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,
6 ;; 2009 MORIOKA Tomohiko
8 ;; Keywords: mule, multilingual, character set, coding system
10 ;; This file is part of XEmacs.
12 ;; XEmacs is free software; you can redistribute it and/or modify
13 ;; it under the terms of the GNU General Public License as published by
14 ;; the Free Software Foundation; either version 2, or (at your option)
17 ;; XEmacs is distributed in the hope that it will be useful,
18 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
19 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
20 ;; GNU General Public License for more details.
22 ;; You should have received a copy of the GNU General Public License
23 ;; along with XEmacs; see the file COPYING. If not, write to the
24 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
25 ;; Boston, MA 02111-1307, USA.
33 "JIS X 0208:1978, unchanged part."
34 '(registry "jisx0208\\.1978"
44 "JIS X 0208:1978, 1st - 3rd impressions."
45 '(registry "jisx0208\\.1978"
48 mother =jis-x0208@1978
55 "JIS X 0208:1978, 1st impression."
57 registry "jisx0208\\.1978"
60 mother =jis-x0208@1978/-4pr
65 "JIS X 0208:1978, index before the 4th impression."
66 '(registry "jisx0208\\.1978"
69 mother =jis-x0208@1978
76 "JIS X 0208:1978, 4th impression or later."
77 '(registry "jisx0208\\.1978"
80 mother =jis-x0208@1978
85 (define-charset-alias '=jis-x0208@1978/i1 '=jis-x0208@1978/1pr)
86 (define-charset-alias '=jis-x0208@1978/i-4 '=jis-x0208@1978/-4pr)
87 (define-charset-alias '=jis-x0208@1978/i4- '=jis-x0208@1978/4-pr)
92 "JIS X0208:1978 Japanese Kanji (so called \"old JIS\")."
94 registry "jisx0208\\.1978"
102 (define-charset-alias '=jis-x0208-1978 '=jis-x0208@1978)
103 (define-charset-alias 'japanese-jisx0208-1978 '=jis-x0208@1978)
104 (define-charset-alias 'chinese-gb2312 '=gb2312)
105 (define-charset-alias '=jis-x0208-1983 '=jis-x0208@1983)
106 (define-charset-alias 'japanese-jisx0208 '=jis-x0208@1983)
107 (define-charset-alias 'korean-ksc5601 '=ks-x1001)
108 (define-charset-alias 'japanese-jisx0212 '=jis-x0212)
109 (define-charset-alias 'chinese-cns11643-1 '=cns11643-1)
110 (define-charset-alias 'chinese-cns11643-2 '=cns11643-2)
111 (define-charset-alias 'chinese-gb12345 '=gb12345)
112 (define-charset-alias 'chinese-big5 '=big5)
115 (make-charset 'sisheng "PinYin-ZhuYin"
116 '(registry "sisheng_cwnn\\|OMRON_UDC_ZH"
124 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
125 (make-charset 'lao "Lao script"
126 '(registry "MuleLao-1"
132 ;; IPA (International Phonetic Alphabet)
133 (make-charset 'ipa "International Phonetic Alphabet"
141 (make-charset 'ethiopic "Ethiopic"
149 ;; ISO-IR-165 (CCITT Extended GB)
150 ;; It is based on CCITT Recommendation T.101, includes GB 2312-80 +
151 ;; GB 8565-88 table A4 + 293 characters.
152 (if (featurep 'utf-2000)
154 (make-charset '=iso-ir165
155 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
163 (define-charset-alias 'chinese-isoir165 '=iso-ir165))
164 (make-charset 'chinese-isoir165
165 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
173 ;; CNS11643 Plane3 thru Plane7
174 ;; These represent more and more obscure Chinese characters.
