1 ;;; mule-conf.el --- configure multilingual environment
3 ;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN.
4 ;; Licensed to the Free Software Foundation.
5 ;; Copyright (C) 2002, 2003 Free Software Foundation, Inc.
7 ;; National Institute of Advanced Industrial Science and Technology (AIST)
8 ;; Registration Number H13PRO009
10 ;; Keywords: i18n, mule, multilingual, character set, coding system
12 ;; This file is part of GNU Emacs.
14 ;; GNU Emacs is free software; you can redistribute it and/or modify
15 ;; it under the terms of the GNU General Public License as published by
16 ;; the Free Software Foundation; either version 2, or (at your option)
19 ;; GNU Emacs is distributed in the hope that it will be useful,
20 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
21 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
22 ;; GNU General Public License for more details.
24 ;; You should have received a copy of the GNU General Public License
25 ;; along with GNU Emacs; see the file COPYING. If not, write to the
26 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
27 ;; Boston, MA 02111-1307, USA.
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 'eight-bit
74 ;; :code-space [128 255]
75 ;; :code-offset #x3FFF80)
77 ;; We now set :docstring, :short-name, and :long-name properties.
80 'ascii
:docstring
"ASCII (ISO646 IRV)")
82 'ascii
:short-name
"ASCII")
84 'ascii
:long-name
"ASCII (ISO646 IRV)")
86 'iso-8859-1
:docstring
"Latin-1 (ISO/IEC 8859-1)")
88 'iso-8859-1
:short-name
"Latin-1")
90 'iso-8859-1
:long-name
"Latin-1")
92 'unicode
:docstring
"Unicode (ISO10646)")
94 'unicode
:short-name
"Unicode")
96 'unicode
:long-name
"Unicode (ISO10646)")
97 (put-charset-property 'eight-bit
:docstring
"Raw bytes 0-255")
98 (put-charset-property 'eight-bit
:short-name
"Raw bytes")
100 (define-charset-alias 'ucs
'unicode
)
102 (define-charset 'emacs
103 "Full Emacs characters"
104 :ascii-compatible-p t
105 :code-space
[ 0 255 0 255 0 63 ]
109 (define-charset 'latin-iso8859-1
110 "Right-Hand Part of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
111 :short-name
"RHP of Latin-1"
112 :long-name
"RHP of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
118 ;; Name perhaps not ideal, but is XEmacs-compatible.
119 (define-charset 'control-1
120 "8-bit control code (0x80..0x9F)"
121 :short-name
"8-bit control code"
122 :code-space
[128 159]
125 (define-charset 'eight-bit-control
126 "Raw bytes in the range 0x80..0x9F (usually produced from invalid encodings)"
127 :short-name
"Raw bytes 0x80..0x9F"
128 :code-space
[128 159]
129 :code-offset
#x3FFF80
) ; see character.h
131 (define-charset 'eight-bit-graphic
132 "Raw bytes in the range 0xA0..0xFF (usually produced from invalid encodings)"
133 :short-name
"Raw bytes 0xA0..0xFF"
134 :code-space
[160 255]
135 :code-offset
#x3FFFA0
) ; see character.h
137 (defmacro define-iso-single-byte-charset
(symbol iso-symbol name nickname
141 (define-charset ,symbol
143 :short-name
,nickname
145 :ascii-compatible-p t
149 (define-charset ,iso-symbol
151 (format "Right-Hand Part of %s (%s): ISO-IR-%d"
152 ,name
,nickname
,iso-ir
)
153 (format "Right-Hand Part of %s (%s)" ,name
,nickname
))
154 :short-name
(format "RHP of %s" ,name
)
155 :long-name
(format "RHP of %s (%s)" ,name
,nickname
)
156 :iso-final-char
,iso-final
157 :emacs-mule-id
,emacs-mule-id
159 :subset
(list ,symbol
160 255 -
128)))))
161 (define-iso-single-byte-charset 'iso-8859-2
'latin-iso8859-2
162 "ISO/IEC 8859/2" "Latin-2" 101 ?B
130 "8859-2")
164 (define-iso-single-byte-charset 'iso-8859-3
'latin-iso8859-3
165 "ISO/IEC 8859/3" "Latin-3" 109 ?C
131 "8859-3")
167 (define-iso-single-byte-charset 'iso-8859-4
'latin-iso8859-4
168 "ISO/IEC 8859/4" "Latin-4" 110 ?D
132 "8859-4")
170 (define-iso-single-byte-charset 'iso-8859-5
'cyrillic-iso8859-5
171 "ISO/IEC 8859/5" "Latin/Cyrillic" 144 ?L
140 "8859-5")
173 (define-iso-single-byte-charset 'iso-8859-6
'arabic-iso8859-6
174 "ISO/IEC 8859/6" "Latin/Arabic" 127 ?G
135 "8859-6")
176 (define-iso-single-byte-charset 'iso-8859-7
'greek-iso8859-7
177 "ISO/IEC 8859/7" "Latin/Greek" 126 ?F
134 "8859-7")
179 (define-iso-single-byte-charset 'iso-8859-8
'hebrew-iso8859-8
180 "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H
136 "8859-8")
182 (define-iso-single-byte-charset 'iso-8859-9
'latin-iso8859-9
183 "ISO/IEC 8859/9" "Latin-5" 148 ?M
141 "8859-9")
185 (define-iso-single-byte-charset 'iso-8859-10
'latin-iso8859-10
186 "ISO/IEC 8859/10" "Latin-6" 157 ?V nil
"8859-10")
188 ;; http://www.nectec.or.th/it-standards/iso8859-11/
189 ;; http://www.cwi.nl/~dik/english/codes/8859.html says this is tis-620
191 (define-iso-single-byte-charset 'iso-8859-11
'thai-iso8859-11
192 "ISO/IEC 8859/11" "Latin/Thai" 166 ?T nil
"8859-11")
194 ;; 8859-12 doesn't (yet?) exist.
