Mercurial > emacs
annotate lisp/international/mule-conf.el @ 95212:a6a4ada91449
* dispextern.h, xfaces.c (xstrcasecmp): Renamed from xstricmp.
* dosfns.c, fileio.c, font.c, fontset.c, image.c, macfns.c:
* macterm.c, process.c, w32.c, w32fns.c, w32proc.c, xfaces.c:
* xfns.c, xfont.c: Callers changed.
author | Jason Rumney <jasonr@gnu.org> |
---|---|
date | Thu, 22 May 2008 14:52:37 +0000 |
parents | 889bc336b89b |
children | 1e646032185f |
rev | line source |
---|---|
17070 | 1 ;;; mule-conf.el --- configure multilingual environment |
2 | |
74544 | 3 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, |
79709 | 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 | |
62274 | 6 ;; National Institute of Advanced Industrial Science and Technology (AIST) |
7 ;; Registration Number H14PRO021 | |
89483 | 8 ;; Copyright (C) 2003 |
88411 | 9 ;; National Institute of Advanced Industrial Science and Technology (AIST) |
10 ;; Registration Number H13PRO009 | |
17070 | 11 |
88486 | 12 ;; Keywords: i18n, mule, multilingual, character set, coding system |
17070 | 13 |
14 ;; This file is part of GNU Emacs. | |
15 | |
94664
889bc336b89b
Switch to recommended form of GPLv3 permissions notice.
Glenn Morris <rgm@gnu.org>
parents:
93286
diff
changeset
|
16 ;; GNU Emacs is free software: you can redistribute it and/or modify |
17070 | 17 ;; it under the terms of the GNU General Public License as published by |
94664
889bc336b89b
Switch to recommended form of GPLv3 permissions notice.
Glenn Morris <rgm@gnu.org>
parents:
93286
diff
changeset
|
18 ;; the Free Software Foundation, either version 3 of the License, or |
889bc336b89b
Switch to recommended form of GPLv3 permissions notice.
Glenn Morris <rgm@gnu.org>
parents:
93286
diff
changeset
|
19 ;; (at your option) any later version. |
17070 | 20 |
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. | |
25 | |
26 ;; You should have received a copy of the GNU General Public License | |
94664
889bc336b89b
Switch to recommended form of GPLv3 permissions notice.
Glenn Morris <rgm@gnu.org>
parents:
93286
diff
changeset
|
27 ;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. |
17070 | 28 |
29 ;;; Commentary: | |
30 | |
88575 | 31 ;; This file defines the Emacs charsets and some basic coding systems. |
32 ;; Other coding systems are defined in the files in directory | |
33 ;; lisp/language. | |
17070 | 34 |
35 ;;; Code: | |
36 | |
88666 | 37 ;;; Remarks |
38 | |
88575 | 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/. | |
42 | |
88717 | 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: | |
88666 | 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 | |
49 | |
17070 | 50 ;;; Definitions of character sets. |
51 | |
89089 | 52 ;; The charsets `ascii', `unicode' and `eight-bit' are already defined |
53 ;; in charset.c as below: | |
88411 | 54 ;; |
55 ;; (define-charset 'ascii | |
56 ;; "" | |
57 ;; :dimension 1 | |
58 ;; :code-space [0 127] | |
89089 | 59 ;; :iso-final-char ?B |
88411 | 60 ;; :ascii-compatible-p t |
61 ;; :emacs-mule-id 0 | |
62 ;; :code-offset 0) | |
63 ;; | |
64 ;; (define-charset 'unicode | |
65 ;; "" | |
66 ;; :dimension 3 | |
67 ;; :code-space [0 255 0 255 0 16] | |
68 ;; :ascii-compatible-p t | |
69 ;; :code-offset 0) | |
70 ;; | |
89089 | 71 ;; (define-charset 'eight-bit |
72 ;; "" | |
73 ;; :dimension 1 | |
74 ;; :code-space [128 255] | |
75 ;; :code-offset #x3FFF80) | |
76 ;; | |
88411 | 77 ;; We now set :docstring, :short-name, and :long-name properties. |
78 | |
79 (put-charset-property | |
80 'ascii :docstring "ASCII (ISO646 IRV)") | |
81 (put-charset-property | |
82 'ascii :short-name "ASCII") | |
83 (put-charset-property | |
84 'ascii :long-name "ASCII (ISO646 IRV)") | |
85 (put-charset-property | |
89050
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
86 'iso-8859-1 :docstring "Latin-1 (ISO/IEC 8859-1)") |
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
87 (put-charset-property |
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
88 'iso-8859-1 :short-name "Latin-1") |
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
89 (put-charset-property |
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
90 'iso-8859-1 :long-name "Latin-1") |
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
91 (put-charset-property |
88411 | 92 'unicode :docstring "Unicode (ISO10646)") |
93 (put-charset-property | |
94 'unicode :short-name "Unicode") | |
95 (put-charset-property | |
96 'unicode :long-name "Unicode (ISO10646)") | |
89089 | 97 (put-charset-property 'eight-bit :docstring "Raw bytes 0-255") |
98 (put-charset-property 'eight-bit :short-name "Raw bytes") | |
17070 | 99 |
88411 | 100 (define-charset-alias 'ucs 'unicode) |
101 | |
102 (define-charset 'emacs | |
88647 | 103 "Full Emacs characters" |
88411 | 104 :ascii-compatible-p t |
105 :code-space [ 0 255 0 255 0 63 ] | |
106 :code-offset 0 | |
107 :supplementary-p t) | |
108 | |
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" | |
113 :iso-final-char ?A | |
114 :emacs-mule-id 129 | |
115 :code-space [32 127] | |
116 :code-offset 160) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
117 |
88735 | 118 ;; Name perhaps not ideal, but is XEmacs-compatible. |
119 (define-charset 'control-1 | |
88411 | 120 "8-bit control code (0x80..0x9F)" |
121 :short-name "8-bit control code" | |
122 :code-space [128 159] | |
123 :code-offset 128) | |
124 | |
88735 | 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" | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
128 :supplementary-p t |
88735 | 129 :code-space [128 159] |
130 :code-offset #x3FFF80) ; see character.h | |
131 | |
88411 | 132 (define-charset 'eight-bit-graphic |
88735 | 133 "Raw bytes in the range 0xA0..0xFF (usually produced from invalid encodings)" |
134 :short-name "Raw bytes 0xA0..0xFF" | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
135 :supplementary-p t |
88411 | 136 :code-space [160 255] |
88735 | 137 :code-offset #x3FFFA0) ; see character.h |
17070 | 138 |
88411 | 139 (defmacro define-iso-single-byte-charset (symbol iso-symbol name nickname |
140 iso-ir iso-final | |
141 emacs-mule-id map) | |
142 `(progn | |
143 (define-charset ,symbol | |
144 ,name | |
145 :short-name ,nickname | |
146 :long-name ,name | |
147 :ascii-compatible-p t | |
148 :code-space [0 255] | |
149 :map ,map) | |
150 (if ,iso-symbol | |
151 (define-charset ,iso-symbol | |
152 (if ,iso-ir | |
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 | |
88486 | 159 :emacs-mule-id ,emacs-mule-id |
88411 | 160 :code-space [32 127] |
88751
809b6bfe4dfa
Adjusted for the change of define-charset (:parent -> :subset or
Kenichi Handa <handa@m17n.org>
parents:
88735
diff
changeset
|
161 :subset (list ,symbol 160 255 -128))))) |
88411 | 162 |
163 (define-iso-single-byte-charset 'iso-8859-2 'latin-iso8859-2 | |
164 "ISO/IEC 8859/2" "Latin-2" 101 ?B 130 "8859-2") | |
165 | |
166 (define-iso-single-byte-charset 'iso-8859-3 'latin-iso8859-3 | |
167 "ISO/IEC 8859/3" "Latin-3" 109 ?C 131 "8859-3") | |
168 | |
169 (define-iso-single-byte-charset 'iso-8859-4 'latin-iso8859-4 | |
170 "ISO/IEC 8859/4" "Latin-4" 110 ?D 132 "8859-4") | |
171 | |
172 (define-iso-single-byte-charset 'iso-8859-5 'cyrillic-iso8859-5 | |
173 "ISO/IEC 8859/5" "Latin/Cyrillic" 144 ?L 140 "8859-5") | |
174 | |
175 (define-iso-single-byte-charset 'iso-8859-6 'arabic-iso8859-6 | |
176 "ISO/IEC 8859/6" "Latin/Arabic" 127 ?G 135 "8859-6") | |
177 | |
178 (define-iso-single-byte-charset 'iso-8859-7 'greek-iso8859-7 | |
179 "ISO/IEC 8859/7" "Latin/Greek" 126 ?F 134 "8859-7") | |
180 | |
181 (define-iso-single-byte-charset 'iso-8859-8 'hebrew-iso8859-8 | |
182 "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H 136 "8859-8") | |
183 | |
184 (define-iso-single-byte-charset 'iso-8859-9 'latin-iso8859-9 | |
185 "ISO/IEC 8859/9" "Latin-5" 148 ?M 141 "8859-9") | |
17070 | 186 |
88575 | 187 (define-iso-single-byte-charset 'iso-8859-10 'latin-iso8859-10 |
88671 | 188 "ISO/IEC 8859/10" "Latin-6" 157 ?V nil "8859-10") |
88575 | 189 |
88671 | 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 | |
192 ;; plus nbsp | |
193 (define-iso-single-byte-charset 'iso-8859-11 'thai-iso8859-11 | |
194 "ISO/IEC 8859/11" "Latin/Thai" 166 ?T nil "8859-11") | |
195 | |
196 ;; 8859-12 doesn't (yet?) exist. | |
88575 | 197 |
88411 | 198 (define-iso-single-byte-charset 'iso-8859-13 'latin-iso8859-13 |
88575 | 199 "ISO/IEC 8859/13" "Latin-7" 179 ?Y nil "8859-13") |
88411 | 200 |
201 (define-iso-single-byte-charset 'iso-8859-14 'latin-iso8859-14 | |
202 "ISO/IEC 8859/14" "Latin-8" 199 ?_ 143 "8859-14") | |
203 | |
204 (define-iso-single-byte-charset 'iso-8859-15 'latin-iso8859-15 | |
205 "ISO/IEC 8859/15" "Latin-9" 203 ?b 142 "8859-15") | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
206 |
88565 | 207 (define-iso-single-byte-charset 'iso-8859-16 'latin-iso8859-16 |
88638 | 208 "ISO/IEC 8859/16" "Latin-10" 226 ?f nil "8859-16") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
209 |
88647 | 210 ;; No point in keeping it around. |
211 (fmakunbound 'define-iso-single-byte-charset) | |
212 | |
88671 | 213 ;; Can this be shared with 8859-11? |
89089 | 214 ;; N.b. not all of these are defined unicodes. |
88411 | 215 (define-charset 'thai-tis620 |
216 "TIS620.2533" | |
217 :short-name "TIS620.2533" | |
218 :iso-final-char ?T | |
219 :emacs-mule-id 133 | |
220 :code-space [32 127] | |
221 :code-offset #x0E00) | |
222 | |
88671 | 223 ;; Fixme: doc for this, c.f. above |
88411 | 224 (define-charset 'tis620-2533 |
225 "TIS620.2533" | |
226 :short-name "TIS620.2533" | |
227 :ascii-compatible-p t | |
228 :code-space [0 255] | |
88751
809b6bfe4dfa
Adjusted for the change of define-charset (:parent -> :subset or
