272 "Big5 with CDP extension"
273 '(long-name "Big5-CDP"
279 registry "big5\\.cdp-0"
283 (define-charset-alias 'chinese-big5-cdp '=big5-cdp)
294 min-code ,(lsh #x6100 16)
295 max-code ,(+ (lsh #x6100 16) 67547)
296 code-offset ,(lsh #x6100 16)))
297 (define-charset-alias 'ideograph-gt '=gt)
299 "Ideographic components of GT"
300 `(long-name "GT components"
307 min-code ,(lsh #x6110 16)
308 max-code ,(+ (lsh #x6110 16) 17090)
309 code-offset ,(lsh #x6110 16)))
310 (define-charset-alias 'ideograph-gt-k '=gt-k)
314 (intern (format "=gt-pj-%d" i))
315 (format "GT 2000 (pseudo JIS encoding) part %d" i)
316 `(long-name ,(format "GT PJ %d" i)
322 registry ,(format "\\(GTpj-%d\\|jisx0208\\.GT-%d\\)$" i i)))
323 (define-charset-alias
324 (intern (format "ideograph-gt-pj-%d" i))
325 (intern (format "=gt-pj-%d" i)))
329 "Ideographic parts of GT (pseudo JIS encoding) part 1"
336 registry "\\(GTKpj-1\\|jisx0208\\.GTK-1\\)$"))
337 (define-charset-alias 'ideograph-gt-pj-k1 '=gt-pj-k1)
340 "Ideographic parts of GT (pseudo JIS encoding) part 2"
347 registry "\\(GTKpj-2\\|jisx0208\\.GTK-2\\)$"))
348 (define-charset-alias 'ideograph-gt-pj-k2 '=gt-pj-k2)
350 (make-charset '=daikanwa
351 "Daikanwa dictionary (revised version 2)"
352 `(long-name "Daikanwa"
358 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
360 max-code ,(+ #xE00000 50100)
361 code-offset #xE00000))
362 (define-charset-alias 'ideograph-daikanwa '=daikanwa)
364 (make-charset '=daikanwa@rev1
365 "Daikanwa dictionary (revised version)"
366 `(long-name "Daikanwa Rev."
372 registry "Daikanwa\\(\\.[0-9]+\\)?-2"
375 (define-charset-alias 'ideograph-daikanwa-2 '=daikanwa@rev1)
376 (define-charset-alias '=daikanwa-rev1 '=daikanwa@rev1)
378 (make-charset '=daikanwa@rev2
379 "Daikanwa dictionary (revised version 2)"
380 `(long-name "Daikanwa"
386 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
391 ;; max-code ,(+ #xE00000 50100)
392 ;; code-offset #xE00000
394 (define-charset-alias '=daikanwa-rev2 '=daikanwa@rev2)
396 (make-charset '=shinjigen
397 "Kadokawa ShinJigen dictionary (common parts)"
398 `(long-name "Shinjigen common parts"
404 registry "Shinjigen\\(\\.[0-9]+\\)?-*"))
406 (make-charset '=shinjigen@1ed
407 "Kadokawa ShinJigen dictionary (the first edition)"
408 `(long-name "Shinjigen-1"
415 registry "Shinjigen\\(\\.[0-9]+\\)?-1"))
416 (define-charset-alias 'shinjigen-1 '=shinjigen@1ed)
418 (make-charset '=shinjigen@1ed/24pr
419 "Kadokawa ShinJigen dictionary (the 24th impression)"
420 `(long-name "Shinjigen-1 24pr"
426 mother =shinjigen@1ed))
428 (make-charset '=shinjigen@rev
429 "Kadokawa ShinJigen dictionary (the revised edition)"
430 `(long-name "Shinjigen-2"
437 registry "Shinjigen\\(\\.[0-9]+\\)?-2"))
438 (define-charset-alias 'shinjigen-2 '=shinjigen@rev)
439 (make-charset '=shinjigen/+p@rev
440 "ShinJigen (the second edition) number with '"
441 `(long-name "Shinjigen-2 with '"
447 (define-charset-alias 'shinjigen-2-p '=shinjigen/+p@rev)
449 (make-charset '=big5-pua
450 "Big5 with private used area"
451 '(long-name "Big5-PUA"
458 registry "Big5\\.ETEN"))
459 (define-charset-alias 'chinese-big5-pua '=big5-pua)