196 (define-iso-single-byte-charset 'iso-8859-13
'latin-iso8859-13
197 "ISO/IEC 8859/13" "Latin-7" 179 ?Y nil
"8859-13")
199 (define-iso-single-byte-charset 'iso-8859-14
'latin-iso8859-14
200 "ISO/IEC 8859/14" "Latin-8" 199 ?_
143 "8859-14")
202 (define-iso-single-byte-charset 'iso-8859-15
'latin-iso8859-15
203 "ISO/IEC 8859/15" "Latin-9" 203 ?b
142 "8859-15")
205 (define-iso-single-byte-charset 'iso-8859-16
'latin-iso8859-16
206 "ISO/IEC 8859/16" "Latin-10" 226 ?f nil
"8859-16")
208 ;; No point in keeping it around.
209 (fmakunbound 'define-iso-single-byte-charset
)
211 ;; Can this be shared with 8859-11?
212 ;; N.b. not all of these are defined unicodes.
213 (define-charset 'thai-tis620
215 :short-name
"TIS620.2533"
221 ;; Fixme: doc for this, c.f. above
222 (define-charset 'tis620-2533
224 :short-name
"TIS620.2533"
225 :ascii-compatible-p t
227 :superset
'(ascii eight-bit-control
(thai-tis620 .
128)))
229 (define-charset 'jisx0201
231 :short-name
"JISX0201"
235 (define-charset 'latin-jisx0201
236 "Roman Part of JISX0201.1976"
237 :short-name
"JISX0201 Roman"
238 :long-name
"Japanese Roman (JISX0201.1976)"
242 :subset
'(jisx0201 33 126 0))
244 (define-charset 'katakana-jisx0201
245 "Katakana Part of JISX0201.1976"
246 :short-name
"JISX0201 Katakana"
247 :long-name
"Japanese Katakana (JISX0201.1976)"
251 :subset
'(jisx0201 161 254 -
128))
253 (define-charset 'chinese-gb2312
254 "GB2312 Chinese simplified: ISO-IR-58"
256 :long-name
"GB2312: ISO-IR-58"
259 :code-space
[33 126 33 126]
260 :code-offset
#x110000
263 (define-charset 'chinese-gbk
264 "GBK Chinese simplified."
266 :code-space
[#x40
#xFE
#x81
#xFE
]
267 :code-offset
#x160000
269 (define-charset-alias 'cp936
'chinese-gbk
)
270 (define-charset-alias 'windows-936
'chinese-gbk
)
272 (define-charset 'chinese-cns11643-1
273 "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"
274 :short-name
"CNS11643-1"
275 :long-name
"CNS11643-1 (Chinese traditional): ISO-IR-171"
278 :code-space
[33 126 33 126]
279 :code-offset
#x114000
282 (define-charset 'chinese-cns11643-2
283 "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"
284 :short-name
"CNS11643-2"
285 :long-name
"CNS11643-2 (Chinese traditional): ISO-IR-172"
288 :code-space
[33 126 33 126]
289 :code-offset
#x118000
292 (define-charset 'chinese-cns11643-3
293 "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"
294 :short-name
"CNS11643-3"
295 :long-name
"CNS11643-3 (Chinese traditional): ISO-IR-183"
297 :code-space
[33 126 33 126]
299 :code-offset
#x11C000
302 (define-charset 'chinese-cns11643-4
303 "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"
304 :short-name
"CNS11643-4"
305 :long-name
"CNS11643-4 (Chinese traditional): ISO-IR-184"
308 :code-space
[33 126 33 126]
309 :code-offset
#x120000
312 (define-charset 'chinese-cns11643-5
313 "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"
314 :short-name
"CNS11643-5"
315 :long-name
"CNS11643-5 (Chinese traditional): ISO-IR-185"
318 :code-space
[33 126 33 126]
319 :code-offset
#x124000
322 (define-charset 'chinese-cns11643-6
323 "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"
324 :short-name
"CNS11643-6"
325 :long-name
"CNS11643-6 (Chinese traditional): ISO-IR-186"
328 :code-space
[33 126 33 126]
329 :code-offset
#x128000
332 (define-charset 'chinese-cns11643-7
333 "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"
334 :short-name
"CNS11643-7"
335 :long-name
"CNS11643-7 (Chinese traditional): ISO-IR-187"
338 :code-space
[33 126 33 126]
339 :code-offset
#x12C000
342 (define-charset 'big5
343 "Big5 (Chinese traditional)"
345 :code-space
[#x40
#xFE
#xA1
#xFE
]
346 :code-offset
#x130000
348 ;; Fixme: AKA cp950 according to
349 ;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>. Is
352 (define-charset 'chinese-big5-1
353 "Frequently used part (A141-C67E) of Big5 (Chinese traditional)"
354 :short-name
"Big5 (Level-1)"
355 :long-name
"Big5 (Level-1) A141-C67F"
358 :code-space
[#x21
#x7E
#x21
#x7E
]
359 :code-offset
#x135000
362 (define-charset 'chinese-big5-2
363 "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)"
364 :short-name
"Big5 (Level-2)"
365 :long-name
"Big5 (Level-2) C940-FEFE"
368 :code-space
[#x21
#x7E
#x21
#x7E
]
369 :code-offset
#x137800
372 (define-charset 'japanese-jisx0208
373 "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87"
374 :short-name
"JISX0208"
375 :long-name
"JISX0208.1983/1990 (Japanese): ISO-IR-87"
378 :code-space
[33 126 33 126]
379 :code-offset
#x140000
380 :unify-map
"JISX0208")
382 (define-charset 'japanese-jisx0208-1978
383 "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42"
384 :short-name
"JISX0208.1978"
385 :long-name
"JISX0208.1978 (JISC6226.1978): ISO-IR-42"
388 :code-space
[33 126 33 126]
389 :code-offset
#x144000
390 :unify-map
"JISC6226")
392 (define-charset 'japanese-jisx0212
393 "JISX0212 Japanese supplement: ISO-IR-159"
394 :short-name
"JISX0212"
395 :long-name
"JISX0212 (Japanese): ISO-IR-159"
398 :code-space
[33 126 33 126]
399 :code-offset
#x148000
400 :unify-map
"JISX0212")
402 ;; Note that jisx0213 contains characters not in Unicode (3.2?). It's
403 ;; arguable whether it should have a unify-map.