Kenichi Handa <handa@m17n.org>
parents:
88735
diff
changeset
|
229 :superset '(ascii eight-bit-control (thai-tis620 . 128))) |
88411 | 230 |
231 (define-charset 'jisx0201 | |
232 "JISX0201" | |
233 :short-name "JISX0201" | |
89483 | 234 :code-space [0 #xDF] |
235 :map "JISX0201") | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
236 |
88411 | 237 (define-charset 'latin-jisx0201 |
238 "Roman Part of JISX0201.1976" | |
239 :short-name "JISX0201 Roman" | |
240 :long-name "Japanese Roman (JISX0201.1976)" | |
241 :iso-final-char ?J | |
242 :emacs-mule-id 138 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
243 :supplementary-p t |
88411 | 244 :code-space [33 126] |
88751
809b6bfe4dfa
Adjusted for the change of define-charset (:parent -> :subset or
Kenichi Handa <handa@m17n.org>
parents:
88735
diff
changeset
|
245 :subset '(jisx0201 33 126 0)) |
88411 | 246 |
247 (define-charset 'katakana-jisx0201 | |
248 "Katakana Part of JISX0201.1976" | |
249 :short-name "JISX0201 Katakana" | |
250 :long-name "Japanese Katakana (JISX0201.1976)" | |
251 :iso-final-char ?I | |
252 :emacs-mule-id 137 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
253 :supplementary-p t |
88411 | 254 :code-space [33 126] |
88751
809b6bfe4dfa
Adjusted for the change of define-charset (:parent -> :subset or
Kenichi Handa <handa@m17n.org>
parents:
88735
diff
changeset
|
255 :subset '(jisx0201 161 254 -128)) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
256 |
88411 | 257 (define-charset 'chinese-gb2312 |
258 "GB2312 Chinese simplified: ISO-IR-58" | |
259 :short-name "GB2312" | |
260 :long-name "GB2312: ISO-IR-58" | |
261 :iso-final-char ?A | |
262 :emacs-mule-id 145 | |
263 :code-space [33 126 33 126] | |
264 :code-offset #x110000 | |
89483 | 265 :unify-map "GB2312") |
88411 | 266 |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
267 (define-charset 'chinese-gbk |
88486 | 268 "GBK Chinese simplified." |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
269 :short-name "GBK" |
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
270 :code-space [#x40 #xFE #x81 #xFE] |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
271 :code-offset #x160000 |
89483 | 272 :unify-map "GBK") |
88666 | 273 (define-charset-alias 'cp936 'chinese-gbk) |
88717 | 274 (define-charset-alias 'windows-936 'chinese-gbk) |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
275 |
88411 | 276 (define-charset 'chinese-cns11643-1 |
277 "CNS11643 Plane 1 Chinese traditional: ISO-IR-171" | |
278 :short-name "CNS11643-1" | |
279 :long-name "CNS11643-1 (Chinese traditional): ISO-IR-171" | |
280 :iso-final-char ?G | |
281 :emacs-mule-id 149 | |
282 :code-space [33 126 33 126] | |
283 :code-offset #x114000 | |
89483 | 284 :unify-map "CNS-1") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
285 |
88411 | 286 (define-charset 'chinese-cns11643-2 |
287 "CNS11643 Plane 2 Chinese traditional: ISO-IR-172" | |
288 :short-name "CNS11643-2" | |
289 :long-name "CNS11643-2 (Chinese traditional): ISO-IR-172" | |
290 :iso-final-char ?H | |
291 :emacs-mule-id 150 | |
292 :code-space [33 126 33 126] | |
293 :code-offset #x118000 | |
89483 | 294 :unify-map "CNS-2") |
88411 | 295 |
296 (define-charset 'chinese-cns11643-3 | |
297 "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183" | |
298 :short-name "CNS11643-3" | |
299 :long-name "CNS11643-3 (Chinese traditional): ISO-IR-183" | |
300 :iso-final-char ?I | |
301 :code-space [33 126 33 126] | |
302 :emacs-mule-id 246 | |
89483 | 303 :code-offset #x11C000 |
304 :unify-map "CNS-3") | |
88411 | 305 |
306 (define-charset 'chinese-cns11643-4 | |
307 "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184" | |
308 :short-name "CNS11643-4" | |
309 :long-name "CNS11643-4 (Chinese traditional): ISO-IR-184" | |
310 :iso-final-char ?J | |
311 :emacs-mule-id 247 | |
312 :code-space [33 126 33 126] | |
89483 | 313 :code-offset #x120000 |
314 :unify-map "CNS-4") | |
88411 | 315 |
316 (define-charset 'chinese-cns11643-5 | |
317 "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185" | |
318 :short-name "CNS11643-5" | |
319 :long-name "CNS11643-5 (Chinese traditional): ISO-IR-185" | |
320 :iso-final-char ?K | |
321 :emacs-mule-id 248 | |
322 :code-space [33 126 33 126] | |
89483 | 323 :code-offset #x124000 |
324 :unify-map "CNS-5") | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
325 |
88411 | 326 (define-charset 'chinese-cns11643-6 |
327 "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186" | |
328 :short-name "CNS11643-6" | |
329 :long-name "CNS11643-6 (Chinese traditional): ISO-IR-186" | |
330 :iso-final-char ?L | |
331 :emacs-mule-id 249 | |
332 :code-space [33 126 33 126] | |
89483 | 333 :code-offset #x128000 |
334 :unify-map "CNS-6") | |
88411 | 335 |
336 (define-charset 'chinese-cns11643-7 | |
337 "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187" | |
338 :short-name "CNS11643-7" | |
339 :long-name "CNS11643-7 (Chinese traditional): ISO-IR-187" | |
340 :iso-final-char ?M | |
341 :emacs-mule-id 250 | |
342 :code-space [33 126 33 126] | |
89483 | 343 :code-offset #x12C000 |
344 :unify-map "CNS-7") | |
88411 | 345 |
346 (define-charset 'big5 | |
347 "Big5 (Chinese traditional)" | |
348 :short-name "Big5" | |
349 :code-space [#x40 #xFE #xA1 #xFE] | |
350 :code-offset #x130000 | |
89483 | 351 :unify-map "BIG5") |
88666 | 352 ;; Fixme: AKA cp950 according to |
353 ;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>. Is | |
354 ;; that correct? | |
88411 | 355 |
356 (define-charset 'chinese-big5-1 | |
88486 | 357 "Frequently used part (A141-C67E) of Big5 (Chinese traditional)" |
88411 | 358 :short-name "Big5 (Level-1)" |
359 :long-name "Big5 (Level-1) A141-C67F" | |
360 :iso-final-char ?0 | |
361 :emacs-mule-id 152 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
362 :supplementary-p t |
88411 | 363 :code-space [#x21 #x7E #x21 #x7E] |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
364 :code-offset #x135000 |
89483 | 365 :unify-map "BIG5-1") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
366 |
88411 | 367 (define-charset 'chinese-big5-2 |
88486 | 368 "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)" |
88411 | 369 :short-name "Big5 (Level-2)" |
370 :long-name "Big5 (Level-2) C940-FEFE" | |
371 :iso-final-char ?1 | |
372 :emacs-mule-id 153 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
373 :supplementary-p t |
88411 | 374 :code-space [#x21 #x7E #x21 #x7E] |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
375 :code-offset #x137800 |
89483 | 376 :unify-map "BIG5-2") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
377 |
88411 | 378 (define-charset 'japanese-jisx0208 |
379 "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87" | |
380 :short-name "JISX0208" | |
381 :long-name "JISX0208.1983/1990 (Japanese): ISO-IR-87" | |
382 :iso-final-char ?B | |
383 :emacs-mule-id 146 | |
384 :code-space [33 126 33 126] | |
385 :code-offset #x140000 | |
89483 | 386 :unify-map "JISX0208") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
387 |
88411 | 388 (define-charset 'japanese-jisx0208-1978 |
389 "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42" | |
390 :short-name "JISX0208.1978" | |
89483 | 391 :long-name "JISX0208.1978 (JISC6226.1978): ISO-IR-42" |
88411 | 392 :iso-final-char ?@ |
393 :emacs-mule-id 144 | |
394 :code-space [33 126 33 126] | |
395 :code-offset #x144000 | |
89483 | 396 :unify-map "JISC6226") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
397 |
88411 | 398 (define-charset 'japanese-jisx0212 |
399 "JISX0212 Japanese supplement: ISO-IR-159" | |
400 :short-name "JISX0212" | |
401 :long-name "JISX0212 (Japanese): ISO-IR-159" | |
402 :iso-final-char ?D | |
403 :emacs-mule-id 148 | |
404 :code-space [33 126 33 126] | |
405 :code-offset #x148000 | |
89483 | 406 :unify-map "JISX0212") |
88411 | 407 |
89426 | 408 ;; Note that jisx0213 contains characters not in Unicode (3.2?). It's |
409 ;; arguable whether it should have a unify-map. | |
88411 | 410 (define-charset 'japanese-jisx0213-1 |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
411 "JISX0213.2000 Plane 1 (Japanese)" |
88411 | 412 :short-name "JISX0213-1" |
413 :iso-final-char ?O | |
414 :emacs-mule-id 151 | |
89483 | 415 :unify-map "JISX2131" |
88411 | 416 :code-space [33 126 33 126] |
417 :code-offset #x14C000) | |
17070 | 418 |
88411 | 419 (define-charset 'japanese-jisx0213-2 |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
420 "JISX0213.2000 Plane 2 (Japanese)" |
88411 | 421 :short-name "JISX0213-2" |
422 :iso-final-char ?P | |
423 :emacs-mule-id 254 | |
89483 | 424 :unify-map "JISX2132" |
88411 | 425 :code-space [33 126 33 126] |
426 :code-offset #x150000) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
427 |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
428 (define-charset 'japanese-jisx0213-a |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
429 "JISX0213.2004 adds these characters to JISX0213.2000." |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
430 :short-name "JISX0213A" |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
431 :dimension 2 |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
432 :code-space [33 126 33 126] |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
433 :supplementary-p t |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
434 :map "JISX213A") |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
435 |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
436 (define-charset 'japanese-jisx0213.2004-1 |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
437 "JISX0213.2004 Plane1 (Japanese)" |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
438 :short-name "JISX0213.2004-1" |
89793
cdb516af172d
(japanese-jisx0213.2004-1): Specify :dimension 2.
