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 "Ideographic components of GT"
305 `(long-name "GT components"
312 min-code ,(lsh #x6110 16)
313 max-code ,(+ (lsh #x6110 16) 17090)
314 code-offset ,(lsh #x6110 16)))
315 (define-charset-alias 'ideograph-gt-k '=gt-k)
319 (intern (format "=gt-pj-%d" i))
320 (format "GT 2000 (pseudo JIS encoding) part %d" i)
321 `(long-name ,(format "GT PJ %d" i)
327 registry ,(format "\\(GTpj-%d\\|jisx0208\\.GT-%d\\)$" i i)))
328 (define-charset-alias
329 (intern (format "ideograph-gt-pj-%d" i))
330 (intern (format "=gt-pj-%d" i)))
334 "Ideographic parts of GT (pseudo JIS encoding) part 1"
341 registry "\\(GTKpj-1\\|jisx0208\\.GTK-1\\)$"))
342 (define-charset-alias 'ideograph-gt-pj-k1 '=gt-pj-k1)
345 "Ideographic parts of GT (pseudo JIS encoding) part 2"
352 registry "\\(GTKpj-2\\|jisx0208\\.GTK-2\\)$"))
353 (define-charset-alias 'ideograph-gt-pj-k2 '=gt-pj-k2)
355 (make-charset '=daikanwa
356 "Daikanwa dictionary (revised version 2)"
357 `(long-name "Daikanwa"
363 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
365 max-code ,(+ #xE00000 50100)
366 code-offset #xE00000))
367 (define-charset-alias 'ideograph-daikanwa '=daikanwa)
369 (make-charset '=daikanwa@rev1
370 "Daikanwa dictionary (revised version)"
371 `(long-name "Daikanwa Rev."
377 registry "Daikanwa\\(\\.[0-9]+\\)?-2"
380 (define-charset-alias 'ideograph-daikanwa-2 '=daikanwa@rev1)
381 (define-charset-alias '=daikanwa-rev1 '=daikanwa@rev1)
383 (make-charset '=daikanwa@rev2
384 "Daikanwa dictionary (revised version 2)"
385 `(long-name "Daikanwa"
391 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
396 ;; max-code ,(+ #xE00000 50100)
397 ;; code-offset #xE00000
399 (define-charset-alias '=daikanwa-rev2 '=daikanwa@rev2)
401 (make-charset '=shinjigen
402 "Kadokawa ShinJigen dictionary (common parts)"
403 `(long-name "Shinjigen common parts"
409 registry "Shinjigen\\(\\.[0-9]+\\)?-*"))
411 (make-charset '=shinjigen@1ed
412 "Kadokawa ShinJigen dictionary (the first edition)"
413 `(long-name "Shinjigen-1"
420 registry "Shinjigen\\(\\.[0-9]+\\)?-1"))
421 (define-charset-alias 'shinjigen-1 '=shinjigen@1ed)
423 (make-charset '=shinjigen@1ed/24pr
424 "Kadokawa ShinJigen dictionary (the 24th impression)"
425 `(long-name "Shinjigen-1 24pr"
431 mother =shinjigen@1ed))
433 (make-charset '=shinjigen@rev
434 "Kadokawa ShinJigen dictionary (the revised edition)"
435 `(long-name "Shinjigen-2"
442 registry "Shinjigen\\(\\.[0-9]+\\)?-2"))
443 (define-charset-alias 'shinjigen-2 '=shinjigen@rev)
444 (make-charset '=shinjigen/+p@rev
445 "ShinJigen (the second edition) number with '"
446 `(long-name "Shinjigen-2 with '"
452 (define-charset-alias 'shinjigen-2-p '=shinjigen/+p@rev)
454 (make-charset '=big5-pua
455 "Big5 with private used area"
456 '(long-name "Big5-PUA"
463 registry "Big5\\.ETEN"))
464 (define-charset-alias 'chinese-big5-pua '=big5-pua)
465 (make-charset '=big5-eten
467 '(long-name "Big5-ETEN"
476 registry "Big5\\.ETEN"))
477 (define-charset-alias 'chinese-big5-eten '=big5-eten)
478 (make-charset 'chinese-big5-eten-a
479 "Big5 ETEN (#xF9D6 .. #xF9FE)"
480 '(long-name "Big5-ETEN-a"
489 registry "Big5\\.ETEN"))
490 (make-charset 'chinese-big5-eten-b
491 "Big5 ETEN (#xC6A1 .. #xC8FE)"
492 '(long-name "Big5-ETEN-b"
501 registry "Big5\\.ETEN"))
504 (hzk-min (+ (lsh #x6200 16) 65536))
505 (hzk-max (+ hzk-min 65535)))
508 (intern (format "=hanziku-%d" i))
509 (format "HANZIKU (pseudo BIG5 encoding) part %d" i)
510 `(long-name ,(format "HANZIKU-%d" i)
516 registry ,(format "hanziku-%d$" i i)
519 code-offset ,hzk-min))
520 (define-charset-alias
521 (intern (format "ideograph-hanziku-%d" i))
522 (intern (format "=hanziku-%d" i)))
523 (setq hzk-min (1+ hzk-max)
524 hzk-max (+ hzk-min 65535))
527 (make-charset '=cbeta "CBETA private characters"
528 '(long-name "CBETA PUA"
538 (define-charset-alias 'ideograph-cbeta '=cbeta)
540 (make-charset '=zinbun-oracle
541 "Oracle Bones Script"
542 `(long-name "Oracle Bones Script in Zinbun, Kyoto Univ."