404 (define-charset 'japanese-jisx0213-1
405 "JISX0213.2000 Plane 1 (Japanese)"
406 :short-name
"JISX0213-1"
409 :unify-map
"JISX2131"
410 :code-space
[33 126 33 126]
411 :code-offset
#x14C000
)
413 (define-charset 'japanese-jisx0213-2
414 "JISX0213.2000 Plane 2 (Japanese)"
415 :short-name
"JISX0213-2"
418 :unify-map
"JISX2132"
419 :code-space
[33 126 33 126]
420 :code-offset
#x150000
)
422 (define-charset 'japanese-jisx0213-a
423 "JISX0213.2004 adds these characters to JISX0213.2000."
424 :short-name
"JISX0213A"
426 :code-space
[33 126 33 126]
430 (define-charset 'japanese-jisx0213.2004-
1
431 "JISX0213.2004 Plane1 (Japanese)"
432 :short-name
"JISX0213.2004-1"
434 :code-space
[33 126 33 126]
436 :superset
'(japanese-jisx0213-a japanese-jisx0213-1
))
438 (define-charset 'katakana-sjis
439 "Katakana part of Shift-JIS"
441 :code-space
[#xA1
#xDF
]
442 :subset
'(jisx0201 #xA1
#xDF
0)
445 (define-charset 'cp932-2-byte
446 "2-byte part of CP932"
449 :code-space
[#x40
#xFC
#x81
#xEF
]
452 (define-charset 'cp932
453 "CP932 (Microsoft shift-jis)"
454 :code-space
[#x00
#xFF
#x00
#xFE
]
456 :superset
'(ascii katakana-sjis cp932-2-byte
))
458 (define-charset 'korean-ksc5601
459 "KSC5601 Korean Hangul and Hanja: ISO-IR-149"
460 :short-name
"KSC5601"
461 :long-name
"KSC5601 (Korean): ISO-IR-149"
464 :code-space
[33 126 33 126]
465 :code-offset
#x279f94
; ... #x27c217
466 :unify-map
"KSC5601")
468 (define-charset 'big5-hkscs
469 "Big5-HKSCS (Chinese traditional, Hong Kong supplement)"
471 :code-space
[#x40
#xFE
#xA1
#xFE
]
472 :code-offset
#x27c218
; ... #x280839
473 :unify-map
"BIG5-HKSCS")
475 ;; Fixme: Korean cp949/UHC
477 (define-charset 'chinese-sisheng
478 "SiSheng characters for PinYin/ZhuYin"
479 :short-name
"SiSheng"
480 :long-name
"SiSheng (PinYin/ZhuYin)"
484 :unify-map
"MULE-sisheng"
485 :code-offset
#x200000
)
487 ;; A subset of the 1989 version of IPA. It consists of the consonant
488 ;; signs used in English, French, German and Italian, and all vowels
489 ;; signs in the table. [says old MULE doc]
491 "IPA (International Phonetic Association)"
495 :unify-map
"MULE-ipa"
497 :code-offset
#x200080
)
499 (define-charset 'viscii
502 :long-name
"VISCII 1.1"
506 (define-charset 'vietnamese-viscii-lower
507 "VISCII1.1 lower-case"
508 :short-name
"VISCII lower"
509 :long-name
"VISCII lower-case"
513 :code-offset
#x200200
514 :unify-map
"MULE-lviscii")
516 (define-charset 'vietnamese-viscii-upper
517 "VISCII1.1 upper-case"
518 :short-name
"VISCII upper"
519 :long-name
"VISCII upper-case"
523 :code-offset
#x200280
524 :unify-map
"MULE-uviscii")
526 (define-charset 'vscii
527 "VSCII1.1 (TCVN-5712 VN1)"
532 (define-charset-alias 'tcvn-5712
'vscii
)
534 ;; Fixme: see note in tcvn.map about combining characters
535 (define-charset 'vscii-2
536 "VSCII-2 (TCVN-5712 VN2)"
540 (define-charset 'koi8-r
543 :ascii-compatible-p t
547 (define-charset-alias 'koi8
'koi8-r
)
549 (define-charset 'alternativnyj
551 :short-name
"alternativnyj"
552 :ascii-compatible-p t
554 :map
"ALTERNATIVNYJ")
556 (define-charset 'cp866
559 :ascii-compatible-p t
562 (define-charset-alias 'ibm866
'cp866
)
564 (define-charset 'koi8-u
567 :ascii-compatible-p t
571 (define-charset 'koi8-t
574 :ascii-compatible-p t
578 (define-charset 'georgian-ps
580 :short-name
"GEORGIAN-PS"
581 :ascii-compatible-p t
585 (define-charset 'georgian-academy
587 :short-name
"GEORGIAN-ACADEMY"
588 :ascii-compatible-p t
592 (define-charset 'windows-1250
593 "WINDOWS-1250 (Central Europe)"
594 :short-name
"WINDOWS-1250"
595 :ascii-compatible-p t
598 (define-charset-alias 'cp1250
'windows-1250
)
600 (define-charset 'windows-1251
601 "WINDOWS-1251 (Cyrillic)"
602 :short-name
"WINDOWS-1251"
603 :ascii-compatible-p t
606 (define-charset-alias 'cp1251
'windows-1251
)
608 (define-charset 'windows-1252
609 "WINDOWS-1252 (Latin I)"
610 :short-name
"WINDOWS-1252"
611 :ascii-compatible-p t
614 (define-charset-alias 'cp1252
'windows-1252
)
616 (define-charset 'windows-1253
617 "WINDOWS-1253 (Greek)"
618 :short-name
"WINDOWS-1253"
619 :ascii-compatible-p t