Kenichi Handa <handa@m17n.org>
parents:
89766
diff
changeset
|
439 :dimension 2 |
89797
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
440 :code-space [33 126 33 126] |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
441 :iso-final-char ?Q |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
442 :superset '(japanese-jisx0213-a japanese-jisx0213-1)) |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
443 |
89734
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
444 (define-charset 'katakana-sjis |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
445 "Katakana part of Shift-JIS" |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
446 :dimension 1 |
89753
d91d2d88af05
(katakana-sjis): Fix :superset to :subset.
Kenichi Handa <handa@m17n.org>
parents:
89741
diff
changeset
|
447 :code-space [#xA1 #xDF] |
d91d2d88af05
(katakana-sjis): Fix :superset to :subset.
Kenichi Handa <handa@m17n.org>
parents:
89741
diff
changeset
|
448 :subset '(jisx0201 #xA1 #xDF 0) |
89734
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
449 :supplementary-p t) |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
450 |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
451 (define-charset 'cp932-2-byte |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
452 "2-byte part of CP932" |
89741
fb91cfc5ed37
(cp932-2-byte): Specify :dimension.
Kenichi Handa <handa@m17n.org>
parents:
89734
diff
changeset
|
453 :dimension 2 |
89734
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
454 :map "CP932-2BYTE" |
89926
c452bfea1458
(cp932-2-byte): Fix :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89909
diff
changeset
|
455 :code-space [#x40 #xFC #x81 #xFC] |
89734
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
456 :supplementary-p t) |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
457 |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
458 (define-charset 'cp932 |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
459 "CP932 (Microsoft shift-jis)" |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
460 :code-space [#x00 #xFF #x00 #xFE] |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
461 :short-name "CP932" |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
462 :superset '(ascii katakana-sjis cp932-2-byte)) |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
463 |
88411 | 464 (define-charset 'korean-ksc5601 |
465 "KSC5601 Korean Hangul and Hanja: ISO-IR-149" | |
466 :short-name "KSC5601" | |
467 :long-name "KSC5601 (Korean): ISO-IR-149" | |
468 :iso-final-char ?C | |
469 :emacs-mule-id 147 | |
470 :code-space [33 126 33 126] | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
471 :code-offset #x279f94 ; ... #x27c217 |
89483 | 472 :unify-map "KSC5601") |
17070 | 473 |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
474 (define-charset 'big5-hkscs |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
475 "Big5-HKSCS (Chinese traditional, Hong Kong supplement)" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
476 :short-name "Big5" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
477 :code-space [#x40 #xFE #xA1 #xFE] |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
478 :code-offset #x27c218 ; ... #x280839 |
89483 | 479 :unify-map "BIG5-HKSCS") |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
480 |
88666 | 481 ;; Fixme: Korean cp949/UHC |
482 | |
88411 | 483 (define-charset 'chinese-sisheng |
484 "SiSheng characters for PinYin/ZhuYin" | |
485 :short-name "SiSheng" | |
486 :long-name "SiSheng (PinYin/ZhuYin)" | |
487 :iso-final-char ?0 | |
488 :emacs-mule-id 160 | |
489 :code-space [33 126] | |
89483 | 490 :unify-map "MULE-sisheng" |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
491 :supplementary-p t |
88411 | 492 :code-offset #x200000) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
493 |
88735 | 494 ;; A subset of the 1989 version of IPA. It consists of the consonant |
495 ;; signs used in English, French, German and Italian, and all vowels | |
496 ;; signs in the table. [says old MULE doc] | |
88411 | 497 (define-charset 'ipa |
498 "IPA (International Phonetic Association)" | |
499 :short-name "IPA" | |
500 :iso-final-char ?0 | |
501 :emacs-mule-id 161 | |
89483 | 502 :unify-map "MULE-ipa" |
88411 | 503 :code-space [32 127] |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
504 :supplementary-p t |
88411 | 505 :code-offset #x200080) |
17070 | 506 |
88411 | 507 (define-charset 'viscii |
508 "VISCII1.1" | |
509 :short-name "VISCII" | |
510 :long-name "VISCII 1.1" | |
511 :code-space [0 255] | |
89483 | 512 :map "VISCII") |
88411 | 513 |
514 (define-charset 'vietnamese-viscii-lower | |
515 "VISCII1.1 lower-case" | |
516 :short-name "VISCII lower" | |
517 :long-name "VISCII lower-case" | |
518 :iso-final-char ?1 | |
519 :emacs-mule-id 162 | |
520 :code-space [32 127] | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
521 :code-offset #x200200 |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
522 :supplementary-p t |
89483 | 523 :unify-map "MULE-lviscii") |
17070 | 524 |
88411 | 525 (define-charset 'vietnamese-viscii-upper |
526 "VISCII1.1 upper-case" | |
527 :short-name "VISCII upper" | |
528 :long-name "VISCII upper-case" | |
529 :iso-final-char ?2 | |
530 :emacs-mule-id 163 | |
531 :code-space [32 127] | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
532 :code-offset #x200280 |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
533 :supplementary-p t |
89483 | 534 :unify-map "MULE-uviscii") |
88411 | 535 |
536 (define-charset 'vscii | |
89483 | 537 "VSCII1.1 (TCVN-5712 VN1)" |
88411 | 538 :short-name "VSCII" |
539 :code-space [0 255] | |
89483 | 540 :map "VSCII") |
541 | |
542 (define-charset-alias 'tcvn-5712 'vscii) | |
88411 | 543 |
88727 | 544 ;; Fixme: see note in tcvn.map about combining characters |
89483 | 545 (define-charset 'vscii-2 |
546 "VSCII-2 (TCVN-5712 VN2)" | |
88727 | 547 :code-space [0 255] |
89483 | 548 :map "VSCII-2") |
88727 | 549 |
88411 | 550 (define-charset 'koi8-r |
551 "KOI8-R" | |
552 :short-name "KOI8-R" | |
553 :ascii-compatible-p t | |
554 :code-space [0 255] | |
89483 | 555 :map "KOI8-R") |
88411 | 556 |
557 (define-charset-alias 'koi8 'koi8-r) | |
558 | |
559 (define-charset 'alternativnyj | |
560 "ALTERNATIVNYJ" | |
561 :short-name "alternativnyj" | |
562 :ascii-compatible-p t | |
563 :code-space [0 255] | |
89483 | 564 :map "ALTERNATIVNYJ") |
89200 | 565 |
566 (define-charset 'cp866 | |
567 "CP866" | |
568 :short-name "cp866" | |
569 :ascii-compatible-p t | |
570 :code-space [0 255] | |
89483 | 571 :map "IBM866") |
89200 | 572 (define-charset-alias 'ibm866 'cp866) |
17070 | 573 |
88533 | 574 (define-charset 'koi8-u |
575 "KOI8-U" | |
576 :short-name "KOI8-U" | |
577 :ascii-compatible-p t | |
578 :code-space [0 255] | |
89483 | 579 :map "KOI8-U") |
88533 | 580 |
581 (define-charset 'koi8-t | |
582 "KOI8-T" | |
583 :short-name "KOI8-T" | |
584 :ascii-compatible-p t | |
585 :code-space [0 255] | |
89483 | 586 :map "KOI8-T") |
88533 | 587 |
588 (define-charset 'georgian-ps | |
589 "GEORGIAN-PS" | |
590 :short-name "GEORGIAN-PS" | |
591 :ascii-compatible-p t | |
592 :code-space [0 255] | |
89483 | 593 :map "KA-PS") |
88533 | 594 |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
595 (define-charset 'georgian-academy |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
596 "GEORGIAN-ACADEMY" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
597 :short-name "GEORGIAN-ACADEMY" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
598 :ascii-compatible-p t |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
599 :code-space [0 255] |
89483 | 600 :map "KA-ACADEMY") |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
601 |
88533 | 602 (define-charset 'windows-1250 |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
603 "WINDOWS-1250 (Central Europe)" |
88533 | 604 :short-name "WINDOWS-1250" |
605 :ascii-compatible-p t | |
606 :code-space [0 255] | |
89483 | 607 :map "CP1250") |
88533 | 608 (define-charset-alias 'cp1250 'windows-1250) |
609 | |
610 (define-charset 'windows-1251 | |
88666 | 611 "WINDOWS-1251 (Cyrillic)" |
88533 | 612 :short-name "WINDOWS-1251" |
613 :ascii-compatible-p t | |
614 :code-space [0 255] | |
89483 | 615 :map "CP1251") |
88533 | 616 (define-charset-alias 'cp1251 'windows-1251) |
17070 | 617 |
88533 | 618 (define-charset 'windows-1252 |
88666 | 619 "WINDOWS-1252 (Latin I)" |
88533 | 620 :short-name "WINDOWS-1252" |
621 :ascii-compatible-p t | |
622 :code-space [0 255] | |
89483 | 623 :map "CP1252") |
88533 | 624 (define-charset-alias 'cp1252 'windows-1252) |
625 | |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
626 (define-charset 'windows-1253 |
88666 | 627 "WINDOWS-1253 (Greek)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
628 :short-name "WINDOWS-1253" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
629 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
630 :code-space [0 255] |
89483 | 631 :map "CP1253") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
632 (define-charset-alias 'cp1253 'windows-1253) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
633 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
634 (define-charset 'windows-1254 |
88666 | 635 "WINDOWS-1254 (Turkish)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
636 :short-name "WINDOWS-1254" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
637 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
638 :code-space [0 255] |
89483 | 639 :map "CP1254") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
640 (define-charset-alias 'cp1254 'windows-1254) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
641 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
642 (define-charset 'windows-1255 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
643 "WINDOWS-1255 (Hebrew)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
644 :short-name "WINDOWS-1255" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
645 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
646 :code-space [0 255] |
89483 | 647 :map "CP1255") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
648 (define-charset-alias 'cp1255 'windows-1255) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
649 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
650 (define-charset 'windows-1256 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
651 "WINDOWS-1256 (Arabic)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
652 :short-name "WINDOWS-1256" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
653 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
654 :code-space [0 255] |
89483 | 655 :map "CP1256") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
656 (define-charset-alias 'cp1256 'windows-1256) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
657 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
658 (define-charset 'windows-1257 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
659 "WINDOWS-1257 (Baltic)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
660 :short-name "WINDOWS-1257" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
661 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
662 :code-space [0 255] |
89483 | 663 :map "CP1257") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
664 (define-charset-alias 'cp1257 'windows-1257) |
17070 | 665 |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
666 (define-charset 'windows-1258 |
88666 | 667 "WINDOWS-1258 (Viet Nam)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
668 :short-name "WINDOWS-1258" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
669 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
670 :code-space [0 255] |
89483 | 671 :map "CP1258") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
672 (define-charset-alias 'cp1258 'windows-1258) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
673 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
674 (define-charset 'next |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
675 "NEXT" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
676 :short-name "NEXT" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
677 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
678 :code-space [0 255] |
89483 | 679 :map "NEXTSTEP") |
17070 | 680 |
88533 | 681 (define-charset 'cp1125 |
682 "CP1125" | |
683 :short-name "CP1125" | |
684 :code-space [0 255] | |
90217
4e5457cf7dc7
(cp1125): Set :ascii-compatible-p property to t.
