Mercurial > emacs
annotate lisp/international/mule-conf.el @ 91196:0243246adece
(define-charset): Update the docstring for
:supplementary-p.
author | Kenichi Handa <handa@m17n.org> |
---|---|
date | Thu, 06 Dec 2007 07:28:58 +0000 |
parents | ec7b5eef2638 |
children | a7ee91d853bc |
rev | line source |
---|---|
17070 | 1 ;;; mule-conf.el --- configure multilingual environment |
2 | |
74544 | 3 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, |
75347 | 4 ;; 2004, 2005, 2006, 2007 Free Software Foundation, Inc. |
5 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007 | |
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 | |
16 ;; GNU Emacs is free software; you can redistribute it and/or modify | |
17 ;; it under the terms of the GNU General Public License as published by | |
78310
2daf9c28b3a4
Restore comma mistakenly removed in last change.
Glenn Morris <rgm@gnu.org>
parents:
78301
diff
changeset
|
18 ;; the Free Software Foundation; either version 3, or (at your option) |
17070 | 19 ;; any later version. |
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 | |
27 ;; along with GNU Emacs; see the file COPYING. If not, write to the | |
64085 | 28 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, |
29 ;; Boston, MA 02110-1301, USA. | |
17070 | 30 |
31 ;;; Commentary: | |
32 | |
88575 | 33 ;; This file defines the Emacs charsets and some basic coding systems. |
34 ;; Other coding systems are defined in the files in directory | |
35 ;; lisp/language. | |
17070 | 36 |
37 ;;; Code: | |
38 | |
88666 | 39 ;;; Remarks |
40 | |
88575 | 41 ;; The ISO-IR registry is at http://www.itscj.ipsj.or.jp/ISO-IR/. |
42 ;; Standards docs equivalent to iso-2022 and iso-8859 are at | |
43 ;; http://www.ecma.ch/. | |
44 | |
88717 | 45 ;; FWIW, http://www.microsoft.com/globaldev/ lists the following for |
46 ;; MS Windows, which are presumably the only charsets we really need | |
47 ;; to worry about on such systems: | |
88666 | 48 ;; `OEM codepages': 437, 720, 737, 775, 850, 852, 855, 857, 858, 862, 866 |
49 ;; `Windows codepages': 1250, 1251, 1252, 1253, 1254, 1255, 1256, 1257, | |
50 ;; 1258, 874, 932, 936, 949, 950 | |
51 | |
17070 | 52 ;;; Definitions of character sets. |
53 | |
89089 | 54 ;; The charsets `ascii', `unicode' and `eight-bit' are already defined |
55 ;; in charset.c as below: | |
88411 | 56 ;; |
57 ;; (define-charset 'ascii | |
58 ;; "" | |
59 ;; :dimension 1 | |
60 ;; :code-space [0 127] | |
89089 | 61 ;; :iso-final-char ?B |
88411 | 62 ;; :ascii-compatible-p t |
63 ;; :emacs-mule-id 0 | |
64 ;; :code-offset 0) | |
65 ;; | |
66 ;; (define-charset 'unicode | |
67 ;; "" | |
68 ;; :dimension 3 | |
69 ;; :code-space [0 255 0 255 0 16] | |
70 ;; :ascii-compatible-p t | |
71 ;; :code-offset 0) | |
72 ;; | |
89089 | 73 ;; (define-charset 'eight-bit |
74 ;; "" | |
75 ;; :dimension 1 | |
76 ;; :code-space [128 255] | |
77 ;; :code-offset #x3FFF80) | |
78 ;; | |
88411 | 79 ;; We now set :docstring, :short-name, and :long-name properties. |
80 | |
81 (put-charset-property | |
82 'ascii :docstring "ASCII (ISO646 IRV)") | |
83 (put-charset-property | |
84 'ascii :short-name "ASCII") | |
85 (put-charset-property | |
86 'ascii :long-name "ASCII (ISO646 IRV)") | |
87 (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
|
88 '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
|
89 (put-charset-property |
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
90 'iso-8859-1 :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
|
91 (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
|
92 '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
|
93 (put-charset-property |
88411 | 94 'unicode :docstring "Unicode (ISO10646)") |
95 (put-charset-property | |
96 'unicode :short-name "Unicode") | |
97 (put-charset-property | |
98 'unicode :long-name "Unicode (ISO10646)") | |
89089 | 99 (put-charset-property 'eight-bit :docstring "Raw bytes 0-255") |
100 (put-charset-property 'eight-bit :short-name "Raw bytes") | |
17070 | 101 |
88411 | 102 (define-charset-alias 'ucs 'unicode) |
103 | |
104 (define-charset 'emacs | |
88647 | 105 "Full Emacs characters" |
88411 | 106 :ascii-compatible-p t |
107 :code-space [ 0 255 0 255 0 63 ] | |
108 :code-offset 0 | |
109 :supplementary-p t) | |
110 | |
111 (define-charset 'latin-iso8859-1 | |
112 "Right-Hand Part of ISO/IEC 8859/1 (Latin-1): ISO-IR-100" | |
113 :short-name "RHP of Latin-1" | |
114 :long-name "RHP of ISO/IEC 8859/1 (Latin-1): ISO-IR-100" | |
115 :iso-final-char ?A | |
116 :emacs-mule-id 129 | |
117 :code-space [32 127] | |
118 :code-offset 160) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
119 |
88735 | 120 ;; Name perhaps not ideal, but is XEmacs-compatible. |
121 (define-charset 'control-1 | |
88411 | 122 "8-bit control code (0x80..0x9F)" |
123 :short-name "8-bit control code" | |
124 :code-space [128 159] | |
125 :code-offset 128) | |
126 | |
88735 | 127 (define-charset 'eight-bit-control |
128 "Raw bytes in the range 0x80..0x9F (usually produced from invalid encodings)" | |
129 :short-name "Raw bytes 0x80..0x9F" | |
130 :code-space [128 159] | |
131 :code-offset #x3FFF80) ; see character.h | |
132 | |
88411 | 133 (define-charset 'eight-bit-graphic |
88735 | 134 "Raw bytes in the range 0xA0..0xFF (usually produced from invalid encodings)" |
135 :short-name "Raw bytes 0xA0..0xFF" | |
88411 | 136 :code-space [160 255] |
88735 | 137 :code-offset #x3FFFA0) ; see character.h |
17070 | 138 |
88411 | 139 (defmacro define-iso-single-byte-charset (symbol iso-symbol name nickname |
140 iso-ir iso-final | |
141 emacs-mule-id map) | |
142 `(progn | |
143 (define-charset ,symbol | |
144 ,name | |
145 :short-name ,nickname | |
146 :long-name ,name | |
147 :ascii-compatible-p t | |
148 :code-space [0 255] | |
149 :map ,map) | |
150 (if ,iso-symbol | |
151 (define-charset ,iso-symbol | |
152 (if ,iso-ir | |
153 (format "Right-Hand Part of %s (%s): ISO-IR-%d" | |
154 ,name ,nickname ,iso-ir) | |
155 (format "Right-Hand Part of %s (%s)" ,name ,nickname)) | |
156 :short-name (format "RHP of %s" ,name) | |
157 :long-name (format "RHP of %s (%s)" ,name ,nickname) | |
158 :iso-final-char ,iso-final | |
