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, 4th impression or later."
66 '(registry "jisx0208\\.1978"
69 mother =jis-x0208@1978
74 (define-charset-alias '=jis-x0208@1978/i1 '=jis-x0208@1978/1pr)
75 (define-charset-alias '=jis-x0208@1978/i-4 '=jis-x0208@1978/-4pr)
76 (define-charset-alias '=jis-x0208@1978/i4- '=jis-x0208@1978/4-pr)
81 "JIS X0208:1978 Japanese Kanji (so called \"old JIS\")."
83 registry "jisx0208\\.1978"
91 (define-charset-alias '=jis-x0208-1978 '=jis-x0208@1978)
92 (define-charset-alias 'japanese-jisx0208-1978 '=jis-x0208@1978)
93 (define-charset-alias 'chinese-gb2312 '=gb2312)
94 (define-charset-alias '=jis-x0208-1983 '=jis-x0208@1983)
95 (define-charset-alias 'japanese-jisx0208 '=jis-x0208@1983)
96 (define-charset-alias 'korean-ksc5601 '=ks-x1001)
97 (define-charset-alias 'japanese-jisx0212 '=jis-x0212)
98 (define-charset-alias 'chinese-cns11643-1 '=cns11643-1)
99 (define-charset-alias 'chinese-cns11643-2 '=cns11643-2)
100 (define-charset-alias 'chinese-gb12345 '=gb12345)
101 (define-charset-alias 'chinese-big5 '=big5)
104 (make-charset 'sisheng "PinYin-ZhuYin"
105 '(registry "sisheng_cwnn\\|OMRON_UDC_ZH"
113 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
114 (make-charset 'lao "Lao script"
115 '(registry "MuleLao-1"
121 ;; IPA (International Phonetic Alphabet)
122 (make-charset 'ipa "International Phonetic Alphabet"
130 (make-charset 'ethiopic "Ethiopic"
138 ;; ISO-IR-165 (CCITT Extended GB)
139 ;; It is based on CCITT Recommendation T.101, includes GB 2312-80 +
140 ;; GB 8565-88 table A4 + 293 characters.
141 (if (featurep 'utf-2000)
143 (make-charset '=iso-ir165
144 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
152 (define-charset-alias 'chinese-isoir165 '=iso-ir165))
153 (make-charset 'chinese-isoir165
154 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
162 ;; CNS11643 Plane3 thru Plane7
163 ;; These represent more and more obscure Chinese characters.
164 ;; By the time you get to Plane 7, we're talking about characters
165 ;; that appear once in some ancient manuscript and whose meaning
169 ((make-chinese-cns11643-charset
170 (name iso-ir plane final)
172 name (concat "CNS 11643 Plane " plane " (Chinese traditional)")
175 ,(concat "CNS11643[.-]\\(.*[.-]\\)?" plane "$")
181 (make-chinese-cns11643-charset '=cns11643-3 183 "3" ?I)
182 (make-chinese-cns11643-charset '=cns11643-4 184 "4" ?J)
183 (make-chinese-cns11643-charset '=cns11643-5 185 "5" ?K)
184 (make-chinese-cns11643-charset '=cns11643-6 186 "6" ?L)
185 (make-chinese-cns11643-charset '=cns11643-7 187 "7" ?M)
186 (define-charset-alias 'chinese-cns11643-3 '=cns11643-3)
187 (define-charset-alias 'chinese-cns11643-4 '=cns11643-4)
188 (define-charset-alias 'chinese-cns11643-5 '=cns11643-5)
189 (define-charset-alias 'chinese-cns11643-6 '=cns11643-6)
190 (define-charset-alias 'chinese-cns11643-7 '=cns11643-7)
195 ((featurep 'utf-2000)
198 "JIS X 0213 Plain 1 (unchanged part)"
199 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
209 "JIS X 0213:2000 Plain 1"
211 registry "jisx0213\\(\\.2000\\)-1"
221 registry "jisx0213\\(\\.\\(2000\\|2004\\)\\)?-2"
229 "JIS X 0213:2004 Plain 1"
231 registry "jisx0213\\(\\.2004\\)-1"
238 (define-charset-alias 'japanese-jisx0213-1 '=jis-x0213-1@2000)
239 (define-charset-alias 'japanese-jisx0213-2 '=jis-x0213-2)
240 (define-charset-alias '=jis-x0213-1-2000 '=jis-x0213-1@2000)
241 (define-charset-alias '=jis-x0213-2-2000 '=jis-x0213-2)
246 "JIS X 0213:2000 Plain 1"
247 '(registry "jisx0213\\(\\.2000\\)-1"
254 "JIS X 0213:2000 Plain 2"
255 '(registry "jisx0213\\(\\.2000\\)-2"
262 (when (featurep 'utf-2000)
263 (define-charset-alias 'ucs '=ucs)
264 (define-charset-alias '=jis-x0208-1990 '=jis-x0208@1990)
265 (define-charset-alias 'japanese-jisx0208-1990 '=jis-x0208@1990)
268 "JIS X 0208 based on the unification rule of 1997 edition."