548 max-code ,(+ #xE70000 8192)
553 (make-charset '=jef-china3
554 "JEF + CHINA3 private characters"
555 '(long-name "JEF + CHINA3"
561 registry "china3jef-0"
564 code-offset #xE80000))
565 (define-charset-alias 'china3-jef '=jef-china3)
567 (make-charset '=ruimoku-v6
568 "private characters used in RUIMOKU Version.6"
577 min-code #xE90000 ; #xE000
578 max-code #xE908FF ; #xE8FF
579 code-offset ,(- #xE90000 #xE000)))
581 (make-charset '=ucs@iso
582 "ISO/IEC 10646 for its representative glyphs"
583 '(long-name "UCS for ISO"
591 (make-charset '=ucs@unicode
592 "Unicode for its representative glyphs"
593 '(long-name "UCS for Unicode"
601 (make-charset '=ucs@gb
602 "ISO/IEC 10646 for GB"
603 '(long-name "UCS for GB"
610 mother =ucs@unicode))
611 (define-charset-alias 'ucs-gb '=ucs@gb)
612 (make-charset '=ucs@gb/fw
613 "ISO/IEC 10646 for GB with fullwidth"
614 '(long-name "UCS for GB-fullwidth"
622 (make-charset '=ucs-bmp@gb
623 "ISO/IEC 10646 BMP for GB"
624 '(long-name "BMP for GB"
633 (make-charset '=ucs@cns
634 "ISO/IEC 10646 for CNS 11643"
635 '(long-name "UCS for CNS"
642 mother =ucs@unicode))
643 (define-charset-alias 'ucs-cns '=ucs@cns)
644 (make-charset '=ucs@cns/fw
645 "ISO/IEC 10646 for CNS 11643 with fullwidth"
646 '(long-name "UCS for CNS-fullwidth"
654 (make-charset '=ucs-bmp@cns
655 "ISO/IEC 10646 BMP for CNS"
656 '(long-name "BMP for CNS"
665 (make-charset '=ucs@jis
666 "ISO/IEC 10646 for JIS X0208/0212/0213"
667 '(long-name "UCS for JIS"
674 mother =ucs@unicode))
675 (define-charset-alias 'ucs-jis '=ucs@jis)
676 (make-charset '=ucs@jis/fw
677 "ISO/IEC 10646 for JIS X0208/0212/0213 with fullwidth"
678 '(long-name "UCS for JIS-fullwidth"
686 (make-charset '=ucs-bmp@jis
687 "ISO/IEC 10646 BMP for JIS"
688 '(long-name "BMP for JIS"
697 (make-charset '=ucs@jis/1990
698 "ISO/IEC 10646 for JIS X 0208/0212:1990"
699 '(long-name "UCS for JIS:1990"
707 (define-charset-alias '=ucs@jis-1990 '=ucs@jis/1990)
708 (define-charset-alias '=ucs-jis-1990 '=ucs@jis/1990)
709 (make-charset '=ucs@jis/2000
710 "ISO/IEC 10646 for JIS X 0213:2000"
711 '(long-name "UCS for JIS:2000"
719 (define-charset-alias '=ucs@jis-2000 '=ucs@jis/2000)
720 (define-charset-alias '=ucs-jis-2000 '=ucs@jis/2000)
721 (make-charset '=ucs@jis/2004
722 "ISO/IEC 10646 for JIS X 0213:2004"
723 '(long-name "UCS for JIS:2004"
731 (make-charset '=ucs@JP
732 "UCS for common glyphs used in Japan"
733 '(long-name "UCS for Japan"
740 mother =ucs@jis/2004))
741 (define-charset-alias '=ucs@jp '=ucs@JP)
742 (make-charset '=ucs@ks
743 "ISO/IEC 10646 for Korean Standards"
744 '(long-name "UCS for KS"
751 mother =ucs@unicode))
