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, 2nd impression or later."
88 '(registry "jisx0208\\.1978"
91 mother =jis-x0208@1978/1er-pr
98 "JIS X 0208:1978, replaced by errata of 4th impression."
99 '(registry "jisx0208\\.1978"
102 mother =jis-x0208@1978/2-pr
108 '=jis-x0208@1978/4-pr
109 "JIS X 0208:1978, 4th impression or later."
110 '(registry "jisx0208\\.1978"
113 mother =jis-x0208@1978/2-pr
120 "JIS X 0208:1978, 5th impression."
121 '(registry "jisx0208\\.1978"
124 mother =jis-x0208@1978/4-pr
129 (define-charset-alias '=jis-x0208@1978/i1 '=jis-x0208@1978/1pr)
130 (define-charset-alias '=jis-x0208@1978/i-4 '=jis-x0208@1978/-4pr)
131 (define-charset-alias '=jis-x0208@1978/i4- '=jis-x0208@1978/4-pr)
136 "JIS X0208:1978 Japanese Kanji (so called \"old JIS\")."
138 registry "jisx0208\\.1978"
146 (define-charset-alias '=jis-x0208-1978 '=jis-x0208@1978)
147 (define-charset-alias 'japanese-jisx0208-1978 '=jis-x0208@1978)
148 (define-charset-alias 'chinese-gb2312 '=gb2312)
149 (define-charset-alias '=jis-x0208-1983 '=jis-x0208@1983)
150 (define-charset-alias 'japanese-jisx0208 '=jis-x0208@1983)
151 (define-charset-alias 'korean-ksc5601 '=ks-x1001)
152 (define-charset-alias 'japanese-jisx0212 '=jis-x0212)
153 (define-charset-alias 'chinese-cns11643-1 '=cns11643-1)
154 (define-charset-alias 'chinese-cns11643-2 '=cns11643-2)
155 (define-charset-alias 'chinese-gb12345 '=gb12345)
156 (define-charset-alias 'chinese-big5 '=big5)
159 (make-charset 'sisheng "PinYin-ZhuYin"
160 '(registry "sisheng_cwnn\\|OMRON_UDC_ZH"
168 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
169 (make-charset 'lao "Lao script"
170 '(registry "MuleLao-1"
176 ;; IPA (International Phonetic Alphabet)
177 (make-charset 'ipa "International Phonetic Alphabet"
185 (make-charset 'ethiopic "Ethiopic"
193 ;; ISO-IR-165 (CCITT Extended GB)
194 ;; It is based on CCITT Recommendation T.101, includes GB 2312-80 +
195 ;; GB 8565-88 table A4 + 293 characters.
196 (if (featurep 'utf-2000)
198 (make-charset '=iso-ir165
199 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
207 (define-charset-alias 'chinese-isoir165 '=iso-ir165))
208 (make-charset 'chinese-isoir165
209 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
217 ;; CNS11643 Plane3 thru Plane7
218 ;; These represent more and more obscure Chinese characters.
219 ;; By the time you get to Plane 7, we're talking about characters
220 ;; that appear once in some ancient manuscript and whose meaning
224 ((make-chinese-cns11643-charset
225 (name iso-ir plane final)
227 name (concat "CNS 11643 Plane " plane " (Chinese traditional)")
230 ,(concat "CNS11643[.-]\\(.*[.-]\\)?" plane "$")
236 (make-chinese-cns11643-charset '=cns11643-3 183 "3" ?I)
237 (make-chinese-cns11643-charset '=cns11643-4 184 "4" ?J)
238 (make-chinese-cns11643-charset '=cns11643-5 185 "5" ?K)
239 (make-chinese-cns11643-charset '=cns11643-6 186 "6" ?L)
240 (make-chinese-cns11643-charset '=cns11643-7 187 "7" ?M)
241 (define-charset-alias 'chinese-cns11643-3 '=cns11643-3)
242 (define-charset-alias 'chinese-cns11643-4 '=cns11643-4)
243 (define-charset-alias 'chinese-cns11643-5 '=cns11643-5)
244 (define-charset-alias 'chinese-cns11643-6 '=cns11643-6)
245 (define-charset-alias 'chinese-cns11643-7 '=cns11643-7)
250 ((featurep 'utf-2000)
253 "JIS X 0213 Plain 1 (unchanged part)"
254 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
264 "JIS X 0213:2000 Plain 1"
266 registry "jisx0213\\(\\.2000\\)-1"
276 registry "jisx0213\\(\\.\\(2000\\|2004\\)\\)?-2"
284 "JIS X 0213:2004 Plain 1"
286 registry "jisx0213\\(\\.2004\\)-1"
293 (define-charset-alias 'japanese-jisx0213-1 '=jis-x0213-1@2000)
294 (define-charset-alias 'japanese-jisx0213-2 '=jis-x0213-2)
295 (define-charset-alias '=jis-x0213-1-2000 '=jis-x0213-1@2000)
296 (define-charset-alias '=jis-x0213-2-2000 '=jis-x0213-2)
301 "JIS X 0213:2000 Plain 1"
302 '(registry "jisx0213\\(\\.2000\\)-1"
309 "JIS X 0213:2000 Plain 2"
310 '(registry "jisx0213\\(\\.2000\\)-2"
317 (when (featurep 'utf-2000)
318 (define-charset-alias 'ucs '=ucs)
319 (define-charset-alias '=jis-x0208-1990 '=jis-x0208@1990)
320 (define-charset-alias 'japanese-jisx0208-1990 '=jis-x0208@1990)
324 "JIS X 0208 abstract glyphs (unchanged part)."
