Mercurial > emacs
annotate lisp/international/mule-conf.el @ 100625:4655d81daa9a
2008-12-21 Carsten Dominik <dominik@science.uva.nl>
* org-export-latex.el (org-export-latex-special-chars): Handle
case where there is no match group 3.
author | Carsten Dominik <dominik@science.uva.nl> |
---|---|
date | Sun, 21 Dec 2008 10:03:15 +0000 |
parents | 260217a5e2e4 |
children | a9dc0e7c3f2b |
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 ;; | |
95262
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
71 ;; (define-charset 'emacs |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
72 ;; "" |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
73 ;; :dimension 3 |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
74 ;; :code-space [0 255 0 255 0 63] |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
75 ;; :ascii-compatible-p t |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
76 ;; :supplementary-p t |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
77 ;; :code-offset 0) |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
78 ;; |
89089 | 79 ;; (define-charset 'eight-bit |
80 ;; "" | |
81 ;; :dimension 1 | |
82 ;; :code-space [128 255] | |
83 ;; :code-offset #x3FFF80) | |
84 ;; | |
88411 | 85 ;; We now set :docstring, :short-name, and :long-name properties. |
86 | |
87 (put-charset-property | |
88 'ascii :docstring "ASCII (ISO646 IRV)") | |
89 (put-charset-property | |
90 'ascii :short-name "ASCII") | |
91 (put-charset-property | |
92 'ascii :long-name "ASCII (ISO646 IRV)") | |
93 (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
|
94 '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
|
95 (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
|
96 '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
|
97 (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
|
98 '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
|
99 (put-charset-property |
88411 | 100 'unicode :docstring "Unicode (ISO10646)") |
101 (put-charset-property | |
102 'unicode :short-name "Unicode") | |
103 (put-charset-property | |
104 'unicode :long-name "Unicode (ISO10646)") | |
95262
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
105 (put-charset-property |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
106 'emacs :docstring "Full Emacs charset (excluding eight bit chars)") |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
107 (put-charset-property |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
108 'emacs :short-name "Emacs") |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
109 (put-charset-property |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
110 'emacs :long-name "Emacs") |
1e646032185f
Don't define the charset `emacs'
Kenichi Handa <handa@m17n.org>
parents:
94664
diff
changeset
|
111 |
89089 | 112 (put-charset-property 'eight-bit :docstring "Raw bytes 0-255") |
113 (put-charset-property 'eight-bit :short-name "Raw bytes") | |
17070 | 114 |
88411 | 115 (define-charset-alias 'ucs 'unicode) |
116 | |
117 (define-charset 'latin-iso8859-1 | |
118 "Right-Hand Part of ISO/IEC 8859/1 (Latin-1): ISO-IR-100" | |
119 :short-name "RHP of Latin-1" | |
120 :long-name "RHP of ISO/IEC 8859/1 (Latin-1): ISO-IR-100" | |
121 :iso-final-char ?A | |
122 :emacs-mule-id 129 | |
123 :code-space [32 127] | |
124 :code-offset 160) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
125 |
88735 | 126 ;; Name perhaps not ideal, but is XEmacs-compatible. |
127 (define-charset 'control-1 | |
88411 | 128 "8-bit control code (0x80..0x9F)" |
129 :short-name "8-bit control code" | |
130 :code-space [128 159] | |
131 :code-offset 128) | |
132 | |
88735 | 133 (define-charset 'eight-bit-control |
134 "Raw bytes in the range 0x80..0x9F (usually produced from invalid encodings)" | |
135 :short-name "Raw bytes 0x80..0x9F" | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
136 :supplementary-p t |
88735 | 137 :code-space [128 159] |
138 :code-offset #x3FFF80) ; see character.h | |
139 | |
88411 | 140 (define-charset 'eight-bit-graphic |
88735 | 141 "Raw bytes in the range 0xA0..0xFF (usually produced from invalid encodings)" |
142 :short-name "Raw bytes 0xA0..0xFF" | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
143 :supplementary-p t |
88411 | 144 :code-space [160 255] |
88735 | 145 :code-offset #x3FFFA0) ; see character.h |
17070 | 146 |
88411 | 147 (defmacro define-iso-single-byte-charset (symbol iso-symbol name nickname |
148 iso-ir iso-final | |
149 emacs-mule-id map) | |
150 `(progn | |
151 (define-charset ,symbol | |
152 ,name | |
153 :short-name ,nickname | |
154 :long-name ,name | |
155 :ascii-compatible-p t | |
156 :code-space [0 255] | |
157 :map ,map) | |
158 (if ,iso-symbol | |
159 (define-charset ,iso-symbol | |
160 (if ,iso-ir | |
161 (format "Right-Hand Part of %s (%s): ISO-IR-%d" | |
162 ,name ,nickname ,iso-ir) | |
163 (format "Right-Hand Part of %s (%s)" ,name ,nickname)) | |
164 :short-name (format "RHP of %s" ,name) | |
165 :long-name (format "RHP of %s (%s)" ,name ,nickname) | |
166 :iso-final-char ,iso-final | |
88486 | 167 :emacs-mule-id ,emacs-mule-id |
88411 | 168 :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
|
169 :subset (list ,symbol 160 255 -128))))) |
88411 | 170 |
171 (define-iso-single-byte-charset 'iso-8859-2 'latin-iso8859-2 | |
172 "ISO/IEC 8859/2" "Latin-2" 101 ?B 130 "8859-2") | |
173 | |
174 (define-iso-single-byte-charset 'iso-8859-3 'latin-iso8859-3 | |
175 "ISO/IEC 8859/3" "Latin-3" 109 ?C 131 "8859-3") | |
176 | |
177 (define-iso-single-byte-charset 'iso-8859-4 'latin-iso8859-4 | |
178 "ISO/IEC 8859/4" "Latin-4" 110 ?D 132 "8859-4") | |
179 | |
180 (define-iso-single-byte-charset 'iso-8859-5 'cyrillic-iso8859-5 | |
181 "ISO/IEC 8859/5" "Latin/Cyrillic" 144 ?L 140 "8859-5") | |
182 | |
183 (define-iso-single-byte-charset 'iso-8859-6 'arabic-iso8859-6 | |
184 "ISO/IEC 8859/6" "Latin/Arabic" 127 ?G 135 "8859-6") | |
185 | |
186 (define-iso-single-byte-charset 'iso-8859-7 'greek-iso8859-7 | |
187 "ISO/IEC 8859/7" "Latin/Greek" 126 ?F 134 "8859-7") | |
188 | |
189 (define-iso-single-byte-charset 'iso-8859-8 'hebrew-iso8859-8 | |
190 "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H 136 "8859-8") | |
191 | |
192 (define-iso-single-byte-charset 'iso-8859-9 'latin-iso8859-9 | |
193 "ISO/IEC 8859/9" "Latin-5" 148 ?M 141 "8859-9") | |
17070 | 194 |
88575 | 195 (define-iso-single-byte-charset 'iso-8859-10 'latin-iso8859-10 |
88671 | 196 "ISO/IEC 8859/10" "Latin-6" 157 ?V nil "8859-10") |
88575 | 197 |
88671 | 198 ;; http://www.nectec.or.th/it-standards/iso8859-11/ |
199 ;; http://www.cwi.nl/~dik/english/codes/8859.html says this is tis-620 | |
200 ;; plus nbsp | |
201 (define-iso-single-byte-charset 'iso-8859-11 'thai-iso8859-11 | |
202 "ISO/IEC 8859/11" "Latin/Thai" 166 ?T nil "8859-11") | |
203 | |
204 ;; 8859-12 doesn't (yet?) exist. | |
88575 | 205 |
88411 | 206 (define-iso-single-byte-charset 'iso-8859-13 'latin-iso8859-13 |
88575 | 207 "ISO/IEC 8859/13" "Latin-7" 179 ?Y nil "8859-13") |
88411 | 208 |
209 (define-iso-single-byte-charset 'iso-8859-14 'latin-iso8859-14 | |
210 "ISO/IEC 8859/14" "Latin-8" 199 ?_ 143 "8859-14") | |
211 | |
212 (define-iso-single-byte-charset 'iso-8859-15 'latin-iso8859-15 | |
213 "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
|
214 |
88565 | 215 (define-iso-single-byte-charset 'iso-8859-16 'latin-iso8859-16 |
88638 | 216 "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
|
217 |
88647 | 218 ;; No point in keeping it around. |
219 (fmakunbound 'define-iso-single-byte-charset) | |
220 | |
88671 | 221 ;; Can this be shared with 8859-11? |
89089 | 222 ;; N.b. not all of these are defined unicodes. |
88411 | 223 (define-charset 'thai-tis620 |
224 "TIS620.2533" | |
225 :short-name "TIS620.2533" | |
226 :iso-final-char ?T | |
227 :emacs-mule-id 133 | |
228 :code-space [32 127] | |
229 :code-offset #x0E00) | |
230 | |
88671 | 231 ;; Fixme: doc for this, c.f. above |
88411 | 232 (define-charset 'tis620-2533 |
233 "TIS620.2533" | |
234 :short-name "TIS620.2533" | |
235 :ascii-compatible-p t | |
236 :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
|
237 :superset '(ascii eight-bit-control (thai-tis620 . 128))) |
88411 | 238 |
239 (define-charset 'jisx0201 | |
240 "JISX0201" | |
241 :short-name "JISX0201" | |
89483 | 242 :code-space [0 #xDF] |
243 :map "JISX0201") | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
244 |
88411 | 245 (define-charset 'latin-jisx0201 |
246 "Roman Part of JISX0201.1976" | |
247 :short-name "JISX0201 Roman" | |
248 :long-name "Japanese Roman (JISX0201.1976)" | |
249 :iso-final-char ?J | |
250 :emacs-mule-id 138 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
251 :supplementary-p t |
88411 | 252 :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
|