Kenichi Handa <handa@m17n.org>
parents:
90200
diff
changeset
|
685 :ascii-compatible-p t |
89483 | 686 :map "CP1125") |
88533 | 687 (define-charset-alias 'ruscii 'cp1125) |
688 ;; Original name for cp1125, says Serhii Hlodin <hlodin@lutsk.bank.gov.ua> | |
689 (define-charset-alias 'cp866u 'cp1125) | |
17070 | 690 |
88671 | 691 ;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html |
692 ;; shows this as not ASCII comptaible, with various graphics in | |
693 ;; 0x01-0x1F. | |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
694 (define-charset 'cp437 |
88671 | 695 "CP437 (MS-DOS United States, Australia, New Zealand, South Africa)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
696 :short-name "CP437" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
697 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
698 :ascii-compatible-p t |
89483 | 699 :map "IBM437") |
17070 | 700 |
88666 | 701 (define-charset 'cp720 |
702 "CP720 (Arabic)" | |
703 :short-name "CP720" | |
704 :code-space [0 255] | |
705 :ascii-compatible-p t | |
89483 | 706 :map "CP720") |
88666 | 707 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
708 (define-charset 'cp737 |
88671 | 709 "CP737 (PC Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
710 :short-name "CP737" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
711 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
712 :ascii-compatible-p t |
89483 | 713 :map "CP737") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
714 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
715 (define-charset 'cp775 |
88671 | 716 "CP775 (PC Baltic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
717 :short-name "CP775" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
718 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
719 :ascii-compatible-p t |
89483 | 720 :map "CP775") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
721 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
722 (define-charset 'cp851 |
89089 | 723 "CP851 (Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
724 :short-name "CP851" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
725 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
726 :ascii-compatible-p t |
89483 | 727 :map "IBM851") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
728 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
729 (define-charset 'cp852 |
88671 | 730 "CP852 (MS-DOS Latin-2)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
731 :short-name "CP852" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
732 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
733 :ascii-compatible-p t |
89483 | 734 :map "IBM852") |
17070 | 735 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
736 (define-charset 'cp855 |
88671 | 737 "CP855 (IBM Cyrillic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
738 :short-name "CP855" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
739 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
740 :ascii-compatible-p t |
89483 | 741 :map "IBM855") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
742 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
743 (define-charset 'cp857 |
88671 | 744 "CP857 (IBM Turkish)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
745 :short-name "CP857" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
746 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
747 :ascii-compatible-p t |
89483 | 748 :map "IBM857") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
749 |
88666 | 750 (define-charset 'cp858 |
751 "CP858 (Multilingual Latin I + Euro)" | |
752 :short-name "CP858" | |
753 :code-space [0 255] | |
754 :ascii-compatible-p t | |
89483 | 755 :map "CP858") |
88671 | 756 (define-charset-alias 'cp00858 'cp858) ; IANA has IBM00858/CP00858 |
17070 | 757 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
758 (define-charset 'cp860 |
88671 | 759 "CP860 (MS-DOS Portuguese)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
760 :short-name "CP860" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
761 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
762 :ascii-compatible-p t |
89483 | 763 :map "IBM860") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
764 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
765 (define-charset 'cp861 |
88671 | 766 "CP861 (MS-DOS Icelandic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
767 :short-name "CP861" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
768 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
769 :ascii-compatible-p t |
89483 | 770 :map "IBM861") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
771 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
772 (define-charset 'cp862 |
88671 | 773 "CP862 (PC Hebrew)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
774 :short-name "CP862" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
775 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
776 :ascii-compatible-p t |
89483 | 777 :map "IBM862") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
778 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
779 (define-charset 'cp863 |
88671 | 780 "CP863 (MS-DOS Canadian French)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
781 :short-name "CP863" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
782 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
783 :ascii-compatible-p t |
89483 | 784 :map "IBM863") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
785 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
786 (define-charset 'cp864 |
88671 | 787 "CP864 (PC Arabic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
788 :short-name "CP864" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
789 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
790 :ascii-compatible-p t |
89483 | 791 :map "IBM864") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
792 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
793 (define-charset 'cp865 |
88671 | 794 "CP865 (MS-DOS Nordic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
795 :short-name "CP865" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
796 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
797 :ascii-compatible-p t |
89483 | 798 :map "IBM865") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
799 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
800 (define-charset 'cp869 |
88671 | 801 "CP869 (IBM Modern Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
802 :short-name "CP869" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
803 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
804 :ascii-compatible-p t |
89483 | 805 :map "IBM869") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
806 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
807 (define-charset 'cp874 |
88671 | 808 "CP874 (IBM Thai)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
809 :short-name "CP874" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
810 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
811 :ascii-compatible-p t |
89483 | 812 :map "IBM874") |
17070 | 813 |
814 ;; For Arabic, we need three different types of character sets. | |
815 ;; Digits are of direction left-to-right and of width 1-column. | |
816 ;; Others are of direction right-to-left and of width 1-column or | |
817 ;; 2-column. | |
88411 | 818 (define-charset 'arabic-digit |
819 "Arabic digit" | |
820 :short-name "Arabic digit" | |
821 :iso-final-char ?2 | |
822 :emacs-mule-id 164 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
823 :supplementary-p t |
88411 | 824 :code-space [34 42] |
825 :code-offset #x0600) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
826 |
88411 | 827 (define-charset 'arabic-1-column |
828 "Arabic 1-column" | |
829 :short-name "Arabic 1-col" | |
830 :long-name "Arabic 1-column" | |
831 :iso-final-char ?3 | |
832 :emacs-mule-id 165 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
833 :supplementary-p t |
88411 | 834 :code-space [33 126] |
835 :code-offset #x200100) | |
836 | |
837 (define-charset 'arabic-2-column | |
838 "Arabic 2-column" | |
839 :short-name "Arabic 2-col" | |
840 :long-name "Arabic 2-column" | |
841 :iso-final-char ?4 | |
842 :emacs-mule-id 224 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
843 :supplementary-p t |
88411 | 844 :code-space [33 126] |
845 :code-offset #x200180) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
846 |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
847 ;; Lao script. |
88411 | 848 ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF. |
89089 | 849 ;; Not all of them are defined unicodes. |
88411 | 850 (define-charset 'lao |
851 "Lao characters (ISO10646 0E81..0EDF)" | |
852 :short-name "Lao" | |
853 :iso-final-char ?1 | |
854 :emacs-mule-id 167 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
855 :supplementary-p t |
88411 | 856 :code-space [33 126] |
857 :code-offset #x0E81) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
858 |
88411 | 859 (define-charset 'mule-lao |
860 "Lao characters (ISO10646 0E81..0EDF)" | |
861 :short-name "Lao" | |
862 :code-space [0 255] | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
863 :supplementary-p t |
88751
809b6bfe4dfa
Adjusted for the change of define-charset (:parent -> :subset or
Kenichi Handa <handa@m17n.org>
parents:
88735
diff
changeset
|
864 :superset '(ascii eight-bit-control (lao . 128))) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
865 |
17070 | 866 |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
867 ;; Indian scripts. Symbolic charset for data exchange. Glyphs are |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
868 ;; not assigned. They are automatically converted to each Indian |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
869 ;; script which IS-13194 supports. |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
870 |
88411 | 871 (define-charset 'indian-is13194 |
872 "Generic Indian charset for data exchange with IS 13194" | |
873 :short-name "IS 13194" | |
874 :long-name "Indian IS 13194" | |
875 :iso-final-char ?5 | |
876 :emacs-mule-id 225 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
877 :supplementary-p t |
88411 | 878 :code-space [33 126] |
879 :code-offset #x180000) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
880 |
89483 | 881 (let ((code-offset #x180100)) |
882 (dolist (script '(devanagari sanskrit bengali tamil telugu assamese | |
883 oriya kannada malayalam gujarati punjabi)) | |
884 (define-charset (intern (format "%s-cdac" script)) | |
885 (format "Glyphs of %s script for CDAC font. Subset of `indian-glyph'." | |
886 (capitalize (symbol-name script))) | |
887 :short-name (format "CDAC %s glyphs" (capitalize (symbol-name script))) | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
888 :supplementary-p t |
89483 | 889 :code-space [0 255] |
890 :code-offset code-offset) | |
891 (setq code-offset (+ code-offset #x100))) | |
41468
d566b1e9a5bb
Change indian-1-column charset to indian-glyph charset.
Richard M. Stallman <rms@gnu.org>
parents:
36686
diff
changeset
|
892 |
89483 | 893 (dolist (script '(devanagari bengali punjabi gujarati |
894 oriya tamil telugu kannada malayalam)) | |
895 (define-charset (intern (format "%s-akruti" script)) | |
896 (format "Glyphs of %s script for AKRUTI font. Subset of `indian-glyph'." | |
897 (capitalize (symbol-name script))) | |
898 :short-name (format "AKRUTI %s glyphs" (capitalize (symbol-name script))) | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
899 :supplementary-p t |
89483 | 900 :code-space [0 255] |
901 :code-offset code-offset) | |
902 (setq code-offset (+ code-offset #x100)))) | |
89091 | 903 |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
904 (define-charset 'indian-glyph |
88411 | 905 "Glyphs for Indian characters." |
906 :short-name "Indian glyph" | |
907 :iso-final-char ?4 | |
908 :emacs-mule-id 240 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
909 :supplementary-p t |
88411 | 910 :code-space [32 127 32 127] |
911 :code-offset #x180100) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
912 |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
913 ;; Actual Glyph for 1-column width. |
88411 | 914 (define-charset 'indian-1-column |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
915 "Indian charset for 1-column width glyphs." |
88411 | 916 :short-name "Indian 1-col" |
917 :long-name "Indian 1 Column" | |
918 :iso-final-char ?6 | |
89890
f3047b4ebf04
(indian-1-column): Fix :emacs-mule-id.