175 ;; By the time you get to Plane 7, we're talking about characters
176 ;; that appear once in some ancient manuscript and whose meaning
180 ((make-chinese-cns11643-charset
181 (name iso-ir plane final)
183 name (concat "CNS 11643 Plane " plane " (Chinese traditional)")
186 ,(concat "CNS11643[.-]\\(.*[.-]\\)?" plane "$")
192 (make-chinese-cns11643-charset '=cns11643-3 183 "3" ?I)
193 (make-chinese-cns11643-charset '=cns11643-4 184 "4" ?J)
194 (make-chinese-cns11643-charset '=cns11643-5 185 "5" ?K)
195 (make-chinese-cns11643-charset '=cns11643-6 186 "6" ?L)
196 (make-chinese-cns11643-charset '=cns11643-7 187 "7" ?M)
197 (define-charset-alias 'chinese-cns11643-3 '=cns11643-3)
198 (define-charset-alias 'chinese-cns11643-4 '=cns11643-4)
199 (define-charset-alias 'chinese-cns11643-5 '=cns11643-5)
200 (define-charset-alias 'chinese-cns11643-6 '=cns11643-6)
201 (define-charset-alias 'chinese-cns11643-7 '=cns11643-7)
206 ((featurep 'utf-2000)
209 "JIS X 0213 Plain 1 (unchanged part)"
210 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
220 "JIS X 0213:2000 Plain 1"
222 registry "jisx0213\\(\\.2000\\)-1"
232 registry "jisx0213\\(\\.\\(2000\\|2004\\)\\)?-2"
240 "JIS X 0213:2004 Plain 1"
242 registry "jisx0213\\(\\.2004\\)-1"
249 (define-charset-alias 'japanese-jisx0213-1 '=jis-x0213-1@2000)
250 (define-charset-alias 'japanese-jisx0213-2 '=jis-x0213-2)
251 (define-charset-alias '=jis-x0213-1-2000 '=jis-x0213-1@2000)
252 (define-charset-alias '=jis-x0213-2-2000 '=jis-x0213-2)
257 "JIS X 0213:2000 Plain 1"
258 '(registry "jisx0213\\(\\.2000\\)-1"
265 "JIS X 0213:2000 Plain 2"
266 '(registry "jisx0213\\(\\.2000\\)-2"
273 (when (featurep 'utf-2000)
274 (define-charset-alias 'ucs '=ucs)
275 (define-charset-alias '=jis-x0208-1990 '=jis-x0208@1990)
276 (define-charset-alias 'japanese-jisx0208-1990 '=jis-x0208@1990)
280 "JIS X 0208 abstract glyphs (unchanged part)."
281 '(registry "jisx0208\\.1990"
291 "JIS X 0213 Plain 1 abstract glyphs (unchanged part)"
292 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
303 "JIS X 0213:2000 Plain 1 abstract glyphs"
304 '(registry "jisx0213\\(\\.2000\\)-1"
307 mother =>>jis-x0213-1
315 "JIS X 0213:2004 Plain 1 abstract glyphs"
316 '(registry "jisx0213\\(\\.2004\\)-1"
319 mother =>>jis-x0213-1
328 "JIS X 0208 based on the unchanged unification rules."
329 '(registry "jisx0208\\.1990"
336 (define-charset-alias '<=>jis-x0208 '=>jis-x0208)
339 "JIS X 0208 based on the unification rule of 1997 edition."
340 '(registry "jisx0208\\.1990"
347 (define-charset-alias '<=>jis-x0208@1997 '=>jis-x0208@1997)
348 (define-charset-alias ' =jis-x0208@1997 '=>jis-x0208@1997)
352 "JIS X 0213 Plain 1 abstract characters (unchanged part)"
353 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
356 mother =>>jis-x0213-1
362 (define-charset-alias '<=>jis-x0213-1 '=>jis-x0213-1)
365 "JIS X 0213:2000 Plain 1 abstract characters"
366 '(registry "jisx0213\\(\\.2000\\)-1"
375 (define-charset-alias '<=>jis-x0213-1@2000 '=>jis-x0213-1@2000)
378 "JIS X 0213:2004 Plain 1 abstract characters"
379 '(registry "jisx0213\\(\\.2004\\)-1"
388 (define-charset-alias '<=>jis-x0213-1@2004 '=>jis-x0213-1@2004)
390 (make-charset '=big5-cdp
391 "Big5 with CDP extension"
392 '(long-name "Big5-CDP"
398 registry "big5\\.cdp-0"
402 (define-charset-alias 'chinese-big5-cdp '=big5-cdp)
413 min-code ,(lsh #x6100 16)
414 max-code ,(+ (lsh #x6100 16) 67547)
415 code-offset ,(lsh #x6100 16)))
416 (define-charset-alias 'ideograph-gt '=gt)
418 "GT 2000 abstract glyphs"
419 `(long-name "abstract GT"
426 (define-charset-alias '<=>gt '=>>gt)
427 (define-charset-alias '<==>gt '=>>gt)
429 "Ideographic components of GT"
430 `(long-name "GT components"
437 min-code ,(lsh #x6110 16)
438 max-code ,(+ (lsh #x6110 16) 17090)
439 code-offset ,(lsh #x6110 16)))
