1 ;;; mule-conf.el --- configure multilingual environment
3 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003,
4 ;; 2004, 2005, 2006, 2007 Free Software Foundation, Inc.
5 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007
6 ;; National Institute of Advanced Industrial Science and Technology (AIST)
7 ;; Registration Number H14PRO021
9 ;; National Institute of Advanced Industrial Science and Technology (AIST)
10 ;; Registration Number H13PRO009
12 ;; Keywords: i18n, mule, multilingual, character set, coding system
14 ;; This file is part of GNU Emacs.
16 ;; GNU Emacs is free software; you can redistribute it and/or modify
17 ;; it under the terms of the GNU General Public License as published by
18 ;; the Free Software Foundation; either version 2, or (at your option)
21 ;; GNU Emacs is distributed in the hope that it will be useful,
22 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
23 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
24 ;; GNU General Public License for more details.
26 ;; You should have received a copy of the GNU General Public License
27 ;; along with GNU Emacs; see the file COPYING. If not, write to the
28 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
29 ;; Boston, MA 02110-1301, USA.
33 ;; This file defines the Emacs charsets and some basic coding systems.
34 ;; Other coding systems are defined in the files in directory
41 ;; The ISO-IR registry is at http://www.itscj.ipsj.or.jp/ISO-IR/.
42 ;; Standards docs equivalent to iso-2022 and iso-8859 are at
43 ;; http://www.ecma.ch/.
45 ;; FWIW, http://www.microsoft.com/globaldev/ lists the following for
46 ;; MS Windows, which are presumably the only charsets we really need
47 ;; to worry about on such systems:
48 ;; `OEM codepages': 437, 720, 737, 775, 850, 852, 855, 857, 858, 862, 866
49 ;; `Windows codepages': 1250, 1251, 1252, 1253, 1254, 1255, 1256, 1257,
50 ;; 1258, 874, 932, 936, 949, 950
52 ;;; Definitions of character sets.
54 ;; The charsets `ascii', `unicode' and `eight-bit' are already defined
55 ;; in charset.c as below:
57 ;; (define-charset 'ascii
60 ;; :code-space [0 127]
62 ;; :ascii-compatible-p t
66 ;; (define-charset 'unicode
69 ;; :code-space [0 255 0 255 0 16]
70 ;; :ascii-compatible-p t
73 ;; (define-charset 'eight-bit
76 ;; :code-space [128 255]
77 ;; :code-offset #x3FFF80)
79 ;; We now set :docstring, :short-name, and :long-name properties.
82 'ascii :docstring "ASCII (ISO646 IRV)")
84 'ascii :short-name "ASCII")
86 'ascii :long-name "ASCII (ISO646 IRV)")
88 'iso-8859-1 :docstring "Latin-1 (ISO/IEC 8859-1)")
90 'iso-8859-1 :short-name "Latin-1")
92 'iso-8859-1 :long-name "Latin-1")
94 'unicode :docstring "Unicode (ISO10646)")
96 'unicode :short-name "Unicode")
98 'unicode :long-name "Unicode (ISO10646)")
99 (put-charset-property 'eight-bit :docstring "Raw bytes 0-255")
100 (put-charset-property 'eight-bit :short-name "Raw bytes")
102 (define-charset-alias 'ucs 'unicode)
104 (define-charset 'emacs
105 "Full Emacs characters"
106 :ascii-compatible-p t
107 :code-space [ 0 255 0 255 0 63 ]
111 (define-charset 'latin-iso8859-1
112 "Right-Hand Part of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
113 :short-name "RHP of Latin-1"
114 :long-name "RHP of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
120 ;; Name perhaps not ideal, but is XEmacs-compatible.
121 (define-charset 'control-1
122 "8-bit control code (0x80..0x9F)"
123 :short-name "8-bit control code"
124 :code-space [128 159]
127 (define-charset 'eight-bit-control
128 "Raw bytes in the range 0x80..0x9F (usually produced from invalid encodings)"
129 :short-name "Raw bytes 0x80..0x9F"
130 :code-space [128 159]
131 :code-offset #x3FFF80) ; see character.h
133 (define-charset 'eight-bit-graphic
134 "Raw bytes in the range 0xA0..0xFF (usually produced from invalid encodings)"
135 :short-name "Raw bytes 0xA0..0xFF"
136 :code-space [160 255]
137 :code-offset #x3FFFA0) ; see character.h
139 (defmacro define-iso-single-byte-charset (symbol iso-symbol name nickname
143 (define-charset ,symbol
145 :short-name ,nickname
147 :ascii-compatible-p t
151 (define-charset ,iso-symbol
153 (format "Right-Hand Part of %s (%s): ISO-IR-%d"
154 ,name ,nickname ,iso-ir)
155 (format "Right-Hand Part of %s (%s)" ,name ,nickname))
156 :short-name (format "RHP of %s" ,name)
157 :long-name (format "RHP of %s (%s)" ,name ,nickname)
158 :iso-final-char ,iso-final
159 :emacs-mule-id ,emacs-mule-id
161 :subset (list ,symbol 160 255 -128)))))
163 (define-iso-single-byte-charset 'iso-8859-2 'latin-iso8859-2
164 "ISO/IEC 8859/2" "Latin-2" 101 ?B 130 "8859-2")
166 (define-iso-single-byte-charset 'iso-8859-3 'latin-iso8859-3
167 "ISO/IEC 8859/3" "Latin-3" 109 ?C 131 "8859-3")
169 (define-iso-single-byte-charset 'iso-8859-4 'latin-iso8859-4
170 "ISO/IEC 8859/4" "Latin-4" 110 ?D 132 "8859-4")
172 (define-iso-single-byte-charset 'iso-8859-5 'cyrillic-iso8859-5
173 "ISO/IEC 8859/5" "Latin/Cyrillic" 144 ?L 140 "8859-5")
175 (define-iso-single-byte-charset 'iso-8859-6 'arabic-iso8859-6
176 "ISO/IEC 8859/6" "Latin/Arabic" 127 ?G 135 "8859-6")
178 (define-iso-single-byte-charset 'iso-8859-7 'greek-iso8859-7
179 "ISO/IEC 8859/7" "Latin/Greek" 126 ?F 134 "8859-7")
181 (define-iso-single-byte-charset 'iso-8859-8 'hebrew-iso8859-8
182 "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H 136 "8859-8")
184 (define-iso-single-byte-charset 'iso-8859-9 'latin-iso8859-9
185 "ISO/IEC 8859/9" "Latin-5" 148 ?M 141 "8859-9")
187 (define-iso-single-byte-charset 'iso-8859-10 'latin-iso8859-10
188 "ISO/IEC 8859/10" "Latin-6" 157 ?V nil "8859-10")
190 ;; http://www.nectec.or.th/it-standards/iso8859-11/
191 ;; http://www.cwi.nl/~dik/english/codes/8859.html says this is tis-620
193 (define-iso-single-byte-charset 'iso-8859-11 'thai-iso8859-11
194 "ISO/IEC 8859/11" "Latin/Thai" 166 ?T nil "8859-11")
196 ;; 8859-12 doesn't (yet?) exist.