253 :subset '(jisx0201 33 126 0)) |
88411 | 254 |
255 (define-charset 'katakana-jisx0201 | |
256 "Katakana Part of JISX0201.1976" | |
257 :short-name "JISX0201 Katakana" | |
258 :long-name "Japanese Katakana (JISX0201.1976)" | |
259 :iso-final-char ?I | |
260 :emacs-mule-id 137 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
261 :supplementary-p t |
88411 | 262 :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
|
263 :subset '(jisx0201 161 254 -128)) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
264 |
88411 | 265 (define-charset 'chinese-gb2312 |
266 "GB2312 Chinese simplified: ISO-IR-58" | |
267 :short-name "GB2312" | |
268 :long-name "GB2312: ISO-IR-58" | |
269 :iso-final-char ?A | |
270 :emacs-mule-id 145 | |
271 :code-space [33 126 33 126] | |
272 :code-offset #x110000 | |
89483 | 273 :unify-map "GB2312") |
88411 | 274 |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
275 (define-charset 'chinese-gbk |
88486 | 276 "GBK Chinese simplified." |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
277 :short-name "GBK" |
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
278 :code-space [#x40 #xFE #x81 #xFE] |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
279 :code-offset #x160000 |
89483 | 280 :unify-map "GBK") |
88666 | 281 (define-charset-alias 'cp936 'chinese-gbk) |
88717 | 282 (define-charset-alias 'windows-936 'chinese-gbk) |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
283 |
88411 | 284 (define-charset 'chinese-cns11643-1 |
285 "CNS11643 Plane 1 Chinese traditional: ISO-IR-171" | |
286 :short-name "CNS11643-1" | |
287 :long-name "CNS11643-1 (Chinese traditional): ISO-IR-171" | |
288 :iso-final-char ?G | |
289 :emacs-mule-id 149 | |
290 :code-space [33 126 33 126] | |
291 :code-offset #x114000 | |
89483 | 292 :unify-map "CNS-1") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
293 |
88411 | 294 (define-charset 'chinese-cns11643-2 |
295 "CNS11643 Plane 2 Chinese traditional: ISO-IR-172" | |
296 :short-name "CNS11643-2" | |
297 :long-name "CNS11643-2 (Chinese traditional): ISO-IR-172" | |
298 :iso-final-char ?H | |
299 :emacs-mule-id 150 | |
300 :code-space [33 126 33 126] | |
301 :code-offset #x118000 | |
89483 | 302 :unify-map "CNS-2") |
88411 | 303 |
304 (define-charset 'chinese-cns11643-3 | |
305 "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183" | |
306 :short-name "CNS11643-3" | |
307 :long-name "CNS11643-3 (Chinese traditional): ISO-IR-183" | |
308 :iso-final-char ?I | |
309 :code-space [33 126 33 126] | |
310 :emacs-mule-id 246 | |
89483 | 311 :code-offset #x11C000 |
312 :unify-map "CNS-3") | |
88411 | 313 |
314 (define-charset 'chinese-cns11643-4 | |
315 "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184" | |
316 :short-name "CNS11643-4" | |
317 :long-name "CNS11643-4 (Chinese traditional): ISO-IR-184" | |
318 :iso-final-char ?J | |
319 :emacs-mule-id 247 | |
320 :code-space [33 126 33 126] | |
89483 | 321 :code-offset #x120000 |
322 :unify-map "CNS-4") | |
88411 | 323 |
324 (define-charset 'chinese-cns11643-5 | |
325 "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185" | |
326 :short-name "CNS11643-5" | |
327 :long-name "CNS11643-5 (Chinese traditional): ISO-IR-185" | |
328 :iso-final-char ?K | |
329 :emacs-mule-id 248 | |
330 :code-space [33 126 33 126] | |
89483 | 331 :code-offset #x124000 |
332 :unify-map "CNS-5") | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
333 |
88411 | 334 (define-charset 'chinese-cns11643-6 |
335 "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186" | |
336 :short-name "CNS11643-6" | |
337 :long-name "CNS11643-6 (Chinese traditional): ISO-IR-186" | |
338 :iso-final-char ?L | |
339 :emacs-mule-id 249 | |
340 :code-space [33 126 33 126] | |
89483 | 341 :code-offset #x128000 |
342 :unify-map "CNS-6") | |
88411 | 343 |
344 (define-charset 'chinese-cns11643-7 | |
345 "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187" | |
346 :short-name "CNS11643-7" | |
347 :long-name "CNS11643-7 (Chinese traditional): ISO-IR-187" | |
348 :iso-final-char ?M | |
349 :emacs-mule-id 250 | |
350 :code-space [33 126 33 126] | |
89483 | 351 :code-offset #x12C000 |
352 :unify-map "CNS-7") | |
88411 | 353 |
354 (define-charset 'big5 | |
355 "Big5 (Chinese traditional)" | |
356 :short-name "Big5" | |
357 :code-space [#x40 #xFE #xA1 #xFE] | |
358 :code-offset #x130000 | |
89483 | 359 :unify-map "BIG5") |
88666 | 360 ;; Fixme: AKA cp950 according to |
361 ;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>. Is | |
362 ;; that correct? | |
88411 | 363 |
364 (define-charset 'chinese-big5-1 | |
88486 | 365 "Frequently used part (A141-C67E) of Big5 (Chinese traditional)" |
88411 | 366 :short-name "Big5 (Level-1)" |
367 :long-name "Big5 (Level-1) A141-C67F" | |
368 :iso-final-char ?0 | |
369 :emacs-mule-id 152 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
370 :supplementary-p t |
88411 | 371 :code-space [#x21 #x7E #x21 #x7E] |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
372 :code-offset #x135000 |
89483 | 373 :unify-map "BIG5-1") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
374 |
88411 | 375 (define-charset 'chinese-big5-2 |
88486 | 376 "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)" |
88411 | 377 :short-name "Big5 (Level-2)" |
378 :long-name "Big5 (Level-2) C940-FEFE" | |
379 :iso-final-char ?1 | |
380 :emacs-mule-id 153 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
381 :supplementary-p t |
88411 | 382 :code-space [#x21 #x7E #x21 #x7E] |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
383 :code-offset #x137800 |
89483 | 384 :unify-map "BIG5-2") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
385 |
88411 | 386 (define-charset 'japanese-jisx0208 |
387 "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87" | |
388 :short-name "JISX0208" | |
389 :long-name "JISX0208.1983/1990 (Japanese): ISO-IR-87" | |
390 :iso-final-char ?B | |
391 :emacs-mule-id 146 | |
392 :code-space [33 126 33 126] | |
393 :code-offset #x140000 | |
89483 | 394 :unify-map "JISX0208") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
395 |
88411 | 396 (define-charset 'japanese-jisx0208-1978 |
397 "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42" | |
398 :short-name "JISX0208.1978" | |
89483 | 399 :long-name "JISX0208.1978 (JISC6226.1978): ISO-IR-42" |
88411 | 400 :iso-final-char ?@ |
401 :emacs-mule-id 144 | |
402 :code-space [33 126 33 126] | |
403 :code-offset #x144000 | |
89483 | 404 :unify-map "JISC6226") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
405 |
88411 | 406 (define-charset 'japanese-jisx0212 |
407 "JISX0212 Japanese supplement: ISO-IR-159" | |
408 :short-name "JISX0212" | |
409 :long-name "JISX0212 (Japanese): ISO-IR-159" | |
410 :iso-final-char ?D | |
411 :emacs-mule-id 148 | |
412 :code-space [33 126 33 126] | |
413 :code-offset #x148000 | |
89483 | 414 :unify-map "JISX0212") |
88411 | 415 |
89426 | 416 ;; Note that jisx0213 contains characters not in Unicode (3.2?). It's |
417 ;; arguable whether it should have a unify-map. | |
88411 | 418 (define-charset 'japanese-jisx0213-1 |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
419 "JISX0213.2000 Plane 1 (Japanese)" |
88411 | 420 :short-name "JISX0213-1" |
421 :iso-final-char ?O | |
422 :emacs-mule-id 151 | |
89483 | 423 :unify-map "JISX2131" |
88411 | 424 :code-space [33 126 33 126] |
425 :code-offset #x14C000) | |
17070 | 426 |
88411 | 427 (define-charset 'japanese-jisx0213-2 |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
428 "JISX0213.2000 Plane 2 (Japanese)" |
88411 | 429 :short-name "JISX0213-2" |
430 :iso-final-char ?P | |
431 :emacs-mule-id 254 | |
89483 | 432 :unify-map "JISX2132" |
88411 | 433 :code-space [33 126 33 126] |
434 :code-offset #x150000) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
435 |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
436 (define-charset 'japanese-jisx0213-a |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
437 "JISX0213.2004 adds these characters to JISX0213.2000." |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
438 :short-name "JISX0213A" |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
439 :dimension 2 |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
440 :code-space [33 126 33 126] |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
441 :supplementary-p t |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
442 :map "JISX213A") |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
443 |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
444 (define-charset 'japanese-jisx0213.2004-1 |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
445 "JISX0213.2004 Plane1 (Japanese)" |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
446 :short-name "JISX0213.2004-1" |
89793
cdb516af172d
(japanese-jisx0213.2004-1): Specify :dimension 2.
