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, 2010 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
75 '=jis-x0208@1978/1er-pr
76 "JIS X 0208:1978, fixed by errata [Nov 1978]."
77 '(registry "jisx0208\\.1978"
80 mother =jis-x0208@1978
87 "JIS X 0208:1978, 4th impression or later."
88 '(registry "jisx0208\\.1978"
91 mother =jis-x0208@1978/1er-pr
96 (define-charset-alias '=jis-x0208@1978/i1 '=jis-x0208@1978/1pr)
97 (define-charset-alias '=jis-x0208@1978/i-4 '=jis-x0208@1978/-4pr)
98 (define-charset-alias '=jis-x0208@1978/i4- '=jis-x0208@1978/4-pr)
103 "JIS X0208:1978 Japanese Kanji (so called \"old JIS\")."
105 registry "jisx0208\\.1978"
113 (define-charset-alias '=jis-x0208-1978 '=jis-x0208@1978)
114 (define-charset-alias 'japanese-jisx0208-1978 '=jis-x0208@1978)
115 (define-charset-alias 'chinese-gb2312 '=gb2312)
116 (define-charset-alias '=jis-x0208-1983 '=jis-x0208@1983)
117 (define-charset-alias 'japanese-jisx0208 '=jis-x0208@1983)
118 (define-charset-alias 'korean-ksc5601 '=ks-x1001)
119 (define-charset-alias 'japanese-jisx0212 '=jis-x0212)
120 (define-charset-alias 'chinese-cns11643-1 '=cns11643-1)
121 (define-charset-alias 'chinese-cns11643-2 '=cns11643-2)
122 (define-charset-alias 'chinese-gb12345 '=gb12345)
123 (define-charset-alias 'chinese-big5 '=big5)
126 (make-charset 'sisheng "PinYin-ZhuYin"
127 '(registry "sisheng_cwnn\\|OMRON_UDC_ZH"
135 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
136 (make-charset 'lao "Lao script"
137 '(registry "MuleLao-1"
143 ;; IPA (International Phonetic Alphabet)
144 (make-charset 'ipa "International Phonetic Alphabet"
152 (make-charset 'ethiopic "Ethiopic"
160 ;; ISO-IR-165 (CCITT Extended GB)
161 ;; It is based on CCITT Recommendation T.101, includes GB 2312-80 +
162 ;; GB 8565-88 table A4 + 293 characters.
163 (if (featurep 'utf-2000)
165 (make-charset '=iso-ir165
166 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
174 (define-charset-alias 'chinese-isoir165 '=iso-ir165))
175 (make-charset 'chinese-isoir165
176 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
184 ;; CNS11643 Plane3 thru Plane7
185 ;; These represent more and more obscure Chinese characters.
186 ;; By the time you get to Plane 7, we're talking about characters
187 ;; that appear once in some ancient manuscript and whose meaning
191 ((make-chinese-cns11643-charset
192 (name iso-ir plane final)
194 name (concat "CNS 11643 Plane " plane " (Chinese traditional)")
197 ,(concat "CNS11643[.-]\\(.*[.-]\\)?" plane "$")
203 (make-chinese-cns11643-charset '=cns11643-3 183 "3" ?I)
204 (make-chinese-cns11643-charset '=cns11643-4 184 "4" ?J)
205 (make-chinese-cns11643-charset '=cns11643-5 185 "5" ?K)
206 (make-chinese-cns11643-charset '=cns11643-6 186 "6" ?L)
207 (make-chinese-cns11643-charset '=cns11643-7 187 "7" ?M)
208 (define-charset-alias 'chinese-cns11643-3 '=cns11643-3)
209 (define-charset-alias 'chinese-cns11643-4 '=cns11643-4)
210 (define-charset-alias 'chinese-cns11643-5 '=cns11643-5)
211 (define-charset-alias 'chinese-cns11643-6 '=cns11643-6)
212 (define-charset-alias 'chinese-cns11643-7 '=cns11643-7)
217 ((featurep 'utf-2000)
220 "JIS X 0213 Plain 1 (unchanged part)"
221 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
231 "JIS X 0213:2000 Plain 1"
233 registry "jisx0213\\(\\.2000\\)-1"
243 registry "jisx0213\\(\\.\\(2000\\|2004\\)\\)?-2"
251 "JIS X 0213:2004 Plain 1"
253 registry "jisx0213\\(\\.2004\\)-1"
260 (define-charset-alias 'japanese-jisx0213-1 '=jis-x0213-1@2000)
261 (define-charset-alias 'japanese-jisx0213-2 '=jis-x0213-2)
262 (define-charset-alias '=jis-x0213-1-2000 '=jis-x0213-1@2000)
263 (define-charset-alias '=jis-x0213-2-2000 '=jis-x0213-2)
268 "JIS X 0213:2000 Plain 1"
269 '(registry "jisx0213\\(\\.2000\\)-1"
276 "JIS X 0213:2000 Plain 2"
277 '(registry "jisx0213\\(\\.2000\\)-2"
284 (when (featurep 'utf-2000)
285 (define-charset-alias 'ucs '=ucs)
286 (define-charset-alias '=jis-x0208-1990 '=jis-x0208@1990)
287 (define-charset-alias 'japanese-jisx0208-1990 '=jis-x0208@1990)
291 "JIS X 0208 abstract glyphs (unchanged part)."
