1 ;;; mule-conf.el --- configure multilingual environment
3 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003,
4 ;; 2004, 2005, 2006, 2007, 2008 Free Software Foundation, Inc.
5 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008
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 3 of the License, or
19 ;; (at your option) any later version.
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. If not, see <http://www.gnu.org/licenses/>.
31 ;; This file defines the Emacs charsets and some basic coding systems.
32 ;; Other coding systems are defined in the files in directory
39 ;; The ISO-IR registry is at http://www.itscj.ipsj.or.jp/ISO-IR/.
40 ;; Standards docs equivalent to iso-2022 and iso-8859 are at
41 ;; http://www.ecma.ch/.
43 ;; FWIW, http://www.microsoft.com/globaldev/ lists the following for
44 ;; MS Windows, which are presumably the only charsets we really need
45 ;; to worry about on such systems:
46 ;; `OEM codepages': 437, 720, 737, 775, 850, 852, 855, 857, 858, 862, 866
47 ;; `Windows codepages': 1250, 1251, 1252, 1253, 1254, 1255, 1256, 1257,
48 ;; 1258, 874, 932, 936, 949, 950
50 ;;; Definitions of character sets.
52 ;; The charsets `ascii', `unicode' and `eight-bit' are already defined
53 ;; in charset.c as below:
55 ;; (define-charset 'ascii
58 ;; :code-space [0 127]
60 ;; :ascii-compatible-p t
64 ;; (define-charset 'unicode
67 ;; :code-space [0 255 0 255 0 16]
68 ;; :ascii-compatible-p t
71 ;; (define-charset 'emacs
74 ;; :code-space [0 255 0 255 0 63]
75 ;; :ascii-compatible-p t
79 ;; (define-charset 'eight-bit
82 ;; :code-space [128 255]
83 ;; :code-offset #x3FFF80)
85 ;; We now set :docstring, :short-name, and :long-name properties.
88 'ascii
:docstring
"ASCII (ISO646 IRV)")
90 'ascii
:short-name
"ASCII")
92 'ascii
:long-name
"ASCII (ISO646 IRV)")
94 'iso-8859-1
:docstring
"Latin-1 (ISO/IEC 8859-1)")
96 'iso-8859-1
:short-name
"Latin-1")
98 'iso-8859-1
:long-name
"Latin-1")
100 'unicode
:docstring
"Unicode (ISO10646)")
101 (put-charset-property
102 'unicode
:short-name
"Unicode")
103 (put-charset-property
104 'unicode
:long-name
"Unicode (ISO10646)")
105 (put-charset-property
106 'emacs
:docstring
"Full Emacs charset (excluding eight bit chars)")
107 (put-charset-property
108 'emacs
:short-name
"Emacs")
109 (put-charset-property
110 'emacs
:long-name
"Emacs")
112 (put-charset-property 'eight-bit
:docstring
"Raw bytes 0-255")
113 (put-charset-property 'eight-bit
:short-name
"Raw bytes")
115 (define-charset-alias 'ucs
'unicode
)
117 (define-charset 'latin-iso8859-1
118 "Right-Hand Part of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
119 :short-name
"RHP of Latin-1"
120 :long-name
"RHP of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
126 ;; Name perhaps not ideal, but is XEmacs-compatible.
127 (define-charset 'control-1
128 "8-bit control code (0x80..0x9F)"
129 :short-name
"8-bit control code"
130 :code-space
[128 159]
133 (define-charset 'eight-bit-control
134 "Raw bytes in the range 0x80..0x9F (usually produced from invalid encodings)"
135 :short-name
"Raw bytes 0x80..0x9F"
137 :code-space
[128 159]
138 :code-offset
#x3FFF80
) ; see character.h
140 (define-charset 'eight-bit-graphic
141 "Raw bytes in the range 0xA0..0xFF (usually produced from invalid encodings)"
142 :short-name
"Raw bytes 0xA0..0xFF"
144 :code-space
[160 255]
145 :code-offset
#x3FFFA0
) ; see character.h
147 (defmacro define-iso-single-byte-charset
(symbol iso-symbol name nickname
151 (define-charset ,symbol
153 :short-name
,nickname
155 :ascii-compatible-p t
159 (define-charset ,iso-symbol
161 (format "Right-Hand Part of %s (%s): ISO-IR-%d"
162 ,name
,nickname
,iso-ir
)
163 (format "Right-Hand Part of %s (%s)" ,name
,nickname
))
164 :short-name
(format "RHP of %s" ,name
)
165 :long-name
(format "RHP of %s (%s)" ,name
,nickname
)
166 :iso-final-char
,iso-final
167 :emacs-mule-id
,emacs-mule-id
169 :subset
(list ,symbol
160 255 -
128)))))
171 (define-iso-single-byte-charset 'iso-8859-2
'latin-iso8859-2
172 "ISO/IEC 8859/2" "Latin-2" 101 ?B
130 "8859-2")
174 (define-iso-single-byte-charset 'iso-8859-3
'latin-iso8859-3
175 "ISO/IEC 8859/3" "Latin-3" 109 ?C
131 "8859-3")
177 (define-iso-single-byte-charset 'iso-8859-4
'latin-iso8859-4
178 "ISO/IEC 8859/4" "Latin-4" 110 ?D
132 "8859-4")
180 (define-iso-single-byte-charset 'iso-8859-5
'cyrillic-iso8859-5
181 "ISO/IEC 8859/5" "Latin/Cyrillic" 144 ?L
140 "8859-5")
183 (define-iso-single-byte-charset 'iso-8859-6
'arabic-iso8859-6
184 "ISO/IEC 8859/6" "Latin/Arabic" 127 ?G
135 "8859-6")
186 (define-iso-single-byte-charset 'iso-8859-7
'greek-iso8859-7
187 "ISO/IEC 8859/7" "Latin/Greek" 126 ?F
134 "8859-7")
189 (define-iso-single-byte-charset 'iso-8859-8
'hebrew-iso8859-8
190 "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H
136 "8859-8")
192 (define-iso-single-byte-charset 'iso-8859-9
'latin-iso8859-9
193 "ISO/IEC 8859/9" "Latin-5" 148 ?M
141 "8859-9")
195 (define-iso-single-byte-charset 'iso-8859-10
'latin-iso8859-10
196 "ISO/IEC 8859/10" "Latin-6" 157 ?V nil
"8859-10")
198 ;; http://www.nectec.or.th/it-standards/iso8859-11/
199 ;; http://www.cwi.nl/~dik/english/codes/8859.html says this is tis-620
201 (define-iso-single-byte-charset 'iso-8859-11
'thai-iso8859-11
202 "ISO/IEC 8859/11" "Latin/Thai" 166 ?T nil
"8859-11")
204 ;; 8859-12 doesn't (yet?) exist.