Kenichi Handa <handa@m17n.org>
parents:
89766
diff
changeset
|
447 :dimension 2 |
89797
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
448 :code-space [33 126 33 126] |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
449 :iso-final-char ?Q |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
450 :superset '(japanese-jisx0213-a japanese-jisx0213-1)) |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
451 |
89734
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
452 (define-charset 'katakana-sjis |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
453 "Katakana part of Shift-JIS" |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
454 :dimension 1 |
89753
d91d2d88af05
(katakana-sjis): Fix :superset to :subset.
Kenichi Handa <handa@m17n.org>
parents:
89741
diff
changeset
|
455 :code-space [#xA1 #xDF] |
d91d2d88af05
(katakana-sjis): Fix :superset to :subset.
Kenichi Handa <handa@m17n.org>
parents:
89741
diff
changeset
|
456 :subset '(jisx0201 #xA1 #xDF 0) |
89734
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
457 :supplementary-p t) |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
458 |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
459 (define-charset 'cp932-2-byte |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
460 "2-byte part of CP932" |
89741
fb91cfc5ed37
(cp932-2-byte): Specify :dimension.
Kenichi Handa <handa@m17n.org>
parents:
89734
diff
changeset
|
461 :dimension 2 |
89734
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
462 :map "CP932-2BYTE" |
89926
c452bfea1458
(cp932-2-byte): Fix :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89909
diff
changeset
|
463 :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
|
464 :supplementary-p t) |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
465 |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
466 (define-charset 'cp932 |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
467 "CP932 (Microsoft shift-jis)" |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
468 :code-space [#x00 #xFF #x00 #xFE] |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
469 :short-name "CP932" |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
470 :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
|
471 |
88411 | 472 (define-charset 'korean-ksc5601 |
473 "KSC5601 Korean Hangul and Hanja: ISO-IR-149" | |
474 :short-name "KSC5601" | |
475 :long-name "KSC5601 (Korean): ISO-IR-149" | |
476 :iso-final-char ?C | |
477 :emacs-mule-id 147 | |
478 :code-space [33 126 33 126] | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
479 :code-offset #x279f94 ; ... #x27c217 |
89483 | 480 :unify-map "KSC5601") |
17070 | 481 |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
482 (define-charset 'big5-hkscs |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
483 "Big5-HKSCS (Chinese traditional, Hong Kong supplement)" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
484 :short-name "Big5" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
485 :code-space [#x40 #xFE #xA1 #xFE] |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
486 :code-offset #x27c218 ; ... #x280839 |
89483 | 487 :unify-map "BIG5-HKSCS") |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
488 |
88666 | 489 ;; Fixme: Korean cp949/UHC |
490 | |
88411 | 491 (define-charset 'chinese-sisheng |
492 "SiSheng characters for PinYin/ZhuYin" | |
493 :short-name "SiSheng" | |
494 :long-name "SiSheng (PinYin/ZhuYin)" | |
495 :iso-final-char ?0 | |
496 :emacs-mule-id 160 | |
497 :code-space [33 126] | |
89483 | 498 :unify-map "MULE-sisheng" |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
499 :supplementary-p t |
88411 | 500 :code-offset #x200000) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
501 |
88735 | 502 ;; A subset of the 1989 version of IPA. It consists of the consonant |
503 ;; signs used in English, French, German and Italian, and all vowels | |
504 ;; signs in the table. [says old MULE doc] | |
88411 | 505 (define-charset 'ipa |
506 "IPA (International Phonetic Association)" | |
507 :short-name "IPA" | |
508 :iso-final-char ?0 | |
509 :emacs-mule-id 161 | |
89483 | 510 :unify-map "MULE-ipa" |
88411 | 511 :code-space [32 127] |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
512 :supplementary-p t |
88411 | 513 :code-offset #x200080) |
17070 | 514 |
88411 | 515 (define-charset 'viscii |
516 "VISCII1.1" | |
517 :short-name "VISCII" | |
518 :long-name "VISCII 1.1" | |
519 :code-space [0 255] | |
89483 | 520 :map "VISCII") |
88411 | 521 |
522 (define-charset 'vietnamese-viscii-lower | |
523 "VISCII1.1 lower-case" | |
524 :short-name "VISCII lower" | |
525 :long-name "VISCII lower-case" | |
526 :iso-final-char ?1 | |
527 :emacs-mule-id 162 | |
528 :code-space [32 127] | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
529 :code-offset #x200200 |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
530 :supplementary-p t |
89483 | 531 :unify-map "MULE-lviscii") |
17070 | 532 |
88411 | 533 (define-charset 'vietnamese-viscii-upper |
534 "VISCII1.1 upper-case" | |
535 :short-name "VISCII upper" | |
536 :long-name "VISCII upper-case" | |
537 :iso-final-char ?2 | |
538 :emacs-mule-id 163 | |
539 :code-space [32 127] | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
540 :code-offset #x200280 |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
541 :supplementary-p t |
89483 | 542 :unify-map "MULE-uviscii") |
88411 | 543 |
544 (define-charset 'vscii | |
89483 | 545 "VSCII1.1 (TCVN-5712 VN1)" |
88411 | 546 :short-name "VSCII" |
547 :code-space [0 255] | |
89483 | 548 :map "VSCII") |
549 | |
550 (define-charset-alias 'tcvn-5712 'vscii) | |
88411 | 551 |
88727 | 552 ;; Fixme: see note in tcvn.map about combining characters |
89483 | 553 (define-charset 'vscii-2 |
554 "VSCII-2 (TCVN-5712 VN2)" | |
88727 | 555 :code-space [0 255] |
89483 | 556 :map "VSCII-2") |
88727 | 557 |
88411 | 558 (define-charset 'koi8-r |
559 "KOI8-R" | |
560 :short-name "KOI8-R" | |
561 :ascii-compatible-p t | |
562 :code-space [0 255] | |
89483 | 563 :map "KOI8-R") |
88411 | 564 |
565 (define-charset-alias 'koi8 'koi8-r) | |
566 | |
567 (define-charset 'alternativnyj | |
568 "ALTERNATIVNYJ" | |
569 :short-name "alternativnyj" | |
570 :ascii-compatible-p t | |
571 :code-space [0 255] | |
89483 | 572 :map "ALTERNATIVNYJ") |
89200 | 573 |
574 (define-charset 'cp866 | |
575 "CP866" | |
576 :short-name "cp866" | |
577 :ascii-compatible-p t | |
578 :code-space [0 255] | |
89483 | 579 :map "IBM866") |
89200 | 580 (define-charset-alias 'ibm866 'cp866) |
17070 | 581 |
88533 | 582 (define-charset 'koi8-u |
583 "KOI8-U" | |
584 :short-name "KOI8-U" | |
585 :ascii-compatible-p t | |
586 :code-space [0 255] | |
89483 | 587 :map "KOI8-U") |
88533 | 588 |
589 (define-charset 'koi8-t | |
590 "KOI8-T" | |
591 :short-name "KOI8-T" | |
592 :ascii-compatible-p t | |
593 :code-space [0 255] | |
89483 | 594 :map "KOI8-T") |
88533 | 595 |
596 (define-charset 'georgian-ps | |
597 "GEORGIAN-PS" | |
598 :short-name "GEORGIAN-PS" | |
599 :ascii-compatible-p t | |
600 :code-space [0 255] | |
89483 | 601 :map "KA-PS") |
88533 | 602 |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
603 (define-charset 'georgian-academy |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
604 "GEORGIAN-ACADEMY" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
605 :short-name "GEORGIAN-ACADEMY" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
606 :ascii-compatible-p t |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
607 :code-space [0 255] |
89483 | 608 :map "KA-ACADEMY") |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
609 |
88533 | 610 (define-charset 'windows-1250 |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
611 "WINDOWS-1250 (Central Europe)" |
88533 | 612 :short-name "WINDOWS-1250" |
613 :ascii-compatible-p t | |
614 :code-space [0 255] | |
89483 | 615 :map "CP1250") |
88533 | 616 (define-charset-alias 'cp1250 'windows-1250) |
617 | |
618 (define-charset 'windows-1251 | |
88666 | 619 "WINDOWS-1251 (Cyrillic)" |
88533 | 620 :short-name "WINDOWS-1251" |
621 :ascii-compatible-p t | |
622 :code-space [0 255] | |
89483 | 623 :map "CP1251") |
88533 | 624 (define-charset-alias 'cp1251 'windows-1251) |
17070 | 625 |
88533 | 626 (define-charset 'windows-1252 |
88666 | 627 "WINDOWS-1252 (Latin I)" |
88533 | 628 :short-name "WINDOWS-1252" |
629 :ascii-compatible-p t | |
630 :code-space [0 255] | |
89483 | 631 :map "CP1252") |
88533 | 632 (define-charset-alias 'cp1252 'windows-1252) |
633 | |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
634 (define-charset 'windows-1253 |
88666 | 635 "WINDOWS-1253 (Greek)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
636 :short-name "WINDOWS-1253" |
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 "CP1253") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
640 (define-charset-alias 'cp1253 'windows-1253) |
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-1254 |
88666 | 643 "WINDOWS-1254 (Turkish)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
644 :short-name "WINDOWS-1254" |
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 "CP1254") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
648 (define-charset-alias 'cp1254 'windows-1254) |
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-1255 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
651 "WINDOWS-1255 (Hebrew)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
652 :short-name "WINDOWS-1255" |
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 "CP1255") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
656 (define-charset-alias 'cp1255 'windows-1255) |
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-1256 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
659 "WINDOWS-1256 (Arabic)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
660 :short-name "WINDOWS-1256" |
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 "CP1256") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
664 (define-charset-alias 'cp1256 'windows-1256) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
665 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
666 (define-charset 'windows-1257 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
667 "WINDOWS-1257 (Baltic)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
668 :short-name "WINDOWS-1257" |
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 "CP1257") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
672 (define-charset-alias 'cp1257 'windows-1257) |
17070 | 673 |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
674 (define-charset 'windows-1258 |
88666 | 675 "WINDOWS-1258 (Viet Nam)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
676 :short-name "WINDOWS-1258" |
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 "CP1258") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
680 (define-charset-alias 'cp1258 'windows-1258) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
681 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
682 (define-charset 'next |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
683 "NEXT" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
684 :short-name "NEXT" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
685 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
686 :code-space [0 255] |
89483 | 687 :map "NEXTSTEP") |
17070 | 688 |
88533 | 689 (define-charset 'cp1125 |
690 "CP1125" | |
691 :short-name "CP1125" | |
692 :code-space [0 255] | |
90217
4e5457cf7dc7
(cp1125): Set :ascii-compatible-p property to t.