88486 | 159 :emacs-mule-id ,emacs-mule-id |
88411 | 160 :code-space [32 127] |
88751
809b6bfe4dfa
Adjusted for the change of define-charset (:parent -> :subset or
Kenichi Handa <handa@m17n.org>
parents:
88735
diff
changeset
|
161 :subset (list ,symbol 160 255 -128))))) |
88411 | 162 |
163 (define-iso-single-byte-charset 'iso-8859-2 'latin-iso8859-2 | |
164 "ISO/IEC 8859/2" "Latin-2" 101 ?B 130 "8859-2") | |
165 | |
166 (define-iso-single-byte-charset 'iso-8859-3 'latin-iso8859-3 | |
167 "ISO/IEC 8859/3" "Latin-3" 109 ?C 131 "8859-3") | |
168 | |
169 (define-iso-single-byte-charset 'iso-8859-4 'latin-iso8859-4 | |
170 "ISO/IEC 8859/4" "Latin-4" 110 ?D 132 "8859-4") | |
171 | |
172 (define-iso-single-byte-charset 'iso-8859-5 'cyrillic-iso8859-5 | |
173 "ISO/IEC 8859/5" "Latin/Cyrillic" 144 ?L 140 "8859-5") | |
174 | |
175 (define-iso-single-byte-charset 'iso-8859-6 'arabic-iso8859-6 | |
176 "ISO/IEC 8859/6" "Latin/Arabic" 127 ?G 135 "8859-6") | |
177 | |
178 (define-iso-single-byte-charset 'iso-8859-7 'greek-iso8859-7 | |
179 "ISO/IEC 8859/7" "Latin/Greek" 126 ?F 134 "8859-7") | |
180 | |
181 (define-iso-single-byte-charset 'iso-8859-8 'hebrew-iso8859-8 | |
182 "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H 136 "8859-8") | |
183 | |
184 (define-iso-single-byte-charset 'iso-8859-9 'latin-iso8859-9 | |
185 "ISO/IEC 8859/9" "Latin-5" 148 ?M 141 "8859-9") | |
17070 | 186 |
88575 | 187 (define-iso-single-byte-charset 'iso-8859-10 'latin-iso8859-10 |
88671 | 188 "ISO/IEC 8859/10" "Latin-6" 157 ?V nil "8859-10") |
88575 | 189 |
88671 | 190 ;; http://www.nectec.or.th/it-standards/iso8859-11/ |
191 ;; http://www.cwi.nl/~dik/english/codes/8859.html says this is tis-620 | |
192 ;; plus nbsp | |
193 (define-iso-single-byte-charset 'iso-8859-11 'thai-iso8859-11 | |
194 "ISO/IEC 8859/11" "Latin/Thai" 166 ?T nil "8859-11") | |
195 | |
196 ;; 8859-12 doesn't (yet?) exist. | |
88575 | 197 |
88411 | 198 (define-iso-single-byte-charset 'iso-8859-13 'latin-iso8859-13 |
88575 | 199 "ISO/IEC 8859/13" "Latin-7" 179 ?Y nil "8859-13") |
88411 | 200 |
201 (define-iso-single-byte-charset 'iso-8859-14 'latin-iso8859-14 | |
202 "ISO/IEC 8859/14" "Latin-8" 199 ?_ 143 "8859-14") | |
203 | |
204 (define-iso-single-byte-charset 'iso-8859-15 'latin-iso8859-15 | |
205 "ISO/IEC 8859/15" "Latin-9" 203 ?b 142 "8859-15") | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
206 |
88565 | 207 (define-iso-single-byte-charset 'iso-8859-16 'latin-iso8859-16 |
88638 | 208 "ISO/IEC 8859/16" "Latin-10" 226 ?f nil "8859-16") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
209 |
88647 | 210 ;; No point in keeping it around. |
211 (fmakunbound 'define-iso-single-byte-charset) | |
212 | |
88671 | 213 ;; Can this be shared with 8859-11? |
89089 | 214 ;; N.b. not all of these are defined unicodes. |
88411 | 215 (define-charset 'thai-tis620 |
216 "TIS620.2533" | |
217 :short-name "TIS620.2533" | |
218 :iso-final-char ?T | |
219 :emacs-mule-id 133 | |
220 :code-space [32 127] | |
221 :code-offset #x0E00) | |
222 | |
88671 | 223 ;; Fixme: doc for this, c.f. above |
88411 | 224 (define-charset 'tis620-2533 |
225 "TIS620.2533" | |
226 :short-name "TIS620.2533" | |
227 :ascii-compatible-p t | |
228 :code-space [0 255] | |
88751
809b6bfe4dfa
Adjusted for the change of define-charset (:parent -> :subset or
Kenichi Handa <handa@m17n.org>
parents:
88735
diff
changeset
|
229 :superset '(ascii eight-bit-control (thai-tis620 . 128))) |
88411 | 230 |
231 (define-charset 'jisx0201 | |
232 "JISX0201" | |
233 :short-name "JISX0201" | |
89483 | 234 :code-space [0 #xDF] |
235 :map "JISX0201") | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
236 |
88411 | 237 (define-charset 'latin-jisx0201 |
238 "Roman Part of JISX0201.1976" | |
239 :short-name "JISX0201 Roman" | |
240 :long-name "Japanese Roman (JISX0201.1976)" | |
241 :iso-final-char ?J | |
242 :emacs-mule-id 138 | |
243 :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
|
244 :subset '(jisx0201 33 126 0)) |
88411 | 245 |
246 (define-charset 'katakana-jisx0201 | |
247 "Katakana Part of JISX0201.1976" | |
248 :short-name "JISX0201 Katakana" | |
249 :long-name "Japanese Katakana (JISX0201.1976)" | |
250 :iso-final-char ?I | |
251 :emacs-mule-id 137 | |
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 161 254 -128)) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
254 |
88411 | 255 (define-charset 'chinese-gb2312 |
256 "GB2312 Chinese simplified: ISO-IR-58" | |
257 :short-name "GB2312" | |
258 :long-name "GB2312: ISO-IR-58" | |
259 :iso-final-char ?A | |
260 :emacs-mule-id 145 | |
261 :code-space [33 126 33 126] | |
262 :code-offset #x110000 | |
89483 | 263 :unify-map "GB2312") |
88411 | 264 |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
265 (define-charset 'chinese-gbk |
88486 | 266 "GBK Chinese simplified." |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
267 :short-name "GBK" |
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
268 :code-space [#x40 #xFE #x81 #xFE] |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
269 :code-offset #x160000 |
89483 | 270 :unify-map "GBK") |
88666 | 271 (define-charset-alias 'cp936 'chinese-gbk) |
88717 | 272 (define-charset-alias 'windows-936 'chinese-gbk) |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
273 |
88411 | 274 (define-charset 'chinese-cns11643-1 |
275 "CNS11643 Plane 1 Chinese traditional: ISO-IR-171" | |
276 :short-name "CNS11643-1" | |
277 :long-name "CNS11643-1 (Chinese traditional): ISO-IR-171" | |
278 :iso-final-char ?G | |
279 :emacs-mule-id 149 | |
280 :code-space [33 126 33 126] | |
281 :code-offset #x114000 | |
89483 | 282 :unify-map "CNS-1") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
283 |
88411 | 284 (define-charset 'chinese-cns11643-2 |
285 "CNS11643 Plane 2 Chinese traditional: ISO-IR-172" | |
286 :short-name "CNS11643-2" | |
287 :long-name "CNS11643-2 (Chinese traditional): ISO-IR-172" | |
288 :iso-final-char ?H | |
289 :emacs-mule-id 150 | |
290 :code-space [33 126 33 126] | |
291 :code-offset #x118000 | |
89483 | 292 :unify-map "CNS-2") |
88411 | 293 |
294 (define-charset 'chinese-cns11643-3 | |
295 "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183" | |