206 (define-iso-single-byte-charset 'iso-8859-13
'latin-iso8859-13
207 "ISO/IEC 8859/13" "Latin-7" 179 ?Y nil
"8859-13")
209 (define-iso-single-byte-charset 'iso-8859-14
'latin-iso8859-14
210 "ISO/IEC 8859/14" "Latin-8" 199 ?_
143 "8859-14")
212 (define-iso-single-byte-charset 'iso-8859-15
'latin-iso8859-15
213 "ISO/IEC 8859/15" "Latin-9" 203 ?b
142 "8859-15")
215 (define-iso-single-byte-charset 'iso-8859-16
'latin-iso8859-16
216 "ISO/IEC 8859/16" "Latin-10" 226 ?f nil
"8859-16")
218 ;; No point in keeping it around.
219 (fmakunbound 'define-iso-single-byte-charset
)
221 ;; Can this be shared with 8859-11?
222 ;; N.b. not all of these are defined unicodes.
223 (define-charset 'thai-tis620
225 :short-name
"TIS620.2533"
231 ;; Fixme: doc for this, c.f. above
232 (define-charset 'tis620-2533
234 :short-name
"TIS620.2533"
235 :ascii-compatible-p t
237 :superset
'(ascii eight-bit-control
(thai-tis620 .
128)))
239 (define-charset 'jisx0201
241 :short-name
"JISX0201"
245 (define-charset 'latin-jisx0201
246 "Roman Part of JISX0201.1976"
247 :short-name
"JISX0201 Roman"
248 :long-name
"Japanese Roman (JISX0201.1976)"
253 :subset
'(jisx0201 33 126 0))
255 (define-charset 'katakana-jisx0201
256 "Katakana Part of JISX0201.1976"
257 :short-name
"JISX0201 Katakana"
258 :long-name
"Japanese Katakana (JISX0201.1976)"
263 :subset
'(jisx0201 161 254 -
128))
265 (define-charset 'chinese-gb2312
266 "GB2312 Chinese simplified: ISO-IR-58"
268 :long-name
"GB2312: ISO-IR-58"
271 :code-space
[33 126 33 126]
272 :code-offset
#x110000
275 (define-charset 'chinese-gbk
276 "GBK Chinese simplified."
278 :code-space
[#x40
#xFE
#x81
#xFE
]
279 :code-offset
#x160000
281 (define-charset-alias 'cp936
'chinese-gbk
)
282 (define-charset-alias 'windows-936
'chinese-gbk
)
284 (define-charset 'chinese-cns11643-1
285 "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"
286 :short-name
"CNS11643-1"
287 :long-name
"CNS11643-1 (Chinese traditional): ISO-IR-171"
290 :code-space
[33 126 33 126]
291 :code-offset
#x114000
294 (define-charset 'chinese-cns11643-2
295 "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"
296 :short-name
"CNS11643-2"
297 :long-name
"CNS11643-2 (Chinese traditional): ISO-IR-172"
300 :code-space
[33 126 33 126]
301 :code-offset
#x118000
304 (define-charset 'chinese-cns11643-3
305 "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"
306 :short-name
"CNS11643-3"
307 :long-name
"CNS11643-3 (Chinese traditional): ISO-IR-183"
309 :code-space
[33 126 33 126]
311 :code-offset
#x11C000
314 (define-charset 'chinese-cns11643-4
315 "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"
316 :short-name
"CNS11643-4"
317 :long-name
"CNS11643-4 (Chinese traditional): ISO-IR-184"
320 :code-space
[33 126 33 126]
321 :code-offset
#x120000
324 (define-charset 'chinese-cns11643-5
325 "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"
326 :short-name
"CNS11643-5"
327 :long-name
"CNS11643-5 (Chinese traditional): ISO-IR-185"
330 :code-space
[33 126 33 126]
331 :code-offset
#x124000
334 (define-charset 'chinese-cns11643-6
335 "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"
336 :short-name
"CNS11643-6"
337 :long-name
"CNS11643-6 (Chinese traditional): ISO-IR-186"
340 :code-space
[33 126 33 126]
341 :code-offset
#x128000
344 (define-charset 'chinese-cns11643-7
345 "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"
346 :short-name
"CNS11643-7"
347 :long-name
"CNS11643-7 (Chinese traditional): ISO-IR-187"
350 :code-space
[33 126 33 126]
351 :code-offset
#x12C000
354 (define-charset 'big5
355 "Big5 (Chinese traditional)"
357 :code-space
[#x40
#xFE
#xA1
#xFE
]
358 :code-offset
#x130000
360 ;; Fixme: AKA cp950 according to
361 ;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>. Is
364 (define-charset 'chinese-big5-1
365 "Frequently used part (A141-C67E) of Big5 (Chinese traditional)"
366 :short-name
"Big5 (Level-1)"
367 :long-name
"Big5 (Level-1) A141-C67F"
371 :code-space
[#x21
#x7E
#x21
#x7E
]
372 :code-offset
#x135000
375 (define-charset 'chinese-big5-2
376 "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)"
377 :short-name
"Big5 (Level-2)"
378 :long-name
"Big5 (Level-2) C940-FEFE"
382 :code-space
[#x21
#x7E
#x21
#x7E
]
383 :code-offset
#x137800
386 (define-charset 'japanese-jisx0208
387 "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87"
388 :short-name
"JISX0208"
389 :long-name
"JISX0208.1983/1990 (Japanese): ISO-IR-87"
392 :code-space
[33 126 33 126]
393 :code-offset
#x140000
394 :unify-map
"JISX0208")
396 (define-charset 'japanese-jisx0208-1978
397 "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42"
398 :short-name
"JISX0208.1978"
399 :long-name
"JISX0208.1978 (JISC6226.1978): ISO-IR-42"
402 :code-space
[33 126 33 126]
403 :code-offset
#x144000
404 :unify-map
"JISC6226")
406 (define-charset 'japanese-jisx0212
407 "JISX0212 Japanese supplement: ISO-IR-159"
408 :short-name
"JISX0212"
409 :long-name
"JISX0212 (Japanese): ISO-IR-159"
412 :code-space
[33 126 33 126]
413 :code-offset
#x148000
414 :unify-map
"JISX0212")
416 ;; Note that jisx0213 contains characters not in Unicode (3.2?). It's
417 ;; arguable whether it should have a unify-map.
