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 unchanged unification rules."
269 '(registry "jisx0208\\.1990"
277 "JIS X 0208 based on the unification rule of 1997 edition."
278 '(registry "jisx0208\\.1990"
284 (define-charset-alias '=jis-x0208@1997 '<=>jis-x0208@1997)
287 "JIS X 0213 Plain 1 abstract characters (unchanged part)"
288 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
298 "JIS X 0213 Plain 1 abstract characters based on 2000 edition"
299 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
302 mother <=>jis-x0213-1
309 "JIS X 0213 Plain 1 abstract characters based on 2004 edition"
310 '(registry "jisx0213\\(\\.[0-9]+\\)?-1"
313 mother <=>jis-x0213-1
319 (make-charset '=big5-cdp
320 "Big5 with CDP extension"
321 '(long-name "Big5-CDP"
327 registry "big5\\.cdp-0"
331 (define-charset-alias 'chinese-big5-cdp '=big5-cdp)
342 min-code ,(lsh #x6100 16)
343 max-code ,(+ (lsh #x6100 16) 67547)
344 code-offset ,(lsh #x6100 16)))
345 (define-charset-alias 'ideograph-gt '=gt)
347 "GT 2000 abstract characters"
348 `(long-name "abstract GT"
356 "Ideographic components of GT"
357 `(long-name "GT components"
364 min-code ,(lsh #x6110 16)
365 max-code ,(+ (lsh #x6110 16) 17090)
366 code-offset ,(lsh #x6110 16)))
367 (define-charset-alias 'ideograph-gt-k '=gt-k)
371 (intern (format "=gt-pj-%d" i))
372 (format "GT 2000 (pseudo JIS encoding) part %d" i)
373 `(long-name ,(format "GT PJ %d" i)
379 registry ,(format "\\(GTpj-%d\\|jisx0208\\.GT-%d\\)$" i i)))
380 (define-charset-alias
381 (intern (format "ideograph-gt-pj-%d" i))
382 (intern (format "=gt-pj-%d" i)))
386 "Ideographic parts of GT (pseudo JIS encoding) part 1"
393 registry "\\(GTKpj-1\\|jisx0208\\.GTK-1\\)$"))
394 (define-charset-alias 'ideograph-gt-pj-k1 '=gt-pj-k1)
397 "Ideographic parts of GT (pseudo JIS encoding) part 2"
404 registry "\\(GTKpj-2\\|jisx0208\\.GTK-2\\)$"))
405 (define-charset-alias 'ideograph-gt-pj-k2 '=gt-pj-k2)
407 (make-charset '=daikanwa
408 "Daikanwa dictionary (revised version 2)"
409 `(long-name "Daikanwa"
415 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
417 max-code ,(+ #xE00000 50100)
418 code-offset #xE00000))
419 (define-charset-alias 'ideograph-daikanwa '=daikanwa)
421 (make-charset '=daikanwa@rev1
422 "Daikanwa dictionary (revised version)"
423 `(long-name "Daikanwa Rev."
429 registry "Daikanwa\\(\\.[0-9]+\\)?-2"
432 (define-charset-alias 'ideograph-daikanwa-2 '=daikanwa@rev1)
433 (define-charset-alias '=daikanwa-rev1 '=daikanwa@rev1)
435 (make-charset '=daikanwa@rev2
436 "Daikanwa dictionary (revised version 2)"
437 `(long-name "Daikanwa"
443 registry "Daikanwa\\(\\.[0-9]+\\)?-3"
448 ;; max-code ,(+ #xE00000 50100)
449 ;; code-offset #xE00000
451 (define-charset-alias '=daikanwa-rev2 '=daikanwa@rev2)
453 (make-charset '=shinjigen
454 "Kadokawa ShinJigen dictionary (common parts)"
455 `(long-name "Shinjigen common parts"
461 registry "Shinjigen\\(\\.[0-9]+\\)?-*"))
463 (make-charset '=shinjigen@1ed
464 "Kadokawa ShinJigen dictionary (the first edition)"
465 `(long-name "Shinjigen-1"
472 registry "Shinjigen\\(\\.[0-9]+\\)?-1"))
473 (define-charset-alias 'shinjigen-1 '=shinjigen@1ed)
475 (make-charset '=shinjigen@1ed/24pr
476 "Kadokawa ShinJigen dictionary (the 24th impression)"
477 `(long-name "Shinjigen-1 24pr"
483 mother =shinjigen@1ed))
485 (make-charset '=shinjigen@rev
486 "Kadokawa ShinJigen dictionary (the revised edition)"
487 `(long-name "Shinjigen-2"