269 '(registry "jisx0208\\.1990"
276 (make-charset '=big5-cdp
277 "Big5 with CDP extension"
278 '(long-name "Big5-CDP"
284 registry "big5\\.cdp-0"
288 (define-charset-alias 'chinese-big5-cdp '=big5-cdp)
299 min-code ,(lsh #x6100 16)
300 max-code ,(+ (lsh #x6100 16) 67547)
301 code-offset ,(lsh #x6100 16)))
302 (define-charset-alias 'ideograph-gt '=gt)
304 "GT 2000 abstract characters"
305 `(long-name "abstract GT"
313 "Ideographic components of GT"
314 `(long-name "GT components"
321 min-code ,(lsh #x6110 16)
322 max-code ,(+ (lsh #x6110 16) 17090)
323 code-offset ,(lsh #x6110 16)))
324 (define-charset-alias 'ideograph-gt-k '=gt-k)
328 (intern (format "=gt-pj-%d" i))
329 (format "GT 2000 (pseudo JIS encoding) part %d" i)
330 `(long-name ,(format "GT PJ %d" i)
336 registry ,(format "\\(GTpj-%d\\|jisx0208\\.GT-%d\\)$" i i)))
337 (define-charset-alias
338 (intern (format "ideograph-gt-pj-%d" i))
339 (intern (format "=gt-pj-%d" i)))
343 "Ideographic parts of GT (pseudo JIS encoding) part 1"
350 registry "\\(GTKpj-1\\|jisx0208\\.GTK-1\\)$"))
351 (define-charset-alias 'ideograph-gt-pj-k1 '=gt-pj-k1)
354 "Ideographic parts of GT (pseudo JIS encoding) part 2"
361 registry "\\(GTKpj-2\\|jisx0208\\.GTK-2\\)$"))
362 (define-charset-alias 'ideograph-gt-pj-k2 '=gt-pj-k2)
364 (make-charset '=daikanwa
365 "Daikanwa dictionary (revised version 2)"
366 `(long-name "Daikanwa"
372 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
374 max-code ,(+ #xE00000 50100)
375 code-offset #xE00000))
376 (define-charset-alias 'ideograph-daikanwa '=daikanwa)
378 (make-charset '=daikanwa@rev1
379 "Daikanwa dictionary (revised version)"
380 `(long-name "Daikanwa Rev."
386 registry "Daikanwa\\(\\.[0-9]+\\)?-2"
389 (define-charset-alias 'ideograph-daikanwa-2 '=daikanwa@rev1)
390 (define-charset-alias '=daikanwa-rev1 '=daikanwa@rev1)
392 (make-charset '=daikanwa@rev2
393 "Daikanwa dictionary (revised version 2)"
394 `(long-name "Daikanwa"
400 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
405 ;; max-code ,(+ #xE00000 50100)
406 ;; code-offset #xE00000
408 (define-charset-alias '=daikanwa-rev2 '=daikanwa@rev2)
410 (make-charset '=shinjigen
411 "Kadokawa ShinJigen dictionary (common parts)"
412 `(long-name "Shinjigen common parts"
418 registry "Shinjigen\\(\\.[0-9]+\\)?-*"))
420 (make-charset '=shinjigen@1ed
421 "Kadokawa ShinJigen dictionary (the first edition)"
422 `(long-name "Shinjigen-1"
429 registry "Shinjigen\\(\\.[0-9]+\\)?-1"))
430 (define-charset-alias 'shinjigen-1 '=shinjigen@1ed)
432 (make-charset '=shinjigen@1ed/24pr
433 "Kadokawa ShinJigen dictionary (the 24th impression)"
434 `(long-name "Shinjigen-1 24pr"
440 mother =shinjigen@1ed))
442 (make-charset '=shinjigen@rev
443 "Kadokawa ShinJigen dictionary (the revised edition)"
444 `(long-name "Shinjigen-2"
451 registry "Shinjigen\\(\\.[0-9]+\\)?-2"))
452 (define-charset-alias 'shinjigen-2 '=shinjigen@rev)
453 (make-charset '=shinjigen/+p@rev
454 "ShinJigen (the second edition) number with '"
455 `(long-name "Shinjigen-2 with '"
461 (define-charset-alias 'shinjigen-2-p '=shinjigen/+p@rev)
463 (make-charset '=big5-pua
464 "Big5 with private used area"
465 '(long-name "Big5-PUA"
472 registry "Big5\\.ETEN"))