460 (make-charset '=big5-eten
462 '(long-name "Big5-ETEN"
471 registry "Big5\\.ETEN"))
472 (define-charset-alias 'chinese-big5-eten '=big5-eten)
473 (make-charset 'chinese-big5-eten-a
474 "Big5 ETEN (#xF9D6 .. #xF9FE)"
475 '(long-name "Big5-ETEN-a"
484 registry "Big5\\.ETEN"))
485 (make-charset 'chinese-big5-eten-b
486 "Big5 ETEN (#xC6A1 .. #xC8FE)"
487 '(long-name "Big5-ETEN-b"
496 registry "Big5\\.ETEN"))
499 (hzk-min (+ (lsh #x6200 16) 65536))
500 (hzk-max (+ hzk-min 65535)))
503 (intern (format "=hanziku-%d" i))
504 (format "HANZIKU (pseudo BIG5 encoding) part %d" i)
505 `(long-name ,(format "HANZIKU-%d" i)
511 registry ,(format "hanziku-%d$" i i)
514 code-offset ,hzk-min))
515 (define-charset-alias
516 (intern (format "ideograph-hanziku-%d" i))
517 (intern (format "=hanziku-%d" i)))
518 (setq hzk-min (1+ hzk-max)
519 hzk-max (+ hzk-min 65535))
522 (make-charset '=cbeta "CBETA private characters"
523 '(long-name "CBETA PUA"
533 (define-charset-alias 'ideograph-cbeta '=cbeta)
535 (make-charset '=zinbun-oracle
536 "Oracle Bones Script"
537 `(long-name "Oracle Bones Script in Zinbun, Kyoto Univ."
543 max-code ,(+ #xE70000 8192)
548 (make-charset '=jef-china3
549 "JEF + CHINA3 private characters"
550 '(long-name "JEF + CHINA3"
556 registry "china3jef-0"
559 code-offset #xE80000))
560 (define-charset-alias 'china3-jef '=jef-china3)
562 (make-charset '=ruimoku-v6
563 "private characters used in RUIMOKU Version.6"
572 min-code #xE90000 ; #xE000
573 max-code #xE908FF ; #xE8FF
574 code-offset ,(- #xE90000 #xE000)))
576 (make-charset '=ucs@iso
577 "ISO/IEC 10646 for its representative glyphs"
578 '(long-name "UCS for ISO"
585 (make-charset '=ucs@unicode
586 "Unicode for its representative glyphs"
587 '(long-name "UCS for Unicode"
594 (make-charset '=ucs@gb
595 "ISO/IEC 10646 for GB"
596 '(long-name "UCS for GB"
602 mother =ucs@unicode))
603 (define-charset-alias 'ucs-gb '=ucs@gb)
604 (make-charset '=ucs@gb/fw
605 "ISO/IEC 10646 for GB with fullwidth"
606 '(long-name "UCS for GB-fullwidth"
613 (make-charset '=ucs-bmp@gb
614 "ISO/IEC 10646 BMP for GB"
615 '(long-name "BMP for GB"
624 (make-charset '=ucs@cns
625 "ISO/IEC 10646 for CNS 11643"
626 '(long-name "UCS for CNS"
632 mother =ucs@unicode))
633 (define-charset-alias 'ucs-cns '=ucs@cns)
634 (make-charset '=ucs@cns/fw
635 "ISO/IEC 10646 for CNS 11643 with fullwidth"
636 '(long-name "UCS for CNS-fullwidth"
643 (make-charset '=ucs-bmp@cns
644 "ISO/IEC 10646 BMP for CNS"
645 '(long-name "BMP for CNS"
654 (make-charset '=ucs@jis
655 "ISO/IEC 10646 for JIS X0208/0212/0213"
656 '(long-name "UCS for JIS"
662 mother =ucs@unicode))
663 (define-charset-alias 'ucs-jis '=ucs@jis)
664 (make-charset '=ucs@jis/fw
665 "ISO/IEC 10646 for JIS X0208/0212/0213 with fullwidth"
666 '(long-name "UCS for JIS-fullwidth"
673 (make-charset '=ucs-bmp@jis
674 "ISO/IEC 10646 BMP for JIS"
675 '(long-name "BMP for JIS"
684 (make-charset '=ucs@jis/1990
685 "ISO/IEC 10646 for JIS X 0208/0212:1990"
686 '(long-name "UCS for JIS:1990"
693 (define-charset-alias '=ucs@jis-1990 '=ucs@jis/1990)
694 (define-charset-alias '=ucs-jis-1990 '=ucs@jis/1990)
695 (make-charset '=ucs@jis/2000