292 '(registry "jisx0208\\.1990"
301 "JIS X 0208:1978 abstract glyphs (unchanged part)."
302 '(registry "jisx0208\\.1978"
312 "JIS X 0213 Plain 1 abstract glyphs (unchanged part)"
313 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
324 "JIS X 0213:2000 Plain 1 abstract glyphs"
325 '(registry "jisx0213\\(\\.2000\\)-1"
328 mother =>>jis-x0213-1
336 "JIS X 0213 Plain 2 abstract glyphs"
337 '(registry "jisx0213\\(\\.\\(2000\\|2004\\)\\)?-2"
346 "JIS X 0213:2004 Plain 1 abstract glyphs"
347 '(registry "jisx0213\\(\\.2004\\)-1"
350 mother =>>jis-x0213-1
359 "JIS X 0208 based on the unchanged unification rules."
360 '(registry "jisx0208\\.1990"
367 (define-charset-alias '<=>jis-x0208 '=>jis-x0208)
370 "JIS X 0208 based on the unification rule of 1997 edition."
371 '(registry "jisx0208\\.1990"
378 (define-charset-alias '<=>jis-x0208@1997 '=>jis-x0208@1997)
379 (define-charset-alias ' =jis-x0208@1997 '=>jis-x0208@1997)
383 "JIS X 0213 Plain 1 abstract characters (unchanged part)"
384 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
387 mother =>>jis-x0213-1
393 (define-charset-alias '<=>jis-x0213-1 '=>jis-x0213-1)
396 "JIS X 0213:2000 Plain 1 abstract characters"
397 '(registry "jisx0213\\(\\.2000\\)-1"
406 (define-charset-alias '<=>jis-x0213-1@2000 '=>jis-x0213-1@2000)
409 "JIS X 0213:2004 Plain 1 abstract characters"
410 '(registry "jisx0213\\(\\.2004\\)-1"
419 (define-charset-alias '<=>jis-x0213-1@2004 '=>jis-x0213-1@2004)
422 "JIS X 0213 Plain 2 abstract characters"
423 '(registry "jisx0213\\(\\.\\(2000\\|2004\\)\\)?-2"
426 mother =>>jis-x0213-2
431 (make-charset '=big5-cdp
432 "Big5 with CDP extension"
433 '(long-name "Big5-CDP"
439 registry "big5\\.cdp-0"
443 (define-charset-alias 'chinese-big5-cdp '=big5-cdp)
454 min-code ,(lsh #x6100 16)
455 max-code ,(+ (lsh #x6100 16) 67547)
456 code-offset ,(lsh #x6100 16)))
457 (define-charset-alias 'ideograph-gt '=gt)
459 "GT 2000 abstract glyphs"
460 `(long-name "abstract GT glyphs"
467 (define-charset-alias '<=>gt '=>>gt)
468 (define-charset-alias '<==>gt '=>>gt)
470 "GT 2000 abstract characters"
471 `(long-name "abstract GT characters"
479 "Ideographic components of GT"
480 `(long-name "GT components"
487 min-code ,(lsh #x6110 16)
488 max-code ,(+ (lsh #x6110 16) 17090)
489 code-offset ,(lsh #x6110 16)))
490 (define-charset-alias 'ideograph-gt-k '=gt-k)
494 (intern (format "=gt-pj-%d" i))
495 (format "GT 2000 (pseudo JIS encoding) part %d" i)
496 `(long-name ,(format "GT PJ %d" i)
502 registry ,(format "\\(GTpj-%d\\|jisx0208\\.GT-%d\\)$" i i)))
503 (define-charset-alias
504 (intern (format "ideograph-gt-pj-%d" i))
505 (intern (format "=gt-pj-%d" i)))
509 "Ideographic parts of GT (pseudo JIS encoding) part 1"
516 registry "\\(GTKpj-1\\|jisx0208\\.GTK-1\\)$"))
517 (define-charset-alias 'ideograph-gt-pj-k1 '=gt-pj-k1)
520 "Ideographic parts of GT (pseudo JIS encoding) part 2"
527 registry "\\(GTKpj-2\\|jisx0208\\.GTK-2\\)$"))
528 (define-charset-alias 'ideograph-gt-pj-k2 '=gt-pj-k2)
530 (make-charset '=daikanwa
531 "Daikanwa dictionary (revised version 2)"
532 `(long-name "Daikanwa"
538 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
540 max-code ,(+ #xE00000 50100)
541 code-offset #xE00000))
542 (define-charset-alias 'ideograph-daikanwa '=daikanwa)
544 (make-charset '=daikanwa@rev1
545 "Daikanwa dictionary (revised version)"
546 `(long-name "Daikanwa Rev."