440 (define-charset-alias 'ideograph-gt-k '=gt-k)
444 (intern (format "=gt-pj-%d" i))
445 (format "GT 2000 (pseudo JIS encoding) part %d" i)
446 `(long-name ,(format "GT PJ %d" i)
452 registry ,(format "\\(GTpj-%d\\|jisx0208\\.GT-%d\\)$" i i)))
453 (define-charset-alias
454 (intern (format "ideograph-gt-pj-%d" i))
455 (intern (format "=gt-pj-%d" i)))
459 "Ideographic parts of GT (pseudo JIS encoding) part 1"
466 registry "\\(GTKpj-1\\|jisx0208\\.GTK-1\\)$"))
467 (define-charset-alias 'ideograph-gt-pj-k1 '=gt-pj-k1)
470 "Ideographic parts of GT (pseudo JIS encoding) part 2"
477 registry "\\(GTKpj-2\\|jisx0208\\.GTK-2\\)$"))
478 (define-charset-alias 'ideograph-gt-pj-k2 '=gt-pj-k2)
480 (make-charset '=daikanwa
481 "Daikanwa dictionary (revised version 2)"
482 `(long-name "Daikanwa"
488 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
490 max-code ,(+ #xE00000 50100)
491 code-offset #xE00000))
492 (define-charset-alias 'ideograph-daikanwa '=daikanwa)
494 (make-charset '=daikanwa@rev1
495 "Daikanwa dictionary (revised version)"
496 `(long-name "Daikanwa Rev."
502 registry "Daikanwa\\(\\.[0-9]+\\)?-2"
505 (define-charset-alias 'ideograph-daikanwa-2 '=daikanwa@rev1)
506 (define-charset-alias '=daikanwa-rev1 '=daikanwa@rev1)
508 (make-charset '=daikanwa@rev2
509 "Daikanwa dictionary (revised version 2)"
510 `(long-name "Daikanwa"
516 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
521 ;; max-code ,(+ #xE00000 50100)
522 ;; code-offset #xE00000
524 (define-charset-alias '=daikanwa-rev2 '=daikanwa@rev2)
526 (make-charset '=shinjigen
527 "Kadokawa ShinJigen dictionary (common parts)"
528 `(long-name "Shinjigen common parts"
534 registry "Shinjigen\\(\\.[0-9]+\\)?-*"))
536 (make-charset '=shinjigen@1ed
537 "Kadokawa ShinJigen dictionary (the first edition)"
538 `(long-name "Shinjigen-1"
545 registry "Shinjigen\\(\\.[0-9]+\\)?-1"))
546 (define-charset-alias 'shinjigen-1 '=shinjigen@1ed)
548 (make-charset '=shinjigen@1ed/24pr
549 "Kadokawa ShinJigen dictionary (the 24th impression)"
550 `(long-name "Shinjigen-1 24pr"
556 mother =shinjigen@1ed))
558 (make-charset '=shinjigen@rev
559 "Kadokawa ShinJigen dictionary (the revised edition)"
560 `(long-name "Shinjigen-2"
567 registry "Shinjigen\\(\\.[0-9]+\\)?-2"))
568 (define-charset-alias 'shinjigen-2 '=shinjigen@rev)
569 (make-charset '=shinjigen/+p@rev
570 "ShinJigen (the second edition) number with '"
571 `(long-name "Shinjigen-2 with '"
577 (define-charset-alias 'shinjigen-2-p '=shinjigen/+p@rev)
579 (make-charset '=big5-pua
580 "Big5 with private used area"
581 '(long-name "Big5-PUA"
588 registry "Big5\\.ETEN"))
589 (define-charset-alias 'chinese-big5-pua '=big5-pua)
590 (make-charset '=big5-eten
592 '(long-name "Big5-ETEN"
601 registry "Big5\\.ETEN"))
602 (define-charset-alias 'chinese-big5-eten '=big5-eten)
603 (make-charset 'chinese-big5-eten-a
604 "Big5 ETEN (#xF9D6 .. #xF9FE)"
605 '(long-name "Big5-ETEN-a"
614 registry "Big5\\.ETEN"))
615 (make-charset 'chinese-big5-eten-b
616 "Big5 ETEN (#xC6A1 .. #xC8FE)"
617 '(long-name "Big5-ETEN-b"
626 registry "Big5\\.ETEN"))
629 (hzk-min (+ (lsh #x6200 16) 65536))
630 (hzk-max (+ hzk-min 65535)))
633 (intern (format "=hanziku-%d" i))
634 (format "HANZIKU (pseudo BIG5 encoding) part %d" i)
635 `(long-name ,(format "HANZIKU-%d" i)
641 registry ,(format "hanziku-%d$" i i)
644 code-offset ,hzk-min))
645 (define-charset-alias
646 (intern (format "ideograph-hanziku-%d" i))
647 (intern (format "=hanziku-%d" i)))
648 (setq hzk-min (1+ hzk-max)
649 hzk-max (+ hzk-min 65535))
652 (make-charset '=cbeta "CBETA private characters"
653 '(long-name "CBETA PUA"
663 (define-charset-alias 'ideograph-cbeta '=cbeta)
665 (make-charset '=zinbun-oracle
666 "Oracle Bones Script"
667 `(long-name "Oracle Bones Script in Zinbun, Kyoto Univ."