418 (define-charset 'japanese-jisx0213-1
419 "JISX0213.2000 Plane 1 (Japanese)"
420 :short-name
"JISX0213-1"
423 :unify-map
"JISX2131"
424 :code-space
[33 126 33 126]
425 :code-offset
#x14C000
)
427 (define-charset 'japanese-jisx0213-2
428 "JISX0213.2000 Plane 2 (Japanese)"
429 :short-name
"JISX0213-2"
432 :unify-map
"JISX2132"
433 :code-space
[33 126 33 126]
434 :code-offset
#x150000
)
436 (define-charset 'japanese-jisx0213-a
437 "JISX0213.2004 adds these characters to JISX0213.2000."
438 :short-name
"JISX0213A"
440 :code-space
[33 126 33 126]
444 (define-charset 'japanese-jisx0213.2004-
1
445 "JISX0213.2004 Plane1 (Japanese)"
446 :short-name
"JISX0213.2004-1"
448 :code-space
[33 126 33 126]
450 :superset
'(japanese-jisx0213-a japanese-jisx0213-1
))
452 (define-charset 'katakana-sjis
453 "Katakana part of Shift-JIS"
455 :code-space
[#xA1
#xDF
]
456 :subset
'(jisx0201 #xA1
#xDF
0)
459 (define-charset 'cp932-2-byte
460 "2-byte part of CP932"
463 :code-space
[#x40
#xFC
#x81
#xFC
]
466 (define-charset 'cp932
467 "CP932 (Microsoft shift-jis)"
468 :code-space
[#x00
#xFF
#x00
#xFE
]
470 :superset
'(ascii katakana-sjis cp932-2-byte
))
472 (define-charset 'korean-ksc5601
473 "KSC5601 Korean Hangul and Hanja: ISO-IR-149"
474 :short-name
"KSC5601"
475 :long-name
"KSC5601 (Korean): ISO-IR-149"
478 :code-space
[33 126 33 126]
479 :code-offset
#x279f94
; ... #x27c217
480 :unify-map
"KSC5601")
482 (define-charset 'big5-hkscs
483 "Big5-HKSCS (Chinese traditional, Hong Kong supplement)"
485 :code-space
[#x40
#xFE
#xA1
#xFE
]
486 :code-offset
#x27c218
; ... #x280839
487 :unify-map
"BIG5-HKSCS")
489 ;; Fixme: Korean cp949/UHC
491 (define-charset 'chinese-sisheng
492 "SiSheng characters for PinYin/ZhuYin"
493 :short-name
"SiSheng"
494 :long-name
"SiSheng (PinYin/ZhuYin)"
498 :unify-map
"MULE-sisheng"
500 :code-offset
#x200000
)
502 ;; A subset of the 1989 version of IPA. It consists of the consonant
503 ;; signs used in English, French, German and Italian, and all vowels
504 ;; signs in the table. [says old MULE doc]
506 "IPA (International Phonetic Association)"
510 :unify-map
"MULE-ipa"
513 :code-offset
#x200080
)
515 (define-charset 'viscii
518 :long-name
"VISCII 1.1"
522 (define-charset 'vietnamese-viscii-lower
523 "VISCII1.1 lower-case"
524 :short-name
"VISCII lower"
525 :long-name
"VISCII lower-case"
529 :code-offset
#x200200
531 :unify-map
"MULE-lviscii")
533 (define-charset 'vietnamese-viscii-upper
534 "VISCII1.1 upper-case"
535 :short-name
"VISCII upper"
536 :long-name
"VISCII upper-case"
540 :code-offset
#x200280
542 :unify-map
"MULE-uviscii")
544 (define-charset 'vscii
545 "VSCII1.1 (TCVN-5712 VN1)"
550 (define-charset-alias 'tcvn-5712
'vscii
)
552 ;; Fixme: see note in tcvn.map about combining characters
553 (define-charset 'vscii-2
554 "VSCII-2 (TCVN-5712 VN2)"
558 (define-charset 'koi8-r
561 :ascii-compatible-p t
565 (define-charset-alias 'koi8
'koi8-r
)
567 (define-charset 'alternativnyj
569 :short-name
"alternativnyj"
570 :ascii-compatible-p t
572 :map
"ALTERNATIVNYJ")
574 (define-charset 'cp866
577 :ascii-compatible-p t
580 (define-charset-alias 'ibm866
'cp866
)
582 (define-charset 'koi8-u
585 :ascii-compatible-p t
589 (define-charset 'koi8-t
592 :ascii-compatible-p t
596 (define-charset 'georgian-ps
598 :short-name
"GEORGIAN-PS"
599 :ascii-compatible-p t
603 (define-charset 'georgian-academy
605 :short-name
"GEORGIAN-ACADEMY"
606 :ascii-compatible-p t
610 (define-charset 'windows-1250
611 "WINDOWS-1250 (Central Europe)"
612 :short-name
"WINDOWS-1250"
613 :ascii-compatible-p t
616 (define-charset-alias 'cp1250
'windows-1250
)
618 (define-charset 'windows-1251
619 "WINDOWS-1251 (Cyrillic)"
620 :short-name
"WINDOWS-1251"
621 :ascii-compatible-p t
624 (define-charset-alias 'cp1251
'windows-1251
)
626 (define-charset 'windows-1252
627 "WINDOWS-1252 (Latin I)"