494 registry "Shinjigen\\(\\.[0-9]+\\)?-2"))
495 (define-charset-alias 'shinjigen-2 '=shinjigen@rev)
496 (make-charset '=shinjigen/+p@rev
497 "ShinJigen (the second edition) number with '"
498 `(long-name "Shinjigen-2 with '"
504 (define-charset-alias 'shinjigen-2-p '=shinjigen/+p@rev)
506 (make-charset '=big5-pua
507 "Big5 with private used area"
508 '(long-name "Big5-PUA"
515 registry "Big5\\.ETEN"))
516 (define-charset-alias 'chinese-big5-pua '=big5-pua)
517 (make-charset '=big5-eten
519 '(long-name "Big5-ETEN"
528 registry "Big5\\.ETEN"))
529 (define-charset-alias 'chinese-big5-eten '=big5-eten)
530 (make-charset 'chinese-big5-eten-a
531 "Big5 ETEN (#xF9D6 .. #xF9FE)"
532 '(long-name "Big5-ETEN-a"
541 registry "Big5\\.ETEN"))
542 (make-charset 'chinese-big5-eten-b
543 "Big5 ETEN (#xC6A1 .. #xC8FE)"
544 '(long-name "Big5-ETEN-b"
553 registry "Big5\\.ETEN"))
556 (hzk-min (+ (lsh #x6200 16) 65536))
557 (hzk-max (+ hzk-min 65535)))
560 (intern (format "=hanziku-%d" i))
561 (format "HANZIKU (pseudo BIG5 encoding) part %d" i)
562 `(long-name ,(format "HANZIKU-%d" i)
568 registry ,(format "hanziku-%d$" i i)
571 code-offset ,hzk-min))
572 (define-charset-alias
573 (intern (format "ideograph-hanziku-%d" i))
574 (intern (format "=hanziku-%d" i)))
575 (setq hzk-min (1+ hzk-max)
576 hzk-max (+ hzk-min 65535))
579 (make-charset '=cbeta "CBETA private characters"
580 '(long-name "CBETA PUA"
590 (define-charset-alias 'ideograph-cbeta '=cbeta)
592 (make-charset '=zinbun-oracle
593 "Oracle Bones Script"
594 `(long-name "Oracle Bones Script in Zinbun, Kyoto Univ."
600 max-code ,(+ #xE70000 8192)
605 (make-charset '=jef-china3
606 "JEF + CHINA3 private characters"
607 '(long-name "JEF + CHINA3"
613 registry "china3jef-0"
616 code-offset #xE80000))
617 (define-charset-alias 'china3-jef '=jef-china3)
619 (make-charset '=ruimoku-v6
620 "private characters used in RUIMOKU Version.6"
629 min-code #xE90000 ; #xE000
630 max-code #xE908FF ; #xE8FF
631 code-offset ,(- #xE90000 #xE000)))
633 (make-charset '=ucs@iso
634 "ISO/IEC 10646 for its representative glyphs"
635 '(long-name "UCS for ISO"
643 (make-charset '=ucs@unicode
644 "Unicode for its representative glyphs"
645 '(long-name "UCS for Unicode"
653 (make-charset '=ucs@gb
654 "ISO/IEC 10646 for GB"
655 '(long-name "UCS for GB"
662 mother =ucs@unicode))
663 (define-charset-alias 'ucs-gb '=ucs@gb)
664 (make-charset '=ucs@gb/fw
665 "ISO/IEC 10646 for GB with fullwidth"
666 '(long-name "UCS for GB-fullwidth"
674 (make-charset '=ucs-bmp@gb
675 "ISO/IEC 10646 BMP for GB"
676 '(long-name "BMP for GB"
685 (make-charset '=ucs@cns
686 "ISO/IEC 10646 for CNS 11643"
687 '(long-name "UCS for CNS"
694 mother =ucs@unicode))
695 (define-charset-alias 'ucs-cns '=ucs@cns)
696 (make-charset '=ucs@cns/fw
697 "ISO/IEC 10646 for CNS 11643 with fullwidth"
698 '(long-name "UCS for CNS-fullwidth"
706 (make-charset '=ucs-bmp@cns
707 "ISO/IEC 10646 BMP for CNS"
708 '(long-name "BMP for CNS"
717 (make-charset '=ucs@jis
718 "ISO/IEC 10646 for JIS X0208/0212/0213"
719 '(long-name "UCS for JIS"
726 mother =ucs@unicode))
727 (define-charset-alias 'ucs-jis '=ucs@jis)
728 (make-charset '=ucs@jis/fw
729 "ISO/IEC 10646 for JIS X0208/0212/0213 with fullwidth"
730 '(long-name "UCS for JIS-fullwidth"
738 (make-charset '=ucs-bmp@jis
739 "ISO/IEC 10646 BMP for JIS"
740 '(long-name "BMP for JIS"
749 (make-charset '=ucs@jis/1990
750 "ISO/IEC 10646 for JIS X 0208/0212:1990"