673 max-code ,(+ #xE70000 8192)
678 (make-charset '=jef-china3
679 "JEF + CHINA3 private characters"
680 '(long-name "JEF + CHINA3"
686 registry "china3jef-0"
689 code-offset #xE80000))
690 (define-charset-alias 'china3-jef '=jef-china3)
692 (make-charset '=ruimoku-v6
693 "private characters used in RUIMOKU Version.6"
702 min-code #xE90000 ; #xE000
703 max-code #xE908FF ; #xE8FF
704 code-offset ,(- #xE90000 #xE000)))
706 (make-charset '=ucs@iso
707 "ISO/IEC 10646 for its representative glyphs"
708 '(long-name "UCS for ISO"
716 (make-charset '=ucs@unicode
717 "Unicode for its representative glyphs"
718 '(long-name "UCS for Unicode"
726 (make-charset '=ucs@gb
727 "ISO/IEC 10646 for GB"
728 '(long-name "UCS for GB"
735 mother =ucs@unicode))
736 (define-charset-alias 'ucs-gb '=ucs@gb)
737 (make-charset '=ucs@gb/fw
738 "ISO/IEC 10646 for GB with fullwidth"
739 '(long-name "UCS for GB-fullwidth"
747 (make-charset '=ucs-bmp@gb
748 "ISO/IEC 10646 BMP for GB"
749 '(long-name "BMP for GB"
758 (make-charset '=ucs@cns
759 "ISO/IEC 10646 for CNS 11643"
760 '(long-name "UCS for CNS"
767 mother =ucs@unicode))
768 (define-charset-alias 'ucs-cns '=ucs@cns)
769 (make-charset '=ucs@cns/fw
770 "ISO/IEC 10646 for CNS 11643 with fullwidth"
771 '(long-name "UCS for CNS-fullwidth"
779 (make-charset '=ucs-bmp@cns
780 "ISO/IEC 10646 BMP for CNS"
781 '(long-name "BMP for CNS"
790 (make-charset '=ucs@jis
791 "ISO/IEC 10646 for JIS X0208/0212/0213"
792 '(long-name "UCS for JIS"
799 mother =ucs@unicode))
800 (define-charset-alias 'ucs-jis '=ucs@jis)
801 (make-charset '=ucs@jis/fw
802 "ISO/IEC 10646 for JIS X0208/0212/0213 with fullwidth"
803 '(long-name "UCS for JIS-fullwidth"
811 (make-charset '=ucs-bmp@jis
812 "ISO/IEC 10646 BMP for JIS"
813 '(long-name "BMP for JIS"
822 (make-charset '=ucs@jis/1990
823 "ISO/IEC 10646 for JIS X 0208/0212:1990"
824 '(long-name "UCS for JIS:1990"
832 (define-charset-alias '=ucs@jis-1990 '=ucs@jis/1990)
833 (define-charset-alias '=ucs-jis-1990 '=ucs@jis/1990)
834 (make-charset '=ucs@jis/2000
835 "ISO/IEC 10646 for JIS X 0213:2000"
836 '(long-name "UCS for JIS:2000"
844 (define-charset-alias '=ucs@jis-2000 '=ucs@jis/2000)
845 (define-charset-alias '=ucs-jis-2000 '=ucs@jis/2000)
846 (make-charset '=ucs@jis/2004
847 "ISO/IEC 10646 for JIS X 0213:2004"
848 '(long-name "UCS for JIS:2004"
856 (make-charset '=ucs@JP
857 "UCS for common glyphs used in Japan"
858 '(long-name "UCS for Japan"
865 mother =ucs@jis/2004))
866 (define-charset-alias '=ucs@jp '=ucs@JP)
867 (make-charset '=ucs@ks
868 "ISO/IEC 10646 for Korean Standards"
869 '(long-name "UCS for KS"
876 mother =ucs@unicode))
877 (define-charset-alias 'ucs-ks '=ucs@ks)