198 (define-iso-single-byte-charset 'iso-8859-13 'latin-iso8859-13
199 "ISO/IEC 8859/13" "Latin-7" 179 ?Y nil "8859-13")
201 (define-iso-single-byte-charset 'iso-8859-14 'latin-iso8859-14
202 "ISO/IEC 8859/14" "Latin-8" 199 ?_ 143 "8859-14")
204 (define-iso-single-byte-charset 'iso-8859-15 'latin-iso8859-15
205 "ISO/IEC 8859/15" "Latin-9" 203 ?b 142 "8859-15")
207 (define-iso-single-byte-charset 'iso-8859-16 'latin-iso8859-16
208 "ISO/IEC 8859/16" "Latin-10" 226 ?f nil "8859-16")
210 ;; No point in keeping it around.
211 (fmakunbound 'define-iso-single-byte-charset)
213 ;; Can this be shared with 8859-11?
214 ;; N.b. not all of these are defined unicodes.
215 (define-charset 'thai-tis620
217 :short-name "TIS620.2533"
223 ;; Fixme: doc for this, c.f. above
224 (define-charset 'tis620-2533
226 :short-name "TIS620.2533"
227 :ascii-compatible-p t
229 :superset '(ascii eight-bit-control (thai-tis620 . 128)))
231 (define-charset 'jisx0201
233 :short-name "JISX0201"
237 (define-charset 'latin-jisx0201
238 "Roman Part of JISX0201.1976"
239 :short-name "JISX0201 Roman"
240 :long-name "Japanese Roman (JISX0201.1976)"
244 :subset '(jisx0201 33 126 0))
246 (define-charset 'katakana-jisx0201
247 "Katakana Part of JISX0201.1976"
248 :short-name "JISX0201 Katakana"
249 :long-name "Japanese Katakana (JISX0201.1976)"
253 :subset '(jisx0201 161 254 -128))
255 (define-charset 'chinese-gb2312
256 "GB2312 Chinese simplified: ISO-IR-58"
258 :long-name "GB2312: ISO-IR-58"
261 :code-space [33 126 33 126]
262 :code-offset #x110000
265 (define-charset 'chinese-gbk
266 "GBK Chinese simplified."
268 :code-space [#x40 #xFE #x81 #xFE]
269 :code-offset #x160000
271 (define-charset-alias 'cp936 'chinese-gbk)
272 (define-charset-alias 'windows-936 'chinese-gbk)
274 (define-charset 'chinese-cns11643-1
275 "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"
276 :short-name "CNS11643-1"
277 :long-name "CNS11643-1 (Chinese traditional): ISO-IR-171"
280 :code-space [33 126 33 126]
281 :code-offset #x114000
284 (define-charset 'chinese-cns11643-2
285 "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"
286 :short-name "CNS11643-2"
287 :long-name "CNS11643-2 (Chinese traditional): ISO-IR-172"
290 :code-space [33 126 33 126]
291 :code-offset #x118000
294 (define-charset 'chinese-cns11643-3
295 "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"
296 :short-name "CNS11643-3"
297 :long-name "CNS11643-3 (Chinese traditional): ISO-IR-183"
299 :code-space [33 126 33 126]
301 :code-offset #x11C000
304 (define-charset 'chinese-cns11643-4
305 "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"
306 :short-name "CNS11643-4"
307 :long-name "CNS11643-4 (Chinese traditional): ISO-IR-184"
310 :code-space [33 126 33 126]
311 :code-offset #x120000
314 (define-charset 'chinese-cns11643-5
315 "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"
316 :short-name "CNS11643-5"
317 :long-name "CNS11643-5 (Chinese traditional): ISO-IR-185"
320 :code-space [33 126 33 126]
321 :code-offset #x124000
324 (define-charset 'chinese-cns11643-6
325 "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"
326 :short-name "CNS11643-6"
327 :long-name "CNS11643-6 (Chinese traditional): ISO-IR-186"
330 :code-space [33 126 33 126]
331 :code-offset #x128000
334 (define-charset 'chinese-cns11643-7
335 "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"
336 :short-name "CNS11643-7"
337 :long-name "CNS11643-7 (Chinese traditional): ISO-IR-187"
340 :code-space [33 126 33 126]
341 :code-offset #x12C000
344 (define-charset 'big5
345 "Big5 (Chinese traditional)"
347 :code-space [#x40 #xFE #xA1 #xFE]
348 :code-offset #x130000
350 ;; Fixme: AKA cp950 according to
351 ;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>. Is
354 (define-charset 'chinese-big5-1
355 "Frequently used part (A141-C67E) of Big5 (Chinese traditional)"
356 :short-name "Big5 (Level-1)"
357 :long-name "Big5 (Level-1) A141-C67F"
360 :code-space [#x21 #x7E #x21 #x7E]
361 :code-offset #x135000
364 (define-charset 'chinese-big5-2
365 "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)"
366 :short-name "Big5 (Level-2)"
367 :long-name "Big5 (Level-2) C940-FEFE"