628 :short-name
"WINDOWS-1252"
629 :ascii-compatible-p t
632 (define-charset-alias 'cp1252
'windows-1252
)
634 (define-charset 'windows-1253
635 "WINDOWS-1253 (Greek)"
636 :short-name
"WINDOWS-1253"
637 :ascii-compatible-p t
640 (define-charset-alias 'cp1253
'windows-1253
)
642 (define-charset 'windows-1254
643 "WINDOWS-1254 (Turkish)"
644 :short-name
"WINDOWS-1254"
645 :ascii-compatible-p t
648 (define-charset-alias 'cp1254
'windows-1254
)
650 (define-charset 'windows-1255
651 "WINDOWS-1255 (Hebrew)"
652 :short-name
"WINDOWS-1255"
653 :ascii-compatible-p t
656 (define-charset-alias 'cp1255
'windows-1255
)
658 (define-charset 'windows-1256
659 "WINDOWS-1256 (Arabic)"
660 :short-name
"WINDOWS-1256"
661 :ascii-compatible-p t
664 (define-charset-alias 'cp1256
'windows-1256
)
666 (define-charset 'windows-1257
667 "WINDOWS-1257 (Baltic)"
668 :short-name
"WINDOWS-1257"
669 :ascii-compatible-p t
672 (define-charset-alias 'cp1257
'windows-1257
)
674 (define-charset 'windows-1258
675 "WINDOWS-1258 (Viet Nam)"
676 :short-name
"WINDOWS-1258"
677 :ascii-compatible-p t
680 (define-charset-alias 'cp1258
'windows-1258
)
682 (define-charset 'next
685 :ascii-compatible-p t
689 (define-charset 'cp1125
693 :ascii-compatible-p t
695 (define-charset-alias 'ruscii
'cp1125
)
696 ;; Original name for cp1125, says Serhii Hlodin <hlodin@lutsk.bank.gov.ua>
697 (define-charset-alias 'cp866u
'cp1125
)
699 ;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html
700 ;; shows this as not ASCII comptaible, with various graphics in
702 (define-charset 'cp437
703 "CP437 (MS-DOS United States, Australia, New Zealand, South Africa)"
706 :ascii-compatible-p t
709 (define-charset 'cp720
713 :ascii-compatible-p t
716 (define-charset 'cp737
720 :ascii-compatible-p t
723 (define-charset 'cp775
727 :ascii-compatible-p t
730 (define-charset 'cp851
734 :ascii-compatible-p t
737 (define-charset 'cp852
738 "CP852 (MS-DOS Latin-2)"
741 :ascii-compatible-p t
744 (define-charset 'cp855
745 "CP855 (IBM Cyrillic)"
748 :ascii-compatible-p t
751 (define-charset 'cp857
752 "CP857 (IBM Turkish)"
755 :ascii-compatible-p t
758 (define-charset 'cp858
759 "CP858 (Multilingual Latin I + Euro)"
762 :ascii-compatible-p t
764 (define-charset-alias 'cp00858
'cp858
) ; IANA has IBM00858/CP00858
766 (define-charset 'cp860
767 "CP860 (MS-DOS Portuguese)"
770 :ascii-compatible-p t
773 (define-charset 'cp861
774 "CP861 (MS-DOS Icelandic)"
777 :ascii-compatible-p t
780 (define-charset 'cp862
784 :ascii-compatible-p t
787 (define-charset 'cp863
788 "CP863 (MS-DOS Canadian French)"
791 :ascii-compatible-p t
794 (define-charset 'cp864
798 :ascii-compatible-p t
801 (define-charset 'cp865
802 "CP865 (MS-DOS Nordic)"
805 :ascii-compatible-p t
808 (define-charset 'cp869
809 "CP869 (IBM Modern Greek)"
812 :ascii-compatible-p t
815 (define-charset 'cp874
819 :ascii-compatible-p t
822 ;; For Arabic, we need three different types of character sets.
823 ;; Digits are of direction left-to-right and of width 1-column.
824 ;; Others are of direction right-to-left and of width 1-column or
826 (define-charset 'arabic-digit
828 :short-name
"Arabic digit"
835 (define-charset 'arabic-1-column
837 :short-name
"Arabic 1-col"
838 :long-name
"Arabic 1-column"
843 :code-offset
#x200100
)
845 (define-charset 'arabic-2-column
847 :short-name
"Arabic 2-col"
848 :long-name
"Arabic 2-column"
853 :code-offset
#x200180
)
856 ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF.
857 ;; Not all of them are defined unicodes.
859 "Lao characters (ISO10646 0E81..0EDF)"
867 (define-charset 'mule-lao
868 "Lao characters (ISO10646 0E81..0EDF)"
872 :superset
'(ascii eight-bit-control
(lao .
128)))
875 ;; Indian scripts. Symbolic charset for data exchange. Glyphs are
876 ;; not assigned. They are automatically converted to each Indian
877 ;; script which IS-13194 supports.