Kenichi Handa <handa@m17n.org>
parents:
89822
diff
changeset
|
919 :emacs-mule-id 251 |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
920 :supplementary-p t |
88411 | 921 :code-space [33 126 33 126] |
922 :code-offset #x184000) | |
923 | |
924 ;; Actual Glyph for 2-column width. | |
925 (define-charset 'indian-2-column | |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
926 "Indian charset for 2-column width glyphs." |
88411 | 927 :short-name "Indian 2-col" |
928 :long-name "Indian 2 Column" | |
929 :iso-final-char ?5 | |
930 :emacs-mule-id 251 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
931 :supplementary-p t |
88411 | 932 :code-space [33 126 33 126] |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
933 :code-offset #x184000) |
88411 | 934 |
935 (define-charset 'tibetan | |
936 "Tibetan characters" | |
937 :iso-final-char ?7 | |
938 :short-name "Tibetan 2-col" | |
88486 | 939 :long-name "Tibetan 2 column" |
88411 | 940 :iso-final-char ?7 |
941 :emacs-mule-id 252 | |
89483 | 942 :unify-map "MULE-tibetan" |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
943 :supplementary-p t |
89292
1bc1e30ea8d5
(tibetan): Fix :code-space property.
Kenichi Handa <handa@m17n.org>
parents:
89267
diff
changeset
|
944 :code-space [33 126 33 37] |
88411 | 945 :code-offset #x190000) |
946 | |
947 (define-charset 'tibetan-1-column | |
948 "Tibetan 1 column glyph" | |
949 :short-name "Tibetan 1-col" | |
950 :long-name "Tibetan 1 column" | |
951 :iso-final-char ?8 | |
952 :emacs-mule-id 241 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
953 :supplementary-p t |
88411 | 954 :code-space [33 126 33 37] |
89292
1bc1e30ea8d5
(tibetan): Fix :code-space property.
Kenichi Handa <handa@m17n.org>
parents:
89267
diff
changeset
|
955 :code-offset #x190000) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
956 |
33044
7878d85aef6d
New charsets mule-unicode-2500-33ff and mule-unicode-e000-ffff.
Kenichi Handa <handa@m17n.org>
parents:
32786
diff
changeset
|
957 ;; Subsets of Unicode. |
88411 | 958 (define-charset 'mule-unicode-2500-33ff |
959 "Unicode characters of the range U+2500..U+33FF." | |
960 :short-name "Unicode subset 2" | |
961 :long-name "Unicode subset (U+2500..U+33FF)" | |
962 :iso-final-char ?2 | |
963 :emacs-mule-id 242 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
964 :supplementary-p t |
88411 | 965 :code-space [#x20 #x7f #x20 #x47] |
966 :code-offset #x2500) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
967 |
88411 | 968 (define-charset 'mule-unicode-e000-ffff |
969 "Unicode characters of the range U+E000..U+FFFF." | |
970 :short-name "Unicode subset 3" | |
971 :long-name "Unicode subset (U+E000+FFFF)" | |
972 :iso-final-char ?3 | |
973 :emacs-mule-id 243 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
974 :supplementary-p t |
88411 | 975 :code-space [#x20 #x7F #x20 #x75] |
88843 | 976 :code-offset #xE000 |
977 :max-code 30015) ; U+FFFF | |
33044
7878d85aef6d
New charsets mule-unicode-2500-33ff and mule-unicode-e000-ffff.
Kenichi Handa <handa@m17n.org>
parents:
32786
diff
changeset
|
978 |
88411 | 979 (define-charset 'mule-unicode-0100-24ff |
980 "Unicode characters of the range U+0100..U+24FF." | |
981 :short-name "Unicode subset" | |
982 :long-name "Unicode subset (U+0100..U+24FF)" | |
983 :iso-final-char ?1 | |
984 :emacs-mule-id 244 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
985 :supplementary-p t |
88411 | 986 :code-space [#x20 #x7F #x20 #x7F] |
987 :code-offset #x100) | |
33044
7878d85aef6d
New charsets mule-unicode-2500-33ff and mule-unicode-e000-ffff.
Kenichi Handa <handa@m17n.org>
parents:
32786
diff
changeset
|
988 |
89089 | 989 (define-charset 'unicode-bmp |
89797
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
990 "Unicode Basic Multilingual Plane (U+0000..U+FFFF)" |
89089 | 991 :short-name "Unicode BMP" |
992 :code-space [0 255 0 255] | |
89356
d2e1c7e5ab1a
(unicode-bmp): Delete duplicated definition. Give it :code-offset 0.
Kenichi Handa <handa@m17n.org>
parents:
89318
diff
changeset
|
993 :code-offset 0) |
89091 | 994 |
89797
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
995 (define-charset 'unicode-smp |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
996 "Unicode Supplementary Multilingual Plane (U+10000..U+1FFFF)" |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
997 :short-name "Unicode SMP " |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
998 :code-space [0 255 0 255] |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
999 :code-offset #x10000) |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1000 |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1001 (define-charset 'unicode-sip |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1002 "Unicode Supplementary Ideographic Plane (U+20000..U+2FFFF)" |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1003 :short-name "Unicode SIP" |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1004 :code-space [0 255 0 255] |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1005 :code-offset #x20000) |
33044
7878d85aef6d
New charsets mule-unicode-2500-33ff and mule-unicode-e000-ffff.
Kenichi Handa <handa@m17n.org>
parents:
32786
diff
changeset
|
1006 |
89797
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1007 (define-charset 'unicode-ssp |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1008 "Unicode Supplementary Special-purpose Plane (U+E0000..U+EFFFF)" |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1009 :short-name "Unicode SSP" |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1010 :code-space [0 255 0 255] |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1011 :code-offset #xE0000) |
33044
7878d85aef6d
New charsets mule-unicode-2500-33ff and mule-unicode-e000-ffff.
Kenichi Handa <handa@m17n.org>
parents:
32786
diff
changeset
|
1012 |
88411 | 1013 (define-charset 'ethiopic |
88486 | 1014 "Ethiopic characters for Amharic and Tigrigna." |
88411 | 1015 :short-name "Ethiopic" |
1016 :long-name "Ethiopic characters" | |
1017 :iso-final-char ?3 | |
1018 :emacs-mule-id 245 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
1019 :supplementary-p t |
89483 | 1020 :unify-map "MULE-ethiopic" |
88411 | 1021 :code-space [33 126 33 126] |
1022 :code-offset #x1A0000) | |
17070 | 1023 |
88411 | 1024 (define-charset 'mac-roman |
1025 "Mac Roman charset" | |
1026 :short-name "Mac Roman" | |
1027 :ascii-compatible-p t | |
1028 :code-space [0 255] | |
89483 | 1029 :map "MACINTOSH") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1030 |
88533 | 1031 ;; Fixme: modern EBCDIC variants, e.g. IBM00924? |
1032 (define-charset 'ebcdic-us | |
1033 "US version of EBCDIC" | |
1034 :short-name "EBCDIC-US" | |
1035 :code-space [0 255] | |
1036 :mime-charset 'ebcdic-us | |
89483 | 1037 :map "EBCDICUS") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1038 |
88533 | 1039 (define-charset 'ebcdic-uk |
1040 "UK version of EBCDIC" | |
1041 :short-name "EBCDIC-UK" | |
1042 :code-space [0 255] | |
1043 :mime-charset 'ebcdic-uk | |
89483 | 1044 :map "EBCDICUK") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1045 |
89200 | 1046 (define-charset 'ibm1047 |
1047 ;; Says groff: | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
1048 "IBM1047, `EBCDIC Latin 1/Open Systems' used by OS/390 Unix." |
89200 | 1049 :short-name "IBM1047" |
1050 :code-space [0 255] | |
1051 :mime-charset 'ibm1047 | |
89483 | 1052 :map "IBM1047") |
89200 | 1053 (define-charset-alias 'cp1047 'ibm1047) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1054 |
88575 | 1055 (define-charset 'hp-roman8 |
1056 "Encoding used by Hewlet-Packard printer software" | |
1057 :short-name "HP-ROMAN8" | |
1058 :ascii-compatible-p t | |
1059 :code-space [0 255] | |
89483 | 1060 :map "HP-ROMAN8") |
17070 | 1061 |
88671 | 1062 ;; To make a coding system with this, a pre-write-conversion should |
1063 ;; account for the commented-out multi-valued code points in | |
1064 ;; stdenc.map. | |
88575 | 1065 (define-charset 'adobe-standard-encoding |
1066 "Adobe `standard encoding' used in PostScript" | |
1067 :short-name "ADOBE-STANDARD-ENCODING" | |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
1068 :code-space [#x20 255] |
88575 | 1069 :map "stdenc") |
17070 | 1070 |
88575 | 1071 (define-charset 'symbol |
1072 "Adobe symbol encoding used in PostScript" | |
1073 :short-name "ADOBE-SYMBOL" | |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
1074 :code-space [#x20 255] |
88575 | 1075 :map "symbol") |
1076 | |
1077 (define-charset 'ibm850 | |
88671 | 1078 "DOS codepage 850 (Latin-1)" |
88575 | 1079 :short-name "IBM850" |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
1080 :ascii-compatible-p t |
88575 | 1081 :code-space [0 255] |
89483 | 1082 :map "IBM850") |
88575 | 1083 (define-charset-alias 'cp850 'ibm850) |
1084 | |
89318 | 1085 (define-charset 'mik |
1086 "Bulgarian DOS codepage" | |
1087 :short-name "MIK" | |
1088 :ascii-compatible-p t | |
1089 :code-space [0 255] | |
89483 | 1090 :map "MIK") |
89318 | 1091 |
89483 | 1092 (define-charset 'ptcp154 |
89318 | 1093 "`Paratype' codepage (Asian Cyrillic)" |
1094 :short-name "PT154" | |
1095 :ascii-compatible-p t | |
1096 :code-space [0 255] | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
1097 :mime-charset 'pt154 |
89483 | 1098 :map "PTCP154") |
1099 (define-charset-alias 'pt154 'ptcp154) | |
1100 (define-charset-alias 'cp154 'ptcp154) | |
89318 | 1101 |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1102 (define-charset 'gb18030-2-byte |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1103 "GB18030 2-byte (0x814E..0xFEFE)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1104 :code-space [#x40 #xFE #x81 #xFE] |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1105 :supplementary-p t |
89483 | 1106 :map "GB180302") |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1107 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1108 (define-charset 'gb18030-4-byte-bmp |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1109 "GB18030 4-byte for BMP (0x81308130-0x8431A439)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1110 :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x81 #x84] |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1111 :supplementary-p t |
89483 | 1112 :map "GB180304") |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1113 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1114 (define-charset 'gb18030-4-byte-smp |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1115 "GB18030 4-byte for SMP (0x90308130-0xE3329A35)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1116 :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x90 #xE3] |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1117 :min-code '(#x9030 . #x8130) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1118 :max-code '(#xE332 . #x9A35) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1119 :supplementary-p t |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1120 :code-offset #x10000) |