878 (make-charset '=ucs-bmp@ks
879 "ISO/IEC 10646 BMP for KS"
880 '(long-name "BMP for KS"
889 (make-charset '=ucs@big5
890 "ISO/IEC 10646 for Big5"
891 '(long-name "UCS for Big5"
898 mother =ucs@unicode))
899 (define-charset-alias 'ucs-big5 '=ucs@big5)
900 (make-charset '=ucs@big5/cns11643
901 "ISO/IEC 10646 for Big5 based on www.cns11643.gov.tw"
902 '(long-name "UCS for Big5@CNS11643"
910 (make-charset '=ucs@cns11643
911 "ISO/IEC 10646 for CNS based on www.cns11643.gov.tw"
912 '(long-name "UCS for CNS11643"
923 "CJK Radicals of UCS"
924 '(long-name "UCS-Radicals"
930 registry "-zhRadicals-.*-ucs-0"
932 min-code #x2E00 max-code #x2FFF))
934 '=ucs-radicals@unicode
935 "CJK Radicals of UCS"
936 '(long-name "UCS-Radicals"
942 registry "-zhRadicals-.*-ucs-0"
944 min-code #x2E00 max-code #x2FFF))
947 "Hangul Syllables of UCS"
948 '(long-name "UCS-Hangul-Syllables"
954 registry "-Hangul-.*-ucs-0"
956 min-code #xAC00 max-code #xD7AF))
959 "CJK Characters in BMP of UCS"
960 '(long-name "UCS-BMP-CJK"
966 registry "-zh-.*-ucs-0"
973 '=ucs-bmp-cjk@unicode
974 "CJK Characters in BMP of Unicode"
975 '(long-name "Unicode-BMP-CJK"
981 registry "-zh-.*-ucs-0"
989 "CJK Ideographs Extension B"
990 '(long-name "UCS CJK Ext-B"
996 registry "\\(iso10646\\|ucs02\\)-2$"
998 min-code #x20000 max-code #x2A6D6
999 code-offset #x20000))
1002 "CJK Ideographs Extension B (ISO/IEC 10646-2)"
1003 '(long-name "UCS CJK Ext-B"
1009 registry "\\(iso10646\\|ucs02\\)-2$"
1011 min-code #x20000 max-code #x2A6D6
1012 code-offset #x20000))
1016 "Adobe-Japan1-0 Character Collection for CID-Keyed Fonts"
1017 '(long-name "Adobe-Japan1-0"
1023 registry "AdobeJapan1-0$"))
1026 "Adobe-Japan1-1 Character Collection for CID-Keyed Fonts"
1027 '(long-name "Adobe-Japan1-1"
1033 mother =adobe-japan1-0
1034 registry "AdobeJapan1-1$"))
1037 "Adobe-Japan1-2 Character Collection for CID-Keyed Fonts"
1038 '(long-name "Adobe-Japan1-2"
1044 mother =adobe-japan1-1
1045 registry "AdobeJapan1-2$"))
1048 "Adobe-Japan1-3 Character Collection for CID-Keyed Fonts"
1049 '(long-name "Adobe-Japan1-3"
1055 mother =adobe-japan1-2
1056 registry "AdobeJapan1-3$"))
1059 "Adobe-Japan1-4 Character Collection for CID-Keyed Fonts"
1060 '(long-name "Adobe-Japan1-4"
1066 mother =adobe-japan1-3
1067 registry "AdobeJapan1-4$"))
1070 "Adobe-Japan1-5 Character Collection for CID-Keyed Fonts"
1071 '(long-name "Adobe-Japan1-5"
1077 mother =adobe-japan1-4
1078 registry "AdobeJapan1-5$"))
1081 "Adobe-Japan1-6 Character Collection for CID-Keyed Fonts"
1082 '(long-name "Adobe-Japan1-6"
1088 mother =adobe-japan1-5
1089 registry "AdobeJapan1-6$"))
1092 ;;; mule-conf.el ends here