296 :short-name "CNS11643-3" | |
297 :long-name "CNS11643-3 (Chinese traditional): ISO-IR-183" | |
298 :iso-final-char ?I | |
299 :code-space [33 126 33 126] | |
300 :emacs-mule-id 246 | |
89483 | 301 :code-offset #x11C000 |
302 :unify-map "CNS-3") | |
88411 | 303 |
304 (define-charset 'chinese-cns11643-4 | |
305 "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184" | |
306 :short-name "CNS11643-4" | |
307 :long-name "CNS11643-4 (Chinese traditional): ISO-IR-184" | |
308 :iso-final-char ?J | |
309 :emacs-mule-id 247 | |
310 :code-space [33 126 33 126] | |
89483 | 311 :code-offset #x120000 |
312 :unify-map "CNS-4") | |
88411 | 313 |
314 (define-charset 'chinese-cns11643-5 | |
315 "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185" | |
316 :short-name "CNS11643-5" | |
317 :long-name "CNS11643-5 (Chinese traditional): ISO-IR-185" | |
318 :iso-final-char ?K | |
319 :emacs-mule-id 248 | |
320 :code-space [33 126 33 126] | |
89483 | 321 :code-offset #x124000 |
322 :unify-map "CNS-5") | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
323 |
88411 | 324 (define-charset 'chinese-cns11643-6 |
325 "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186" | |
326 :short-name "CNS11643-6" | |
327 :long-name "CNS11643-6 (Chinese traditional): ISO-IR-186" | |
328 :iso-final-char ?L | |
329 :emacs-mule-id 249 | |
330 :code-space [33 126 33 126] | |
89483 | 331 :code-offset #x128000 |
332 :unify-map "CNS-6") | |
88411 | 333 |
334 (define-charset 'chinese-cns11643-7 | |
335 "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187" | |
336 :short-name "CNS11643-7" | |
337 :long-name "CNS11643-7 (Chinese traditional): ISO-IR-187" | |
338 :iso-final-char ?M | |
339 :emacs-mule-id 250 | |
340 :code-space [33 126 33 126] | |
89483 | 341 :code-offset #x12C000 |
342 :unify-map "CNS-7") | |
88411 | 343 |
344 (define-charset 'big5 | |
345 "Big5 (Chinese traditional)" | |
346 :short-name "Big5" | |
347 :code-space [#x40 #xFE #xA1 #xFE] | |
348 :code-offset #x130000 | |
89483 | 349 :unify-map "BIG5") |
88666 | 350 ;; Fixme: AKA cp950 according to |
351 ;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>. Is | |
352 ;; that correct? | |
88411 | 353 |
354 (define-charset 'chinese-big5-1 | |
88486 | 355 "Frequently used part (A141-C67E) of Big5 (Chinese traditional)" |
88411 | 356 :short-name "Big5 (Level-1)" |
357 :long-name "Big5 (Level-1) A141-C67F" | |
358 :iso-final-char ?0 | |
359 :emacs-mule-id 152 | |
360 :code-space [#x21 #x7E #x21 #x7E] | |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
361 :code-offset #x135000 |
89483 | 362 :unify-map "BIG5-1") |
88411 | 363 |
364 (define-charset 'chinese-big5-2 | |
88486 | 365 "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)" |
88411 | 366 :short-name "Big5 (Level-2)" |
367 :long-name "Big5 (Level-2) C940-FEFE" | |
368 :iso-final-char ?1 | |
369 :emacs-mule-id 153 | |
370 :code-space [#x21 #x7E #x21 #x7E] | |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
371 :code-offset #x137800 |
89483 | 372 :unify-map "BIG5-2") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
373 |
88411 | 374 (define-charset 'japanese-jisx0208 |
375 "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87" | |
376 :short-name "JISX0208" | |
377 :long-name "JISX0208.1983/1990 (Japanese): ISO-IR-87" | |
378 :iso-final-char ?B | |
379 :emacs-mule-id 146 | |
380 :code-space [33 126 33 126] | |
381 :code-offset #x140000 | |
89483 | 382 :unify-map "JISX0208") |
88411 | 383 |
384 (define-charset 'japanese-jisx0208-1978 | |
385 "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42" | |
386 :short-name "JISX0208.1978" | |
89483 | 387 :long-name "JISX0208.1978 (JISC6226.1978): ISO-IR-42" |
88411 | 388 :iso-final-char ?@ |
389 :emacs-mule-id 144 | |
390 :code-space [33 126 33 126] | |
391 :code-offset #x144000 | |
89483 | 392 :unify-map "JISC6226") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
393 |
88411 | 394 (define-charset 'japanese-jisx0212 |
395 "JISX0212 Japanese supplement: ISO-IR-159" | |
396 :short-name "JISX0212" | |
397 :long-name "JISX0212 (Japanese): ISO-IR-159" | |
398 :iso-final-char ?D | |
399 :emacs-mule-id 148 | |
400 :code-space [33 126 33 126] | |
401 :code-offset #x148000 | |
89483 | 402 :unify-map "JISX0212") |
88411 | 403 |
89426 | 404 ;; Note that jisx0213 contains characters not in Unicode (3.2?). It's |
405 ;; arguable whether it should have a unify-map. | |
88411 | 406 (define-charset 'japanese-jisx0213-1 |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
407 "JISX0213.2000 Plane 1 (Japanese)" |
88411 | 408 :short-name "JISX0213-1" |
409 :iso-final-char ?O | |
410 :emacs-mule-id 151 | |
89483 | 411 :unify-map "JISX2131" |
88411 | 412 :code-space [33 126 33 126] |
413 :code-offset #x14C000) | |
17070 | 414 |
88411 | 415 (define-charset 'japanese-jisx0213-2 |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
416 "JISX0213.2000 Plane 2 (Japanese)" |
88411 | 417 :short-name "JISX0213-2" |
418 :iso-final-char ?P | |
419 :emacs-mule-id 254 | |
89483 | 420 :unify-map "JISX2132" |
88411 | 421 :code-space [33 126 33 126] |
422 :code-offset #x150000) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
423 |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
424 (define-charset 'japanese-jisx0213-a |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
425 "JISX0213.2004 adds these characters to JISX0213.2000." |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
426 :short-name "JISX0213A" |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
427 :dimension 2 |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
428 :code-space [33 126 33 126] |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
429 :supplementary-p t |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
430 :map "JISX213A") |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
431 |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
432 (define-charset 'japanese-jisx0213.2004-1 |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
433 "JISX0213.2004 Plane1 (Japanese)" |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
434 :short-name "JISX0213.2004-1" |
89793
cdb516af172d
(japanese-jisx0213.2004-1): Specify :dimension 2.