473 (define-charset-alias 'chinese-big5-pua '=big5-pua)
474 (make-charset '=big5-eten
476 '(long-name "Big5-ETEN"
485 registry "Big5\\.ETEN"))
486 (define-charset-alias 'chinese-big5-eten '=big5-eten)
487 (make-charset 'chinese-big5-eten-a
488 "Big5 ETEN (#xF9D6 .. #xF9FE)"
489 '(long-name "Big5-ETEN-a"
498 registry "Big5\\.ETEN"))
499 (make-charset 'chinese-big5-eten-b
500 "Big5 ETEN (#xC6A1 .. #xC8FE)"
501 '(long-name "Big5-ETEN-b"
510 registry "Big5\\.ETEN"))
513 (hzk-min (+ (lsh #x6200 16) 65536))
514 (hzk-max (+ hzk-min 65535)))
517 (intern (format "=hanziku-%d" i))
518 (format "HANZIKU (pseudo BIG5 encoding) part %d" i)
519 `(long-name ,(format "HANZIKU-%d" i)
525 registry ,(format "hanziku-%d$" i i)
528 code-offset ,hzk-min))
529 (define-charset-alias
530 (intern (format "ideograph-hanziku-%d" i))
531 (intern (format "=hanziku-%d" i)))
532 (setq hzk-min (1+ hzk-max)
533 hzk-max (+ hzk-min 65535))
536 (make-charset '=cbeta "CBETA private characters"
537 '(long-name "CBETA PUA"
547 (define-charset-alias 'ideograph-cbeta '=cbeta)
549 (make-charset '=zinbun-oracle
550 "Oracle Bones Script"
551 `(long-name "Oracle Bones Script in Zinbun, Kyoto Univ."
557 max-code ,(+ #xE70000 8192)
562 (make-charset '=jef-china3
563 "JEF + CHINA3 private characters"
564 '(long-name "JEF + CHINA3"
570 registry "china3jef-0"
573 code-offset #xE80000))
574 (define-charset-alias 'china3-jef '=jef-china3)
576 (make-charset '=ruimoku-v6
577 "private characters used in RUIMOKU Version.6"
586 min-code #xE90000 ; #xE000
587 max-code #xE908FF ; #xE8FF
588 code-offset ,(- #xE90000 #xE000)))
590 (make-charset '=ucs@iso
591 "ISO/IEC 10646 for its representative glyphs"
592 '(long-name "UCS for ISO"
600 (make-charset '=ucs@unicode
601 "Unicode for its representative glyphs"
602 '(long-name "UCS for Unicode"
610 (make-charset '=ucs@gb
611 "ISO/IEC 10646 for GB"
612 '(long-name "UCS for GB"
619 mother =ucs@unicode))
620 (define-charset-alias 'ucs-gb '=ucs@gb)
621 (make-charset '=ucs@gb/fw
622 "ISO/IEC 10646 for GB with fullwidth"
623 '(long-name "UCS for GB-fullwidth"
631 (make-charset '=ucs-bmp@gb
632 "ISO/IEC 10646 BMP for GB"
633 '(long-name "BMP for GB"
642 (make-charset '=ucs@cns
643 "ISO/IEC 10646 for CNS 11643"
644 '(long-name "UCS for CNS"
651 mother =ucs@unicode))
652 (define-charset-alias 'ucs-cns '=ucs@cns)
653 (make-charset '=ucs@cns/fw
654 "ISO/IEC 10646 for CNS 11643 with fullwidth"
655 '(long-name "UCS for CNS-fullwidth"
663 (make-charset '=ucs-bmp@cns
664 "ISO/IEC 10646 BMP for CNS"
665 '(long-name "BMP for CNS"
674 (make-charset '=ucs@jis
675 "ISO/IEC 10646 for JIS X0208/0212/0213"
676 '(long-name "UCS for JIS"
683 mother =ucs@unicode))
684 (define-charset-alias 'ucs-jis '=ucs@jis)
685 (make-charset '=ucs@jis/fw
686 "ISO/IEC 10646 for JIS X0208/0212/0213 with fullwidth"
687 '(long-name "UCS for JIS-fullwidth"
695 (make-charset '=ucs-bmp@jis
696 "ISO/IEC 10646 BMP for JIS"
697 '(long-name "BMP for JIS"
706 (make-charset '=ucs@jis/1990
707 "ISO/IEC 10646 for JIS X 0208/0212:1990"
708 '(long-name "UCS for JIS:1990"
716 (define-charset-alias '=ucs@jis-1990 '=ucs@jis/1990)
717 (define-charset-alias '=ucs-jis-1990 '=ucs@jis/1990)
718 (make-charset '=ucs@jis/2000
719 "ISO/IEC 10646 for JIS X 0213:2000"