879 (define-charset 'indian-is13194
880 "Generic Indian charset for data exchange with IS 13194"
881 :short-name
"IS 13194"
882 :long-name
"Indian IS 13194"
887 :code-offset
#x180000
)
889 (let ((code-offset #x180100
))
890 (dolist (script '(devanagari sanskrit bengali tamil telugu assamese
891 oriya kannada malayalam gujarati punjabi
))
892 (define-charset (intern (format "%s-cdac" script
))
893 (format "Glyphs of %s script for CDAC font. Subset of `indian-glyph'."
894 (capitalize (symbol-name script
)))
895 :short-name
(format "CDAC %s glyphs" (capitalize (symbol-name script
)))
898 :code-offset code-offset
)
899 (setq code-offset
(+ code-offset
#x100
)))
901 (dolist (script '(devanagari bengali punjabi gujarati
902 oriya tamil telugu kannada malayalam
))
903 (define-charset (intern (format "%s-akruti" script
))
904 (format "Glyphs of %s script for AKRUTI font. Subset of `indian-glyph'."
905 (capitalize (symbol-name script
)))
906 :short-name
(format "AKRUTI %s glyphs" (capitalize (symbol-name script
)))
909 :code-offset code-offset
)
910 (setq code-offset
(+ code-offset
#x100
))))
912 (define-charset 'indian-glyph
913 "Glyphs for Indian characters."
914 :short-name
"Indian glyph"
918 :code-space
[32 127 32 127]
919 :code-offset
#x180100
)
921 ;; Actual Glyph for 1-column width.
922 (define-charset 'indian-1-column
923 "Indian charset for 1-column width glyphs."
924 :short-name
"Indian 1-col"
925 :long-name
"Indian 1 Column"
929 :code-space
[33 126 33 126]
930 :code-offset
#x184000
)
932 ;; Actual Glyph for 2-column width.
933 (define-charset 'indian-2-column
934 "Indian charset for 2-column width glyphs."
935 :short-name
"Indian 2-col"
936 :long-name
"Indian 2 Column"
940 :code-space
[33 126 33 126]
941 :code-offset
#x184000
)
943 (define-charset 'tibetan
946 :short-name
"Tibetan 2-col"
947 :long-name
"Tibetan 2 column"
950 :unify-map
"MULE-tibetan"
952 :code-space
[33 126 33 37]
953 :code-offset
#x190000
)
955 (define-charset 'tibetan-1-column
956 "Tibetan 1 column glyph"
957 :short-name
"Tibetan 1-col"
958 :long-name
"Tibetan 1 column"
962 :code-space
[33 126 33 37]
963 :code-offset
#x190000
)
965 ;; Subsets of Unicode.
966 (define-charset 'mule-unicode-2500-33ff
967 "Unicode characters of the range U+2500..U+33FF."
968 :short-name
"Unicode subset 2"
969 :long-name
"Unicode subset (U+2500..U+33FF)"
973 :code-space
[#x20
#x7f
#x20
#x47
]
976 (define-charset 'mule-unicode-e000-ffff
977 "Unicode characters of the range U+E000..U+FFFF."
978 :short-name
"Unicode subset 3"
979 :long-name
"Unicode subset (U+E000+FFFF)"
983 :code-space
[#x20
#x7F
#x20
#x75
]
985 :max-code
30015) ; U+FFFF
987 (define-charset 'mule-unicode-0100-24ff
988 "Unicode characters of the range U+0100..U+24FF."
989 :short-name
"Unicode subset"
990 :long-name
"Unicode subset (U+0100..U+24FF)"
994 :code-space
[#x20
#x7F
#x20
#x7F
]
997 (define-charset 'unicode-bmp
998 "Unicode Basic Multilingual Plane (U+0000..U+FFFF)"
999 :short-name
"Unicode BMP"
1000 :code-space
[0 255 0 255]
1003 (define-charset 'unicode-smp
1004 "Unicode Supplementary Multilingual Plane (U+10000..U+1FFFF)"
1005 :short-name
"Unicode SMP "
1006 :code-space
[0 255 0 255]
1007 :code-offset
#x10000
)
1009 (define-charset 'unicode-sip
1010 "Unicode Supplementary Ideographic Plane (U+20000..U+2FFFF)"
1011 :short-name
"Unicode SIP"
1012 :code-space
[0 255 0 255]
1013 :code-offset
#x20000
)
1015 (define-charset 'unicode-ssp
1016 "Unicode Supplementary Special-purpose Plane (U+E0000..U+EFFFF)"
1017 :short-name
"Unicode SSP"
1018 :code-space
[0 255 0 255]
1019 :code-offset
#xE0000
)
1021 (define-charset 'ethiopic
1022 "Ethiopic characters for Amharic and Tigrigna."
1023 :short-name
"Ethiopic"
1024 :long-name
"Ethiopic characters"
1028 :unify-map
"MULE-ethiopic"
1029 :code-space
[33 126 33 126]
1030 :code-offset
#x1A0000
)
1032 (define-charset 'mac-roman
1034 :short-name
"Mac Roman"
1035 :ascii-compatible-p t
1039 ;; Fixme: modern EBCDIC variants, e.g. IBM00924?
1040 (define-charset 'ebcdic-us
1041 "US version of EBCDIC"
1042 :short-name
"EBCDIC-US"
1044 :mime-charset
'ebcdic-us
1047 (define-charset 'ebcdic-uk
1048 "UK version of EBCDIC"
1049 :short-name
"EBCDIC-UK"
1051 :mime-charset
'ebcdic-uk
1054 (define-charset 'ibm1047
1056 "IBM1047, `EBCDIC Latin 1/Open Systems' used by OS/390 Unix."