622 (define-charset-alias 'cp1253
'windows-1253
)
624 (define-charset 'windows-1254
625 "WINDOWS-1254 (Turkish)"
626 :short-name
"WINDOWS-1254"
627 :ascii-compatible-p t
630 (define-charset-alias 'cp1254
'windows-1254
)
632 (define-charset 'windows-1255
633 "WINDOWS-1255 (Hebrew)"
634 :short-name
"WINDOWS-1255"
635 :ascii-compatible-p t
638 (define-charset-alias 'cp1255
'windows-1255
)
640 (define-charset 'windows-1256
641 "WINDOWS-1256 (Arabic)"
642 :short-name
"WINDOWS-1256"
643 :ascii-compatible-p t
646 (define-charset-alias 'cp1256
'windows-1256
)
648 (define-charset 'windows-1257
649 "WINDOWS-1257 (Baltic)"
650 :short-name
"WINDOWS-1257"
651 :ascii-compatible-p t
654 (define-charset-alias 'cp1257
'windows-1257
)
656 (define-charset 'windows-1258
657 "WINDOWS-1258 (Viet Nam)"
658 :short-name
"WINDOWS-1258"
659 :ascii-compatible-p t
662 (define-charset-alias 'cp1258
'windows-1258
)
664 (define-charset 'next
667 :ascii-compatible-p t
671 (define-charset 'cp1125
676 (define-charset-alias 'ruscii
'cp1125
)
677 ;; Original name for cp1125, says Serhii Hlodin <hlodin@lutsk.bank.gov.ua>
678 (define-charset-alias 'cp866u
'cp1125
)
680 ;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html
681 ;; shows this as not ASCII comptaible, with various graphics in
683 (define-charset 'cp437
684 "CP437 (MS-DOS United States, Australia, New Zealand, South Africa)"
687 :ascii-compatible-p t
690 (define-charset 'cp720
694 :ascii-compatible-p t
697 (define-charset 'cp737
701 :ascii-compatible-p t
704 (define-charset 'cp775
708 :ascii-compatible-p t
711 (define-charset 'cp851
715 :ascii-compatible-p t
718 (define-charset 'cp852
719 "CP852 (MS-DOS Latin-2)"
722 :ascii-compatible-p t
725 (define-charset 'cp855
726 "CP855 (IBM Cyrillic)"
729 :ascii-compatible-p t
732 (define-charset 'cp857
733 "CP857 (IBM Turkish)"
736 :ascii-compatible-p t
739 (define-charset 'cp858
740 "CP858 (Multilingual Latin I + Euro)"
743 :ascii-compatible-p t
745 (define-charset-alias 'cp00858
'cp858
) ; IANA has IBM00858/CP00858
747 (define-charset 'cp860
748 "CP860 (MS-DOS Portuguese)"
751 :ascii-compatible-p t
754 (define-charset 'cp861
755 "CP861 (MS-DOS Icelandic)"
758 :ascii-compatible-p t
761 (define-charset 'cp862
765 :ascii-compatible-p t
768 (define-charset 'cp863
769 "CP863 (MS-DOS Canadian French)"
772 :ascii-compatible-p t
775 (define-charset 'cp864
779 :ascii-compatible-p t
782 (define-charset 'cp865
783 "CP865 (MS-DOS Nordic)"
786 :ascii-compatible-p t
789 (define-charset 'cp869
790 "CP869 (IBM Modern Greek)"
793 :ascii-compatible-p t
796 (define-charset 'cp874
800 :ascii-compatible-p t
803 ;; For Arabic, we need three different types of character sets.
804 ;; Digits are of direction left-to-right and of width 1-column.
805 ;; Others are of direction right-to-left and of width 1-column or
807 (define-charset 'arabic-digit
809 :short-name
"Arabic digit"
815 (define-charset 'arabic-1-column
817 :short-name
"Arabic 1-col"
818 :long-name
"Arabic 1-column"
822 :code-offset
#x200100
)
824 (define-charset 'arabic-2-column
826 :short-name
"Arabic 2-col"
827 :long-name
"Arabic 2-column"
831 :code-offset
#x200180
)
834 ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF.
835 ;; Not all of them are defined unicodes.
837 "Lao characters (ISO10646 0E81..0EDF)"
844 (define-charset 'mule-lao
845 "Lao characters (ISO10646 0E81..0EDF)"
848 :superset
'(ascii eight-bit-control
(lao .
128)))
851 ;; Indian scripts. Symbolic charset for data exchange. Glyphs are
852 ;; not assigned. They are automatically converted to each Indian
853 ;; script which IS-13194 supports.
855 (define-charset 'indian-is13194
856 "Generic Indian charset for data exchange with IS 13194"
857 :short-name
"IS 13194"
858 :long-name
"Indian IS 13194"
862 :code-offset
#x180000
)
864 (let ((code-offset #x180100
))
865 (dolist (script '(devanagari sanskrit bengali tamil telugu assamese
866 oriya kannada malayalam gujarati punjabi
))
867 (define-charset (intern (format "%s-cdac" script
))
868 (format "Glyphs of %s script for CDAC font. Subset of `indian-glyph'."