Kenichi Handa <handa@m17n.org>
parents:
90200
diff
changeset
|
693 :ascii-compatible-p t |
89483 | 694 :map "CP1125") |
88533 | 695 (define-charset-alias 'ruscii 'cp1125) |
696 ;; Original name for cp1125, says Serhii Hlodin <hlodin@lutsk.bank.gov.ua> | |
697 (define-charset-alias 'cp866u 'cp1125) | |
17070 | 698 |
88671 | 699 ;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html |
700 ;; shows this as not ASCII comptaible, with various graphics in | |
701 ;; 0x01-0x1F. | |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
702 (define-charset 'cp437 |
88671 | 703 "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
|
704 :short-name "CP437" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
705 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
706 :ascii-compatible-p t |
89483 | 707 :map "IBM437") |
17070 | 708 |
88666 | 709 (define-charset 'cp720 |
710 "CP720 (Arabic)" | |
711 :short-name "CP720" | |
712 :code-space [0 255] | |
713 :ascii-compatible-p t | |
89483 | 714 :map "CP720") |
88666 | 715 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
716 (define-charset 'cp737 |
88671 | 717 "CP737 (PC Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
718 :short-name "CP737" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
719 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
720 :ascii-compatible-p t |
89483 | 721 :map "CP737") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
722 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
723 (define-charset 'cp775 |
88671 | 724 "CP775 (PC Baltic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
725 :short-name "CP775" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
726 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
727 :ascii-compatible-p t |
89483 | 728 :map "CP775") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
729 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
730 (define-charset 'cp851 |
89089 | 731 "CP851 (Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
732 :short-name "CP851" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
733 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
734 :ascii-compatible-p t |
89483 | 735 :map "IBM851") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
736 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
737 (define-charset 'cp852 |
88671 | 738 "CP852 (MS-DOS Latin-2)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
739 :short-name "CP852" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
740 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
741 :ascii-compatible-p t |
89483 | 742 :map "IBM852") |
17070 | 743 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
744 (define-charset 'cp855 |
88671 | 745 "CP855 (IBM Cyrillic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
746 :short-name "CP855" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
747 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
748 :ascii-compatible-p t |
89483 | 749 :map "IBM855") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
750 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
751 (define-charset 'cp857 |
88671 | 752 "CP857 (IBM Turkish)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
753 :short-name "CP857" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
754 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
755 :ascii-compatible-p t |
89483 | 756 :map "IBM857") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
757 |
88666 | 758 (define-charset 'cp858 |
759 "CP858 (Multilingual Latin I + Euro)" | |
760 :short-name "CP858" | |
761 :code-space [0 255] | |
762 :ascii-compatible-p t | |
89483 | 763 :map "CP858") |
88671 | 764 (define-charset-alias 'cp00858 'cp858) ; IANA has IBM00858/CP00858 |
17070 | 765 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
766 (define-charset 'cp860 |
88671 | 767 "CP860 (MS-DOS Portuguese)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
768 :short-name "CP860" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
769 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
770 :ascii-compatible-p t |
89483 | 771 :map "IBM860") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
772 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
773 (define-charset 'cp861 |
88671 | 774 "CP861 (MS-DOS Icelandic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
775 :short-name "CP861" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
776 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
777 :ascii-compatible-p t |
89483 | 778 :map "IBM861") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
779 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
780 (define-charset 'cp862 |
88671 | 781 "CP862 (PC Hebrew)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
782 :short-name "CP862" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
783 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
784 :ascii-compatible-p t |
89483 | 785 :map "IBM862") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
786 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
787 (define-charset 'cp863 |
88671 | 788 "CP863 (MS-DOS Canadian French)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
789 :short-name "CP863" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
790 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
791 :ascii-compatible-p t |
89483 | 792 :map "IBM863") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
793 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
794 (define-charset 'cp864 |
88671 | 795 "CP864 (PC Arabic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
796 :short-name "CP864" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
797 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
798 :ascii-compatible-p t |
89483 | 799 :map "IBM864") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
800 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
801 (define-charset 'cp865 |
88671 | 802 "CP865 (MS-DOS Nordic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
803 :short-name "CP865" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
804 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
805 :ascii-compatible-p t |
89483 | 806 :map "IBM865") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
807 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
808 (define-charset 'cp869 |
88671 | 809 "CP869 (IBM Modern Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
810 :short-name "CP869" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
811 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
812 :ascii-compatible-p t |
89483 | 813 :map "IBM869") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
814 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
815 (define-charset 'cp874 |
88671 | 816 "CP874 (IBM Thai)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
817 :short-name "CP874" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
818 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
819 :ascii-compatible-p t |
89483 | 820 :map "IBM874") |
17070 | 821 |
822 ;; For Arabic, we need three different types of character sets. | |
823 ;; Digits are of direction left-to-right and of width 1-column. | |
824 ;; Others are of direction right-to-left and of width 1-column or | |
825 ;; 2-column. | |
88411 | 826 (define-charset 'arabic-digit |
827 "Arabic digit" | |
828 :short-name "Arabic digit" | |
829 :iso-final-char ?2 | |
830 :emacs-mule-id 164 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
831 :supplementary-p t |
88411 | 832 :code-space [34 42] |
833 :code-offset #x0600) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
834 |
88411 | 835 (define-charset 'arabic-1-column |
836 "Arabic 1-column" | |
837 :short-name "Arabic 1-col" | |
838 :long-name "Arabic 1-column" | |
839 :iso-final-char ?3 | |
840 :emacs-mule-id 165 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
841 :supplementary-p t |
88411 | 842 :code-space [33 126] |
843 :code-offset #x200100) | |
844 | |
845 (define-charset 'arabic-2-column | |
846 "Arabic 2-column" | |
847 :short-name "Arabic 2-col" | |
848 :long-name "Arabic 2-column" | |
849 :iso-final-char ?4 | |
850 :emacs-mule-id 224 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
851 :supplementary-p t |
88411 | 852 :code-space [33 126] |
853 :code-offset #x200180) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
854 |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
855 ;; Lao script. |
88411 | 856 ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF. |
89089 | 857 ;; Not all of them are defined unicodes. |
88411 | 858 (define-charset 'lao |
859 "Lao characters (ISO10646 0E81..0EDF)" | |
860 :short-name "Lao" | |
861 :iso-final-char ?1 | |
862 :emacs-mule-id 167 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