1057 :short-name
"IBM1047"
1059 :mime-charset
'ibm1047
1061 (define-charset-alias 'cp1047
'ibm1047
)
1063 (define-charset 'hp-roman8
1064 "Encoding used by Hewlet-Packard printer software"
1065 :short-name
"HP-ROMAN8"
1066 :ascii-compatible-p t
1070 ;; To make a coding system with this, a pre-write-conversion should
1071 ;; account for the commented-out multi-valued code points in
1073 (define-charset 'adobe-standard-encoding
1074 "Adobe `standard encoding' used in PostScript"
1075 :short-name
"ADOBE-STANDARD-ENCODING"
1076 :code-space
[#x20
255]
1079 (define-charset 'symbol
1080 "Adobe symbol encoding used in PostScript"
1081 :short-name
"ADOBE-SYMBOL"
1082 :code-space
[#x20
255]
1085 (define-charset 'ibm850
1086 "DOS codepage 850 (Latin-1)"
1087 :short-name
"IBM850"
1088 :ascii-compatible-p t
1091 (define-charset-alias 'cp850
'ibm850
)
1093 (define-charset 'mik
1094 "Bulgarian DOS codepage"
1096 :ascii-compatible-p t
1100 (define-charset 'ptcp154
1101 "`Paratype' codepage (Asian Cyrillic)"
1103 :ascii-compatible-p t
1105 :mime-charset
'pt154
1107 (define-charset-alias 'pt154
'ptcp154
)
1108 (define-charset-alias 'cp154
'ptcp154
)
1110 (define-charset 'gb18030-2-byte
1111 "GB18030 2-byte (0x814E..0xFEFE)"
1112 :code-space
[#x40
#xFE
#x81
#xFE
]
1116 (define-charset 'gb18030-4-byte-bmp
1117 "GB18030 4-byte for BMP (0x81308130-0x8431A439)"
1118 :code-space
[#x30
#x39
#x81
#xFE
#x30
#x39
#x81
#x84
]
1122 (define-charset 'gb18030-4-byte-smp
1123 "GB18030 4-byte for SMP (0x90308130-0xE3329A35)"
1124 :code-space
[#x30
#x39
#x81
#xFE
#x30
#x39
#x90
#xE3
]
1125 :min-code
'(#x9030 .
#x8130
)
1126 :max-code
'(#xE332 .
#x9A35
)
1128 :code-offset
#x10000
)
1130 (define-charset 'gb18030-4-byte-ext-1
1131 "GB18030 4-byte (0x8431A530-0x8F39FE39)"
1132 :code-space
[#x30
#x39
#x81
#xFE
#x30
#x39
#x84
#x8F
]
1133 :min-code
'(#x8431 .
#xA530
)
1134 :max-code
'(#x8F39 .
#xFE39
)
1136 :code-offset
#x200000
; ... #x22484B
1139 (define-charset 'gb18030-4-byte-ext-2
1140 "GB18030 4-byte (0xE3329A36-0xFE39FE39)"
1141 :code-space
[#x30
#x39
#x81
#xFE
#x30
#x39
#xE3
#xFE
]
1142 :min-code
'(#xE332 .
#x9A36
)
1143 :max-code
'(#xFE39 .
#xFE39
)
1145 :code-offset
#x22484C
; ... #x279f93
1148 (define-charset 'gb18030
1150 :code-space
[#x00
#xFF
#x00
#xFE
#x00
#xFE
#x00
#xFE
]
1152 :max-code
'(#xFE39 .
#xFE39
)
1153 :superset
'(ascii gb18030-2-byte
1154 gb18030-4-byte-bmp gb18030-4-byte-smp
1155 gb18030-4-byte-ext-1 gb18030-4-byte-ext-2
))
1157 (define-charset 'chinese-cns11643-15
1158 "CNS11643 Plane 15 Chinese Traditional"
1159 :short-name
"CNS11643-15"
1160 :long-name
"CNS11643-15 (Chinese traditional)"
1161 :code-space
[33 126 33 126]
1162 :code-offset
#x27A000
)
1164 (unify-charset 'chinese-gb2312
)
1165 (unify-charset 'chinese-gbk
)
1166 (unify-charset 'chinese-cns11643-1
)
1167 (unify-charset 'chinese-cns11643-2
)
1168 (unify-charset 'chinese-cns11643-3
)
1169 (unify-charset 'chinese-cns11643-4
)
1170 (unify-charset 'chinese-cns11643-5
)
1171 (unify-charset 'chinese-cns11643-6
)
1172 (unify-charset 'chinese-cns11643-7
)
1173 (unify-charset 'big5
)
1174 (unify-charset 'chinese-big5-1
)
1175 (unify-charset 'chinese-big5-2
)
1176 (unify-charset 'big5-hkscs
)
1177 (unify-charset 'korean-ksc5601
)
1178 (unify-charset 'vietnamese-viscii-lower
)
1179 (unify-charset 'vietnamese-viscii-upper
)
1180 (unify-charset 'chinese-sisheng
)
1181 (unify-charset 'ipa
)
1182 (unify-charset 'tibetan
)
1183 (unify-charset 'ethiopic
)
1184 (unify-charset 'japanese-jisx0208-1978
)
1185 (unify-charset 'japanese-jisx0208
)
1186 (unify-charset 'japanese-jisx0212
)
1187 (unify-charset 'japanese-jisx0213-1
)
1188 (unify-charset 'japanese-jisx0213-2
)
1191 ;; These are tables for translating characters on decoding and
1193 ;; Fixme: these aren't used now -- should they be?
1194 (setq standard-translation-table-for-decode nil
)
1196 (setq standard-translation-table-for-encode nil
)
1198 ;;; Make fundamental coding systems.
1200 ;; The coding system `no-conversion' and `undecided' are already
1201 ;; defined in coding.c as below:
1203 ;; (define-coding-system 'no-conversion
1205 ;; :coding-type 'raw-text
1207 ;; (define-coding-system 'undecided
1209 ;; :coding-type 'undecided
1212 (define-coding-system-alias 'binary
'no-conversion
)
1213 (define-coding-system-alias 'unix
'undecided-unix
)
1214 (define-coding-system-alias 'dos
'undecided-dos
)
1215 (define-coding-system-alias 'mac
'undecided-mac
)
1217 (define-coding-system 'raw-text
1218 "Raw text, which means text contains random 8-bit codes.