869 (capitalize (symbol-name script
)))
870 :short-name
(format "CDAC %s glyphs" (capitalize (symbol-name script
)))
872 :code-offset code-offset
)
873 (setq code-offset
(+ code-offset
#x100
)))
875 (dolist (script '(devanagari bengali punjabi gujarati
876 oriya tamil telugu kannada malayalam
))
877 (define-charset (intern (format "%s-akruti" script
))
878 (format "Glyphs of %s script for AKRUTI font. Subset of `indian-glyph'."
879 (capitalize (symbol-name script
)))
880 :short-name
(format "AKRUTI %s glyphs" (capitalize (symbol-name script
)))
882 :code-offset code-offset
)
883 (setq code-offset
(+ code-offset
#x100
))))
885 (define-charset 'indian-glyph
886 "Glyphs for Indian characters."
887 :short-name
"Indian glyph"
890 :code-space
[32 127 32 127]
891 :code-offset
#x180100
)
893 ;; Actual Glyph for 1-column width.
894 (define-charset 'indian-1-column
895 "Indian charset for 1-column width glyphs."
896 :short-name
"Indian 1-col"
897 :long-name
"Indian 1 Column"
900 :code-space
[33 126 33 126]
901 :code-offset
#x184000
)
903 ;; Actual Glyph for 2-column width.
904 (define-charset 'indian-2-column
905 "Indian charset for 2-column width glyphs."
906 :short-name
"Indian 2-col"
907 :long-name
"Indian 2 Column"
910 :code-space
[33 126 33 126]
911 :code-offset
#x184000
)
913 (define-charset 'tibetan
916 :short-name
"Tibetan 2-col"
917 :long-name
"Tibetan 2 column"
920 :unify-map
"MULE-tibetan"
921 :code-space
[33 126 33 37]
922 :code-offset
#x190000
)
924 (define-charset 'tibetan-1-column
925 "Tibetan 1 column glyph"
926 :short-name
"Tibetan 1-col"
927 :long-name
"Tibetan 1 column"
930 :code-space
[33 126 33 37]
931 :code-offset
#x190000
)
933 ;; Subsets of Unicode.
934 (define-charset 'mule-unicode-2500-33ff
935 "Unicode characters of the range U+2500..U+33FF."
936 :short-name
"Unicode subset 2"
937 :long-name
"Unicode subset (U+2500..U+33FF)"
940 :code-space
[#x20
#x7f
#x20
#x47
]
943 (define-charset 'mule-unicode-e000-ffff
944 "Unicode characters of the range U+E000..U+FFFF."
945 :short-name
"Unicode subset 3"
946 :long-name
"Unicode subset (U+E000+FFFF)"
949 :code-space
[#x20
#x7F
#x20
#x75
]
951 :max-code
30015) ; U+FFFF
953 (define-charset 'mule-unicode-0100-24ff
954 "Unicode characters of the range U+0100..U+24FF."
955 :short-name
"Unicode subset"
956 :long-name
"Unicode subset (U+0100..U+24FF)"
959 :code-space
[#x20
#x7F
#x20
#x7F
]
962 (define-charset 'unicode-bmp
963 "Unicode Basic Multilingual Plane (U+0000..U+FFFF)"
964 :short-name
"Unicode BMP"
965 :code-space
[0 255 0 255]
968 (define-charset 'unicode-smp
969 "Unicode Supplementary Multilingual Plane (U+10000..U+1FFFF)"
970 :short-name
"Unicode SMP "
971 :code-space
[0 255 0 255]
972 :code-offset
#x10000
)
974 (define-charset 'unicode-sip
975 "Unicode Supplementary Ideographic Plane (U+20000..U+2FFFF)"
976 :short-name
"Unicode SIP"
977 :code-space
[0 255 0 255]
978 :code-offset
#x20000
)
980 (define-charset 'unicode-ssp
981 "Unicode Supplementary Special-purpose Plane (U+E0000..U+EFFFF)"
982 :short-name
"Unicode SSP"
983 :code-space
[0 255 0 255]
984 :code-offset
#xE0000
)
986 (define-charset 'ethiopic
987 "Ethiopic characters for Amharic and Tigrigna."
988 :short-name
"Ethiopic"
989 :long-name
"Ethiopic characters"
992 :unify-map
"MULE-ethiopic"
993 :code-space
[33 126 33 126]
994 :code-offset
#x1A0000
)
996 (define-charset 'mac-roman
998 :short-name
"Mac Roman"
999 :ascii-compatible-p t
1003 ;; Fixme: modern EBCDIC variants, e.g. IBM00924?
1004 (define-charset 'ebcdic-us
1005 "US version of EBCDIC"
1006 :short-name
"EBCDIC-US"
1008 :mime-charset
'ebcdic-us
1011 (define-charset 'ebcdic-uk
1012 "UK version of EBCDIC"
1013 :short-name
"EBCDIC-UK"
1015 :mime-charset
'ebcdic-uk
1018 (define-charset 'ibm1047
1020 "IBM1047, `EBCDIC Latin 1/Open Systems' used by OS/390 Unix."