863 :supplementary-p t |
88411 | 864 :code-space [33 126] |
865 :code-offset #x0E81) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
866 |
88411 | 867 (define-charset 'mule-lao |
868 "Lao characters (ISO10646 0E81..0EDF)" | |
869 :short-name "Lao" | |
870 :code-space [0 255] | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
871 :supplementary-p t |
88751
809b6bfe4dfa
Adjusted for the change of define-charset (:parent -> :subset or
Kenichi Handa <handa@m17n.org>
parents:
88735
diff
changeset
|
872 :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
|
873 |
17070 | 874 |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
875 ;; 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
|
876 ;; 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
|
877 ;; script which IS-13194 supports. |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
878 |
88411 | 879 (define-charset 'indian-is13194 |
880 "Generic Indian charset for data exchange with IS 13194" | |
881 :short-name "IS 13194" | |
882 :long-name "Indian IS 13194" | |
883 :iso-final-char ?5 | |
884 :emacs-mule-id 225 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
885 :supplementary-p t |
88411 | 886 :code-space [33 126] |
887 :code-offset #x180000) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
888 |
89483 | 889 (let ((code-offset #x180100)) |
890 (dolist (script '(devanagari sanskrit bengali tamil telugu assamese | |
891 oriya kannada malayalam gujarati punjabi)) | |
892 (define-charset (intern (format "%s-cdac" script)) | |
893 (format "Glyphs of %s script for CDAC font. Subset of `indian-glyph'." | |
894 (capitalize (symbol-name script))) | |
895 :short-name (format "CDAC %s glyphs" (capitalize (symbol-name script))) | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
896 :supplementary-p t |
89483 | 897 :code-space [0 255] |
898 :code-offset code-offset) | |
899 (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
|
900 |
89483 | 901 (dolist (script '(devanagari bengali punjabi gujarati |
902 oriya tamil telugu kannada malayalam)) | |
903 (define-charset (intern (format "%s-akruti" script)) | |
904 (format "Glyphs of %s script for AKRUTI font. Subset of `indian-glyph'." | |
905 (capitalize (symbol-name script))) | |
906 :short-name (format "AKRUTI %s glyphs" (capitalize (symbol-name script))) | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
907 :supplementary-p t |
89483 | 908 :code-space [0 255] |
909 :code-offset code-offset) | |
910 (setq code-offset (+ code-offset #x100)))) | |
89091 | 911 |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
912 (define-charset 'indian-glyph |
88411 | 913 "Glyphs for Indian characters." |
914 :short-name "Indian glyph" | |
915 :iso-final-char ?4 | |
916 :emacs-mule-id 240 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
917 :supplementary-p t |
88411 | 918 :code-space [32 127 32 127] |
919 :code-offset #x180100) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
920 |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
921 ;; Actual Glyph for 1-column width. |
88411 | 922 (define-charset 'indian-1-column |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
923 "Indian charset for 1-column width glyphs." |
88411 | 924 :short-name "Indian 1-col" |
925 :long-name "Indian 1 Column" | |
926 :iso-final-char ?6 | |
89890
f3047b4ebf04
(indian-1-column): Fix :emacs-mule-id.
Kenichi Handa <handa@m17n.org>
parents:
89822
diff
changeset
|
927 :emacs-mule-id 251 |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
928 :supplementary-p t |
88411 | 929 :code-space [33 126 33 126] |
930 :code-offset #x184000) | |
931 | |
932 ;; Actual Glyph for 2-column width. | |
933 (define-charset 'indian-2-column | |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
934 "Indian charset for 2-column width glyphs." |
88411 | 935 :short-name "Indian 2-col" |
936 :long-name "Indian 2 Column" | |
937 :iso-final-char ?5 | |
938 :emacs-mule-id 251 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
939 :supplementary-p t |
88411 | 940 :code-space [33 126 33 126] |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
941 :code-offset #x184000) |
88411 | 942 |
943 (define-charset 'tibetan | |
944 "Tibetan characters" | |
945 :iso-final-char ?7 | |
946 :short-name "Tibetan 2-col" | |
88486 | 947 :long-name "Tibetan 2 column" |
88411 | 948 :iso-final-char ?7 |
949 :emacs-mule-id 252 | |
89483 | 950 :unify-map "MULE-tibetan" |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
951 :supplementary-p t |
89292
1bc1e30ea8d5
(tibetan): Fix :code-space property.
Kenichi Handa <handa@m17n.org>
parents:
89267
diff
changeset
|
952 :code-space [33 126 33 37] |
88411 | 953 :code-offset #x190000) |
954 | |
955 (define-charset 'tibetan-1-column | |
956 "Tibetan 1 column glyph" | |
957 :short-name "Tibetan 1-col" | |
958 :long-name "Tibetan 1 column" | |
959 :iso-final-char ?8 | |
960 :emacs-mule-id 241 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
961 :supplementary-p t |
88411 | 962 :code-space [33 126 33 37] |
89292
1bc1e30ea8d5
(tibetan): Fix :code-space property.
Kenichi Handa <handa@m17n.org>
parents:
89267
diff
changeset
|
963 :code-offset #x190000) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
964 |
33044
7878d85aef6d
New charsets mule-unicode-2500-33ff and mule-unicode-e000-ffff.
Kenichi Handa <handa@m17n.org>
parents:
32786
diff
changeset
|
965 ;; Subsets of Unicode. |
88411 | 966 (define-charset 'mule-unicode-2500-33ff |
967 "Unicode characters of the range U+2500..U+33FF." | |
968 :short-name "Unicode subset 2" | |
969 :long-name "Unicode subset (U+2500..U+33FF)" | |
970 :iso-final-char ?2 | |
971 :emacs-mule-id 242 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
972 :supplementary-p t |
88411 | 973 :code-space [#x20 #x7f #x20 #x47] |
974 :code-offset #x2500) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
975 |
88411 | 976 (define-charset 'mule-unicode-e000-ffff |
977 "Unicode characters of the range U+E000..U+FFFF." | |
978 :short-name "Unicode subset 3" | |
979 :long-name "Unicode subset (U+E000+FFFF)" | |
980 :iso-final-char ?3 | |
981 :emacs-mule-id 243 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
982 :supplementary-p t |
88411 | 983 :code-space [#x20 #x7F #x20 #x75] |
88843 | 984 :code-offset #xE000 |
985 :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
|
986 |
88411 | 987 (define-charset 'mule-unicode-0100-24ff |
988 "Unicode characters of the range U+0100..U+24FF." | |
989 :short-name "Unicode subset" | |
990 :long-name "Unicode subset (U+0100..U+24FF)" | |
991 :iso-final-char ?1 | |
992 :emacs-mule-id 244 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
993 :supplementary-p t |
88411 | 994 :code-space [#x20 #x7F #x20 #x7F] |
995 :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
|
996 |
89089 | 997 (define-charset 'unicode-bmp |
89797
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
998 "Unicode Basic Multilingual Plane (U+0000..U+FFFF)" |
89089 | 999 :short-name "Unicode BMP" |
1000 :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
|
1001 :code-offset 0) |
89091 | 1002 |
89797
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1003 (define-charset 'unicode-smp |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1004 "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
|
1005 :short-name "Unicode SMP " |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1006 :code-space [0 255 0 255] |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1007 :code-offset #x10000) |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1008 |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1009 (define-charset 'unicode-sip |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1010 "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
|
1011 :short-name "Unicode SIP" |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1012 :code-space [0 255 0 255] |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1013 :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
|
1014 |
89797
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1015 (define-charset 'unicode-ssp |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1016 "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
|
1017 :short-name "Unicode SSP" |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1018 :code-space [0 255 0 255] |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
1019 :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
|
1020 |
88411 | 1021 (define-charset 'ethiopic |
88486 | 1022 "Ethiopic characters for Amharic and Tigrigna." |
88411 | 1023 :short-name "Ethiopic" |
1024 :long-name "Ethiopic characters" | |
1025 :iso-final-char ?3 | |
1026 :emacs-mule-id 245 | |
91197
a7ee91d853bc
Flag many charsets as supplementary.