17070 | 1121 |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1122 (define-charset 'gb18030-4-byte-ext-1 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1123 "GB18030 4-byte (0x8431A530-0x8F39FE39)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1124 :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x84 #x8F] |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1125 :min-code '(#x8431 . #xA530) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1126 :max-code '(#x8F39 . #xFE39) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1127 :supplementary-p t |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1128 :code-offset #x200000 ; ... #x22484B |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1129 ) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1130 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1131 (define-charset 'gb18030-4-byte-ext-2 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1132 "GB18030 4-byte (0xE3329A36-0xFE39FE39)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1133 :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #xE3 #xFE] |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1134 :min-code '(#xE332 . #x9A36) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1135 :max-code '(#xFE39 . #xFE39) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1136 :supplementary-p t |
89822
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1137 :code-offset #x22484C ; ... #x279f93 |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1138 ) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1139 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1140 (define-charset 'gb18030 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1141 "GB18030" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1142 :code-space [#x00 #xFF #x00 #xFE #x00 #xFE #x00 #xFE] |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1143 :min-code 0 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1144 :max-code '(#xFE39 . #xFE39) |
88751
809b6bfe4dfa
Adjusted for the change of define-charset (:parent -> :subset or
Kenichi Handa <handa@m17n.org>
parents:
88735
diff
changeset
|
1145 :superset '(ascii gb18030-2-byte |
809b6bfe4dfa
Adjusted for the change of define-charset (:parent -> :subset or
Kenichi Handa <handa@m17n.org>
parents:
88735
diff
changeset
|
1146 gb18030-4-byte-bmp gb18030-4-byte-smp |
809b6bfe4dfa
Adjusted for the change of define-charset (:parent -> :subset or
Kenichi Handa <handa@m17n.org>
parents:
88735
diff
changeset
|
1147 gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)) |
17070 | 1148 |
89822
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1149 (define-charset 'chinese-cns11643-15 |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1150 "CNS11643 Plane 15 Chinese Traditional" |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1151 :short-name "CNS11643-15" |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1152 :long-name "CNS11643-15 (Chinese traditional)" |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1153 :code-space [33 126 33 126] |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1154 :code-offset #x27A000) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1155 |
88411 | 1156 (unify-charset 'chinese-gb2312) |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
1157 (unify-charset 'chinese-gbk) |
88411 | 1158 (unify-charset 'chinese-cns11643-1) |
1159 (unify-charset 'chinese-cns11643-2) | |
89483 | 1160 (unify-charset 'chinese-cns11643-3) |
1161 (unify-charset 'chinese-cns11643-4) | |
1162 (unify-charset 'chinese-cns11643-5) | |
1163 (unify-charset 'chinese-cns11643-6) | |
1164 (unify-charset 'chinese-cns11643-7) | |
88411 | 1165 (unify-charset 'big5) |
1166 (unify-charset 'chinese-big5-1) | |
1167 (unify-charset 'chinese-big5-2) | |
89483 | 1168 (unify-charset 'big5-hkscs) |
1169 (unify-charset 'korean-ksc5601) | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
1170 (unify-charset 'vietnamese-viscii-lower) |
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
1171 (unify-charset 'vietnamese-viscii-upper) |
88760 | 1172 (unify-charset 'chinese-sisheng) |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1173 (unify-charset 'ipa) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1174 (unify-charset 'tibetan) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1175 (unify-charset 'ethiopic) |
89483 | 1176 (unify-charset 'japanese-jisx0208-1978) |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1177 (unify-charset 'japanese-jisx0208) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1178 (unify-charset 'japanese-jisx0212) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1179 (unify-charset 'japanese-jisx0213-1) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1180 (unify-charset 'japanese-jisx0213-2) |
17070 | 1181 |
1182 | |
22126
97cf1cae1971
Change term unification to
Kenichi Handa <handa@m17n.org>
parents:
21713
diff
changeset
|
1183 ;; These are tables for translating characters on decoding and |
97cf1cae1971
Change term unification to
Kenichi Handa <handa@m17n.org>
parents:
21713
diff
changeset
|
1184 ;; encoding. |
88760 | 1185 ;; Fixme: these aren't used now -- should they be? |
88411 | 1186 (setq standard-translation-table-for-decode nil) |
17760
b3d62674b210
Delete code for alternate-charset-table.
Kenichi Handa <handa@m17n.org>
parents:
17541
diff
changeset
|
1187 |
22186
fc4aaf1b1772
Change term "character translation table" to "translation table".
Kenichi Handa <handa@m17n.org>
parents:
22126
diff
changeset
|
1188 (setq standard-translation-table-for-encode nil) |
17760
b3d62674b210
Delete code for alternate-charset-table.
Kenichi Handa <handa@m17n.org>
parents:
17541
diff
changeset
|
1189 |
17070 | 1190 ;;; Make fundamental coding systems. |
1191 | |
90039
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1192 ;; The coding system `no-conversion' and `undecided' are already |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1193 ;; defined in coding.c as below: |
88411 | 1194 ;; |
1195 ;; (define-coding-system 'no-conversion | |
90039
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1196 ;; "..." |
88411 | 1197 ;; :coding-type 'raw-text |
90039
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1198 ;; ...) |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1199 ;; (define-coding-system 'undecided |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1200 ;; "..." |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1201 ;; :coding-type 'undecided |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1202 ;; ...) |
17070 | 1203 |
18529
8e293f1a19a9
(binary): Define as coding system alias.
Richard M. Stallman <rms@gnu.org>
parents:
18519
diff
changeset
|
1204 (define-coding-system-alias 'binary 'no-conversion) |
29543
4711a63436ee
(unix): New alias for the coding system undecided-unix.
Kenichi Handa <handa@m17n.org>
parents:
29167
diff
changeset
|
1205 (define-coding-system-alias 'unix 'undecided-unix) |
24120
372fcaa211c4
Coding system alias `dos' for `undecided-dos', `mac' for `undecided-mac'.
Richard M. Stallman <rms@gnu.org>
parents:
23260
diff
changeset
|
1206 (define-coding-system-alias 'dos 'undecided-dos) |
372fcaa211c4
Coding system alias `dos' for `undecided-dos', `mac' for `undecided-mac'.
Richard M. Stallman <rms@gnu.org>
parents:
23260
diff
changeset
|
1207 (define-coding-system-alias 'mac 'undecided-mac) |
372fcaa211c4
Coding system alias `dos' for `undecided-dos', `mac' for `undecided-mac'.
Richard M. Stallman <rms@gnu.org>
parents:
23260
diff
changeset
|
1208 |
88411 | 1209 (define-coding-system 'raw-text |
89483 | 1210 "Raw text, which means text contains random 8-bit codes. |
36518
60e98df5c4ce
(emacs-mule, raw-text): Docstring modified.
Kenichi Handa <handa@m17n.org>
parents:
35805
diff
changeset
|
1211 Encoding text with this coding system produces the actual byte |
60e98df5c4ce
(emacs-mule, raw-text): Docstring modified.
Kenichi Handa <handa@m17n.org>
parents:
35805
diff
changeset
|
1212 sequence of the text in buffers and strings. An exception is made for |
60e98df5c4ce
(emacs-mule, raw-text): Docstring modified.
Kenichi Handa <handa@m17n.org>
parents:
35805
diff
changeset
|
1213 eight-bit-control characters. Each of them is encoded into a single |
36686
9688519d51d6
(no-conversion): Fix docstring.
Kenichi Handa <handa@m17n.org>
parents:
36518
diff
changeset
|
1214 byte. |
9688519d51d6
(no-conversion): Fix docstring.
Kenichi Handa <handa@m17n.org>
parents:
36518
diff
changeset
|
1215 |
9688519d51d6
(no-conversion): Fix docstring.
Kenichi Handa <handa@m17n.org>
parents:
36518
diff
changeset
|
1216 When you visit a file with this coding, the file is read into a |
9688519d51d6
(no-conversion): Fix docstring.
Kenichi Handa <handa@m17n.org>
parents:
36518
diff
changeset
|
1217 unibyte buffer as is (except for EOL format), thus each byte of a file |
9688519d51d6
(no-conversion): Fix docstring.
Kenichi Handa <handa@m17n.org>
parents:
36518
diff
changeset
|
1218 is treated as a character." |
89483 | 1219 :coding-type 'raw-text |
1220 :for-unibyte t | |
1221 :mnemonic ?t) | |
88411 | 1222 |
89483 | 1223 (define-coding-system 'no-conversion-multibyte |
1224 "Like `no-conversion' but don't read a file into a unibyte buffer." | |
1225 :coding-type 'raw-text | |
1226 :eol-type 'unix | |
1227 :mnemonic ?=) | |
1228 | |
88411 | 1229 (define-coding-system 'iso-latin-1 |
1230 "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)." | |
89091 | 1231 :coding-type 'charset |
88411 | 1232 :mnemonic ?1 |
89091 | 1233 :charset-list '(iso-8859-1) |
88411 | 1234 :mime-charset 'iso-8859-1) |
1235 | |
1236 (define-coding-system-alias 'iso-8859-1 'iso-latin-1) | |
1237 (define-coding-system-alias 'latin-1 'iso-latin-1) | |
19607
ea0964347a40
(raw-text): New coding system. Set
Kenichi Handa <handa@m17n.org>
parents:
19372
diff
changeset
|
1238 |
88411 | 1239 ;; Coding systems not specific to each language environment. |
1240 | |
1241 (define-coding-system 'emacs-mule | |
1242 "Emacs 21 internal format used in buffer and string." | |
1243 :coding-type 'emacs-mule | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1244 :charset-list 'emacs-mule |
88411 | 1245 :mnemonic ?M) |
19607
ea0964347a40
(raw-text): New coding system. Set
Kenichi Handa <handa@m17n.org>
parents:
19372
diff
changeset
|
1246 |
88411 | 1247 (define-coding-system 'utf-8 |
1248 "UTF-8." | |
1249 :coding-type 'utf-8 | |
1250 :mnemonic ?U | |
89041
2ce9656d788b
(utf-8): Give :mime-charset property.