552 registry "Daikanwa\\(\\.[0-9]+\\)?-2"
555 (define-charset-alias 'ideograph-daikanwa-2 '=daikanwa@rev1)
556 (define-charset-alias '=daikanwa-rev1 '=daikanwa@rev1)
558 (make-charset '=daikanwa@rev2
559 "Daikanwa dictionary (revised version 2)"
560 `(long-name "Daikanwa"
566 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
571 ;; max-code ,(+ #xE00000 50100)
572 ;; code-offset #xE00000
574 (define-charset-alias '=daikanwa-rev2 '=daikanwa@rev2)
576 (make-charset '=shinjigen
577 "Kadokawa ShinJigen dictionary (common parts)"
578 `(long-name "Shinjigen common parts"
584 registry "Shinjigen\\(\\.[0-9]+\\)?-*"))
586 (make-charset '=shinjigen@1ed
587 "Kadokawa ShinJigen dictionary (the first edition)"
588 `(long-name "Shinjigen-1"
595 registry "Shinjigen\\(\\.[0-9]+\\)?-1"))
596 (define-charset-alias 'shinjigen-1 '=shinjigen@1ed)
598 (make-charset '=shinjigen@1ed/24pr
599 "Kadokawa ShinJigen dictionary (the 24th impression)"
600 `(long-name "Shinjigen-1 24pr"
606 mother =shinjigen@1ed))
608 (make-charset '=shinjigen@rev
609 "Kadokawa ShinJigen dictionary (the revised edition)"
610 `(long-name "Shinjigen-2"
617 registry "Shinjigen\\(\\.[0-9]+\\)?-2"))
618 (define-charset-alias 'shinjigen-2 '=shinjigen@rev)
619 (make-charset '=shinjigen/+p@rev
620 "ShinJigen (the second edition) number with '"
621 `(long-name "Shinjigen-2 with '"
627 (define-charset-alias 'shinjigen-2-p '=shinjigen/+p@rev)
629 (make-charset '=big5-pua
630 "Big5 with private used area"
631 '(long-name "Big5-PUA"
638 registry "Big5\\.ETEN"))
639 (define-charset-alias 'chinese-big5-pua '=big5-pua)
640 (make-charset '=big5-eten
642 '(long-name "Big5-ETEN"
651 registry "Big5\\.ETEN"))
652 (define-charset-alias 'chinese-big5-eten '=big5-eten)
653 (make-charset 'chinese-big5-eten-a
654 "Big5 ETEN (#xF9D6 .. #xF9FE)"
655 '(long-name "Big5-ETEN-a"
664 registry "Big5\\.ETEN"))
665 (make-charset 'chinese-big5-eten-b
666 "Big5 ETEN (#xC6A1 .. #xC8FE)"
667 '(long-name "Big5-ETEN-b"
676 registry "Big5\\.ETEN"))
679 (hzk-min (+ (lsh #x6200 16) 65536))
680 (hzk-max (+ hzk-min 65535)))
683 (intern (format "=hanziku-%d" i))
684 (format "HANZIKU (pseudo BIG5 encoding) part %d" i)
685 `(long-name ,(format "HANZIKU-%d" i)
691 registry ,(format "hanziku-%d$" i i)
694 code-offset ,hzk-min))
695 (define-charset-alias
696 (intern (format "ideograph-hanziku-%d" i))
697 (intern (format "=hanziku-%d" i)))
698 (setq hzk-min (1+ hzk-max)
699 hzk-max (+ hzk-min 65535))
702 (make-charset '=cbeta "CBETA private characters"
703 '(long-name "CBETA PUA"
713 (define-charset-alias 'ideograph-cbeta '=cbeta)
715 (make-charset '=zinbun-oracle
716 "Oracle Bones Script"
717 `(long-name "Oracle Bones Script in Zinbun, Kyoto Univ."