Kenichi Handa <handa@m17n.org>
parents:
89766
diff
changeset
|
435 :dimension 2 |
89797
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
436 :code-space [33 126 33 126] |
89766
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
437 :iso-final-char ?Q |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
438 :superset '(japanese-jisx0213-a japanese-jisx0213-1)) |
c7813ec27ad7
(japanese-jisx0213-a): New supplementary charset.
Kenichi Handa <handa@m17n.org>
parents:
89753
diff
changeset
|
439 |
89734
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
440 (define-charset 'katakana-sjis |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
441 "Katakana part of Shift-JIS" |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
442 :dimension 1 |
89753
d91d2d88af05
(katakana-sjis): Fix :superset to :subset.
Kenichi Handa <handa@m17n.org>
parents:
89741
diff
changeset
|
443 :code-space [#xA1 #xDF] |
d91d2d88af05
(katakana-sjis): Fix :superset to :subset.
Kenichi Handa <handa@m17n.org>
parents:
89741
diff
changeset
|
444 :subset '(jisx0201 #xA1 #xDF 0) |
89734
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
445 :supplementary-p t) |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
446 |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
447 (define-charset 'cp932-2-byte |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
448 "2-byte part of CP932" |
89741
fb91cfc5ed37
(cp932-2-byte): Specify :dimension.
Kenichi Handa <handa@m17n.org>
parents:
89734
diff
changeset
|
449 :dimension 2 |
89734
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
450 :map "CP932-2BYTE" |
89926
c452bfea1458
(cp932-2-byte): Fix :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89909
diff
changeset
|
451 :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
|
452 :supplementary-p t) |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
453 |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
454 (define-charset 'cp932 |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
455 "CP932 (Microsoft shift-jis)" |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
456 :code-space [#x00 #xFF #x00 #xFE] |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
457 :short-name "CP932" |
bb0fde79c866
(katakana-sjis, cp932-2-byte, cp932): New charsets.
Kenichi Handa <handa@m17n.org>
parents:
89647
diff
changeset
|
458 :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
|
459 |
88411 | 460 (define-charset 'korean-ksc5601 |
461 "KSC5601 Korean Hangul and Hanja: ISO-IR-149" | |
462 :short-name "KSC5601" | |
463 :long-name "KSC5601 (Korean): ISO-IR-149" | |
464 :iso-final-char ?C | |
465 :emacs-mule-id 147 | |
466 :code-space [33 126 33 126] | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
467 :code-offset #x279f94 ; ... #x27c217 |
89483 | 468 :unify-map "KSC5601") |
17070 | 469 |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
470 (define-charset 'big5-hkscs |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
471 "Big5-HKSCS (Chinese traditional, Hong Kong supplement)" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
472 :short-name "Big5" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
473 :code-space [#x40 #xFE #xA1 #xFE] |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
474 :code-offset #x27c218 ; ... #x280839 |
89483 | 475 :unify-map "BIG5-HKSCS") |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
476 |
88666 | 477 ;; Fixme: Korean cp949/UHC |
478 | |
88411 | 479 (define-charset 'chinese-sisheng |
480 "SiSheng characters for PinYin/ZhuYin" | |
481 :short-name "SiSheng" | |
482 :long-name "SiSheng (PinYin/ZhuYin)" | |
483 :iso-final-char ?0 | |
484 :emacs-mule-id 160 | |
485 :code-space [33 126] | |
89483 | 486 :unify-map "MULE-sisheng" |
88411 | 487 :code-offset #x200000) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
488 |
88735 | 489 ;; A subset of the 1989 version of IPA. It consists of the consonant |
490 ;; signs used in English, French, German and Italian, and all vowels | |
491 ;; signs in the table. [says old MULE doc] | |
88411 | 492 (define-charset 'ipa |
493 "IPA (International Phonetic Association)" | |
494 :short-name "IPA" | |
495 :iso-final-char ?0 | |
496 :emacs-mule-id 161 | |
89483 | 497 :unify-map "MULE-ipa" |
88411 | 498 :code-space [32 127] |
499 :code-offset #x200080) | |
17070 | 500 |
88411 | 501 (define-charset 'viscii |
502 "VISCII1.1" | |
503 :short-name "VISCII" | |
504 :long-name "VISCII 1.1" | |
505 :code-space [0 255] | |
89483 | 506 :map "VISCII") |
88411 | 507 |
508 (define-charset 'vietnamese-viscii-lower | |
509 "VISCII1.1 lower-case" | |
510 :short-name "VISCII lower" | |
511 :long-name "VISCII lower-case" | |
512 :iso-final-char ?1 | |
513 :emacs-mule-id 162 | |
514 :code-space [32 127] | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
515 :code-offset #x200200 |
89483 | 516 :unify-map "MULE-lviscii") |
17070 | 517 |
88411 | 518 (define-charset 'vietnamese-viscii-upper |
519 "VISCII1.1 upper-case" | |
520 :short-name "VISCII upper" | |
521 :long-name "VISCII upper-case" | |
522 :iso-final-char ?2 | |
523 :emacs-mule-id 163 | |
524 :code-space [32 127] | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
525 :code-offset #x200280 |
89483 | 526 :unify-map "MULE-uviscii") |
88411 | 527 |
528 (define-charset 'vscii | |
89483 | 529 "VSCII1.1 (TCVN-5712 VN1)" |
88411 | 530 :short-name "VSCII" |
531 :code-space [0 255] | |
89483 | 532 :map "VSCII") |
533 | |
534 (define-charset-alias 'tcvn-5712 'vscii) | |
88411 | 535 |
88727 | 536 ;; Fixme: see note in tcvn.map about combining characters |
89483 | 537 (define-charset 'vscii-2 |
538 "VSCII-2 (TCVN-5712 VN2)" | |
88727 | 539 :code-space [0 255] |
89483 | 540 :map "VSCII-2") |
88727 | 541 |
88411 | 542 (define-charset 'koi8-r |