Kenichi Handa <handa@m17n.org>
parents:
91116
diff
changeset
|
1027 :supplementary-p t |
89483 | 1028 :unify-map "MULE-ethiopic" |
88411 | 1029 :code-space [33 126 33 126] |
1030 :code-offset #x1A0000) | |
17070 | 1031 |
88411 | 1032 (define-charset 'mac-roman |
1033 "Mac Roman charset" | |
1034 :short-name "Mac Roman" | |
1035 :ascii-compatible-p t | |
1036 :code-space [0 255] | |
89483 | 1037 :map "MACINTOSH") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1038 |
88533 | 1039 ;; Fixme: modern EBCDIC variants, e.g. IBM00924? |
1040 (define-charset 'ebcdic-us | |
1041 "US version of EBCDIC" | |
1042 :short-name "EBCDIC-US" | |
1043 :code-space [0 255] | |
1044 :mime-charset 'ebcdic-us | |
89483 | 1045 :map "EBCDICUS") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1046 |
88533 | 1047 (define-charset 'ebcdic-uk |
1048 "UK version of EBCDIC" | |
1049 :short-name "EBCDIC-UK" | |
1050 :code-space [0 255] | |
1051 :mime-charset 'ebcdic-uk | |
89483 | 1052 :map "EBCDICUK") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1053 |
89200 | 1054 (define-charset 'ibm1047 |
1055 ;; Says groff: | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
1056 "IBM1047, `EBCDIC Latin 1/Open Systems' used by OS/390 Unix." |
89200 | 1057 :short-name "IBM1047" |
1058 :code-space [0 255] | |
1059 :mime-charset 'ibm1047 | |
89483 | 1060 :map "IBM1047") |
89200 | 1061 (define-charset-alias 'cp1047 'ibm1047) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1062 |
88575 | 1063 (define-charset 'hp-roman8 |
1064 "Encoding used by Hewlet-Packard printer software" | |
1065 :short-name "HP-ROMAN8" | |
1066 :ascii-compatible-p t | |
1067 :code-space [0 255] | |
89483 | 1068 :map "HP-ROMAN8") |
17070 | 1069 |
88671 | 1070 ;; To make a coding system with this, a pre-write-conversion should |
1071 ;; account for the commented-out multi-valued code points in | |
1072 ;; stdenc.map. | |
88575 | 1073 (define-charset 'adobe-standard-encoding |
1074 "Adobe `standard encoding' used in PostScript" | |
1075 :short-name "ADOBE-STANDARD-ENCODING" | |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
1076 :code-space [#x20 255] |
88575 | 1077 :map "stdenc") |
17070 | 1078 |
88575 | 1079 (define-charset 'symbol |
1080 "Adobe symbol encoding used in PostScript" | |
1081 :short-name "ADOBE-SYMBOL" | |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
1082 :code-space [#x20 255] |
88575 | 1083 :map "symbol") |
1084 | |
1085 (define-charset 'ibm850 | |
88671 | 1086 "DOS codepage 850 (Latin-1)" |
88575 | 1087 :short-name "IBM850" |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
1088 :ascii-compatible-p t |
88575 | 1089 :code-space [0 255] |
89483 | 1090 :map "IBM850") |
88575 | 1091 (define-charset-alias 'cp850 'ibm850) |
1092 | |
89318 | 1093 (define-charset 'mik |
1094 "Bulgarian DOS codepage" | |
1095 :short-name "MIK" | |
1096 :ascii-compatible-p t | |
1097 :code-space [0 255] | |
89483 | 1098 :map "MIK") |
89318 | 1099 |
89483 | 1100 (define-charset 'ptcp154 |
89318 | 1101 "`Paratype' codepage (Asian Cyrillic)" |
1102 :short-name "PT154" | |
1103 :ascii-compatible-p t | |
1104 :code-space [0 255] | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
1105 :mime-charset 'pt154 |
89483 | 1106 :map "PTCP154") |
1107 (define-charset-alias 'pt154 'ptcp154) | |
1108 (define-charset-alias 'cp154 'ptcp154) | |
89318 | 1109 |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1110 (define-charset 'gb18030-2-byte |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1111 "GB18030 2-byte (0x814E..0xFEFE)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1112 :code-space [#x40 #xFE #x81 #xFE] |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1113 :supplementary-p t |
89483 | 1114 :map "GB180302") |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1115 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1116 (define-charset 'gb18030-4-byte-bmp |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1117 "GB18030 4-byte for BMP (0x81308130-0x8431A439)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1118 :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
|
1119 :supplementary-p t |
89483 | 1120 :map "GB180304") |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1121 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1122 (define-charset 'gb18030-4-byte-smp |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1123 "GB18030 4-byte for SMP (0x90308130-0xE3329A35)" |
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 #x90 #xE3] |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1125 :min-code '(#x9030 . #x8130) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1126 :max-code '(#xE332 . #x9A35) |
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 #x10000) |
17070 | 1129 |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1130 (define-charset 'gb18030-4-byte-ext-1 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1131 "GB18030 4-byte (0x8431A530-0x8F39FE39)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1132 :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
|
1133 :min-code '(#x8431 . #xA530) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1134 :max-code '(#x8F39 . #xFE39) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1135 :supplementary-p t |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1136 :code-offset #x200000 ; ... #x22484B |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1137 ) |
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 (define-charset 'gb18030-4-byte-ext-2 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1140 "GB18030 4-byte (0xE3329A36-0xFE39FE39)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1141 :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
|
1142 :min-code '(#xE332 . #x9A36) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1143 :max-code '(#xFE39 . #xFE39) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1144 :supplementary-p t |
89822
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1145 :code-offset #x22484C ; ... #x279f93 |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1146 ) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1147 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1148 (define-charset 'gb18030 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1149 "GB18030" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1150 :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
|
1151 :min-code 0 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1152 :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
|
1153 :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
|
1154 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
|
1155 gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)) |
17070 | 1156 |
89822
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1157 (define-charset 'chinese-cns11643-15 |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1158 "CNS11643 Plane 15 Chinese Traditional" |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1159 :short-name "CNS11643-15" |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1160 :long-name "CNS11643-15 (Chinese traditional)" |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1161 :code-space [33 126 33 126] |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1162 :code-offset #x27A000) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1163 |
88411 | 1164 (unify-charset 'chinese-gb2312) |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
1165 (unify-charset 'chinese-gbk) |
88411 | 1166 (unify-charset 'chinese-cns11643-1) |
1167 (unify-charset 'chinese-cns11643-2) | |
89483 | 1168 (unify-charset 'chinese-cns11643-3) |
1169 (unify-charset 'chinese-cns11643-4) | |
1170 (unify-charset 'chinese-cns11643-5) | |
1171 (unify-charset 'chinese-cns11643-6) | |
1172 (unify-charset 'chinese-cns11643-7) | |
88411 | 1173 (unify-charset 'big5) |
1174 (unify-charset 'chinese-big5-1) | |
1175 (unify-charset 'chinese-big5-2) | |
89483 | 1176 (unify-charset 'big5-hkscs) |
1177 (unify-charset 'korean-ksc5601) | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
1178 (unify-charset 'vietnamese-viscii-lower) |
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
1179 (unify-charset 'vietnamese-viscii-upper) |
88760 | 1180 (unify-charset 'chinese-sisheng) |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1181 (unify-charset 'ipa) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1182 (unify-charset 'tibetan) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1183 (unify-charset 'ethiopic) |
89483 | 1184 (unify-charset 'japanese-jisx0208-1978) |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1185 (unify-charset 'japanese-jisx0208) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1186 (unify-charset 'japanese-jisx0212) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1187 (unify-charset 'japanese-jisx0213-1) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1188 (unify-charset 'japanese-jisx0213-2) |
17070 | 1189 |
1190 | |
22126
97cf1cae1971
Change term unification to
Kenichi Handa <handa@m17n.org>
parents:
21713
diff
changeset
|
1191 ;; These are tables for translating characters on decoding and |
97cf1cae1971
Change term unification to
Kenichi Handa <handa@m17n.org>
parents:
21713
diff
changeset
|
1192 ;; encoding. |
88760 | 1193 ;; Fixme: these aren't used now -- should they be? |
88411 | 1194 (setq standard-translation-table-for-decode nil) |
17760
b3d62674b210
Delete code for alternate-charset-table.
Kenichi Handa <handa@m17n.org>
parents:
17541
diff
changeset
|
1195 |
22186
fc4aaf1b1772
Change term "character translation table" to "translation table".
Kenichi Handa <handa@m17n.org>
parents:
22126
diff
changeset
|
1196 (setq standard-translation-table-for-encode nil) |
17760
b3d62674b210
Delete code for alternate-charset-table.
Kenichi Handa <handa@m17n.org>
parents:
17541
diff
changeset
|
1197 |
17070 | 1198 ;;; Make fundamental coding systems. |
1199 | |
90039
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1200 ;; 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
|
1201 ;; defined in coding.c as below: |
88411 | 1202 ;; |
1203 ;; (define-coding-system 'no-conversion | |
90039
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1204 ;; "..." |
88411 | 1205 ;; :coding-type 'raw-text |
90039
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1206 ;; ...) |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1207 ;; (define-coding-system 'undecided |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1208 ;; "..." |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1209 ;; :coding-type 'undecided |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1210 ;; ...) |
17070 | 1211 |
18529
8e293f1a19a9
(binary): Define as coding system alias.
Richard M. Stallman <rms@gnu.org>
parents:
18519
diff
changeset
|
1212 (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
|
1213 (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
|
1214 (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
|
1215 (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
|
1216 |
88411 | 1217 (define-coding-system 'raw-text |
89483 | 1218 "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
|
1219 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
|
1220 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
|
1221 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
|
1222 byte. |
9688519d51d6
(no-conversion): Fix docstring.
Kenichi Handa <handa@m17n.org>
parents:
36518
diff
changeset
|
1223 |
9688519d51d6
(no-conversion): Fix docstring.