370 :code-space [#x21 #x7E #x21 #x7E]
371 :code-offset #x137800
374 (define-charset 'japanese-jisx0208
375 "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87"
376 :short-name "JISX0208"
377 :long-name "JISX0208.1983/1990 (Japanese): ISO-IR-87"
380 :code-space [33 126 33 126]
381 :code-offset #x140000
382 :unify-map "JISX0208")
384 (define-charset 'japanese-jisx0208-1978
385 "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42"
386 :short-name "JISX0208.1978"
387 :long-name "JISX0208.1978 (JISC6226.1978): ISO-IR-42"
390 :code-space [33 126 33 126]
391 :code-offset #x144000
392 :unify-map "JISC6226")
394 (define-charset 'japanese-jisx0212
395 "JISX0212 Japanese supplement: ISO-IR-159"
396 :short-name "JISX0212"
397 :long-name "JISX0212 (Japanese): ISO-IR-159"
400 :code-space [33 126 33 126]
401 :code-offset #x148000
402 :unify-map "JISX0212")
404 ;; Note that jisx0213 contains characters not in Unicode (3.2?). It's
405 ;; arguable whether it should have a unify-map.
406 (define-charset 'japanese-jisx0213-1
407 "JISX0213.2000 Plane 1 (Japanese)"
408 :short-name "JISX0213-1"
411 :unify-map "JISX2131"
412 :code-space [33 126 33 126]
413 :code-offset #x14C000)
415 (define-charset 'japanese-jisx0213-2
416 "JISX0213.2000 Plane 2 (Japanese)"
417 :short-name "JISX0213-2"
420 :unify-map "JISX2132"
421 :code-space [33 126 33 126]
422 :code-offset #x150000)
424 (define-charset 'japanese-jisx0213-a
425 "JISX0213.2004 adds these characters to JISX0213.2000."
426 :short-name "JISX0213A"
428 :code-space [33 126 33 126]
432 (define-charset 'japanese-jisx0213.2004-1
433 "JISX0213.2004 Plane1 (Japanese)"
434 :short-name "JISX0213.2004-1"
436 :code-space [33 126 33 126]
438 :superset '(japanese-jisx0213-a japanese-jisx0213-1))
440 (define-charset 'katakana-sjis
441 "Katakana part of Shift-JIS"
443 :code-space [#xA1 #xDF]
444 :subset '(jisx0201 #xA1 #xDF 0)
447 (define-charset 'cp932-2-byte
448 "2-byte part of CP932"
451 :code-space [#x40 #xFC #x81 #xFC]
454 (define-charset 'cp932
455 "CP932 (Microsoft shift-jis)"
456 :code-space [#x00 #xFF #x00 #xFE]
458 :superset '(ascii katakana-sjis cp932-2-byte))
460 (define-charset 'korean-ksc5601
461 "KSC5601 Korean Hangul and Hanja: ISO-IR-149"
462 :short-name "KSC5601"
463 :long-name "KSC5601 (Korean): ISO-IR-149"
466 :code-space [33 126 33 126]
467 :code-offset #x279f94 ; ... #x27c217
468 :unify-map "KSC5601")
470 (define-charset 'big5-hkscs
471 "Big5-HKSCS (Chinese traditional, Hong Kong supplement)"
473 :code-space [#x40 #xFE #xA1 #xFE]
474 :code-offset #x27c218 ; ... #x280839
475 :unify-map "BIG5-HKSCS")
477 ;; Fixme: Korean cp949/UHC
479 (define-charset 'chinese-sisheng
480 "SiSheng characters for PinYin/ZhuYin"
481 :short-name "SiSheng"
482 :long-name "SiSheng (PinYin/ZhuYin)"
486 :unify-map "MULE-sisheng"
487 :code-offset #x200000)
489 ;; A subset of the 1989 version of IPA. It consists of the consonant
490 ;; signs used in English, French, German and Italian, and all vowels
491 ;; signs in the table. [says old MULE doc]
493 "IPA (International Phonetic Association)"
497 :unify-map "MULE-ipa"
499 :code-offset #x200080)
501 (define-charset 'viscii
504 :long-name "VISCII 1.1"
508 (define-charset 'vietnamese-viscii-lower
509 "VISCII1.1 lower-case"
510 :short-name "VISCII lower"
511 :long-name "VISCII lower-case"
515 :code-offset #x200200
516 :unify-map "MULE-lviscii")
518 (define-charset 'vietnamese-viscii-upper
519 "VISCII1.1 upper-case"
520 :short-name "VISCII upper"
521 :long-name "VISCII upper-case"
525 :code-offset #x200280
526 :unify-map "MULE-uviscii")
528 (define-charset 'vscii
529 "VSCII1.1 (TCVN-5712 VN1)"
534 (define-charset-alias 'tcvn-5712 'vscii)
536 ;; Fixme: see note in tcvn.map about combining characters
537 (define-charset 'vscii-2
538 "VSCII-2 (TCVN-5712 VN2)"
542 (define-charset 'koi8-r
545 :ascii-compatible-p t
549 (define-charset-alias 'koi8 'koi8-r)
551 (define-charset 'alternativnyj
553 :short-name "alternativnyj"
554 :ascii-compatible-p t
556 :map "ALTERNATIVNYJ")
558 (define-charset 'cp866
561 :ascii-compatible-p t
564 (define-charset-alias 'ibm866 'cp866)