325 '(registry "jisx0208\\.1990"
334 "JIS X 0208:1978 abstract glyphs (unchanged part)."
335 '(registry "jisx0208\\.1978"
345 "JIS X 0213 Plain 1 abstract glyphs (unchanged part)"
346 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
357 "JIS X 0213:2000 Plain 1 abstract glyphs"
358 '(registry "jisx0213\\(\\.2000\\)-1"
361 mother =>>jis-x0213-1
369 "JIS X 0213 Plain 2 abstract glyphs"
370 '(registry "jisx0213\\(\\.\\(2000\\|2004\\)\\)?-2"
379 "JIS X 0213:2004 Plain 1 abstract glyphs"
380 '(registry "jisx0213\\(\\.2004\\)-1"
383 mother =>>jis-x0213-1
392 "JIS X 0208 based on the unchanged unification rules."
393 '(registry "jisx0208\\.1990"
400 (define-charset-alias '<=>jis-x0208 '=>jis-x0208)
403 "JIS X 0208 based on the unification rule of 1997 edition."
404 '(registry "jisx0208\\.1990"
411 (define-charset-alias '<=>jis-x0208@1997 '=>jis-x0208@1997)
412 (define-charset-alias ' =jis-x0208@1997 '=>jis-x0208@1997)
416 "JIS X 0213 Plain 1 abstract characters (unchanged part)"
417 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
420 mother =>>jis-x0213-1
426 (define-charset-alias '<=>jis-x0213-1 '=>jis-x0213-1)
429 "JIS X 0213:2000 Plain 1 abstract characters"
430 '(registry "jisx0213\\(\\.2000\\)-1"
439 (define-charset-alias '<=>jis-x0213-1@2000 '=>jis-x0213-1@2000)
442 "JIS X 0213:2004 Plain 1 abstract characters"
443 '(registry "jisx0213\\(\\.2004\\)-1"
452 (define-charset-alias '<=>jis-x0213-1@2004 '=>jis-x0213-1@2004)
455 "JIS X 0213 Plain 2 abstract characters"
456 '(registry "jisx0213\\(\\.\\(2000\\|2004\\)\\)?-2"
459 mother =>>jis-x0213-2
464 (make-charset '=big5-cdp
465 "Big5 with CDP extension"
466 '(long-name "Big5-CDP"
472 registry "big5\\.cdp-0"
476 (define-charset-alias 'chinese-big5-cdp '=big5-cdp)
487 min-code ,(lsh #x6100 16)
488 max-code ,(+ (lsh #x6100 16) 67547)
489 code-offset ,(lsh #x6100 16)))
490 (define-charset-alias 'ideograph-gt '=gt)
492 "GT 2000 abstract glyphs"
493 `(long-name "abstract GT glyphs"
500 (define-charset-alias '<=>gt '=>>gt)
501 (define-charset-alias '<==>gt '=>>gt)
503 "GT 2000 abstract characters"
504 `(long-name "abstract GT characters"
512 "Ideographic components of GT"
513 `(long-name "GT components"
520 min-code ,(lsh #x6110 16)
521 max-code ,(+ (lsh #x6110 16) 17090)
522 code-offset ,(lsh #x6110 16)))
523 (define-charset-alias 'ideograph-gt-k '=gt-k)
527 (intern (format "=gt-pj-%d" i))
528 (format "GT 2000 (pseudo JIS encoding) part %d" i)
529 `(long-name ,(format "GT PJ %d" i)
535 registry ,(format "\\(GTpj-%d\\|jisx0208\\.GT-%d\\)$" i i)))
536 (define-charset-alias
537 (intern (format "ideograph-gt-pj-%d" i))
538 (intern (format "=gt-pj-%d" i)))
542 "Ideographic parts of GT (pseudo JIS encoding) part 1"
549 registry "\\(GTKpj-1\\|jisx0208\\.GTK-1\\)$"))
550 (define-charset-alias 'ideograph-gt-pj-k1 '=gt-pj-k1)
553 "Ideographic parts of GT (pseudo JIS encoding) part 2"
560 registry "\\(GTKpj-2\\|jisx0208\\.GTK-2\\)$"))
561 (define-charset-alias 'ideograph-gt-pj-k2 '=gt-pj-k2)
563 (make-charset '=daikanwa
564 "Daikanwa dictionary (revised version 2)"
565 `(long-name "Daikanwa"
571 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
573 max-code ,(+ #xE00000 50100)
574 code-offset #xE00000))
575 (define-charset-alias 'ideograph-daikanwa '=daikanwa)
577 (make-charset '=daikanwa@rev1
578 "Daikanwa dictionary (revised version)"
579 `(long-name "Daikanwa Rev."