1021 :short-name
"IBM1047"
1023 :mime-charset
'ibm1047
1025 (define-charset-alias 'cp1047
'ibm1047
)
1027 (define-charset 'hp-roman8
1028 "Encoding used by Hewlet-Packard printer software"
1029 :short-name
"HP-ROMAN8"
1030 :ascii-compatible-p t
1034 ;; To make a coding system with this, a pre-write-conversion should
1035 ;; account for the commented-out multi-valued code points in
1037 (define-charset 'adobe-standard-encoding
1038 "Adobe `standard encoding' used in PostScript"
1039 :short-name
"ADOBE-STANDARD-ENCODING"
1040 :code-space
[#x20
255]
1043 (define-charset 'symbol
1044 "Adobe symbol encoding used in PostScript"
1045 :short-name
"ADOBE-SYMBOL"
1046 :code-space
[#x20
255]
1049 (define-charset 'ibm850
1050 "DOS codepage 850 (Latin-1)"
1051 :short-name
"IBM850"
1052 :ascii-compatible-p t
1055 (define-charset-alias 'cp850
'ibm850
)
1057 (define-charset 'mik
1058 "Bulgarian DOS codepage"
1060 :ascii-compatible-p t
1064 (define-charset 'ptcp154
1065 "`Paratype' codepage (Asian Cyrillic)"
1067 :ascii-compatible-p t
1069 :mime-charset
'pt154
1071 (define-charset-alias 'pt154
'ptcp154
)
1072 (define-charset-alias 'cp154
'ptcp154
)
1074 (define-charset 'gb18030-2-byte
1075 "GB18030 2-byte (0x814E..0xFEFE)"
1076 :code-space
[#x40
#xFE
#x81
#xFE
]
1080 (define-charset 'gb18030-4-byte-bmp
1081 "GB18030 4-byte for BMP (0x81308130-0x8431A439)"
1082 :code-space
[#x30
#x39
#x81
#xFE
#x30
#x39
#x81
#x84
]
1086 (define-charset 'gb18030-4-byte-smp
1087 "GB18030 4-byte for SMP (0x90308130-0xE3329A35)"
1088 :code-space
[#x30
#x39
#x81
#xFE
#x30
#x39
#x90
#xE3
]
1089 :min-code
'(#x9030 .
#x8130
)
1090 :max-code
'(#xE332 .
#x9A35
)
1092 :code-offset
#x10000
)
1094 (define-charset 'gb18030-4-byte-ext-1
1095 "GB18030 4-byte (0x8431A530-0x8F39FE39)"
1096 :code-space
[#x30
#x39
#x81
#xFE
#x30
#x39
#x84
#x8F
]
1097 :min-code
'(#x8431 .
#xA530
)
1098 :max-code
'(#x8F39 .
#xFE39
)
1100 :code-offset
#x200000
; ... #x22484B
1103 (define-charset 'gb18030-4-byte-ext-2
1104 "GB18030 4-byte (0xE3329A36-0xFE39FE39)"
1105 :code-space
[#x30
#x39
#x81
#xFE
#x30
#x39
#xE3
#xFE
]
1106 :min-code
'(#xE332 .
#x9A36
)
1107 :max-code
'(#xFE39 .
#xFE39
)
1109 :code-offset
#x22484C
; ... #x279f93
1112 (define-charset 'gb18030
1114 :code-space
[#x00
#xFF
#x00
#xFE
#x00
#xFE
#x00
#xFE
]
1116 :max-code
'(#xFE39 .
#xFE39
)
1117 :superset
'(ascii gb18030-2-byte
1118 gb18030-4-byte-bmp gb18030-4-byte-smp
1119 gb18030-4-byte-ext-1 gb18030-4-byte-ext-2
))
1121 (define-charset 'chinese-cns11643-15
1122 "CNS11643 Plane 15 Chinese Traditional"
1123 :short-name
"CNS11643-15"
1124 :long-name
"CNS11643-15 (Chinese traditional)"
1125 :code-space
[33 126 33 126]
1126 :code-offset
#x27A000
)
1128 (unify-charset 'chinese-gb2312
)
1129 (unify-charset 'chinese-gbk
)
1130 (unify-charset 'chinese-cns11643-1
)
1131 (unify-charset 'chinese-cns11643-2
)
1132 (unify-charset 'chinese-cns11643-3
)
1133 (unify-charset 'chinese-cns11643-4
)
1134 (unify-charset 'chinese-cns11643-5
)
1135 (unify-charset 'chinese-cns11643-6
)
1136 (unify-charset 'chinese-cns11643-7
)
1137 (unify-charset 'big5
)
1138 (unify-charset 'chinese-big5-1
)
1139 (unify-charset 'chinese-big5-2
)
1140 (unify-charset 'big5-hkscs
)
1141 (unify-charset 'korean-ksc5601
)
1142 (unify-charset 'vietnamese-viscii-lower
)
1143 (unify-charset 'vietnamese-viscii-upper
)
1144 (unify-charset 'chinese-sisheng
)
1145 (unify-charset 'ipa
)
1146 (unify-charset 'tibetan
)
1147 (unify-charset 'ethiopic
)
1148 (unify-charset 'japanese-jisx0208-1978
)
1149 (unify-charset 'japanese-jisx0208
)
1150 (unify-charset 'japanese-jisx0212
)
1151 (unify-charset 'japanese-jisx0213-1
)
1152 (unify-charset 'japanese-jisx0213-2
)
1155 ;; These are tables for translating characters on decoding and
1157 ;; Fixme: these aren't used now -- should they be?
1158 (setq standard-translation-table-for-decode nil
)
1160 (setq standard-translation-table-for-encode nil
)
1162 ;; Fixme: should this be retained? I guess it could be useful for
1163 ;; non-unified charsets.
1164 (defvar translation-table-for-input nil
1165 "If non-nil, a char table used to translate characters from input methods.
1166 \(Currently only used by Quail.)")
1168 ;;; Make fundamental coding systems.
1170 ;; The coding system `no-conversion' is already defined in coding.c as
1173 ;; (define-coding-system 'no-conversion
1174 ;; "Do no conversion."
1175 ;; :coding-type 'raw-text
1178 (define-coding-system-alias 'binary
'no-conversion
)
1180 (define-coding-system 'raw-text
1181 "Raw text, which means text contains random 8-bit codes.
1182 Encoding text with this coding system produces the actual byte
1183 sequence of the text in buffers and strings. An exception is made for
1184 eight-bit-control characters. Each of them is encoded into a single
1187 When you visit a file with this coding, the file is read into a
1188 unibyte buffer as is (except for EOL format), thus each byte of a file
1189 is treated as a character."
1190 :coding-type
'raw-text
1194 (define-coding-system 'no-conversion-multibyte
1195 "Like `no-conversion' but don't read a file into a unibyte buffer."