566 (define-charset 'koi8-u
569 :ascii-compatible-p t
573 (define-charset 'koi8-t
576 :ascii-compatible-p t
580 (define-charset 'georgian-ps
582 :short-name "GEORGIAN-PS"
583 :ascii-compatible-p t
587 (define-charset 'georgian-academy
589 :short-name "GEORGIAN-ACADEMY"
590 :ascii-compatible-p t
594 (define-charset 'windows-1250
595 "WINDOWS-1250 (Central Europe)"
596 :short-name "WINDOWS-1250"
597 :ascii-compatible-p t
600 (define-charset-alias 'cp1250 'windows-1250)
602 (define-charset 'windows-1251
603 "WINDOWS-1251 (Cyrillic)"
604 :short-name "WINDOWS-1251"
605 :ascii-compatible-p t
608 (define-charset-alias 'cp1251 'windows-1251)
610 (define-charset 'windows-1252
611 "WINDOWS-1252 (Latin I)"
612 :short-name "WINDOWS-1252"
613 :ascii-compatible-p t
616 (define-charset-alias 'cp1252 'windows-1252)
618 (define-charset 'windows-1253
619 "WINDOWS-1253 (Greek)"
620 :short-name "WINDOWS-1253"
621 :ascii-compatible-p t
624 (define-charset-alias 'cp1253 'windows-1253)
626 (define-charset 'windows-1254
627 "WINDOWS-1254 (Turkish)"
628 :short-name "WINDOWS-1254"
629 :ascii-compatible-p t
632 (define-charset-alias 'cp1254 'windows-1254)
634 (define-charset 'windows-1255
635 "WINDOWS-1255 (Hebrew)"
636 :short-name "WINDOWS-1255"
637 :ascii-compatible-p t
640 (define-charset-alias 'cp1255 'windows-1255)
642 (define-charset 'windows-1256
643 "WINDOWS-1256 (Arabic)"
644 :short-name "WINDOWS-1256"
645 :ascii-compatible-p t
648 (define-charset-alias 'cp1256 'windows-1256)
650 (define-charset 'windows-1257
651 "WINDOWS-1257 (Baltic)"
652 :short-name "WINDOWS-1257"
653 :ascii-compatible-p t
656 (define-charset-alias 'cp1257 'windows-1257)
658 (define-charset 'windows-1258
659 "WINDOWS-1258 (Viet Nam)"
660 :short-name "WINDOWS-1258"
661 :ascii-compatible-p t
664 (define-charset-alias 'cp1258 'windows-1258)
666 (define-charset 'next
669 :ascii-compatible-p t
673 (define-charset 'cp1125
677 :ascii-compatible-p t
679 (define-charset-alias 'ruscii 'cp1125)
680 ;; Original name for cp1125, says Serhii Hlodin <hlodin@lutsk.bank.gov.ua>
681 (define-charset-alias 'cp866u 'cp1125)
683 ;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html
684 ;; shows this as not ASCII comptaible, with various graphics in
686 (define-charset 'cp437
687 "CP437 (MS-DOS United States, Australia, New Zealand, South Africa)"
690 :ascii-compatible-p t
693 (define-charset 'cp720
697 :ascii-compatible-p t
700 (define-charset 'cp737
704 :ascii-compatible-p t
707 (define-charset 'cp775
711 :ascii-compatible-p t
714 (define-charset 'cp851
718 :ascii-compatible-p t
721 (define-charset 'cp852
722 "CP852 (MS-DOS Latin-2)"
725 :ascii-compatible-p t
728 (define-charset 'cp855
729 "CP855 (IBM Cyrillic)"
732 :ascii-compatible-p t
735 (define-charset 'cp857
736 "CP857 (IBM Turkish)"
739 :ascii-compatible-p t
742 (define-charset 'cp858
743 "CP858 (Multilingual Latin I + Euro)"
746 :ascii-compatible-p t
748 (define-charset-alias 'cp00858 'cp858) ; IANA has IBM00858/CP00858
750 (define-charset 'cp860
751 "CP860 (MS-DOS Portuguese)"
754 :ascii-compatible-p t
757 (define-charset 'cp861
758 "CP861 (MS-DOS Icelandic)"
761 :ascii-compatible-p t
764 (define-charset 'cp862
768 :ascii-compatible-p t
771 (define-charset 'cp863
772 "CP863 (MS-DOS Canadian French)"
775 :ascii-compatible-p t
778 (define-charset 'cp864
782 :ascii-compatible-p t
785 (define-charset 'cp865
786 "CP865 (MS-DOS Nordic)"
789 :ascii-compatible-p t
792 (define-charset 'cp869
793 "CP869 (IBM Modern Greek)"
796 :ascii-compatible-p t
799 (define-charset 'cp874
803 :ascii-compatible-p t
806 ;; For Arabic, we need three different types of character sets.
807 ;; Digits are of direction left-to-right and of width 1-column.
808 ;; Others are of direction right-to-left and of width 1-column or
810 (define-charset 'arabic-digit
812 :short-name "Arabic digit"
818 (define-charset 'arabic-1-column
820 :short-name "Arabic 1-col"
821 :long-name "Arabic 1-column"
825 :code-offset #x200100)
827 (define-charset 'arabic-2-column
829 :short-name "Arabic 2-col"
830 :long-name "Arabic 2-column"
834 :code-offset #x200180)
837 ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF.