752 (define-charset-alias 'ucs-ks '=ucs@ks)
753 (make-charset '=ucs-bmp@ks
754 "ISO/IEC 10646 BMP for KS"
755 '(long-name "BMP for KS"
764 (make-charset '=ucs@big5
765 "ISO/IEC 10646 for Big5"
766 '(long-name "UCS for Big5"
773 mother =ucs@unicode))
774 (define-charset-alias 'ucs-big5 '=ucs@big5)
775 (make-charset '=ucs@big5/cns11643
776 "ISO/IEC 10646 for Big5 based on www.cns11643.gov.tw"
777 '(long-name "UCS for Big5@CNS11643"
785 (make-charset '=ucs@cns11643
786 "ISO/IEC 10646 for CNS based on www.cns11643.gov.tw"
787 '(long-name "UCS for CNS11643"
798 "CJK Radicals of UCS"
799 '(long-name "UCS-Radicals"
805 registry "-zhRadicals-.*-ucs-0"
807 min-code #x2E00 max-code #x2FFF))
809 '=ucs-radicals@unicode
810 "CJK Radicals of UCS"
811 '(long-name "UCS-Radicals"
817 registry "-zhRadicals-.*-ucs-0"
819 min-code #x2E00 max-code #x2FFF))
822 "Hangul Syllables of UCS"
823 '(long-name "UCS-Hangul-Syllables"
829 registry "-Hangul-.*-ucs-0"
831 min-code #xAC00 max-code #xD7AF))
834 "CJK Characters in BMP of UCS"
835 '(long-name "UCS-BMP-CJK"
841 registry "-zh-.*-ucs-0"
848 '=ucs-bmp-cjk@unicode
849 "CJK Characters in BMP of Unicode"
850 '(long-name "Unicode-BMP-CJK"
856 registry "-zh-.*-ucs-0"
864 "CJK Ideographs Extension B"
865 '(long-name "UCS CJK Ext-B"
871 registry "\\(iso10646\\|ucs02\\)-2$"
873 min-code #x20000 max-code #x2A6D6
874 code-offset #x20000))
877 "CJK Ideographs Extension B (ISO/IEC 10646-2)"
878 '(long-name "UCS CJK Ext-B"
884 registry "\\(iso10646\\|ucs02\\)-2$"
886 min-code #x20000 max-code #x2A6D6
887 code-offset #x20000))
891 "Adobe-Japan1-0 Character Collection for CID-Keyed Fonts"
892 '(long-name "Adobe-Japan1-0"
898 registry "AdobeJapan1-0$"))
901 "Adobe-Japan1-1 Character Collection for CID-Keyed Fonts"
902 '(long-name "Adobe-Japan1-1"
908 mother =adobe-japan1-0
909 registry "AdobeJapan1-1$"))
912 "Adobe-Japan1-2 Character Collection for CID-Keyed Fonts"
913 '(long-name "Adobe-Japan1-2"
919 mother =adobe-japan1-1
920 registry "AdobeJapan1-2$"))
923 "Adobe-Japan1-3 Character Collection for CID-Keyed Fonts"
924 '(long-name "Adobe-Japan1-3"
930 mother =adobe-japan1-2
931 registry "AdobeJapan1-3$"))
934 "Adobe-Japan1-4 Character Collection for CID-Keyed Fonts"
935 '(long-name "Adobe-Japan1-4"
941 mother =adobe-japan1-3
942 registry "AdobeJapan1-4$"))
945 "Adobe-Japan1-5 Character Collection for CID-Keyed Fonts"
946 '(long-name "Adobe-Japan1-5"
952 mother =adobe-japan1-4
953 registry "AdobeJapan1-5$"))
956 "Adobe-Japan1-6 Character Collection for CID-Keyed Fonts"
957 '(long-name "Adobe-Japan1-6"
963 mother =adobe-japan1-5
964 registry "AdobeJapan1-6$"))
967 ;;; mule-conf.el ends here