720 '(long-name "UCS for JIS:2000"
728 (define-charset-alias '=ucs@jis-2000 '=ucs@jis/2000)
729 (define-charset-alias '=ucs-jis-2000 '=ucs@jis/2000)
730 (make-charset '=ucs@jis/2004
731 "ISO/IEC 10646 for JIS X 0213:2004"
732 '(long-name "UCS for JIS:2004"
740 (make-charset '=ucs@JP
741 "UCS for common glyphs used in Japan"
742 '(long-name "UCS for Japan"
749 mother =ucs@jis/2004))
750 (define-charset-alias '=ucs@jp '=ucs@JP)
751 (make-charset '=ucs@ks
752 "ISO/IEC 10646 for Korean Standards"
753 '(long-name "UCS for KS"
760 mother =ucs@unicode))
761 (define-charset-alias 'ucs-ks '=ucs@ks)
762 (make-charset '=ucs-bmp@ks
763 "ISO/IEC 10646 BMP for KS"
764 '(long-name "BMP for KS"
773 (make-charset '=ucs@big5
774 "ISO/IEC 10646 for Big5"
775 '(long-name "UCS for Big5"
782 mother =ucs@unicode))
783 (define-charset-alias 'ucs-big5 '=ucs@big5)
784 (make-charset '=ucs@big5/cns11643
785 "ISO/IEC 10646 for Big5 based on www.cns11643.gov.tw"
786 '(long-name "UCS for Big5@CNS11643"
794 (make-charset '=ucs@cns11643
795 "ISO/IEC 10646 for CNS based on www.cns11643.gov.tw"
796 '(long-name "UCS for CNS11643"
807 "CJK Radicals of UCS"
808 '(long-name "UCS-Radicals"
814 registry "-zhRadicals-.*-ucs-0"
816 min-code #x2E00 max-code #x2FFF))
818 '=ucs-radicals@unicode
819 "CJK Radicals of UCS"
820 '(long-name "UCS-Radicals"
826 registry "-zhRadicals-.*-ucs-0"
828 min-code #x2E00 max-code #x2FFF))
831 "Hangul Syllables of UCS"
832 '(long-name "UCS-Hangul-Syllables"
838 registry "-Hangul-.*-ucs-0"
840 min-code #xAC00 max-code #xD7AF))
843 "CJK Characters in BMP of UCS"
844 '(long-name "UCS-BMP-CJK"
850 registry "-zh-.*-ucs-0"
857 '=ucs-bmp-cjk@unicode
858 "CJK Characters in BMP of Unicode"
859 '(long-name "Unicode-BMP-CJK"
865 registry "-zh-.*-ucs-0"
873 "CJK Ideographs Extension B"
874 '(long-name "UCS CJK Ext-B"
880 registry "\\(iso10646\\|ucs02\\)-2$"
882 min-code #x20000 max-code #x2A6D6
883 code-offset #x20000))
886 "CJK Ideographs Extension B (ISO/IEC 10646-2)"
887 '(long-name "UCS CJK Ext-B"
893 registry "\\(iso10646\\|ucs02\\)-2$"
895 min-code #x20000 max-code #x2A6D6
896 code-offset #x20000))
900 "Adobe-Japan1-0 Character Collection for CID-Keyed Fonts"
901 '(long-name "Adobe-Japan1-0"
907 registry "AdobeJapan1-0$"))
910 "Adobe-Japan1-1 Character Collection for CID-Keyed Fonts"
911 '(long-name "Adobe-Japan1-1"
917 mother =adobe-japan1-0
918 registry "AdobeJapan1-1$"))
921 "Adobe-Japan1-2 Character Collection for CID-Keyed Fonts"
922 '(long-name "Adobe-Japan1-2"
928 mother =adobe-japan1-1
929 registry "AdobeJapan1-2$"))
932 "Adobe-Japan1-3 Character Collection for CID-Keyed Fonts"
933 '(long-name "Adobe-Japan1-3"
939 mother =adobe-japan1-2
940 registry "AdobeJapan1-3$"))
943 "Adobe-Japan1-4 Character Collection for CID-Keyed Fonts"
944 '(long-name "Adobe-Japan1-4"
950 mother =adobe-japan1-3
951 registry "AdobeJapan1-4$"))
954 "Adobe-Japan1-5 Character Collection for CID-Keyed Fonts"
955 '(long-name "Adobe-Japan1-5"
961 mother =adobe-japan1-4
962 registry "AdobeJapan1-5$"))
965 "Adobe-Japan1-6 Character Collection for CID-Keyed Fonts"
966 '(long-name "Adobe-Japan1-6"
972 mother =adobe-japan1-5
973 registry "AdobeJapan1-6$"))
976 ;;; mule-conf.el ends here