Kenichi Handa <handa@m17n.org>
parents:
88894
diff
changeset
|
1251 :charset-list '(unicode) |
2ce9656d788b
(utf-8): Give :mime-charset property.
Kenichi Handa <handa@m17n.org>
parents:
88894
diff
changeset
|
1252 :mime-charset 'utf-8) |
88411 | 1253 |
1254 (define-coding-system-alias 'mule-utf-8 'utf-8) | |
1255 | |
1256 (define-coding-system 'utf-8-emacs | |
88468 | 1257 "Support for all Emacs characters (including non-Unicode characters)." |
88411 | 1258 :coding-type 'utf-8 |
1259 :mnemonic ?U | |
89244
bf10578caec8
(utf-8-emacs): Delete :mime-charset.
Dave Love <fx@gnu.org>
parents:
89200
diff
changeset
|
1260 :charset-list '(emacs)) |
88411 | 1261 |
89436 | 1262 (define-coding-system 'utf-16le |
89475
d6468503c001
(utf-16-be): Make it an alias of utf-16be-with-signature.
Kenichi Handa <handa@m17n.org>
parents:
89436
diff
changeset
|
1263 "UTF-16LE (little endian, no signature (BOM))." |
88411 | 1264 :coding-type 'utf-16 |
1265 :mnemonic ?U | |
88503 | 1266 :charset-list '(unicode) |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1267 :endian 'little |
89436 | 1268 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1269 :mime-charset 'utf-16le) |
17070 | 1270 |
89436 | 1271 (define-coding-system 'utf-16be |
89475
d6468503c001
(utf-16-be): Make it an alias of utf-16be-with-signature.
Kenichi Handa <handa@m17n.org>
parents:
89436
diff
changeset
|
1272 "UTF-16BE (big endian, no signature (BOM))." |
88411 | 1273 :coding-type 'utf-16 |
1274 :mnemonic ?U | |
1275 :charset-list '(unicode) | |
89422 | 1276 :endian 'big |
89436 | 1277 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1278 :mime-charset 'utf-16be) |
17070 | 1279 |
89436 | 1280 (define-coding-system 'utf-16le-with-signature |
89475
d6468503c001
(utf-16-be): Make it an alias of utf-16be-with-signature.
Kenichi Handa <handa@m17n.org>
parents:
89436
diff
changeset
|
1281 "UTF-16 (little endian, with signature (BOM))." |
88411 | 1282 :coding-type 'utf-16 |
1283 :mnemonic ?U | |
1284 :charset-list '(unicode) | |
88440
5b1dd2e30f16
(utf-16-le): Use :bom attribute instead of :signature.
Kenichi Handa <handa@m17n.org>
parents:
88411
diff
changeset
|
1285 :bom t |
88503 | 1286 :endian 'little |
89436 | 1287 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1288 :mime-charset 'utf-16) |
17070 | 1289 |
89436 | 1290 (define-coding-system 'utf-16be-with-signature |
89475
d6468503c001
(utf-16-be): Make it an alias of utf-16be-with-signature.
Kenichi Handa <handa@m17n.org>
parents:
89436
diff
changeset
|
1291 "UTF-16 (big endian, with signature)." |
88411 | 1292 :coding-type 'utf-16 |
1293 :mnemonic ?U | |
1294 :charset-list '(unicode) | |
88440
5b1dd2e30f16
(utf-16-le): Use :bom attribute instead of :signature.
Kenichi Handa <handa@m17n.org>
parents:
88411
diff
changeset
|
1295 :bom t |
89422 | 1296 :endian 'big |
89436 | 1297 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1298 :mime-charset 'utf-16) |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1299 |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1300 (define-coding-system 'utf-16 |
89475
d6468503c001
(utf-16-be): Make it an alias of utf-16be-with-signature.
Kenichi Handa <handa@m17n.org>
parents:
89436
diff
changeset
|
1301 "UTF-16 (detect endian on decoding, use big endian on encoding with BOM)." |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1302 :coding-type 'utf-16 |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1303 :mnemonic ?U |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1304 :charset-list '(unicode) |
89436 | 1305 :bom '(utf-16le-with-signature . utf-16be-with-signature) |
89422 | 1306 :endian 'big |
89436 | 1307 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1308 :mime-charset 'utf-16) |
17070 | 1309 |
89436 | 1310 ;; Backwards compatibility (old names, also used by Mule-UCS). We |
1311 ;; prefer the MIME names. | |
89475
d6468503c001
(utf-16-be): Make it an alias of utf-16be-with-signature.
Kenichi Handa <handa@m17n.org>
parents:
89436
diff
changeset
|
1312 (define-coding-system-alias 'utf-16-le 'utf-16le-with-signature) |
d6468503c001
(utf-16-be): Make it an alias of utf-16be-with-signature.
Kenichi Handa <handa@m17n.org>
parents:
89436
diff
changeset
|
1313 (define-coding-system-alias 'utf-16-be 'utf-16be-with-signature) |
d6468503c001
(utf-16-be): Make it an alias of utf-16be-with-signature.
Kenichi Handa <handa@m17n.org>
parents:
89436
diff
changeset
|
1314 |
89436 | 1315 |
88411 | 1316 (define-coding-system 'iso-2022-7bit |
88647 | 1317 "ISO 2022 based 7-bit encoding using only G0." |
88411 | 1318 :coding-type 'iso-2022 |
1319 :mnemonic ?J | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1320 :charset-list 'iso-2022 |
88411 | 1321 :designation [(ascii t) nil nil nil] |
1322 :flags '(short ascii-at-eol ascii-at-cntl 7-bit designation composition)) | |
1323 | |
1324 (define-coding-system 'iso-2022-7bit-ss2 | |
88647 | 1325 "ISO 2022 based 7-bit encoding using SS2 for 96-charset." |
88411 | 1326 :coding-type 'iso-2022 |
1327 :mnemonic ?$ | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1328 :charset-list 'iso-2022 |
88411 | 1329 :designation [(ascii 94) nil (nil 96) nil] |
1330 :flags '(short ascii-at-eol ascii-at-cntl 7-bit | |
1331 designation single-shift composition)) | |
1332 | |
1333 (define-coding-system 'iso-2022-7bit-lock | |
88647 | 1334 "ISO-2022 coding system using Locking-Shift for 96-charset." |
88411 | 1335 :coding-type 'iso-2022 |
1336 :mnemonic ?& | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1337 :charset-list 'iso-2022 |
88411 | 1338 :designation [(ascii 94) (nil 96) nil nil] |
1339 :flags '(ascii-at-eol ascii-at-cntl 7-bit | |
1340 designation locking-shift composition)) | |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1341 |
18519
b6badf3614ea
Fix calls to define-coding-system-alias.
Richard M. Stallman <rms@gnu.org>
parents:
18377
diff
changeset
|
1342 (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock) |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1343 |
88411 | 1344 (define-coding-system 'iso-2022-7bit-lock-ss2 |
88647 | 1345 "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN." |
88411 | 1346 :coding-type 'iso-2022 |
1347 :mnemonic ?i | |
1348 :charset-list '(ascii | |
1349 japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201 | |
1350 korean-ksc5601 | |
1351 chinese-gb2312 | |
1352 chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3 | |
1353 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6 | |
1354 chinese-cns11643-7) | |
1355 :designation [(ascii 94) | |
1356 (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 96) | |
1357 (nil chinese-cns11643-2) | |
1358 (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5 | |
1359 chinese-cns11643-6 chinese-cns11643-7)] | |
1360 :flags '(short ascii-at-eol ascii-at-cntl 7-bit locking-shift | |
1361 single-shift init-bol)) | |
17070 | 1362 |
18519
b6badf3614ea
Fix calls to define-coding-system-alias.
Richard M. Stallman <rms@gnu.org>
parents:
18377
diff
changeset
|
1363 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2) |
17070 | 1364 |
88411 | 1365 (define-coding-system 'iso-2022-8bit-ss2 |
88647 | 1366 "ISO 2022 based 8-bit encoding using SS2 for 96-charset." |
88411 | 1367 :coding-type 'iso-2022 |
1368 :mnemonic ?@ | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1369 :charset-list 'iso-2022 |
88411 | 1370 :designation [(ascii 94) nil (nil 96) nil] |
1371 :flags '(ascii-at-eol ascii-at-cntl designation single-shift composition)) | |
17070 | 1372 |
88411 | 1373 (define-coding-system 'compound-text |
1374 "Compound text based generic encoding for decoding unknown messages. | |
17070 | 1375 |
89483 | 1376 This coding system does not support extended segments of CTEXT." |
88411 | 1377 :coding-type 'iso-2022 |
1378 :mnemonic ?x | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1379 :charset-list 'iso-2022 |
88411 | 1380 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] |
90352 | 1381 :flags '(ascii-at-eol ascii-at-cntl long-form |
88411 | 1382 designation locking-shift single-shift composition) |
88503 | 1383 ;; Fixme: this isn't a valid MIME charset and has to be |
1384 ;; special-cased elsewhere -- fx | |
88411 | 1385 :mime-charset 'x-ctext) |
24619
6057f7a48050
(x-ctext): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
24308
diff
changeset
|
1386 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1387 (define-coding-system-alias 'x-ctext 'compound-text) |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1388 (define-coding-system-alias 'ctext 'compound-text) |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1389 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1390 ;; Same as compound-text, but doesn't produce composition escape |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1391 ;; sequences. Used in post-read and pre-write conversions of |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1392 ;; compound-text-with-extensions, see mule.el. Note that this should |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1393 ;; not have a mime-charset property, to prevent it from showing up |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1394 ;; close to the beginning of coding systems ordered by priority. |
89647
b1e7c4bffed1
(ctext-no-compositions): Remove garbage arguments.