543 "KOI8-R" | |
544 :short-name "KOI8-R" | |
545 :ascii-compatible-p t | |
546 :code-space [0 255] | |
89483 | 547 :map "KOI8-R") |
88411 | 548 |
549 (define-charset-alias 'koi8 'koi8-r) | |
550 | |
551 (define-charset 'alternativnyj | |
552 "ALTERNATIVNYJ" | |
553 :short-name "alternativnyj" | |
554 :ascii-compatible-p t | |
555 :code-space [0 255] | |
89483 | 556 :map "ALTERNATIVNYJ") |
89200 | 557 |
558 (define-charset 'cp866 | |
559 "CP866" | |
560 :short-name "cp866" | |
561 :ascii-compatible-p t | |
562 :code-space [0 255] | |
89483 | 563 :map "IBM866") |
89200 | 564 (define-charset-alias 'ibm866 'cp866) |
17070 | 565 |
88533 | 566 (define-charset 'koi8-u |
567 "KOI8-U" | |
568 :short-name "KOI8-U" | |
569 :ascii-compatible-p t | |
570 :code-space [0 255] | |
89483 | 571 :map "KOI8-U") |
88533 | 572 |
573 (define-charset 'koi8-t | |
574 "KOI8-T" | |
575 :short-name "KOI8-T" | |
576 :ascii-compatible-p t | |
577 :code-space [0 255] | |
89483 | 578 :map "KOI8-T") |
88533 | 579 |
580 (define-charset 'georgian-ps | |
581 "GEORGIAN-PS" | |
582 :short-name "GEORGIAN-PS" | |
583 :ascii-compatible-p t | |
584 :code-space [0 255] | |
89483 | 585 :map "KA-PS") |
88533 | 586 |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
587 (define-charset 'georgian-academy |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
588 "GEORGIAN-ACADEMY" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
589 :short-name "GEORGIAN-ACADEMY" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
590 :ascii-compatible-p t |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
591 :code-space [0 255] |
89483 | 592 :map "KA-ACADEMY") |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
593 |
88533 | 594 (define-charset 'windows-1250 |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
595 "WINDOWS-1250 (Central Europe)" |
88533 | 596 :short-name "WINDOWS-1250" |
597 :ascii-compatible-p t | |
598 :code-space [0 255] | |
89483 | 599 :map "CP1250") |
88533 | 600 (define-charset-alias 'cp1250 'windows-1250) |
601 | |
602 (define-charset 'windows-1251 | |
88666 | 603 "WINDOWS-1251 (Cyrillic)" |
88533 | 604 :short-name "WINDOWS-1251" |
605 :ascii-compatible-p t | |
606 :code-space [0 255] | |
89483 | 607 :map "CP1251") |
88533 | 608 (define-charset-alias 'cp1251 'windows-1251) |
17070 | 609 |
88533 | 610 (define-charset 'windows-1252 |
88666 | 611 "WINDOWS-1252 (Latin I)" |
88533 | 612 :short-name "WINDOWS-1252" |
613 :ascii-compatible-p t | |
614 :code-space [0 255] | |
89483 | 615 :map "CP1252") |
88533 | 616 (define-charset-alias 'cp1252 'windows-1252) |
617 | |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
618 (define-charset 'windows-1253 |
88666 | 619 "WINDOWS-1253 (Greek)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
620 :short-name "WINDOWS-1253" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
621 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
622 :code-space [0 255] |
89483 | 623 :map "CP1253") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
624 (define-charset-alias 'cp1253 'windows-1253) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
625 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
626 (define-charset 'windows-1254 |
88666 | 627 "WINDOWS-1254 (Turkish)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
628 :short-name "WINDOWS-1254" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
629 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
630 :code-space [0 255] |
89483 | 631 :map "CP1254") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
632 (define-charset-alias 'cp1254 'windows-1254) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
633 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
634 (define-charset 'windows-1255 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
635 "WINDOWS-1255 (Hebrew)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
636 :short-name "WINDOWS-1255" |
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 "CP1255") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
640 (define-charset-alias 'cp1255 'windows-1255) |
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-1256 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
643 "WINDOWS-1256 (Arabic)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
644 :short-name "WINDOWS-1256" |
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 "CP1256") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
648 (define-charset-alias 'cp1256 'windows-1256) |
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-1257 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
651 "WINDOWS-1257 (Baltic)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
652 :short-name "WINDOWS-1257" |
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 "CP1257") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
656 (define-charset-alias 'cp1257 'windows-1257) |
17070 | 657 |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
658 (define-charset 'windows-1258 |
88666 | 659 "WINDOWS-1258 (Viet Nam)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
660 :short-name "WINDOWS-1258" |
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 "CP1258") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
664 (define-charset-alias 'cp1258 'windows-1258) |
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 'next |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
667 "NEXT" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
668 :short-name "NEXT" |
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 "NEXTSTEP") |
17070 | 672 |
88533 | 673 (define-charset 'cp1125 |
674 "CP1125" | |
675 :short-name "CP1125" | |
676 :code-space [0 255] | |
90217
4e5457cf7dc7
(cp1125): Set :ascii-compatible-p property to t.