Kenichi Handa <handa@m17n.org>
parents:
36518
diff
changeset
|
1224 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
|
1225 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
|
1226 is treated as a character." |
89483 | 1227 :coding-type 'raw-text |
1228 :for-unibyte t | |
1229 :mnemonic ?t) | |
88411 | 1230 |
89483 | 1231 (define-coding-system 'no-conversion-multibyte |
1232 "Like `no-conversion' but don't read a file into a unibyte buffer." | |
1233 :coding-type 'raw-text | |
1234 :eol-type 'unix | |
1235 :mnemonic ?=) | |
1236 | |
88411 | 1237 (define-coding-system 'iso-latin-1 |
1238 "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)." | |
89091 | 1239 :coding-type 'charset |
88411 | 1240 :mnemonic ?1 |
89091 | 1241 :charset-list '(iso-8859-1) |
88411 | 1242 :mime-charset 'iso-8859-1) |
1243 | |
1244 (define-coding-system-alias 'iso-8859-1 'iso-latin-1) | |
1245 (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
|
1246 |
88411 | 1247 ;; Coding systems not specific to each language environment. |
1248 | |
1249 (define-coding-system 'emacs-mule | |
1250 "Emacs 21 internal format used in buffer and string." | |
1251 :coding-type 'emacs-mule | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1252 :charset-list 'emacs-mule |
88411 | 1253 :mnemonic ?M) |
19607
ea0964347a40
(raw-text): New coding system. Set
Kenichi Handa <handa@m17n.org>
parents:
19372
diff
changeset
|
1254 |
88411 | 1255 (define-coding-system 'utf-8 |
95399
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1256 "UTF-8 (no signature (BOM))" |
88411 | 1257 :coding-type 'utf-8 |
1258 :mnemonic ?U | |
89041
2ce9656d788b
(utf-8): Give :mime-charset property.
Kenichi Handa <handa@m17n.org>
parents:
88894
diff
changeset
|
1259 :charset-list '(unicode) |
2ce9656d788b
(utf-8): Give :mime-charset property.
Kenichi Handa <handa@m17n.org>
parents:
88894
diff
changeset
|
1260 :mime-charset 'utf-8) |
88411 | 1261 |
95408
9cc865eba421
(utf-8-with-signature): Renamed from utf-8-sig.
Kenichi Handa <handa@m17n.org>
parents:
95399
diff
changeset
|
1262 (define-coding-system 'utf-8-with-signature |
95399
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1263 "UTF-8 (with signature (BOM))" |
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1264 :coding-type 'utf-8 |
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1265 :mnemonic ?U |
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1266 :charset-list '(unicode) |
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1267 :bom t) |
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1268 |
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1269 (define-coding-system 'utf-8-auto |
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1270 "UTF-8 (auto-detect signature (BOM))" |
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1271 :coding-type 'utf-8 |
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1272 :mnemonic ?U |
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1273 :charset-list '(unicode) |
95408
9cc865eba421
(utf-8-with-signature): Renamed from utf-8-sig.
Kenichi Handa <handa@m17n.org>
parents:
95399
diff
changeset
|
1274 :bom '(utf-8-with-signature . utf-8)) |
95399
3a9b63459609
(utf-8-sig, utf-8-auto): New coding systems.
Kenichi Handa <handa@m17n.org>
parents:
95262
diff
changeset
|
1275 |
88411 | 1276 (define-coding-system-alias 'mule-utf-8 'utf-8) |
1277 | |
1278 (define-coding-system 'utf-8-emacs | |
88468 | 1279 "Support for all Emacs characters (including non-Unicode characters)." |
88411 | 1280 :coding-type 'utf-8 |
1281 :mnemonic ?U | |
89244
bf10578caec8
(utf-8-emacs): Delete :mime-charset.
Dave Love <fx@gnu.org>
parents:
89200
diff
changeset
|
1282 :charset-list '(emacs)) |
88411 | 1283 |
98849
260217a5e2e4
(emacs-internal): New coding system alias.
Stefan Monnier <monnier@iro.umontreal.ca>
parents:
98777
diff
changeset
|
1284 ;; The encoding used internally. This encoding is meant to be able to save |
260217a5e2e4
(emacs-internal): New coding system alias.
Stefan Monnier <monnier@iro.umontreal.ca>
parents:
98777
diff
changeset
|
1285 ;; any multibyte buffer without losing information. It can change between |
260217a5e2e4
(emacs-internal): New coding system alias.
Stefan Monnier <monnier@iro.umontreal.ca>
parents:
98777
diff
changeset
|
1286 ;; Emacs releases, tho, so should only be used for internal files. |
260217a5e2e4
(emacs-internal): New coding system alias.
Stefan Monnier <monnier@iro.umontreal.ca>
parents:
98777
diff
changeset
|
1287 (define-coding-system-alias 'emacs-internal 'utf-8-emacs-unix) |
260217a5e2e4
(emacs-internal): New coding system alias.
Stefan Monnier <monnier@iro.umontreal.ca>
parents:
98777
diff
changeset
|
1288 |
89436 | 1289 (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
|
1290 "UTF-16LE (little endian, no signature (BOM))." |
88411 | 1291 :coding-type 'utf-16 |
1292 :mnemonic ?U | |
88503 | 1293 :charset-list '(unicode) |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1294 :endian 'little |
89436 | 1295 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1296 :mime-charset 'utf-16le) |
17070 | 1297 |
89436 | 1298 (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
|
1299 "UTF-16BE (big endian, no signature (BOM))." |
88411 | 1300 :coding-type 'utf-16 |
1301 :mnemonic ?U | |
1302 :charset-list '(unicode) | |
89422 | 1303 :endian 'big |
89436 | 1304 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1305 :mime-charset 'utf-16be) |
17070 | 1306 |
89436 | 1307 (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
|
1308 "UTF-16 (little endian, with signature (BOM))." |
88411 | 1309 :coding-type 'utf-16 |
1310 :mnemonic ?U | |
1311 :charset-list '(unicode) | |
88440
5b1dd2e30f16
(utf-16-le): Use :bom attribute instead of :signature.
Kenichi Handa <handa@m17n.org>
parents:
88411
diff
changeset
|
1312 :bom t |
88503 | 1313 :endian 'little |
89436 | 1314 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1315 :mime-charset 'utf-16) |
17070 | 1316 |
89436 | 1317 (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
|
1318 "UTF-16 (big endian, with signature)." |
88411 | 1319 :coding-type 'utf-16 |
1320 :mnemonic ?U | |
1321 :charset-list '(unicode) | |
88440
5b1dd2e30f16
(utf-16-le): Use :bom attribute instead of :signature.
Kenichi Handa <handa@m17n.org>
parents:
88411
diff
changeset
|
1322 :bom t |
89422 | 1323 :endian 'big |
89436 | 1324 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1325 :mime-charset 'utf-16) |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1326 |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1327 (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
|
1328 "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
|
1329 :coding-type 'utf-16 |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1330 :mnemonic ?U |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1331 :charset-list '(unicode) |
89436 | 1332 :bom '(utf-16le-with-signature . utf-16be-with-signature) |
89422 | 1333 :endian 'big |
89436 | 1334 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1335 :mime-charset 'utf-16) |
17070 | 1336 |
89436 | 1337 ;; Backwards compatibility (old names, also used by Mule-UCS). We |
1338 ;; 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
|
1339 (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
|
1340 (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
|
1341 |
89436 | 1342 |
88411 | 1343 (define-coding-system 'iso-2022-7bit |
88647 | 1344 "ISO 2022 based 7-bit encoding using only G0." |
88411 | 1345 :coding-type 'iso-2022 |
1346 :mnemonic ?J | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1347 :charset-list 'iso-2022 |
88411 | 1348 :designation [(ascii t) nil nil nil] |
1349 :flags '(short ascii-at-eol ascii-at-cntl 7-bit designation composition)) | |
1350 | |
1351 (define-coding-system 'iso-2022-7bit-ss2 | |
88647 | 1352 "ISO 2022 based 7-bit encoding using SS2 for 96-charset." |
88411 | 1353 :coding-type 'iso-2022 |
1354 :mnemonic ?$ | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1355 :charset-list 'iso-2022 |
88411 | 1356 :designation [(ascii 94) nil (nil 96) nil] |
1357 :flags '(short ascii-at-eol ascii-at-cntl 7-bit | |
1358 designation single-shift composition)) | |
1359 | |
1360 (define-coding-system 'iso-2022-7bit-lock | |
88647 | 1361 "ISO-2022 coding system using Locking-Shift for 96-charset." |
88411 | 1362 :coding-type 'iso-2022 |
1363 :mnemonic ?& | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1364 :charset-list 'iso-2022 |
88411 | 1365 :designation [(ascii 94) (nil 96) nil nil] |
1366 :flags '(ascii-at-eol ascii-at-cntl 7-bit | |
1367 designation locking-shift composition)) | |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1368 |
18519
b6badf3614ea
Fix calls to define-coding-system-alias.
Richard M. Stallman <rms@gnu.org>
parents:
18377
diff
changeset
|
1369 (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
|
1370 |
88411 | 1371 (define-coding-system 'iso-2022-7bit-lock-ss2 |
88647 | 1372 "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN." |
88411 | 1373 :coding-type 'iso-2022 |
1374 :mnemonic ?i | |
1375 :charset-list '(ascii | |
1376 japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201 | |
1377 korean-ksc5601 | |
1378 chinese-gb2312 | |
1379 chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3 | |
1380 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6 | |
1381 chinese-cns11643-7) | |
1382 :designation [(ascii 94) | |
1383 (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 96) | |
1384 (nil chinese-cns11643-2) | |
1385 (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5 | |
1386 chinese-cns11643-6 chinese-cns11643-7)] | |
1387 :flags '(short ascii-at-eol ascii-at-cntl 7-bit locking-shift | |
1388 single-shift init-bol)) | |
17070 | 1389 |
18519
b6badf3614ea
Fix calls to define-coding-system-alias.