585 registry "Daikanwa\\(\\.[0-9]+\\)?-2"
588 (define-charset-alias 'ideograph-daikanwa-2 '=daikanwa@rev1)
589 (define-charset-alias '=daikanwa-rev1 '=daikanwa@rev1)
591 (make-charset '=daikanwa@rev2
592 "Daikanwa dictionary (revised version 2)"
593 `(long-name "Daikanwa"
599 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
604 ;; max-code ,(+ #xE00000 50100)
605 ;; code-offset #xE00000
607 (define-charset-alias '=daikanwa-rev2 '=daikanwa@rev2)
609 (make-charset '=shinjigen
610 "Kadokawa ShinJigen dictionary (common parts)"
611 `(long-name "Shinjigen common parts"
617 registry "Shinjigen\\(\\.[0-9]+\\)?-*"))
619 (make-charset '=shinjigen@1ed
620 "Kadokawa ShinJigen dictionary (the first edition)"
621 `(long-name "Shinjigen-1"
628 registry "Shinjigen\\(\\.[0-9]+\\)?-1"))
629 (define-charset-alias 'shinjigen-1 '=shinjigen@1ed)
631 (make-charset '=shinjigen@1ed/24pr
632 "Kadokawa ShinJigen dictionary (the 24th impression)"
633 `(long-name "Shinjigen-1 24pr"
639 mother =shinjigen@1ed))
641 (make-charset '=shinjigen@rev
642 "Kadokawa ShinJigen dictionary (the revised edition)"
643 `(long-name "Shinjigen-2"
650 registry "Shinjigen\\(\\.[0-9]+\\)?-2"))
651 (define-charset-alias 'shinjigen-2 '=shinjigen@rev)
652 (make-charset '=shinjigen/+p@rev
653 "ShinJigen (the second edition) number with '"
654 `(long-name "Shinjigen-2 with '"
660 (define-charset-alias 'shinjigen-2-p '=shinjigen/+p@rev)
662 (make-charset '=big5-pua
663 "Big5 with private used area"
664 '(long-name "Big5-PUA"
671 registry "Big5\\.ETEN"))
672 (define-charset-alias 'chinese-big5-pua '=big5-pua)
673 (make-charset '=big5-eten
675 '(long-name "Big5-ETEN"
684 registry "Big5\\.ETEN"))
685 (define-charset-alias 'chinese-big5-eten '=big5-eten)
686 (make-charset 'chinese-big5-eten-a
687 "Big5 ETEN (#xF9D6 .. #xF9FE)"
688 '(long-name "Big5-ETEN-a"
697 registry "Big5\\.ETEN"))
698 (make-charset 'chinese-big5-eten-b
699 "Big5 ETEN (#xC6A1 .. #xC8FE)"
700 '(long-name "Big5-ETEN-b"
709 registry "Big5\\.ETEN"))
712 (hzk-min (+ (lsh #x6200 16) 65536))
713 (hzk-max (+ hzk-min 65535)))
716 (intern (format "=hanziku-%d" i))
717 (format "HANZIKU (pseudo BIG5 encoding) part %d" i)
718 `(long-name ,(format "HANZIKU-%d" i)
724 registry ,(format "hanziku-%d$" i i)
727 code-offset ,hzk-min))
728 (define-charset-alias
729 (intern (format "ideograph-hanziku-%d" i))
730 (intern (format "=hanziku-%d" i)))
731 (setq hzk-min (1+ hzk-max)
732 hzk-max (+ hzk-min 65535))
735 (make-charset '=cbeta "CBETA private characters"
736 '(long-name "CBETA PUA"
746 (define-charset-alias 'ideograph-cbeta '=cbeta)
748 (make-charset '=zinbun-oracle
749 "Oracle Bones Script"
750 `(long-name "Oracle Bones Script in Zinbun, Kyoto Univ."