723 max-code ,(+ #xE70000 8192)
728 (make-charset '=>zinbun-oracle
729 "Abstract Oracle Bones"
730 '(long-name "Abstract characters of Zinbun Oracle Bones."
733 mother =zinbun-oracle
739 (make-charset '=jef-china3
740 "JEF + CHINA3 private characters"
741 '(long-name "JEF + CHINA3"
747 registry "china3jef-0"
750 code-offset #xE80000))
751 (define-charset-alias 'china3-jef '=jef-china3)
753 (make-charset '=ruimoku-v6
754 "private characters used in RUIMOKU Version.6"
763 min-code #xE90000 ; #xE000
764 max-code #xE908FF ; #xE8FF
765 code-offset ,(- #xE90000 #xE000)))
767 (make-charset '=ucs@iso
768 "ISO/IEC 10646 for its representative glyphs"
769 '(long-name "UCS for ISO"
777 (make-charset '=ucs@unicode
778 "Unicode for its representative glyphs"
779 '(long-name "UCS for Unicode"
787 (make-charset '=ucs@gb
788 "ISO/IEC 10646 for GB"
789 '(long-name "UCS for GB"
796 mother =ucs@unicode))
797 (define-charset-alias 'ucs-gb '=ucs@gb)
798 (make-charset '=ucs@gb/fw
799 "ISO/IEC 10646 for GB with fullwidth"
800 '(long-name "UCS for GB-fullwidth"
808 (make-charset '=ucs-bmp@gb
809 "ISO/IEC 10646 BMP for GB"
810 '(long-name "BMP for GB"
819 (make-charset '=ucs@cns
820 "ISO/IEC 10646 for CNS 11643"
821 '(long-name "UCS for CNS"
828 mother =ucs@unicode))
829 (define-charset-alias 'ucs-cns '=ucs@cns)
830 (make-charset '=ucs@cns/fw
831 "ISO/IEC 10646 for CNS 11643 with fullwidth"
832 '(long-name "UCS for CNS-fullwidth"
840 (make-charset '=ucs-bmp@cns
841 "ISO/IEC 10646 BMP for CNS"
842 '(long-name "BMP for CNS"
851 (make-charset '=ucs@jis
852 "ISO/IEC 10646 for JIS X0208/0212/0213"
853 '(long-name "UCS for JIS"
860 mother =ucs@unicode))
861 (define-charset-alias 'ucs-jis '=ucs@jis)
862 (make-charset '=ucs@jis/fw
863 "ISO/IEC 10646 for JIS X0208/0212/0213 with fullwidth"
864 '(long-name "UCS for JIS-fullwidth"
872 (make-charset '=ucs-bmp@jis
873 "ISO/IEC 10646 BMP for JIS"
874 '(long-name "BMP for JIS"
883 (make-charset '=ucs@jis/1990
884 "ISO/IEC 10646 for JIS X 0208/0212:1990"
885 '(long-name "UCS for JIS:1990"
893 (define-charset-alias '=ucs@jis-1990 '=ucs@jis/1990)
894 (define-charset-alias '=ucs-jis-1990 '=ucs@jis/1990)
895 (make-charset '=ucs@jis/2000
896 "ISO/IEC 10646 for JIS X 0213:2000"
897 '(long-name "UCS for JIS:2000"
905 (define-charset-alias '=ucs@jis-2000 '=ucs@jis/2000)
906 (define-charset-alias '=ucs-jis-2000 '=ucs@jis/2000)
907 (make-charset '=ucs@jis/2004
908 "ISO/IEC 10646 for JIS X 0213:2004"
909 '(long-name "UCS for JIS:2004"
917 (make-charset '=ucs@JP
918 "UCS for common glyphs used in Japan"
919 '(long-name "UCS for Japan"
926 mother =ucs@jis/2004))
927 (define-charset-alias '=ucs@jp '=ucs@JP)
928 (make-charset '=ucs@ks
929 "ISO/IEC 10646 for Korean Standards"
930 '(long-name "UCS for KS"
937 mother =ucs@unicode))
938 (define-charset-alias 'ucs-ks '=ucs@ks)
939 (make-charset '=ucs-bmp@ks
940 "ISO/IEC 10646 BMP for KS"
941 '(long-name "BMP for KS"
950 (make-charset '=ucs@cns11643