1219 Encoding text with this coding system produces the actual byte
1220 sequence of the text in buffers and strings. An exception is made for
1221 eight-bit-control characters. Each of them is encoded into a single
1224 When you visit a file with this coding, the file is read into a
1225 unibyte buffer as is (except for EOL format), thus each byte of a file
1226 is treated as a character."
1227 :coding-type
'raw-text
1231 (define-coding-system 'no-conversion-multibyte
1232 "Like `no-conversion' but don't read a file into a unibyte buffer."
1233 :coding-type
'raw-text
1237 (define-coding-system 'iso-latin-1
1238 "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)."
1239 :coding-type
'charset
1241 :charset-list
'(iso-8859-1)
1242 :mime-charset
'iso-8859-1
)
1244 (define-coding-system-alias 'iso-8859-1
'iso-latin-1
)
1245 (define-coding-system-alias 'latin-1
'iso-latin-1
)
1247 ;; Coding systems not specific to each language environment.
1249 (define-coding-system 'emacs-mule
1250 "Emacs 21 internal format used in buffer and string."
1251 :coding-type
'emacs-mule
1252 :charset-list
'emacs-mule
1255 (define-coding-system 'utf-8
1259 :charset-list
'(unicode)
1260 :mime-charset
'utf-8
)
1262 (define-coding-system-alias 'mule-utf-8
'utf-8
)
1264 (define-coding-system 'utf-8-emacs
1265 "Support for all Emacs characters (including non-Unicode characters)."
1268 :charset-list
'(emacs))
1270 (define-coding-system 'utf-16le
1271 "UTF-16LE (little endian, no signature (BOM))."
1272 :coding-type
'utf-16
1274 :charset-list
'(unicode)
1276 :mime-text-unsuitable t
1277 :mime-charset
'utf-16le
)
1279 (define-coding-system 'utf-16be
1280 "UTF-16BE (big endian, no signature (BOM))."
1281 :coding-type
'utf-16
1283 :charset-list
'(unicode)
1285 :mime-text-unsuitable t
1286 :mime-charset
'utf-16be
)
1288 (define-coding-system 'utf-16le-with-signature
1289 "UTF-16 (little endian, with signature (BOM))."
1290 :coding-type
'utf-16
1292 :charset-list
'(unicode)
1295 :mime-text-unsuitable t
1296 :mime-charset
'utf-16
)
1298 (define-coding-system 'utf-16be-with-signature
1299 "UTF-16 (big endian, with signature)."
1300 :coding-type
'utf-16
1302 :charset-list
'(unicode)
1305 :mime-text-unsuitable t
1306 :mime-charset
'utf-16
)
1308 (define-coding-system 'utf-16
1309 "UTF-16 (detect endian on decoding, use big endian on encoding with BOM)."
1310 :coding-type
'utf-16
1312 :charset-list
'(unicode)
1313 :bom
'(utf-16le-with-signature . utf-16be-with-signature
)
1315 :mime-text-unsuitable t
1316 :mime-charset
'utf-16
)
1318 ;; Backwards compatibility (old names, also used by Mule-UCS). We
1319 ;; prefer the MIME names.
1320 (define-coding-system-alias 'utf-16-le
'utf-16le-with-signature
)
1321 (define-coding-system-alias 'utf-16-be
'utf-16be-with-signature
)
1324 (define-coding-system 'iso-2022-7bit
1325 "ISO 2022 based 7-bit encoding using only G0."
1326 :coding-type
'iso-2022
1328 :charset-list
'iso-2022
1329 :designation
[(ascii t
) nil nil nil
]
1330 :flags
'(short ascii-at-eol ascii-at-cntl
7-bit designation composition
))
1332 (define-coding-system 'iso-2022-7bit-ss2
1333 "ISO 2022 based 7-bit encoding using SS2 for 96-charset."
1334 :coding-type
'iso-2022
1336 :charset-list
'iso-2022
1337 :designation
[(ascii 94) nil
(nil 96) nil
]
1338 :flags
'(short ascii-at-eol ascii-at-cntl
7-bit
1339 designation single-shift composition
))
1341 (define-coding-system 'iso-2022-7bit-lock
1342 "ISO-2022 coding system using Locking-Shift for 96-charset."
1343 :coding-type
'iso-2022
1345 :charset-list
'iso-2022
1346 :designation
[(ascii 94) (nil 96) nil nil
]
1347 :flags
'(ascii-at-eol ascii-at-cntl
7-bit
1348 designation locking-shift composition
))
1350 (define-coding-system-alias 'iso-2022-int-1
'iso-2022-7bit-lock
)
1352 (define-coding-system 'iso-2022-7bit-lock-ss2
1353 "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN."
1354 :coding-type
'iso-2022
1356 :charset-list
'(ascii
1357 japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
1360 chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
1361 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
1363 :designation
[(ascii 94)
1364 (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1
96)
1365 (nil chinese-cns11643-2
)
1366 (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
1367 chinese-cns11643-6 chinese-cns11643-7
)]
1368 :flags
'(short ascii-at-eol ascii-at-cntl
7-bit locking-shift
1369 single-shift init-bol
))
1371 (define-coding-system-alias 'iso-2022-cjk
'iso-2022-7bit-lock-ss2
)
1373 (define-coding-system 'iso-2022-8bit-ss2
1374 "ISO 2022 based 8-bit encoding using SS2 for 96-charset."
1375 :coding-type
'iso-2022
1377 :charset-list
'iso-2022
1378 :designation
[(ascii 94) nil
(nil 96) nil
]
1379 :flags
'(ascii-at-eol ascii-at-cntl designation single-shift composition
))
1381 (define-coding-system 'compound-text
1382 "Compound text based generic encoding for decoding unknown messages.