696 "ISO/IEC 10646 for JIS X 0213:2000"
697 '(long-name "UCS for JIS:2000"
704 (define-charset-alias '=ucs@jis-2000 '=ucs@jis/2000)
705 (define-charset-alias '=ucs-jis-2000 '=ucs@jis/2000)
706 (make-charset '=ucs@JP
707 "UCS for common glyphs used in Japan"
708 '(long-name "UCS for Japan"
714 mother =ucs@jis/2000))
715 (define-charset-alias '=ucs@jp '=ucs@JP)
716 (make-charset '=ucs@ks
717 "ISO/IEC 10646 for Korean Standards"
718 '(long-name "UCS for KS"
724 mother =ucs@unicode))
725 (define-charset-alias 'ucs-ks '=ucs@ks)
726 (make-charset '=ucs-bmp@ks
727 "ISO/IEC 10646 BMP for KS"
728 '(long-name "BMP for KS"
737 (make-charset '=ucs@big5
738 "ISO/IEC 10646 for Big5"
739 '(long-name "UCS for Big5"
745 mother =ucs@unicode))
746 (define-charset-alias 'ucs-big5 '=ucs@big5)
747 (make-charset '=ucs@big5/cns11643
748 "ISO/IEC 10646 for Big5 based on www.cns11643.gov.tw"
749 '(long-name "UCS for Big5@CNS11643"
756 (make-charset '=ucs@cns11643
757 "ISO/IEC 10646 for CNS based on www.cns11643.gov.tw"
758 '(long-name "UCS for CNS11643"
768 "CJK Radicals of UCS"
769 '(long-name "UCS-Radicals"
775 registry "-zhRadicals-.*-ucs-0"
777 min-code #x2E00 max-code #x2FFF))
779 '=ucs-radicals@unicode
780 "CJK Radicals of UCS"
781 '(long-name "UCS-Radicals"
787 registry "-zhRadicals-.*-ucs-0"
789 min-code #x2E00 max-code #x2FFF))
792 "Hangul Syllables of UCS"
793 '(long-name "UCS-Hangul-Syllables"
799 registry "-Hangul-.*-ucs-0"
801 min-code #xAC00 max-code #xD7AF))
804 "CJK Characters in BMP of UCS"
805 '(long-name "UCS-BMP-CJK"
811 registry "-zh-.*-ucs-0"
818 '=ucs-bmp-cjk@unicode
819 "CJK Characters in BMP of Unicode"
820 '(long-name "Unicode-BMP-CJK"
826 registry "-zh-.*-ucs-0"
834 "CJK Ideographs Extension B"
835 '(long-name "UCS CJK Ext-B"
841 registry "\\(iso10646\\|ucs02\\)-2$"
843 min-code #x20000 max-code #x2A6D6
844 code-offset #x20000))
847 "CJK Ideographs Extension B (ISO/IEC 10646-2)"
848 '(long-name "UCS CJK Ext-B"
854 registry "\\(iso10646\\|ucs02\\)-2$"
856 min-code #x20000 max-code #x2A6D6
857 code-offset #x20000))
861 "Adobe-Japan1-0 Character Collection for CID-Keyed Fonts"
862 '(long-name "Adobe-Japan1-0"
868 registry "AdobeJapan1-0$"))
871 "Adobe-Japan1-1 Character Collection for CID-Keyed Fonts"
872 '(long-name "Adobe-Japan1-1"
878 mother =adobe-japan1-0
879 registry "AdobeJapan1-1$"))
882 "Adobe-Japan1-2 Character Collection for CID-Keyed Fonts"
883 '(long-name "Adobe-Japan1-2"
889 mother =adobe-japan1-1
890 registry "AdobeJapan1-2$"))
893 "Adobe-Japan1-3 Character Collection for CID-Keyed Fonts"
894 '(long-name "Adobe-Japan1-3"
900 mother =adobe-japan1-2
901 registry "AdobeJapan1-3$"))
904 "Adobe-Japan1-4 Character Collection for CID-Keyed Fonts"
905 '(long-name "Adobe-Japan1-4"
911 mother =adobe-japan1-3
912 registry "AdobeJapan1-4$"))
915 "Adobe-Japan1-5 Character Collection for CID-Keyed Fonts"
916 '(long-name "Adobe-Japan1-5"
922 mother =adobe-japan1-4
923 registry "AdobeJapan1-5$"))
926 "Adobe-Japan1-6 Character Collection for CID-Keyed Fonts"
927 '(long-name "Adobe-Japan1-6"
933 mother =adobe-japan1-5
934 registry "AdobeJapan1-6$"))
937 ;;; mule-conf.el ends here