838 ;; Not all of them are defined unicodes.
840 "Lao characters (ISO10646 0E81..0EDF)"
847 (define-charset 'mule-lao
848 "Lao characters (ISO10646 0E81..0EDF)"
851 :superset '(ascii eight-bit-control (lao . 128)))
854 ;; Indian scripts. Symbolic charset for data exchange. Glyphs are
855 ;; not assigned. They are automatically converted to each Indian
856 ;; script which IS-13194 supports.
858 (define-charset 'indian-is13194
859 "Generic Indian charset for data exchange with IS 13194"
860 :short-name "IS 13194"
861 :long-name "Indian IS 13194"
865 :code-offset #x180000)
867 (let ((code-offset #x180100))
868 (dolist (script '(devanagari sanskrit bengali tamil telugu assamese
869 oriya kannada malayalam gujarati punjabi))
870 (define-charset (intern (format "%s-cdac" script))
871 (format "Glyphs of %s script for CDAC font. Subset of `indian-glyph'."
872 (capitalize (symbol-name script)))
873 :short-name (format "CDAC %s glyphs" (capitalize (symbol-name script)))
875 :code-offset code-offset)
876 (setq code-offset (+ code-offset #x100)))
878 (dolist (script '(devanagari bengali punjabi gujarati
879 oriya tamil telugu kannada malayalam))
880 (define-charset (intern (format "%s-akruti" script))
881 (format "Glyphs of %s script for AKRUTI font. Subset of `indian-glyph'."
882 (capitalize (symbol-name script)))
883 :short-name (format "AKRUTI %s glyphs" (capitalize (symbol-name script)))
885 :code-offset code-offset)
886 (setq code-offset (+ code-offset #x100))))
888 (define-charset 'indian-glyph
889 "Glyphs for Indian characters."
890 :short-name "Indian glyph"
893 :code-space [32 127 32 127]
894 :code-offset #x180100)
896 ;; Actual Glyph for 1-column width.
897 (define-charset 'indian-1-column
898 "Indian charset for 1-column width glyphs."
899 :short-name "Indian 1-col"
900 :long-name "Indian 1 Column"
903 :code-space [33 126 33 126]
904 :code-offset #x184000)
906 ;; Actual Glyph for 2-column width.
907 (define-charset 'indian-2-column
908 "Indian charset for 2-column width glyphs."
909 :short-name "Indian 2-col"
910 :long-name "Indian 2 Column"
913 :code-space [33 126 33 126]
914 :code-offset #x184000)
916 (define-charset 'tibetan
919 :short-name "Tibetan 2-col"
920 :long-name "Tibetan 2 column"
923 :unify-map "MULE-tibetan"
924 :code-space [33 126 33 37]
925 :code-offset #x190000)
927 (define-charset 'tibetan-1-column
928 "Tibetan 1 column glyph"
929 :short-name "Tibetan 1-col"
930 :long-name "Tibetan 1 column"
933 :code-space [33 126 33 37]
934 :code-offset #x190000)
936 ;; Subsets of Unicode.
937 (define-charset 'mule-unicode-2500-33ff
938 "Unicode characters of the range U+2500..U+33FF."
939 :short-name "Unicode subset 2"
940 :long-name "Unicode subset (U+2500..U+33FF)"
943 :code-space [#x20 #x7f #x20 #x47]
946 (define-charset 'mule-unicode-e000-ffff
947 "Unicode characters of the range U+E000..U+FFFF."
948 :short-name "Unicode subset 3"
949 :long-name "Unicode subset (U+E000+FFFF)"
952 :code-space [#x20 #x7F #x20 #x75]
954 :max-code 30015) ; U+FFFF
956 (define-charset 'mule-unicode-0100-24ff
957 "Unicode characters of the range U+0100..U+24FF."
958 :short-name "Unicode subset"
959 :long-name "Unicode subset (U+0100..U+24FF)"
962 :code-space [#x20 #x7F #x20 #x7F]
965 (define-charset 'unicode-bmp
966 "Unicode Basic Multilingual Plane (U+0000..U+FFFF)"
967 :short-name "Unicode BMP"
968 :code-space [0 255 0 255]
971 (define-charset 'unicode-smp
972 "Unicode Supplementary Multilingual Plane (U+10000..U+1FFFF)"
973 :short-name "Unicode SMP "
974 :code-space [0 255 0 255]
975 :code-offset #x10000)
977 (define-charset 'unicode-sip
978 "Unicode Supplementary Ideographic Plane (U+20000..U+2FFFF)"
979 :short-name "Unicode SIP"
980 :code-space [0 255 0 255]
981 :code-offset #x20000)
983 (define-charset 'unicode-ssp
984 "Unicode Supplementary Special-purpose Plane (U+E0000..U+EFFFF)"
985 :short-name "Unicode SSP"
986 :code-space [0 255 0 255]
987 :code-offset #xE0000)
989 (define-charset 'ethiopic
990 "Ethiopic characters for Amharic and Tigrigna."
991 :short-name "Ethiopic"
992 :long-name "Ethiopic characters"
995 :unify-map "MULE-ethiopic"
996 :code-space [33 126 33 126]
997 :code-offset #x1A0000)
999 (define-charset 'mac-roman
1001 :short-name "Mac Roman"
1002 :ascii-compatible-p t
1006 ;; Fixme: modern EBCDIC variants, e.g. IBM00924?
1007 (define-charset 'ebcdic-us
1008 "US version of EBCDIC"
1009 :short-name "EBCDIC-US"
1011 :mime-charset 'ebcdic-us
1014 (define-charset 'ebcdic-uk
1015 "UK version of EBCDIC"
1016 :short-name "EBCDIC-UK"
1018 :mime-charset 'ebcdic-uk
1021 (define-charset 'ibm1047
1023 "IBM1047, `EBCDIC Latin 1/Open Systems' used by OS/390 Unix."