Kenichi Handa <handa@m17n.org>
parents:
89483
diff
changeset
|
1395 (define-coding-system 'ctext-no-compositions |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1396 "Compound text based generic encoding for decoding unknown messages. |
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1397 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1398 Like `compound-text', but does not produce escape sequences for compositions." |
88411 | 1399 :coding-type 'iso-2022 |
1400 :mnemonic ?x | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1401 :charset-list 'iso-2022 |
88411 | 1402 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] |
1403 :flags '(ascii-at-eol ascii-at-cntl | |
1404 designation locking-shift single-shift)) | |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1405 |
88411 | 1406 (define-coding-system 'compound-text-with-extensions |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1407 "Compound text encoding with ICCCM Extended Segment extensions. |
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1408 |
53241
b5acb6a7d79b
(compound-text-with-extensions): Change the type to 2 (iso-2022 base).
Kenichi Handa <handa@m17n.org>
parents:
52401
diff
changeset
|
1409 See the variable `ctext-non-standard-encodings-alist' for the |
b5acb6a7d79b
(compound-text-with-extensions): Change the type to 2 (iso-2022 base).
Kenichi Handa <handa@m17n.org>
parents:
52401
diff
changeset
|
1410 detail about how extended segments are handled. |
b5acb6a7d79b
(compound-text-with-extensions): Change the type to 2 (iso-2022 base).
Kenichi Handa <handa@m17n.org>
parents:
52401
diff
changeset
|
1411 |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1412 This coding system should be used only for X selections. It is inappropriate |
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1413 for decoding and encoding files, process I/O, etc." |
89909 | 1414 :coding-type 'iso-2022 |
88411 | 1415 :mnemonic ?x |
89909 | 1416 :charset-list 'iso-2022 |
1417 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] | |
90352 | 1418 :flags '(ascii-at-eol ascii-at-cntl long-form |
89909 | 1419 designation locking-shift single-shift) |
88411 | 1420 :post-read-conversion 'ctext-post-read-conversion |
1421 :pre-write-conversion 'ctext-pre-write-conversion) | |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1422 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1423 (define-coding-system-alias |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1424 'x-ctext-with-extensions 'compound-text-with-extensions) |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1425 (define-coding-system-alias |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1426 'ctext-with-extensions 'compound-text-with-extensions) |
33221
22ea1d0f7521
(compound-text): Define this coding system here. Make x-ctext and
Kenichi Handa <handa@m17n.org>
parents:
33044
diff
changeset
|
1427 |
88411 | 1428 (define-coding-system 'us-ascii |
89483 | 1429 "Encode ASCII as-is and encode non-ASCII characters to `?'." |
88411 | 1430 :coding-type 'charset |
1431 :mnemonic ?- | |
1432 :charset-list '(ascii) | |
1433 :default-char ?? | |
1434 :mime-charset 'us-ascii) | |
19266
a042f26b7a4c
(iso-safe): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
19005
diff
changeset
|
1435 |
88411 | 1436 (define-coding-system-alias 'iso-safe 'us-ascii) |
46492
4bc90b6a952f
(us-ascii): Define it as an alias of iso-safe.
Kenichi Handa <handa@m17n.org>
parents:
43929
diff
changeset
|
1437 |
89426 | 1438 (define-coding-system 'utf-7 |
1439 "UTF-7 encoding of Unicode (RFC 2152)." | |
1440 :coding-type 'utf-8 | |
1441 :mnemonic ?U | |
1442 :mime-charset 'utf-7 | |
1443 :charset-list '(unicode) | |
1444 :pre-write-conversion 'utf-7-pre-write-conversion | |
1445 :post-read-conversion 'utf-7-post-read-conversion) | |
50118
c38bf27db0aa
(iso-latin-1): Moved from european.el.
Kenichi Handa <handa@m17n.org>
parents:
49598
diff
changeset
|
1446 |
91116
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1447 (define-coding-system 'utf-7-imap |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1448 "UTF-7 encoding of Unicode, IMAP version (RFC 2060)" |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1449 :coding-type 'utf-8 |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1450 :mnemonic ?u |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1451 :charset-list '(unicode) |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1452 :pre-write-conversion 'utf-7-imap-pre-write-conversion |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1453 :post-read-conversion 'utf-7-imap-post-read-conversion) |
50118
c38bf27db0aa
(iso-latin-1): Moved from european.el.
Kenichi Handa <handa@m17n.org>
parents:
49598
diff
changeset
|
1454 |
88411 | 1455 ;; Use us-ascii for terminal output if some other coding system is not |
23196 | 1456 ;; specified explicitly. |
88411 | 1457 (set-safe-terminal-coding-system-internal 'us-ascii) |
19266
a042f26b7a4c
(iso-safe): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
19005
diff
changeset
|
1458 |
17070 | 1459 ;; The other coding-systems are defined in each language specific |
88411 | 1460 ;; files under lisp/language. |
17070 | 1461 |
21713
aa160e4358ac
(file-coding-system-alist): Use emacs-mule for .elc files.
Richard M. Stallman <rms@gnu.org>
parents:
20732
diff
changeset
|
1462 ;; Normally, set coding system to `undecided' before reading a file. |
aa160e4358ac
(file-coding-system-alist): Use emacs-mule for .elc files.
Richard M. Stallman <rms@gnu.org>
parents:
20732
diff
changeset
|
1463 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all, |
aa160e4358ac
(file-coding-system-alist): Use emacs-mule for .elc files.
Richard M. Stallman <rms@gnu.org>
parents:
20732
diff
changeset
|
1464 ;; but we regard them as containing multibyte characters. |
aa160e4358ac
(file-coding-system-alist): Use emacs-mule for .elc files.
Richard M. Stallman <rms@gnu.org>
parents:
20732
diff
changeset
|
1465 ;; Tar files are not decoded at all, but we treat them as raw bytes. |
17070 | 1466 |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1467 (setq file-coding-system-alist |
88776
805a3bb7daf4
(file-coding-system-alist): Change
Dave Love <fx@gnu.org>
parents:
88760
diff
changeset
|
1468 '(("\\.elc\\'" . utf-8-emacs) |
42047
83eb799f3657
(translation-table-for-input): New
Dave Love <fx@gnu.org>
parents:
41468
diff
changeset
|
1469 ("\\.utf\\(-8\\)?\\'" . utf-8) |
91922
89b7a215ead9
* international/mule.el (sgml-xml-auto-coding-function): Detect
Jason Rumney <jasonr@gnu.org>
parents:
91327
diff
changeset
|
1470 ("\\.xml\\'" . xml-find-file-coding-system) |
34264
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1471 ;; We use raw-text for reading loaddefs.el so that if it |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1472 ;; happens to have DOS or Mac EOLs, they are converted to |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1473 ;; newlines. This is required to make the special treatment |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1474 ;; of the "\ newline" combination in loaddefs.el, which marks |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1475 ;; the beginning of a doc string, work. |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1476 ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix)) |
32228
6a5bae3ed1c1
file-coding-system-alist): Use \',
Dave Love <fx@gnu.org>
parents:
30260
diff
changeset
|
1477 ("\\.tar\\'" . (no-conversion . no-conversion)) |
43929
75ed7127d6fc
(file-coding-system-alist): Add an association for PO files.
Eli Zaretskii <eliz@gnu.org>
parents:
43552
diff
changeset
|
1478 ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system) |
61933
e555645f13f4
(file-coding-system-alist): Fix regexp for latexenc.
Stefan Monnier <monnier@iro.umontreal.ca>
parents:
61912
diff
changeset
|
1479 ("\\.\\(tex\\|ltx\\|dtx\\|drv\\)\\'" . latexenc-find-file-coding-system) |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1480 ("" . (undecided . nil)))) |
17070 | 1481 |
1482 | |
1483 ;;; Setting coding categories and their priorities. | |
1484 | |
1485 ;; This setting is just to read an Emacs Lisp source files which | |
1486 ;; contain multilingual text while dumping Emacs. More appropriate | |
18302
6fbbef4e6c39
Change mnemonic letters for iso-2022-7bit-ss2 and
Kenichi Handa <handa@m17n.org>
parents:
18196
diff
changeset
|
1487 ;; values are set by the command `set-language-environment' for each |
17070 | 1488 ;; language environment. |
1489 | |
88411 | 1490 (set-coding-system-priority |
1491 'iso-latin-1 | |
1492 'utf-8 | |
1493 'iso-2022-7bit | |
1494 ) | |
17070 | 1495 |
19372 | 1496 |
1497 ;;; Miscellaneous settings. | |
88411 | 1498 |
1499 ;; Make all multibyte characters self-insert. | |
1500 (set-char-table-range (nth 1 global-map) | |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
1501 (cons 128 (max-char)) |
88411 | 1502 'self-insert-command) |
1503 | |
50511
5930672784ee
Register ?\221 and ?\226 in latin-extra-code-table.
Kenichi Handa <handa@m17n.org>
parents:
50488
diff
changeset
|
1504 (aset latin-extra-code-table ?\221 t) |
19372 | 1505 (aset latin-extra-code-table ?\222 t) |
35187
cb583146cc55
(latin-extra-code-table): Set to t for \223 and \224.
Kenichi Handa <handa@m17n.org>
parents:
34264
diff
changeset
|
1506 (aset latin-extra-code-table ?\223 t) |
cb583146cc55
(latin-extra-code-table): Set to t for \223 and \224.
Kenichi Handa <handa@m17n.org>
parents:
34264
diff
changeset
|
1507 (aset latin-extra-code-table ?\224 t) |
50488
a23ddd4b5a0b
Register ?\225 in latin-extra-code-table.
Kenichi Handa <handa@m17n.org>
parents:
50182
diff
changeset
|
1508 (aset latin-extra-code-table ?\225 t) |
50511
5930672784ee
Register ?\221 and ?\226 in latin-extra-code-table.
Kenichi Handa <handa@m17n.org>
parents:
50488
diff
changeset
|
1509 (aset latin-extra-code-table ?\226 t) |
19372 | 1510 |
88600 | 1511 ;; The old code-pages library is obsoleted by coding systems based on |
1512 ;; the charsets defined in this file but might be required by user | |
1513 ;; code. | |
1514 (provide 'code-pages) | |
1515 | |
88575 | 1516 ;; Local variables: |
1517 ;; no-byte-compile: t | |
1518 ;; End: | |
23260
1e8cac8d2c50
Call update-coding-systems-internal at the tail.
Kenichi Handa <handa@m17n.org>
parents:
23196
diff
changeset
|
1519 |
61698
19c94353380d
(translation-table-for-input): Remove redundant declaration.
Stefan Monnier <monnier@iro.umontreal.ca>
parents:
53241
diff
changeset
|
1520 ;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5 |
17070 | 1521 ;;; mule-conf.el ends here |