951 "ISO/IEC 10646 for CNS based on www.cns11643.gov.tw"
952 '(long-name "UCS for CNS11643"
961 (make-charset '=>>ucs@unicode
962 "Representative abstract glyphs of Unicode"
963 '(long-name "Unicode abstract glyphs"
970 mother =ucs@unicode))
971 (make-charset '=ucs@big5
972 "ISO/IEC 10646 for Big5"
973 '(long-name "UCS for Big5"
980 mother =>>ucs@unicode))
981 (define-charset-alias 'ucs-big5 '=ucs@big5)
982 (make-charset '=ucs@big5/cns11643
983 "ISO/IEC 10646 for Big5 based on www.cns11643.gov.tw"
984 '(long-name "UCS for Big5@CNS11643"
995 "CJK Radicals of UCS"
996 '(long-name "UCS-Radicals"
1002 registry "-zhRadicals-.*-ucs-0"
1004 min-code #x2E00 max-code #x2FFF))
1006 '=ucs-radicals@unicode
1007 "CJK Radicals of UCS"
1008 '(long-name "UCS-Radicals"
1014 registry "-zhRadicals-.*-ucs-0"
1016 min-code #x2E00 max-code #x2FFF))
1019 "Hangul Syllables of UCS"
1020 '(long-name "UCS-Hangul-Syllables"
1026 registry "-Hangul-.*-ucs-0"
1028 min-code #xAC00 max-code #xD7AF))
1031 "CJK Characters in BMP of UCS"
1032 '(long-name "UCS-BMP-CJK"
1038 registry "-zh-.*-ucs-0"
1045 '=ucs-bmp-cjk@unicode
1046 "CJK Characters in BMP of Unicode"
1047 '(long-name "Unicode-BMP-CJK"
1053 registry "-zh-.*-ucs-0"
1061 "CJK Ideographs Extension B"
1062 '(long-name "UCS CJK Ext-B"
1068 registry "\\(iso10646\\|ucs02\\)-2$"
1070 min-code #x20000 max-code #x2A6D6
1071 code-offset #x20000))
1074 "CJK Ideographs Extension B (ISO/IEC 10646-2)"
1075 '(long-name "UCS CJK Ext-B"
1081 registry "\\(iso10646\\|ucs02\\)-2$"
1083 min-code #x20000 max-code #x2A6D6
1084 code-offset #x20000))
1088 "Adobe-Japan1 Character Collection for CID-Keyed Fonts"
1089 `(long-name "Adobe-Japan1"
1095 registry "AdobeJapan1-[0-6]$"
1096 min-code ,(lsh #x6300 16)
1097 max-code ,(+ (lsh #x6300 16) 23057)
1098 code-offset ,(lsh #x6300 16)))
1101 "Adobe-Japan1-0 Character Collection for CID-Keyed Fonts"
1102 '(long-name "Adobe-Japan1-0"
1108 mother =adobe-japan1-base
1111 registry "AdobeJapan1-0$"))
1114 "Adobe-Japan1-1 Character Collection for CID-Keyed Fonts"
1115 '(long-name "Adobe-Japan1-1"
1121 mother =adobe-japan1-0
1124 registry "AdobeJapan1-1$"))
1127 "Adobe-Japan1-2 Character Collection for CID-Keyed Fonts"
1128 '(long-name "Adobe-Japan1-2"
1134 mother =adobe-japan1-1
1137 registry "AdobeJapan1-2$"))
1140 "Adobe-Japan1-3 Character Collection for CID-Keyed Fonts"
1141 '(long-name "Adobe-Japan1-3"
1147 mother =adobe-japan1-2
1150 registry "AdobeJapan1-3$"))
1153 "Adobe-Japan1-4 Character Collection for CID-Keyed Fonts"
1154 '(long-name "Adobe-Japan1-4"
1160 mother =adobe-japan1-3
1163 registry "AdobeJapan1-4$"))
1166 "Adobe-Japan1-5 Character Collection for CID-Keyed Fonts"
1167 '(long-name "Adobe-Japan1-5"
1173 mother =adobe-japan1-4
1176 registry "AdobeJapan1-5$"))
1179 "Adobe-Japan1-6 Character Collection for CID-Keyed Fonts"
1180 '(long-name "Adobe-Japan1-6"
1186 mother =adobe-japan1-5
1189 registry "AdobeJapan1-6$"))
1192 ;;; mule-conf.el ends here