1024 :short-name "IBM1047"
1026 :mime-charset 'ibm1047
1028 (define-charset-alias 'cp1047 'ibm1047)
1030 (define-charset 'hp-roman8
1031 "Encoding used by Hewlet-Packard printer software"
1032 :short-name "HP-ROMAN8"
1033 :ascii-compatible-p t
1037 ;; To make a coding system with this, a pre-write-conversion should
1038 ;; account for the commented-out multi-valued code points in
1040 (define-charset 'adobe-standard-encoding
1041 "Adobe `standard encoding' used in PostScript"
1042 :short-name "ADOBE-STANDARD-ENCODING"
1043 :code-space [#x20 255]
1046 (define-charset 'symbol
1047 "Adobe symbol encoding used in PostScript"
1048 :short-name "ADOBE-SYMBOL"
1049 :code-space [#x20 255]
1052 (define-charset 'ibm850
1053 "DOS codepage 850 (Latin-1)"
1054 :short-name "IBM850"
1055 :ascii-compatible-p t
1058 (define-charset-alias 'cp850 'ibm850)
1060 (define-charset 'mik
1061 "Bulgarian DOS codepage"
1063 :ascii-compatible-p t
1067 (define-charset 'ptcp154
1068 "`Paratype' codepage (Asian Cyrillic)"
1070 :ascii-compatible-p t
1072 :mime-charset 'pt154
1074 (define-charset-alias 'pt154 'ptcp154)
1075 (define-charset-alias 'cp154 'ptcp154)
1077 (define-charset 'gb18030-2-byte
1078 "GB18030 2-byte (0x814E..0xFEFE)"
1079 :code-space [#x40 #xFE #x81 #xFE]
1083 (define-charset 'gb18030-4-byte-bmp
1084 "GB18030 4-byte for BMP (0x81308130-0x8431A439)"
1085 :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x81 #x84]
1089 (define-charset 'gb18030-4-byte-smp
1090 "GB18030 4-byte for SMP (0x90308130-0xE3329A35)"
1091 :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x90 #xE3]
1092 :min-code '(#x9030 . #x8130)
1093 :max-code '(#xE332 . #x9A35)
1095 :code-offset #x10000)
1097 (define-charset 'gb18030-4-byte-ext-1
1098 "GB18030 4-byte (0x8431A530-0x8F39FE39)"
1099 :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x84 #x8F]
1100 :min-code '(#x8431 . #xA530)
1101 :max-code '(#x8F39 . #xFE39)
1103 :code-offset #x200000 ; ... #x22484B
1106 (define-charset 'gb18030-4-byte-ext-2
1107 "GB18030 4-byte (0xE3329A36-0xFE39FE39)"
1108 :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #xE3 #xFE]
1109 :min-code '(#xE332 . #x9A36)
1110 :max-code '(#xFE39 . #xFE39)
1112 :code-offset #x22484C ; ... #x279f93
1115 (define-charset 'gb18030
1117 :code-space [#x00 #xFF #x00 #xFE #x00 #xFE #x00 #xFE]
1119 :max-code '(#xFE39 . #xFE39)
1120 :superset '(ascii gb18030-2-byte
1121 gb18030-4-byte-bmp gb18030-4-byte-smp
1122 gb18030-4-byte-ext-1 gb18030-4-byte-ext-2))
1124 (define-charset 'chinese-cns11643-15
1125 "CNS11643 Plane 15 Chinese Traditional"
1126 :short-name "CNS11643-15"
1127 :long-name "CNS11643-15 (Chinese traditional)"
1128 :code-space [33 126 33 126]
1129 :code-offset #x27A000)
1131 (unify-charset 'chinese-gb2312)
1132 (unify-charset 'chinese-gbk)
1133 (unify-charset 'chinese-cns11643-1)
1134 (unify-charset 'chinese-cns11643-2)
1135 (unify-charset 'chinese-cns11643-3)
1136 (unify-charset 'chinese-cns11643-4)
1137 (unify-charset 'chinese-cns11643-5)
1138 (unify-charset 'chinese-cns11643-6)
1139 (unify-charset 'chinese-cns11643-7)
1140 (unify-charset 'big5)
1141 (unify-charset 'chinese-big5-1)
1142 (unify-charset 'chinese-big5-2)
1143 (unify-charset 'big5-hkscs)
1144 (unify-charset 'korean-ksc5601)
1145 (unify-charset 'vietnamese-viscii-lower)
1146 (unify-charset 'vietnamese-viscii-upper)
1147 (unify-charset 'chinese-sisheng)
1148 (unify-charset 'ipa)
1149 (unify-charset 'tibetan)
1150 (unify-charset 'ethiopic)
1151 (unify-charset 'japanese-jisx0208-1978)
1152 (unify-charset 'japanese-jisx0208)
1153 (unify-charset 'japanese-jisx0212)
1154 (unify-charset 'japanese-jisx0213-1)
1155 (unify-charset 'japanese-jisx0213-2)
1158 ;; These are tables for translating characters on decoding and
1160 ;; Fixme: these aren't used now -- should they be?
1161 (setq standard-translation-table-for-decode nil)
1163 (setq standard-translation-table-for-encode nil)
1165 ;;; Make fundamental coding systems.