Kenichi Handa <handa@m17n.org>
parents:
90200
diff
changeset
|
677 :ascii-compatible-p t |
89483 | 678 :map "CP1125") |
88533 | 679 (define-charset-alias 'ruscii 'cp1125) |
680 ;; Original name for cp1125, says Serhii Hlodin <hlodin@lutsk.bank.gov.ua> | |
681 (define-charset-alias 'cp866u 'cp1125) | |
17070 | 682 |
88671 | 683 ;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html |
684 ;; shows this as not ASCII comptaible, with various graphics in | |
685 ;; 0x01-0x1F. | |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
686 (define-charset 'cp437 |
88671 | 687 "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
|
688 :short-name "CP437" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
689 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
690 :ascii-compatible-p t |
89483 | 691 :map "IBM437") |
17070 | 692 |
88666 | 693 (define-charset 'cp720 |
694 "CP720 (Arabic)" | |
695 :short-name "CP720" | |
696 :code-space [0 255] | |
697 :ascii-compatible-p t | |
89483 | 698 :map "CP720") |
88666 | 699 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
700 (define-charset 'cp737 |
88671 | 701 "CP737 (PC Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
702 :short-name "CP737" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
703 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
704 :ascii-compatible-p t |
89483 | 705 :map "CP737") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
706 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
707 (define-charset 'cp775 |
88671 | 708 "CP775 (PC Baltic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
709 :short-name "CP775" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
710 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
711 :ascii-compatible-p t |
89483 | 712 :map "CP775") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
713 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
714 (define-charset 'cp851 |
89089 | 715 "CP851 (Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
716 :short-name "CP851" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
717 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
718 :ascii-compatible-p t |
89483 | 719 :map "IBM851") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
720 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
721 (define-charset 'cp852 |
88671 | 722 "CP852 (MS-DOS Latin-2)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
723 :short-name "CP852" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
724 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
725 :ascii-compatible-p t |
89483 | 726 :map "IBM852") |
17070 | 727 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
728 (define-charset 'cp855 |
88671 | 729 "CP855 (IBM Cyrillic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
730 :short-name "CP855" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
731 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
732 :ascii-compatible-p t |
89483 | 733 :map "IBM855") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
734 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
735 (define-charset 'cp857 |
88671 | 736 "CP857 (IBM Turkish)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
737 :short-name "CP857" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
738 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
739 :ascii-compatible-p t |
89483 | 740 :map "IBM857") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
741 |
88666 | 742 (define-charset 'cp858 |
743 "CP858 (Multilingual Latin I + Euro)" | |
744 :short-name "CP858" | |
745 :code-space [0 255] | |
746 :ascii-compatible-p t | |
89483 | 747 :map "CP858") |
88671 | 748 (define-charset-alias 'cp00858 'cp858) ; IANA has IBM00858/CP00858 |
17070 | 749 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
750 (define-charset 'cp860 |
88671 | 751 "CP860 (MS-DOS Portuguese)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
752 :short-name "CP860" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
753 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
754 :ascii-compatible-p t |
89483 | 755 :map "IBM860") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
756 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
757 (define-charset 'cp861 |
88671 | 758 "CP861 (MS-DOS Icelandic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
759 :short-name "CP861" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
760 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
761 :ascii-compatible-p t |
89483 | 762 :map "IBM861") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
763 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
764 (define-charset 'cp862 |
88671 | 765 "CP862 (PC Hebrew)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
766 :short-name "CP862" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
767 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
768 :ascii-compatible-p t |
89483 | 769 :map "IBM862") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
770 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
771 (define-charset 'cp863 |
88671 | 772 "CP863 (MS-DOS Canadian French)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
773 :short-name "CP863" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
774 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
775 :ascii-compatible-p t |
89483 | 776 :map "IBM863") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
777 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
778 (define-charset 'cp864 |
88671 | 779 "CP864 (PC Arabic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
780 :short-name "CP864" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
781 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
782 :ascii-compatible-p t |
89483 | 783 :map "IBM864") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
784 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
785 (define-charset 'cp865 |
88671 | 786 "CP865 (MS-DOS Nordic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
787 :short-name "CP865" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
788 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
789 :ascii-compatible-p t |
89483 | 790 :map "IBM865") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
791 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
792 (define-charset 'cp869 |
88671 | 793 "CP869 (IBM Modern Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
794 :short-name "CP869" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
795 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
796 :ascii-compatible-p t |
89483 | 797 :map "IBM869") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
798 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
799 (define-charset 'cp874 |
88671 | 800 "CP874 (IBM Thai)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
801 :short-name "CP874" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
802 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
803 :ascii-compatible-p t |
89483 | 804 :map "IBM874") |
17070 | 805 |
806 ;; For Arabic, we need three different types of character sets. | |
807 ;; Digits are of direction left-to-right and of width 1-column. | |
808 ;; Others are of direction right-to-left and of width 1-column or | |
809 ;; 2-column. | |
88411 | 810 (define-charset 'arabic-digit |
811 "Arabic digit" | |
812 :short-name "Arabic digit" | |
813 :iso-final-char ?2 | |
814 :emacs-mule-id 164 | |
815 :code-space [34 42] | |
816 :code-offset #x0600) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
817 |
88411 | 818 (define-charset 'arabic-1-column |
819 "Arabic 1-column" | |
820 :short-name "Arabic 1-col" | |
821 :long-name "Arabic 1-column" | |
822 :iso-final-char ?3 | |
823 :emacs-mule-id 165 | |
824 :code-space [33 126] | |
825 :code-offset #x200100) | |
826 | |
827 (define-charset 'arabic-2-column | |
828 "Arabic 2-column" | |
829 :short-name "Arabic 2-col" | |
830 :long-name "Arabic 2-column" | |
831 :iso-final-char ?4 | |
832 :emacs-mule-id 224 | |
833 :code-space [33 126] | |
834 :code-offset #x200180) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
835 |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
836 ;; Lao script. |
88411 | 837 ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF. |
89089 | 838 ;; Not all of them are defined unicodes. |
88411 | 839 (define-charset 'lao |
840 "Lao characters (ISO10646 0E81..0EDF)" | |
841 :short-name "Lao" | |
842 :iso-final-char ?1 | |
843 :emacs-mule-id 167 | |
844 :code-space [33 126] | |
845 :code-offset #x0E81) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
846 |
88411 | 847 (define-charset 'mule-lao |
848 "Lao characters (ISO10646 0E81..0EDF)" | |
849 :short-name "Lao" | |
850 :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
|
851 :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
|
852 |
17070 | 853 |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
854 ;; 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
|
855 ;; 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
|
856 ;; script which IS-13194 supports. |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
857 |
88411 | 858 (define-charset 'indian-is13194 |
859 "Generic Indian charset for data exchange with IS 13194" | |
860 :short-name "IS 13194" | |
861 :long-name "Indian IS 13194" | |
862 :iso-final-char ?5 | |
863 :emacs-mule-id 225 | |
864 :code-space [33 126] | |
865 :code-offset #x180000) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
866 |
89483 | 867 (let ((code-offset #x180100)) |
868 (dolist (script '(devanagari sanskrit bengali tamil telugu assamese | |
869 oriya kannada malayalam gujarati punjabi)) | |
870 (define-charset (intern (format "%s-cdac" script)) | |
871 (format "Glyphs of %s script for CDAC font. Subset of `indian-glyph'." | |
872 (capitalize (symbol-name script))) | |
873 :short-name (format "CDAC %s glyphs" (capitalize (symbol-name script))) | |
874 :code-space [0 255] | |
875 :code-offset code-offset) | |
876 (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
|
877 |
89483 | 878 (dolist (script '(devanagari bengali punjabi gujarati |
879 oriya tamil telugu kannada malayalam)) | |
880 (define-charset (intern (format "%s-akruti" script)) | |
881 (format "Glyphs of %s script for AKRUTI font. Subset of `indian-glyph'." | |
882 (capitalize (symbol-name script))) | |
883 :short-name (format "AKRUTI %s glyphs" (capitalize (symbol-name script))) | |
884 :code-space [0 255] | |
885 :code-offset code-offset) | |
886 (setq code-offset (+ code-offset #x100)))) | |
89091 | 887 |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
888 (define-charset 'indian-glyph |
88411 | 889 "Glyphs for Indian characters." |
890 :short-name "Indian glyph" | |
891 :iso-final-char ?4 | |
892 :emacs-mule-id 240 | |
893 :code-space [32 127 32 127] | |
894 :code-offset #x180100) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
895 |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
896 ;; Actual Glyph for 1-column width. |
88411 | 897 (define-charset 'indian-1-column |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
898 "Indian charset for 1-column width glyphs." |
88411 | 899 :short-name "Indian 1-col" |
900 :long-name "Indian 1 Column" | |
901 :iso-final-char ?6 | |
89890
f3047b4ebf04
(indian-1-column): Fix :emacs-mule-id.