Richard M. Stallman <rms@gnu.org>
parents:
18377
diff
changeset
|
1390 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2) |
17070 | 1391 |
88411 | 1392 (define-coding-system 'iso-2022-8bit-ss2 |
88647 | 1393 "ISO 2022 based 8-bit encoding using SS2 for 96-charset." |
88411 | 1394 :coding-type 'iso-2022 |
1395 :mnemonic ?@ | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1396 :charset-list 'iso-2022 |
88411 | 1397 :designation [(ascii 94) nil (nil 96) nil] |
1398 :flags '(ascii-at-eol ascii-at-cntl designation single-shift composition)) | |
17070 | 1399 |
88411 | 1400 (define-coding-system 'compound-text |
1401 "Compound text based generic encoding for decoding unknown messages. | |
17070 | 1402 |
89483 | 1403 This coding system does not support extended segments of CTEXT." |
88411 | 1404 :coding-type 'iso-2022 |
1405 :mnemonic ?x | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1406 :charset-list 'iso-2022 |
88411 | 1407 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] |
90352 | 1408 :flags '(ascii-at-eol ascii-at-cntl long-form |
88411 | 1409 designation locking-shift single-shift composition) |
88503 | 1410 ;; Fixme: this isn't a valid MIME charset and has to be |
1411 ;; special-cased elsewhere -- fx | |
88411 | 1412 :mime-charset 'x-ctext) |
24619
6057f7a48050
(x-ctext): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
24308
diff
changeset
|
1413 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1414 (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
|
1415 (define-coding-system-alias 'ctext 'compound-text) |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1416 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1417 ;; 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
|
1418 ;; 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
|
1419 ;; 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
|
1420 ;; 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
|
1421 ;; 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
|
1422 (define-coding-system 'ctext-no-compositions |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1423 "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
|
1424 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1425 Like `compound-text', but does not produce escape sequences for compositions." |
88411 | 1426 :coding-type 'iso-2022 |
1427 :mnemonic ?x | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1428 :charset-list 'iso-2022 |
88411 | 1429 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] |
1430 :flags '(ascii-at-eol ascii-at-cntl | |
1431 designation locking-shift single-shift)) | |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1432 |
88411 | 1433 (define-coding-system 'compound-text-with-extensions |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1434 "Compound text encoding with ICCCM Extended Segment extensions. |
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1435 |
53241
b5acb6a7d79b
(compound-text-with-extensions): Change the type to 2 (iso-2022 base).
Kenichi Handa <handa@m17n.org>
parents:
52401
diff
changeset
|
1436 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
|
1437 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
|
1438 |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1439 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
|
1440 for decoding and encoding files, process I/O, etc." |
89909 | 1441 :coding-type 'iso-2022 |
88411 | 1442 :mnemonic ?x |
89909 | 1443 :charset-list 'iso-2022 |
1444 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] | |
90352 | 1445 :flags '(ascii-at-eol ascii-at-cntl long-form |
89909 | 1446 designation locking-shift single-shift) |
88411 | 1447 :post-read-conversion 'ctext-post-read-conversion |
1448 :pre-write-conversion 'ctext-pre-write-conversion) | |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1449 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1450 (define-coding-system-alias |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1451 '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
|
1452 (define-coding-system-alias |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1453 '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
|
1454 |
88411 | 1455 (define-coding-system 'us-ascii |
89483 | 1456 "Encode ASCII as-is and encode non-ASCII characters to `?'." |
88411 | 1457 :coding-type 'charset |
1458 :mnemonic ?- | |
1459 :charset-list '(ascii) | |
1460 :default-char ?? | |
1461 :mime-charset 'us-ascii) | |
19266
a042f26b7a4c
(iso-safe): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
19005
diff
changeset
|
1462 |
88411 | 1463 (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
|
1464 |
89426 | 1465 (define-coding-system 'utf-7 |
1466 "UTF-7 encoding of Unicode (RFC 2152)." | |
1467 :coding-type 'utf-8 | |
1468 :mnemonic ?U | |
1469 :mime-charset 'utf-7 | |
1470 :charset-list '(unicode) | |
1471 :pre-write-conversion 'utf-7-pre-write-conversion | |
1472 :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
|
1473 |
91116
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1474 (define-coding-system 'utf-7-imap |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1475 "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
|
1476 :coding-type 'utf-8 |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1477 :mnemonic ?u |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1478 :charset-list '(unicode) |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1479 :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
|
1480 :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
|
1481 |
88411 | 1482 ;; Use us-ascii for terminal output if some other coding system is not |
23196 | 1483 ;; specified explicitly. |
88411 | 1484 (set-safe-terminal-coding-system-internal 'us-ascii) |
19266
a042f26b7a4c
(iso-safe): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
19005
diff
changeset
|
1485 |
17070 | 1486 ;; The other coding-systems are defined in each language specific |
88411 | 1487 ;; files under lisp/language. |
17070 | 1488 |
21713
aa160e4358ac
(file-coding-system-alist): Use emacs-mule for .elc files.
Richard M. Stallman <rms@gnu.org>
parents:
20732
diff
changeset
|
1489 ;; 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
|
1490 ;; 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
|
1491 ;; 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
|
1492 ;; Tar files are not decoded at all, but we treat them as raw bytes. |
17070 | 1493 |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1494 (setq file-coding-system-alist |
88776
805a3bb7daf4
(file-coding-system-alist): Change
Dave Love <fx@gnu.org>
parents:
88760
diff
changeset
|
1495 '(("\\.elc\\'" . utf-8-emacs) |
42047
83eb799f3657
(translation-table-for-input): New
Dave Love <fx@gnu.org>
parents:
41468
diff
changeset
|
1496 ("\\.utf\\(-8\\)?\\'" . utf-8) |
91922
89b7a215ead9
* international/mule.el (sgml-xml-auto-coding-function): Detect
Jason Rumney <jasonr@gnu.org>
parents:
91327
diff
changeset
|
1497 ("\\.xml\\'" . xml-find-file-coding-system) |
34264
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1498 ;; 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
|
1499 ;; 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
|
1500 ;; newlines. This is required to make the special treatment |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1501 ;; of the "\ newline" combination in loaddefs.el, which marks |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1502 ;; the beginning of a doc string, work. |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1503 ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix)) |
32228
6a5bae3ed1c1
file-coding-system-alist): Use \',
Dave Love <fx@gnu.org>
parents:
30260
diff
changeset
|
1504 ("\\.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
|
1505 ( "\\.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
|
1506 ("\\.\\(tex\\|ltx\\|dtx\\|drv\\)\\'" . latexenc-find-file-coding-system) |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1507 ("" . (undecided . nil)))) |
17070 | 1508 |
1509 | |
1510 ;;; Setting coding categories and their priorities. | |
1511 | |
1512 ;; This setting is just to read an Emacs Lisp source files which | |
1513 ;; 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
|
1514 ;; values are set by the command `set-language-environment' for each |
17070 | 1515 ;; language environment. |
1516 | |
88411 | 1517 (set-coding-system-priority |
1518 'iso-latin-1 | |
1519 'utf-8 | |
1520 'iso-2022-7bit | |
1521 ) | |
17070 | 1522 |
19372 | 1523 |
1524 ;;; Miscellaneous settings. | |
88411 | 1525 |
1526 ;; Make all multibyte characters self-insert. | |
1527 (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
|
1528 (cons 128 (max-char)) |
88411 | 1529 'self-insert-command) |
1530 | |
50511
5930672784ee
Register ?\221 and ?\226 in latin-extra-code-table.
Kenichi Handa <handa@m17n.org>
parents:
50488
diff
changeset
|
1531 (aset latin-extra-code-table ?\221 t) |
19372 | 1532 (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
|
1533 (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
|
1534 (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
|
1535 (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
|
1536 (aset latin-extra-code-table ?\226 t) |
19372 | 1537 |
88600 | 1538 ;; The old code-pages library is obsoleted by coding systems based on |
1539 ;; the charsets defined in this file but might be required by user | |
1540 ;; code. | |
1541 (provide 'code-pages) | |
1542 | |
88575 | 1543 ;; Local variables: |
1544 ;; no-byte-compile: t | |
1545 ;; End: | |
23260
1e8cac8d2c50
Call update-coding-systems-internal at the tail.
Kenichi Handa <handa@m17n.org>
parents:
23196
diff
changeset
|
1546 |
61698
19c94353380d
(translation-table-for-input): Remove redundant declaration.
Stefan Monnier <monnier@iro.umontreal.ca>
parents:
53241
diff
changeset
|
1547 ;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5 |
17070 | 1548 ;;; mule-conf.el ends here |