1167 ;; The coding system `no-conversion' and `undecided' are already
1168 ;; defined in coding.c as below:
1170 ;; (define-coding-system 'no-conversion
1172 ;; :coding-type 'raw-text
1174 ;; (define-coding-system 'undecided
1176 ;; :coding-type 'undecided
1179 (define-coding-system-alias 'binary 'no-conversion)
1180 (define-coding-system-alias 'unix 'undecided-unix)
1181 (define-coding-system-alias 'dos 'undecided-dos)
1182 (define-coding-system-alias 'mac 'undecided-mac)
1184 (define-coding-system 'raw-text
1185 "Raw text, which means text contains random 8-bit codes.
1186 Encoding text with this coding system produces the actual byte
1187 sequence of the text in buffers and strings. An exception is made for
1188 eight-bit-control characters. Each of them is encoded into a single
1191 When you visit a file with this coding, the file is read into a
1192 unibyte buffer as is (except for EOL format), thus each byte of a file
1193 is treated as a character."
1194 :coding-type 'raw-text
1198 (define-coding-system 'no-conversion-multibyte
1199 "Like `no-conversion' but don't read a file into a unibyte buffer."
1200 :coding-type 'raw-text
1204 (define-coding-system 'iso-latin-1
1205 "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)."
1206 :coding-type 'charset
1208 :charset-list '(iso-8859-1)
1209 :mime-charset 'iso-8859-1)
1211 (define-coding-system-alias 'iso-8859-1 'iso-latin-1)
1212 (define-coding-system-alias 'latin-1 'iso-latin-1)
1214 ;; Coding systems not specific to each language environment.
1216 (define-coding-system 'emacs-mule
1217 "Emacs 21 internal format used in buffer and string."
1218 :coding-type 'emacs-mule
1219 :charset-list 'emacs-mule
1222 (define-coding-system 'utf-8
1226 :charset-list '(unicode)
1227 :mime-charset 'utf-8)
1229 (define-coding-system-alias 'mule-utf-8 'utf-8)
1231 (define-coding-system 'utf-8-emacs
1232 "Support for all Emacs characters (including non-Unicode characters)."
1235 :charset-list '(emacs))
1237 (define-coding-system 'utf-16le
1238 "UTF-16LE (little endian, no signature (BOM))."
1239 :coding-type 'utf-16
1241 :charset-list '(unicode)
1243 :mime-text-unsuitable t
1244 :mime-charset 'utf-16le)
1246 (define-coding-system 'utf-16be
1247 "UTF-16BE (big endian, no signature (BOM))."
1248 :coding-type 'utf-16
1250 :charset-list '(unicode)
1252 :mime-text-unsuitable t
1253 :mime-charset 'utf-16be)
1255 (define-coding-system 'utf-16le-with-signature
1256 "UTF-16 (little endian, with signature (BOM))."
1257 :coding-type 'utf-16
1259 :charset-list '(unicode)
1262 :mime-text-unsuitable t
1263 :mime-charset 'utf-16)
1265 (define-coding-system 'utf-16be-with-signature
1266 "UTF-16 (big endian, with signature)."
1267 :coding-type 'utf-16
1269 :charset-list '(unicode)
1272 :mime-text-unsuitable t
1273 :mime-charset 'utf-16)
1275 (define-coding-system 'utf-16
1276 "UTF-16 (detect endian on decoding, use big endian on encoding with BOM)."
1277 :coding-type 'utf-16
1279 :charset-list '(unicode)
1280 :bom '(utf-16le-with-signature . utf-16be-with-signature)
1282 :mime-text-unsuitable t
1283 :mime-charset 'utf-16)
1285 ;; Backwards compatibility (old names, also used by Mule-UCS). We
1286 ;; prefer the MIME names.
1287 (define-coding-system-alias 'utf-16-le 'utf-16le-with-signature)
1288 (define-coding-system-alias 'utf-16-be 'utf-16be-with-signature)
1291 (define-coding-system 'iso-2022-7bit
1292 "ISO 2022 based 7-bit encoding using only G0."
1293 :coding-type 'iso-2022
1295 :charset-list 'iso-2022
1296 :designation [(ascii t) nil nil nil]
1297 :flags '(short ascii-at-eol ascii-at-cntl 7-bit designation composition))
1299 (define-coding-system 'iso-2022-7bit-ss2
1300 "ISO 2022 based 7-bit encoding using SS2 for 96-charset."
1301 :coding-type 'iso-2022
1303 :charset-list 'iso-2022
1304 :designation [(ascii 94) nil (nil 96) nil]
1305 :flags '(short ascii-at-eol ascii-at-cntl 7-bit
1306 designation single-shift composition))
1308 (define-coding-system 'iso-2022-7bit-lock
1309 "ISO-2022 coding system using Locking-Shift for 96-charset."
1310 :coding-type 'iso-2022
1312 :charset-list 'iso-2022
1313 :designation [(ascii 94) (nil 96) nil nil]
1314 :flags '(ascii-at-eol ascii-at-cntl 7-bit
1315 designation locking-shift composition))
1317 (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)
1319 (define-coding-system 'iso-2022-7bit-lock-ss2
1320 "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN."
1321 :coding-type 'iso-2022
1323 :charset-list '(ascii
1324 japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
1327 chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
1328 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
1330 :designation [(ascii 94)
1331 (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 96)
1332 (nil chinese-cns11643-2)
1333 (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
1334 chinese-cns11643-6 chinese-cns11643-7)]
1335 :flags '(short ascii-at-eol ascii-at-cntl 7-bit locking-shift
1336 single-shift init-bol))
1338 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)
1340 (define-coding-system 'iso-2022-8bit-ss2
1341 "ISO 2022 based 8-bit encoding using SS2 for 96-charset."
1342 :coding-type 'iso-2022
1344 :charset-list 'iso-2022
1345 :designation [(ascii 94) nil (nil 96) nil]
1346 :flags '(ascii-at-eol ascii-at-cntl designation single-shift composition))
1348 (define-coding-system 'compound-text
1349 "Compound text based generic encoding for decoding unknown messages.