Kenichi Handa <handa@m17n.org>
parents:
89822
diff
changeset
|
902 :emacs-mule-id 251 |
88411 | 903 :code-space [33 126 33 126] |
904 :code-offset #x184000) | |
905 | |
906 ;; Actual Glyph for 2-column width. | |
907 (define-charset 'indian-2-column | |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
908 "Indian charset for 2-column width glyphs." |
88411 | 909 :short-name "Indian 2-col" |
910 :long-name "Indian 2 Column" | |
911 :iso-final-char ?5 | |
912 :emacs-mule-id 251 | |
913 :code-space [33 126 33 126] | |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
914 :code-offset #x184000) |
88411 | 915 |
916 (define-charset 'tibetan | |
917 "Tibetan characters" | |
918 :iso-final-char ?7 | |
919 :short-name "Tibetan 2-col" | |
88486 | 920 :long-name "Tibetan 2 column" |
88411 | 921 :iso-final-char ?7 |
922 :emacs-mule-id 252 | |
89483 | 923 :unify-map "MULE-tibetan" |
89292
1bc1e30ea8d5
(tibetan): Fix :code-space property.
Kenichi Handa <handa@m17n.org>
parents:
89267
diff
changeset
|
924 :code-space [33 126 33 37] |
88411 | 925 :code-offset #x190000) |
926 | |
927 (define-charset 'tibetan-1-column | |
928 "Tibetan 1 column glyph" | |
929 :short-name "Tibetan 1-col" | |
930 :long-name "Tibetan 1 column" | |
931 :iso-final-char ?8 | |
932 :emacs-mule-id 241 | |
933 :code-space [33 126 33 37] | |
89292
1bc1e30ea8d5
(tibetan): Fix :code-space property.
Kenichi Handa <handa@m17n.org>
parents:
89267
diff
changeset
|
934 :code-offset #x190000) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
935 |
33044
7878d85aef6d
New charsets mule-unicode-2500-33ff and mule-unicode-e000-ffff.
Kenichi Handa <handa@m17n.org>
parents:
32786
diff
changeset
|
936 ;; Subsets of Unicode. |
88411 | 937 (define-charset 'mule-unicode-2500-33ff |
938 "Unicode characters of the range U+2500..U+33FF." | |
939 :short-name "Unicode subset 2" | |
940 :long-name "Unicode subset (U+2500..U+33FF)" | |
941 :iso-final-char ?2 | |
942 :emacs-mule-id 242 | |
943 :code-space [#x20 #x7f #x20 #x47] | |
944 :code-offset #x2500) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
945 |
88411 | 946 (define-charset 'mule-unicode-e000-ffff |
947 "Unicode characters of the range U+E000..U+FFFF." | |
948 :short-name "Unicode subset 3" | |
949 :long-name "Unicode subset (U+E000+FFFF)" | |
950 :iso-final-char ?3 | |
951 :emacs-mule-id 243 | |
952 :code-space [#x20 #x7F #x20 #x75] | |
88843 | 953 :code-offset #xE000 |
954 :max-code 30015) ; U+FFFF | |
17070 | 955 |
88411 | 956 (define-charset 'mule-unicode-0100-24ff |
957 "Unicode characters of the range U+0100..U+24FF." | |
958 :short-name "Unicode subset" | |
959 :long-name "Unicode subset (U+0100..U+24FF)" | |
960 :iso-final-char ?1 | |
961 :emacs-mule-id 244 | |
962 :code-space [#x20 #x7F #x20 #x7F] | |
963 :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
|
964 |
89089 | 965 (define-charset 'unicode-bmp |
89797
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
966 "Unicode Basic Multilingual Plane (U+0000..U+FFFF)" |
89089 | 967 :short-name "Unicode BMP" |
968 :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
|
969 :code-offset 0) |
89091 | 970 |
89797
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
971 (define-charset 'unicode-smp |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
972 "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
|
973 :short-name "Unicode SMP " |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
974 :code-space [0 255 0 255] |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
975 :code-offset #x10000) |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
976 |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
977 (define-charset 'unicode-sip |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
978 "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
|
979 :short-name "Unicode SIP" |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
980 :code-space [0 255 0 255] |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
981 :code-offset #x20000) |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
982 |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
983 (define-charset 'unicode-ssp |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
984 "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
|
985 :short-name "Unicode SSP" |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
986 :code-space [0 255 0 255] |
fdc51e185411
(japanese-jisx0213.2004-1): Specify :code-space.