1384 This coding system does not support extended segments of CTEXT."
1385 :coding-type
'iso-2022
1387 :charset-list
'iso-2022
1388 :designation
[(ascii 94) (latin-iso8859-1 katakana-jisx0201
96) nil nil
]
1389 :flags
'(ascii-at-eol ascii-at-cntl long-form
1390 designation locking-shift single-shift composition
)
1391 ;; Fixme: this isn't a valid MIME charset and has to be
1392 ;; special-cased elsewhere -- fx
1393 :mime-charset
'x-ctext
)
1395 (define-coding-system-alias 'x-ctext
'compound-text
)
1396 (define-coding-system-alias 'ctext
'compound-text
)
1398 ;; Same as compound-text, but doesn't produce composition escape
1399 ;; sequences. Used in post-read and pre-write conversions of
1400 ;; compound-text-with-extensions, see mule.el. Note that this should
1401 ;; not have a mime-charset property, to prevent it from showing up
1402 ;; close to the beginning of coding systems ordered by priority.
1403 (define-coding-system 'ctext-no-compositions
1404 "Compound text based generic encoding for decoding unknown messages.
1406 Like `compound-text', but does not produce escape sequences for compositions."
1407 :coding-type
'iso-2022
1409 :charset-list
'iso-2022
1410 :designation
[(ascii 94) (latin-iso8859-1 katakana-jisx0201
96) nil nil
]
1411 :flags
'(ascii-at-eol ascii-at-cntl
1412 designation locking-shift single-shift
))
1414 (define-coding-system 'compound-text-with-extensions
1415 "Compound text encoding with ICCCM Extended Segment extensions.
1417 See the variable `ctext-non-standard-encodings-alist' for the
1418 detail about how extended segments are handled.
1420 This coding system should be used only for X selections. It is inappropriate
1421 for decoding and encoding files, process I/O, etc."
1422 :coding-type
'iso-2022
1424 :charset-list
'iso-2022
1425 :designation
[(ascii 94) (latin-iso8859-1 katakana-jisx0201
96) nil nil
]
1426 :flags
'(ascii-at-eol ascii-at-cntl long-form
1427 designation locking-shift single-shift
)
1428 :post-read-conversion
'ctext-post-read-conversion
1429 :pre-write-conversion
'ctext-pre-write-conversion
)
1431 (define-coding-system-alias
1432 'x-ctext-with-extensions
'compound-text-with-extensions
)
1433 (define-coding-system-alias
1434 'ctext-with-extensions
'compound-text-with-extensions
)
1436 (define-coding-system 'us-ascii
1437 "Encode ASCII as-is and encode non-ASCII characters to `?'."
1438 :coding-type
'charset
1440 :charset-list
'(ascii)
1442 :mime-charset
'us-ascii
)
1444 (define-coding-system-alias 'iso-safe
'us-ascii
)
1446 (define-coding-system 'utf-7
1447 "UTF-7 encoding of Unicode (RFC 2152)."
1450 :mime-charset
'utf-7
1451 :charset-list
'(unicode)
1452 :pre-write-conversion
'utf-7-pre-write-conversion
1453 :post-read-conversion
'utf-7-post-read-conversion
)
1455 (define-coding-system 'utf-7-imap
1456 "UTF-7 encoding of Unicode, IMAP version (RFC 2060)"
1459 :charset-list
'(unicode)
1460 :pre-write-conversion
'utf-7-imap-pre-write-conversion
1461 :post-read-conversion
'utf-7-imap-post-read-conversion
)
1463 ;; Use us-ascii for terminal output if some other coding system is not
1464 ;; specified explicitly.
1465 (set-safe-terminal-coding-system-internal 'us-ascii
)
1467 ;; The other coding-systems are defined in each language specific
1468 ;; files under lisp/language.
1470 ;; Normally, set coding system to `undecided' before reading a file.
1471 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
1472 ;; but we regard them as containing multibyte characters.
1473 ;; Tar files are not decoded at all, but we treat them as raw bytes.
1475 (setq file-coding-system-alist
1476 '(("\\.elc\\'" . utf-8-emacs
)
1477 ("\\.utf\\(-8\\)?\\'" . utf-8
)
1478 ("\\.xml\\'" . xml-find-file-coding-system
)
1479 ;; We use raw-text for reading loaddefs.el so that if it
1480 ;; happens to have DOS or Mac EOLs, they are converted to
1481 ;; newlines. This is required to make the special treatment
1482 ;; of the "\ newline" combination in loaddefs.el, which marks
1483 ;; the beginning of a doc string, work.
1484 ("\\(\\`\\|/\\)loaddefs.el\\'" .
(raw-text . raw-text-unix
))
1485 ("\\.tar\\'" .
(no-conversion . no-conversion
))
1486 ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system
)
1487 ("\\.\\(tex\\|ltx\\|dtx\\|drv\\)\\'" . latexenc-find-file-coding-system
)
1488 ("" .
(undecided . nil
))))
1491 ;;; Setting coding categories and their priorities.
1493 ;; This setting is just to read an Emacs Lisp source files which
1494 ;; contain multilingual text while dumping Emacs. More appropriate
1495 ;; values are set by the command `set-language-environment' for each
1496 ;; language environment.
1498 (set-coding-system-priority
1505 ;;; Miscellaneous settings.
1507 ;; Make all multibyte characters self-insert.
1508 (set-char-table-range (nth 1 global-map
)
1509 (cons 128 (max-char))
1510 'self-insert-command
)
1512 (aset latin-extra-code-table ?
\221 t
)
1513 (aset latin-extra-code-table ?
\222 t
)
1514 (aset latin-extra-code-table ?
\223 t
)
1515 (aset latin-extra-code-table ?
\224 t
)
1516 (aset latin-extra-code-table ?
\225 t
)
1517 (aset latin-extra-code-table ?
\226 t
)
1519 ;; The old code-pages library is obsoleted by coding systems based on
1520 ;; the charsets defined in this file but might be required by user
1522 (provide 'code-pages
)
1525 ;; no-byte-compile: t
1528 ;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5
1529 ;;; mule-conf.el ends here