1196 :coding-type
'raw-text
1200 (define-coding-system 'undecided
1201 "No conversion on encoding, automatic conversion on decoding."
1202 :coding-type
'undecided
1204 :charset-list
'(ascii))
1206 (define-coding-system-alias 'unix
'undecided-unix
)
1207 (define-coding-system-alias 'dos
'undecided-dos
)
1208 (define-coding-system-alias 'mac
'undecided-mac
)
1210 (define-coding-system 'iso-latin-1
1211 "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)."
1212 :coding-type
'charset
1214 :charset-list
'(iso-8859-1)
1215 :mime-charset
'iso-8859-1
)
1217 (define-coding-system-alias 'iso-8859-1
'iso-latin-1
)
1218 (define-coding-system-alias 'latin-1
'iso-latin-1
)
1220 ;; Coding systems not specific to each language environment.
1222 (define-coding-system 'emacs-mule
1223 "Emacs 21 internal format used in buffer and string."
1224 :coding-type
'emacs-mule
1225 :charset-list
'emacs-mule
1228 (define-coding-system 'utf-8
1232 :charset-list
'(unicode)
1233 :mime-charset
'utf-8
)
1235 (define-coding-system-alias 'mule-utf-8
'utf-8
)
1237 (define-coding-system 'utf-8-emacs
1238 "Support for all Emacs characters (including non-Unicode characters)."
1241 :charset-list
'(emacs))
1243 (define-coding-system 'utf-16le
1244 "UTF-16LE (little endian, no signature (BOM))."
1245 :coding-type
'utf-16
1247 :charset-list
'(unicode)
1249 :mime-text-unsuitable t
1250 :mime-charset
'utf-16le
)
1252 (define-coding-system 'utf-16be
1253 "UTF-16BE (big endian, no signature (BOM))."
1254 :coding-type
'utf-16
1256 :charset-list
'(unicode)
1258 :mime-text-unsuitable t
1259 :mime-charset
'utf-16be
)
1261 (define-coding-system 'utf-16le-with-signature
1262 "UTF-16 (little endian, with signature (BOM))."
1263 :coding-type
'utf-16
1265 :charset-list
'(unicode)
1268 :mime-text-unsuitable t
1269 :mime-charset
'utf-16
)
1271 (define-coding-system 'utf-16be-with-signature
1272 "UTF-16 (big endian, with signature)."
1273 :coding-type
'utf-16
1275 :charset-list
'(unicode)
1278 :mime-text-unsuitable t
1279 :mime-charset
'utf-16
)
1281 (define-coding-system 'utf-16
1282 "UTF-16 (detect endian on decoding, use big endian on encoding with BOM)."
1283 :coding-type
'utf-16
1285 :charset-list
'(unicode)
1286 :bom
'(utf-16le-with-signature . utf-16be-with-signature
)
1288 :mime-text-unsuitable t
1289 :mime-charset
'utf-16
)
1291 ;; Backwards compatibility (old names, also used by Mule-UCS). We
1292 ;; prefer the MIME names.
1293 (define-coding-system-alias 'utf-16-le
'utf-16le-with-signature
)
1294 (define-coding-system-alias 'utf-16-be
'utf-16be-with-signature
)
1297 (define-coding-system 'iso-2022-7bit
1298 "ISO 2022 based 7-bit encoding using only G0."
1299 :coding-type
'iso-2022
1301 :charset-list
'iso-2022
1302 :designation
[(ascii t
) nil nil nil
]
1303 :flags
'(short ascii-at-eol ascii-at-cntl
7-bit designation composition
))
1305 (define-coding-system 'iso-2022-7bit-ss2
1306 "ISO 2022 based 7-bit encoding using SS2 for 96-charset."
1307 :coding-type
'iso-2022
1309 :charset-list
'iso-2022
1310 :designation
[(ascii 94) nil
(nil 96) nil
]
1311 :flags
'(short ascii-at-eol ascii-at-cntl
7-bit
1312 designation single-shift composition
))
1314 (define-coding-system 'iso-2022-7bit-lock
1315 "ISO-2022 coding system using Locking-Shift for 96-charset."
1316 :coding-type
'iso-2022
1318 :charset-list
'iso-2022
1319 :designation
[(ascii 94) (nil 96) nil nil
]
1320 :flags
'(ascii-at-eol ascii-at-cntl
7-bit
1321 designation locking-shift composition
))
1323 (define-coding-system-alias 'iso-2022-int-1
'iso-2022-7bit-lock
)
1325 (define-coding-system 'iso-2022-7bit-lock-ss2
1326 "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN."
1327 :coding-type
'iso-2022
1329 :charset-list
'(ascii
1330 japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
1333 chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
1334 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
1336 :designation
[(ascii 94)
1337 (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1
96)
1338 (nil chinese-cns11643-2
)
1339 (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
1340 chinese-cns11643-6 chinese-cns11643-7
)]
1341 :flags
'(short ascii-at-eol ascii-at-cntl
7-bit locking-shift
1342 single-shift init-bol
))
1344 (define-coding-system-alias 'iso-2022-cjk
'iso-2022-7bit-lock-ss2
)
1346 (define-coding-system 'iso-2022-8bit-ss2
1347 "ISO 2022 based 8-bit encoding using SS2 for 96-charset."
1348 :coding-type
'iso-2022
1350 :charset-list
'iso-2022
1351 :designation
[(ascii 94) nil
(nil 96) nil
]
1352 :flags
'(ascii-at-eol ascii-at-cntl designation single-shift composition
))
1354 (define-coding-system 'compound-text
1355 "Compound text based generic encoding for decoding unknown messages.