756 max-code ,(+ #xE70000 8192)
761 (make-charset '=>zinbun-oracle
762 "Abstract Oracle Bones"
763 '(long-name "Abstract characters of Zinbun Oracle Bones."
766 mother =zinbun-oracle
772 (make-charset '=jef-china3
773 "JEF + CHINA3 private characters"
774 '(long-name "JEF + CHINA3"
780 registry "china3jef-0"
783 code-offset #xE80000))
784 (define-charset-alias 'china3-jef '=jef-china3)
786 (make-charset '=ruimoku-v6
787 "private characters used in RUIMOKU Version.6"
796 min-code #xE90000 ; #xE000
797 max-code #xE908FF ; #xE8FF
798 code-offset ,(- #xE90000 #xE000)))
800 (make-charset '=ucs@iso
801 "ISO/IEC 10646 for its representative glyphs"
802 '(long-name "UCS for ISO"
810 (make-charset '=ucs@unicode
811 "Unicode for its representative glyphs"
812 '(long-name "UCS for Unicode"
820 (make-charset '=ucs@gb
821 "ISO/IEC 10646 for GB"
822 '(long-name "UCS for GB"
829 mother =ucs@unicode))
830 (define-charset-alias 'ucs-gb '=ucs@gb)
831 (make-charset '=ucs@gb/fw
832 "ISO/IEC 10646 for GB with fullwidth"
833 '(long-name "UCS for GB-fullwidth"
841 (make-charset '=ucs-bmp@gb
842 "ISO/IEC 10646 BMP for GB"
843 '(long-name "BMP for GB"
852 (make-charset '=ucs@cns
853 "ISO/IEC 10646 for CNS 11643"
854 '(long-name "UCS for CNS"
861 mother =ucs@unicode))
862 (define-charset-alias 'ucs-cns '=ucs@cns)
863 (make-charset '=ucs@cns/fw
864 "ISO/IEC 10646 for CNS 11643 with fullwidth"
865 '(long-name "UCS for CNS-fullwidth"
873 (make-charset '=ucs-bmp@cns
874 "ISO/IEC 10646 BMP for CNS"
875 '(long-name "BMP for CNS"
884 (make-charset '=ucs@jis
885 "ISO/IEC 10646 for JIS X0208/0212/0213"
886 '(long-name "UCS for JIS"
893 mother =ucs@unicode))
894 (define-charset-alias 'ucs-jis '=ucs@jis)
895 (make-charset '=ucs@jis/fw
896 "ISO/IEC 10646 for JIS X0208/0212/0213 with fullwidth"
897 '(long-name "UCS for JIS-fullwidth"
905 (make-charset '=ucs-bmp@jis
906 "ISO/IEC 10646 BMP for JIS"
907 '(long-name "BMP for JIS"
916 (make-charset '=ucs@jis/1990
917 "ISO/IEC 10646 for JIS X 0208/0212:1990"
918 '(long-name "UCS for JIS:1990"
926 (define-charset-alias '=ucs@jis-1990 '=ucs@jis/1990)
927 (define-charset-alias '=ucs-jis-1990 '=ucs@jis/1990)
928 (make-charset '=ucs@jis/2000
929 "ISO/IEC 10646 for JIS X 0213:2000"
930 '(long-name "UCS for JIS:2000"
938 (define-charset-alias '=ucs@jis-2000 '=ucs@jis/2000)
939 (define-charset-alias '=ucs-jis-2000 '=ucs@jis/2000)
940 (make-charset '=ucs@jis/2004
941 "ISO/IEC 10646 for JIS X 0213:2004"
942 '(long-name "UCS for JIS:2004"
950 (make-charset '=ucs@JP
951 "UCS for common glyphs used in Japan"
952 '(long-name "UCS for Japan"
959 mother =ucs@jis/2004))
960 (define-charset-alias '=ucs@jp '=ucs@JP)
961 (make-charset '=ucs@ks
962 "ISO/IEC 10646 for Korean Standards"
963 '(long-name "UCS for KS"
970 mother =ucs@unicode))
971 (define-charset-alias 'ucs-ks '=ucs@ks)
972 (make-charset '=ucs-bmp@ks
973 "ISO/IEC 10646 BMP for KS"
974 '(long-name "BMP for KS"
983 (make-charset '=ucs@cns11643