1351 This coding system does not support extended segments of CTEXT."
1352 :coding-type 'iso-2022
1354 :charset-list 'iso-2022
1355 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1356 :flags '(ascii-at-eol ascii-at-cntl long-form
1357 designation locking-shift single-shift composition)
1358 ;; Fixme: this isn't a valid MIME charset and has to be
1359 ;; special-cased elsewhere -- fx
1360 :mime-charset 'x-ctext)
1362 (define-coding-system-alias 'x-ctext 'compound-text)
1363 (define-coding-system-alias 'ctext 'compound-text)
1365 ;; Same as compound-text, but doesn't produce composition escape
1366 ;; sequences. Used in post-read and pre-write conversions of
1367 ;; compound-text-with-extensions, see mule.el. Note that this should
1368 ;; not have a mime-charset property, to prevent it from showing up
1369 ;; close to the beginning of coding systems ordered by priority.
1370 (define-coding-system 'ctext-no-compositions
1371 "Compound text based generic encoding for decoding unknown messages.
1373 Like `compound-text', but does not produce escape sequences for compositions."
1374 :coding-type 'iso-2022
1376 :charset-list 'iso-2022
1377 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1378 :flags '(ascii-at-eol ascii-at-cntl
1379 designation locking-shift single-shift))
1381 (define-coding-system 'compound-text-with-extensions
1382 "Compound text encoding with ICCCM Extended Segment extensions.
1384 See the variable `ctext-non-standard-encodings-alist' for the
1385 detail about how extended segments are handled.
1387 This coding system should be used only for X selections. It is inappropriate
1388 for decoding and encoding files, process I/O, etc."
1389 :coding-type 'iso-2022
1391 :charset-list 'iso-2022
1392 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1393 :flags '(ascii-at-eol ascii-at-cntl long-form
1394 designation locking-shift single-shift)
1395 :post-read-conversion 'ctext-post-read-conversion
1396 :pre-write-conversion 'ctext-pre-write-conversion)
1398 (define-coding-system-alias
1399 'x-ctext-with-extensions 'compound-text-with-extensions)
1400 (define-coding-system-alias
1401 'ctext-with-extensions 'compound-text-with-extensions)
1403 (define-coding-system 'us-ascii
1404 "Encode ASCII as-is and encode non-ASCII characters to `?'."
1405 :coding-type 'charset
1407 :charset-list '(ascii)
1409 :mime-charset 'us-ascii)
1411 (define-coding-system-alias 'iso-safe 'us-ascii)
1413 (define-coding-system 'utf-7
1414 "UTF-7 encoding of Unicode (RFC 2152)."
1417 :mime-charset 'utf-7
1418 :charset-list '(unicode)
1419 :pre-write-conversion 'utf-7-pre-write-conversion
1420 :post-read-conversion 'utf-7-post-read-conversion)
1422 ;; Use us-ascii for terminal output if some other coding system is not
1423 ;; specified explicitly.
1424 (set-safe-terminal-coding-system-internal 'us-ascii)
1426 ;; The other coding-systems are defined in each language specific
1427 ;; files under lisp/language.
1429 ;; Normally, set coding system to `undecided' before reading a file.
1430 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
1431 ;; but we regard them as containing multibyte characters.
1432 ;; Tar files are not decoded at all, but we treat them as raw bytes.
1434 (setq file-coding-system-alist
1435 '(("\\.elc\\'" . utf-8-emacs)
1436 ("\\.utf\\(-8\\)?\\'" . utf-8)
1437 ;; This is the defined default for XML documents. It may be
1438 ;; overridden by a charset specification in the header. That
1439 ;; should be grokked by the auto-coding mechanism, but rms
1440 ;; vetoed that. -- fx
1441 ("\\.xml\\'" . utf-8)
1442 ;; We use raw-text for reading loaddefs.el so that if it
1443 ;; happens to have DOS or Mac EOLs, they are converted to
1444 ;; newlines. This is required to make the special treatment
1445 ;; of the "\ newline" combination in loaddefs.el, which marks
1446 ;; the beginning of a doc string, work.
1447 ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix))
1448 ("\\.tar\\'" . (no-conversion . no-conversion))
1449 ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system)
1450 ("\\.\\(tex\\|ltx\\|dtx\\|drv\\)\\'" . latexenc-find-file-coding-system)
1451 ("" . (undecided . nil))))
1454 ;;; Setting coding categories and their priorities.
1456 ;; This setting is just to read an Emacs Lisp source files which
1457 ;; contain multilingual text while dumping Emacs. More appropriate
1458 ;; values are set by the command `set-language-environment' for each
1459 ;; language environment.
1461 (set-coding-system-priority
1468 ;;; Miscellaneous settings.
1470 ;; Make all multibyte characters self-insert.
1471 (set-char-table-range (nth 1 global-map)
1472 (cons 128 (max-char))
1473 'self-insert-command)
1475 (aset latin-extra-code-table ?\221 t)
1476 (aset latin-extra-code-table ?\222 t)
1477 (aset latin-extra-code-table ?\223 t)
1478 (aset latin-extra-code-table ?\224 t)
1479 (aset latin-extra-code-table ?\225 t)
1480 (aset latin-extra-code-table ?\226 t)
1482 ;; Move least specific charsets to end of priority list
1484 (apply #'set-charset-priority
1485 (delq 'unicode (delq 'emacs (charset-priority-list))))
1487 ;; The old code-pages library is obsoleted by coding systems based on
1488 ;; the charsets defined in this file but might be required by user
1490 (provide 'code-pages)
1493 ;; no-byte-compile: t
1496 ;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5
1497 ;;; mule-conf.el ends here