1357 This coding system does not support extended segments of CTEXT."
1358 :coding-type
'iso-2022
1360 :charset-list
'iso-2022
1361 :designation
[(ascii 94) (latin-iso8859-1 katakana-jisx0201
96) nil nil
]
1362 :flags
'(ascii-at-eol ascii-at-cntl
1363 designation locking-shift single-shift composition
)
1364 ;; Fixme: this isn't a valid MIME charset and has to be
1365 ;; special-cased elsewhere -- fx
1366 :mime-charset
'x-ctext
)
1368 (define-coding-system-alias 'x-ctext
'compound-text
)
1369 (define-coding-system-alias 'ctext
'compound-text
)
1371 ;; Same as compound-text, but doesn't produce composition escape
1372 ;; sequences. Used in post-read and pre-write conversions of
1373 ;; compound-text-with-extensions, see mule.el. Note that this should
1374 ;; not have a mime-charset property, to prevent it from showing up
1375 ;; close to the beginning of coding systems ordered by priority.
1376 (define-coding-system 'ctext-no-compositions
1377 "Compound text based generic encoding for decoding unknown messages.
1379 Like `compound-text', but does not produce escape sequences for compositions."
1380 :coding-type
'iso-2022
1382 :charset-list
'iso-2022
1383 :designation
[(ascii 94) (latin-iso8859-1 katakana-jisx0201
96) nil nil
]
1384 :flags
'(ascii-at-eol ascii-at-cntl
1385 designation locking-shift single-shift
))
1387 (define-coding-system 'compound-text-with-extensions
1388 "Compound text encoding with ICCCM Extended Segment extensions.
1390 See the variable `ctext-non-standard-encodings-alist' for the
1391 detail about how extended segments are handled.
1393 This coding system should be used only for X selections. It is inappropriate
1394 for decoding and encoding files, process I/O, etc."
1395 :coding-type
'iso-2022
1397 :charset-list
'iso-2022
1398 :designation
[(ascii 94) (latin-iso8859-1 katakana-jisx0201
96) nil nil
]
1399 :flags
'(ascii-at-eol ascii-at-cntl
1400 designation locking-shift single-shift
)
1401 :post-read-conversion
'ctext-post-read-conversion
1402 :pre-write-conversion
'ctext-pre-write-conversion
)
1404 (define-coding-system-alias
1405 'x-ctext-with-extensions
'compound-text-with-extensions
)
1406 (define-coding-system-alias
1407 'ctext-with-extensions
'compound-text-with-extensions
)
1409 (define-coding-system 'us-ascii
1410 "Encode ASCII as-is and encode non-ASCII characters to `?'."
1411 :coding-type
'charset
1413 :charset-list
'(ascii)
1415 :mime-charset
'us-ascii
)
1417 (define-coding-system-alias 'iso-safe
'us-ascii
)
1419 (define-coding-system 'utf-7
1420 "UTF-7 encoding of Unicode (RFC 2152)."
1423 :mime-charset
'utf-7
1424 :charset-list
'(unicode)
1425 :pre-write-conversion
'utf-7-pre-write-conversion
1426 :post-read-conversion
'utf-7-post-read-conversion
)
1428 ;; Use us-ascii for terminal output if some other coding system is not
1429 ;; specified explicitly.
1430 (set-safe-terminal-coding-system-internal 'us-ascii
)
1432 ;; The other coding-systems are defined in each language specific
1433 ;; files under lisp/language.
1435 ;; Normally, set coding system to `undecided' before reading a file.
1436 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
1437 ;; but we regard them as containing multibyte characters.
1438 ;; Tar files are not decoded at all, but we treat them as raw bytes.
1440 (setq file-coding-system-alist
1441 '(("\\.elc\\'" . utf-8-emacs
)
1442 ("\\.utf\\(-8\\)?\\'" . utf-8
)
1443 ;; This is the defined default for XML documents. It may be
1444 ;; overridden by a charset specification in the header. That
1445 ;; should be grokked by the auto-coding mechanism, but rms
1446 ;; vetoed that. -- fx
1447 ("\\.xml\\'" . utf-8
)
1448 ;; We use raw-text for reading loaddefs.el so that if it
1449 ;; happens to have DOS or Mac EOLs, they are converted to
1450 ;; newlines. This is required to make the special treatment
1451 ;; of the "\ newline" combination in loaddefs.el, which marks
1452 ;; the beginning of a doc string, work.
1453 ("\\(\\`\\|/\\)loaddefs.el\\'" .
(raw-text . raw-text-unix
))
1454 ("\\.tar\\'" .
(no-conversion . no-conversion
))
1455 ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system
)
1456 ("" .
(undecided . nil
))))
1459 ;;; Setting coding categories and their priorities.
1461 ;; This setting is just to read an Emacs Lisp source files which
1462 ;; contain multilingual text while dumping Emacs. More appropriate
1463 ;; values are set by the command `set-language-environment' for each
1464 ;; language environment.
1466 (set-coding-system-priority
1473 ;;; Miscellaneous settings.
1475 ;; Make all multibyte characters self-insert.
1476 (set-char-table-range (nth 1 global-map
)
1477 (cons 128 (max-char))
1478 'self-insert-command
)
1480 (aset latin-extra-code-table ?
\221 t
)
1481 (aset latin-extra-code-table ?
\222 t
)
1482 (aset latin-extra-code-table ?
\223 t
)
1483 (aset latin-extra-code-table ?
\224 t
)
1484 (aset latin-extra-code-table ?
\225 t
)
1485 (aset latin-extra-code-table ?
\226 t
)
1487 ;; Move least specific charsets to end of priority list
1489 (apply #'set-charset-priority
1490 (delq 'unicode
(delq 'emacs
(charset-priority-list))))
1492 ;; The old code-pages library is obsoleted by coding systems based on
1493 ;; the charsets defined in this file but might be required by user
1495 (provide 'code-pages
)
1498 ;; no-byte-compile: t
1501 ;;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5
1502 ;;; mule-conf.el ends here