984 "ISO/IEC 10646 for CNS based on www.cns11643.gov.tw"
985 '(long-name "UCS for CNS11643"
994 (make-charset '=>>ucs@unicode
995 "Representative abstract glyphs of Unicode"
996 '(long-name "Unicode abstract glyphs"
1003 mother =ucs@unicode))
1004 (make-charset '=ucs@big5
1005 "ISO/IEC 10646 for Big5"
1006 '(long-name "UCS for Big5"
1013 mother =>>ucs@unicode))
1014 (define-charset-alias 'ucs-big5 '=ucs@big5)
1015 (make-charset '=ucs@big5/cns11643
1016 "ISO/IEC 10646 for Big5 based on www.cns11643.gov.tw"
1017 '(long-name "UCS for Big5@CNS11643"
1028 "CJK Radicals of UCS"
1029 '(long-name "UCS-Radicals"
1035 registry "-zhRadicals-.*-ucs-0"
1037 min-code #x2E00 max-code #x2FFF))
1039 '=ucs-radicals@unicode
1040 "CJK Radicals of UCS"
1041 '(long-name "UCS-Radicals"
1047 registry "-zhRadicals-.*-ucs-0"
1049 min-code #x2E00 max-code #x2FFF))
1052 "Hangul Syllables of UCS"
1053 '(long-name "UCS-Hangul-Syllables"
1059 registry "-Hangul-.*-ucs-0"
1061 min-code #xAC00 max-code #xD7AF))
1064 "CJK Characters in BMP of UCS"
1065 '(long-name "UCS-BMP-CJK"
1071 registry "-zh-.*-ucs-0"
1078 '=ucs-bmp-cjk@unicode
1079 "CJK Characters in BMP of Unicode"
1080 '(long-name "Unicode-BMP-CJK"
1086 registry "-zh-.*-ucs-0"
1094 "CJK Ideographs Extension B"
1095 '(long-name "UCS CJK Ext-B"
1101 registry "\\(iso10646\\|ucs02\\)-2$"
1103 min-code #x20000 max-code #x2A6D6
1104 code-offset #x20000))
1107 "CJK Ideographs Extension B (ISO/IEC 10646-2)"
1108 '(long-name "UCS CJK Ext-B"
1114 registry "\\(iso10646\\|ucs02\\)-2$"
1116 min-code #x20000 max-code #x2A6D6
1117 code-offset #x20000))
1121 "Adobe-Japan1 Character Collection for CID-Keyed Fonts"
1122 `(long-name "Adobe-Japan1"
1128 registry "AdobeJapan1-[0-6]$"
1129 min-code ,(lsh #x6300 16)
1130 max-code ,(+ (lsh #x6300 16) 23057)
1131 code-offset ,(lsh #x6300 16)))
1134 "Adobe-Japan1-0 Character Collection for CID-Keyed Fonts"
1135 '(long-name "Adobe-Japan1-0"
1141 mother =adobe-japan1-base
1144 registry "AdobeJapan1-0$"))
1147 "Adobe-Japan1-1 Character Collection for CID-Keyed Fonts"
1148 '(long-name "Adobe-Japan1-1"
1154 mother =adobe-japan1-0
1157 registry "AdobeJapan1-1$"))
1160 "Adobe-Japan1-2 Character Collection for CID-Keyed Fonts"
1161 '(long-name "Adobe-Japan1-2"
1167 mother =adobe-japan1-1
1170 registry "AdobeJapan1-2$"))
1173 "Adobe-Japan1-3 Character Collection for CID-Keyed Fonts"
1174 '(long-name "Adobe-Japan1-3"
1180 mother =adobe-japan1-2
1183 registry "AdobeJapan1-3$"))
1186 "Adobe-Japan1-4 Character Collection for CID-Keyed Fonts"
1187 '(long-name "Adobe-Japan1-4"
1193 mother =adobe-japan1-3
1196 registry "AdobeJapan1-4$"))
1199 "Adobe-Japan1-5 Character Collection for CID-Keyed Fonts"
1200 '(long-name "Adobe-Japan1-5"
1206 mother =adobe-japan1-4
1209 registry "AdobeJapan1-5$"))
1212 "Adobe-Japan1-6 Character Collection for CID-Keyed Fonts"
1213 '(long-name "Adobe-Japan1-6"
1219 mother =adobe-japan1-5
1222 registry "AdobeJapan1-6$"))
1225 ;;; mule-conf.el ends here