751 '(long-name "UCS for JIS:1990"
759 (define-charset-alias '=ucs@jis-1990 '=ucs@jis/1990)
760 (define-charset-alias '=ucs-jis-1990 '=ucs@jis/1990)
761 (make-charset '=ucs@jis/2000
762 "ISO/IEC 10646 for JIS X 0213:2000"
763 '(long-name "UCS for JIS:2000"
771 (define-charset-alias '=ucs@jis-2000 '=ucs@jis/2000)
772 (define-charset-alias '=ucs-jis-2000 '=ucs@jis/2000)
773 (make-charset '=ucs@jis/2004
774 "ISO/IEC 10646 for JIS X 0213:2004"
775 '(long-name "UCS for JIS:2004"
783 (make-charset '=ucs@JP
784 "UCS for common glyphs used in Japan"
785 '(long-name "UCS for Japan"
792 mother =ucs@jis/2004))
793 (define-charset-alias '=ucs@jp '=ucs@JP)
794 (make-charset '=ucs@ks
795 "ISO/IEC 10646 for Korean Standards"
796 '(long-name "UCS for KS"
803 mother =ucs@unicode))
804 (define-charset-alias 'ucs-ks '=ucs@ks)
805 (make-charset '=ucs-bmp@ks
806 "ISO/IEC 10646 BMP for KS"
807 '(long-name "BMP for KS"
816 (make-charset '=ucs@big5
817 "ISO/IEC 10646 for Big5"
818 '(long-name "UCS for Big5"
825 mother =ucs@unicode))
826 (define-charset-alias 'ucs-big5 '=ucs@big5)
827 (make-charset '=ucs@big5/cns11643
828 "ISO/IEC 10646 for Big5 based on www.cns11643.gov.tw"
829 '(long-name "UCS for Big5@CNS11643"
837 (make-charset '=ucs@cns11643
838 "ISO/IEC 10646 for CNS based on www.cns11643.gov.tw"
839 '(long-name "UCS for CNS11643"
850 "CJK Radicals of UCS"
851 '(long-name "UCS-Radicals"
857 registry "-zhRadicals-.*-ucs-0"
859 min-code #x2E00 max-code #x2FFF))
861 '=ucs-radicals@unicode
862 "CJK Radicals of UCS"
863 '(long-name "UCS-Radicals"
869 registry "-zhRadicals-.*-ucs-0"
871 min-code #x2E00 max-code #x2FFF))
874 "Hangul Syllables of UCS"
875 '(long-name "UCS-Hangul-Syllables"
881 registry "-Hangul-.*-ucs-0"
883 min-code #xAC00 max-code #xD7AF))
886 "CJK Characters in BMP of UCS"
887 '(long-name "UCS-BMP-CJK"
893 registry "-zh-.*-ucs-0"
900 '=ucs-bmp-cjk@unicode
901 "CJK Characters in BMP of Unicode"
902 '(long-name "Unicode-BMP-CJK"
908 registry "-zh-.*-ucs-0"
916 "CJK Ideographs Extension B"
917 '(long-name "UCS CJK Ext-B"
923 registry "\\(iso10646\\|ucs02\\)-2$"
925 min-code #x20000 max-code #x2A6D6
926 code-offset #x20000))
929 "CJK Ideographs Extension B (ISO/IEC 10646-2)"
930 '(long-name "UCS CJK Ext-B"
936 registry "\\(iso10646\\|ucs02\\)-2$"
938 min-code #x20000 max-code #x2A6D6
939 code-offset #x20000))
943 "Adobe-Japan1-0 Character Collection for CID-Keyed Fonts"
944 '(long-name "Adobe-Japan1-0"
950 registry "AdobeJapan1-0$"))
953 "Adobe-Japan1-1 Character Collection for CID-Keyed Fonts"
954 '(long-name "Adobe-Japan1-1"
960 mother =adobe-japan1-0
961 registry "AdobeJapan1-1$"))
964 "Adobe-Japan1-2 Character Collection for CID-Keyed Fonts"
965 '(long-name "Adobe-Japan1-2"
971 mother =adobe-japan1-1
972 registry "AdobeJapan1-2$"))
975 "Adobe-Japan1-3 Character Collection for CID-Keyed Fonts"
976 '(long-name "Adobe-Japan1-3"
982 mother =adobe-japan1-2
983 registry "AdobeJapan1-3$"))
986 "Adobe-Japan1-4 Character Collection for CID-Keyed Fonts"
987 '(long-name "Adobe-Japan1-4"
993 mother =adobe-japan1-3
994 registry "AdobeJapan1-4$"))
997 "Adobe-Japan1-5 Character Collection for CID-Keyed Fonts"
998 '(long-name "Adobe-Japan1-5"
1004 mother =adobe-japan1-4
1005 registry "AdobeJapan1-5$"))
1008 "Adobe-Japan1-6 Character Collection for CID-Keyed Fonts"
1009 '(long-name "Adobe-Japan1-6"
1015 mother =adobe-japan1-5
1016 registry "AdobeJapan1-6$"))
1019 ;;; mule-conf.el ends here