Kenichi Handa <handa@m17n.org>
parents:
89793
diff
changeset
|
987 :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
|
988 |
88411 | 989 (define-charset 'ethiopic |
88486 | 990 "Ethiopic characters for Amharic and Tigrigna." |
88411 | 991 :short-name "Ethiopic" |
992 :long-name "Ethiopic characters" | |
993 :iso-final-char ?3 | |
994 :emacs-mule-id 245 | |
89483 | 995 :unify-map "MULE-ethiopic" |
88411 | 996 :code-space [33 126 33 126] |
997 :code-offset #x1A0000) | |
17070 | 998 |
88411 | 999 (define-charset 'mac-roman |
1000 "Mac Roman charset" | |
1001 :short-name "Mac Roman" | |
1002 :ascii-compatible-p t | |
1003 :code-space [0 255] | |
89483 | 1004 :map "MACINTOSH") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1005 |
88533 | 1006 ;; Fixme: modern EBCDIC variants, e.g. IBM00924? |
1007 (define-charset 'ebcdic-us | |
1008 "US version of EBCDIC" | |
1009 :short-name "EBCDIC-US" | |
1010 :code-space [0 255] | |
1011 :mime-charset 'ebcdic-us | |
89483 | 1012 :map "EBCDICUS") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1013 |
88533 | 1014 (define-charset 'ebcdic-uk |
1015 "UK version of EBCDIC" | |
1016 :short-name "EBCDIC-UK" | |
1017 :code-space [0 255] | |
1018 :mime-charset 'ebcdic-uk | |
89483 | 1019 :map "EBCDICUK") |
88533 | 1020 |
89200 | 1021 (define-charset 'ibm1047 |
1022 ;; Says groff: | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
1023 "IBM1047, `EBCDIC Latin 1/Open Systems' used by OS/390 Unix." |
89200 | 1024 :short-name "IBM1047" |
1025 :code-space [0 255] | |
1026 :mime-charset 'ibm1047 | |
89483 | 1027 :map "IBM1047") |
89200 | 1028 (define-charset-alias 'cp1047 'ibm1047) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1029 |
88575 | 1030 (define-charset 'hp-roman8 |
1031 "Encoding used by Hewlet-Packard printer software" | |
1032 :short-name "HP-ROMAN8" | |
1033 :ascii-compatible-p t | |
1034 :code-space [0 255] | |
89483 | 1035 :map "HP-ROMAN8") |
88575 | 1036 |
88671 | 1037 ;; To make a coding system with this, a pre-write-conversion should |
1038 ;; account for the commented-out multi-valued code points in | |
1039 ;; stdenc.map. | |
88575 | 1040 (define-charset 'adobe-standard-encoding |
1041 "Adobe `standard encoding' used in PostScript" | |
1042 :short-name "ADOBE-STANDARD-ENCODING" | |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
1043 :code-space [#x20 255] |
88575 | 1044 :map "stdenc") |
17070 | 1045 |
88575 | 1046 (define-charset 'symbol |
1047 "Adobe symbol encoding used in PostScript" | |
1048 :short-name "ADOBE-SYMBOL" | |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
1049 :code-space [#x20 255] |
88575 | 1050 :map "symbol") |
1051 | |
1052 (define-charset 'ibm850 | |
88671 | 1053 "DOS codepage 850 (Latin-1)" |
88575 | 1054 :short-name "IBM850" |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
1055 :ascii-compatible-p t |
88575 | 1056 :code-space [0 255] |
89483 | 1057 :map "IBM850") |
88575 | 1058 (define-charset-alias 'cp850 'ibm850) |
1059 | |
89318 | 1060 (define-charset 'mik |
1061 "Bulgarian DOS codepage" | |
1062 :short-name "MIK" | |
1063 :ascii-compatible-p t | |
1064 :code-space [0 255] | |
89483 | 1065 :map "MIK") |
89318 | 1066 |
89483 | 1067 (define-charset 'ptcp154 |
89318 | 1068 "`Paratype' codepage (Asian Cyrillic)" |
1069 :short-name "PT154" | |
1070 :ascii-compatible-p t | |
1071 :code-space [0 255] | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
1072 :mime-charset 'pt154 |
89483 | 1073 :map "PTCP154") |
1074 (define-charset-alias 'pt154 'ptcp154) | |
1075 (define-charset-alias 'cp154 'ptcp154) | |
89318 | 1076 |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1077 (define-charset 'gb18030-2-byte |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1078 "GB18030 2-byte (0x814E..0xFEFE)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1079 :code-space [#x40 #xFE #x81 #xFE] |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1080 :supplementary-p t |
89483 | 1081 :map "GB180302") |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1082 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1083 (define-charset 'gb18030-4-byte-bmp |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1084 "GB18030 4-byte for BMP (0x81308130-0x8431A439)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1085 :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
|
1086 :supplementary-p t |
89483 | 1087 :map "GB180304") |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1088 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1089 (define-charset 'gb18030-4-byte-smp |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1090 "GB18030 4-byte for SMP (0x90308130-0xE3329A35)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1091 :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
|
1092 :min-code '(#x9030 . #x8130) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1093 :max-code '(#xE332 . #x9A35) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1094 :supplementary-p t |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1095 :code-offset #x10000) |
17070 | 1096 |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1097 (define-charset 'gb18030-4-byte-ext-1 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1098 "GB18030 4-byte (0x8431A530-0x8F39FE39)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1099 :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
|
1100 :min-code '(#x8431 . #xA530) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1101 :max-code '(#x8F39 . #xFE39) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1102 :supplementary-p t |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1103 :code-offset #x200000 ; ... #x22484B |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1104 ) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1105 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1106 (define-charset 'gb18030-4-byte-ext-2 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1107 "GB18030 4-byte (0xE3329A36-0xFE39FE39)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1108 :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
|
1109 :min-code '(#xE332 . #x9A36) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1110 :max-code '(#xFE39 . #xFE39) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1111 :supplementary-p t |
89822
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1112 :code-offset #x22484C ; ... #x279f93 |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1113 ) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1114 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1115 (define-charset 'gb18030 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1116 "GB18030" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1117 :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
|
1118 :min-code 0 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1119 :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
|
1120 :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
|
1121 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
|
1122 gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)) |
17070 | 1123 |
89822
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1124 (define-charset 'chinese-cns11643-15 |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1125 "CNS11643 Plane 15 Chinese Traditional" |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1126 :short-name "CNS11643-15" |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1127 :long-name "CNS11643-15 (Chinese traditional)" |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1128 :code-space [33 126 33 126] |
c6d196788a1c
(chinese-cns11643-15): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89797
diff
changeset
|
1129 :code-offset #x27A000) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
1130 |
88411 | 1131 (unify-charset 'chinese-gb2312) |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
1132 (unify-charset 'chinese-gbk) |
88411 | 1133 (unify-charset 'chinese-cns11643-1) |
1134 (unify-charset 'chinese-cns11643-2) | |
89483 | 1135 (unify-charset 'chinese-cns11643-3) |
1136 (unify-charset 'chinese-cns11643-4) | |
1137 (unify-charset 'chinese-cns11643-5) | |
1138 (unify-charset 'chinese-cns11643-6) | |
1139 (unify-charset 'chinese-cns11643-7) | |
88411 | 1140 (unify-charset 'big5) |
1141 (unify-charset 'chinese-big5-1) | |
1142 (unify-charset 'chinese-big5-2) | |
89483 | 1143 (unify-charset 'big5-hkscs) |
1144 (unify-charset 'korean-ksc5601) | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
1145 (unify-charset 'vietnamese-viscii-lower) |
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
1146 (unify-charset 'vietnamese-viscii-upper) |
88760 | 1147 (unify-charset 'chinese-sisheng) |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1148 (unify-charset 'ipa) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1149 (unify-charset 'tibetan) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1150 (unify-charset 'ethiopic) |
89483 | 1151 (unify-charset 'japanese-jisx0208-1978) |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1152 (unify-charset 'japanese-jisx0208) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1153 (unify-charset 'japanese-jisx0212) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1154 (unify-charset 'japanese-jisx0213-1) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1155 (unify-charset 'japanese-jisx0213-2) |
17070 | 1156 |
1157 | |
22126
97cf1cae1971
Change term unification to
Kenichi Handa <handa@m17n.org>
parents:
21713
diff
changeset
|
1158 ;; These are tables for translating characters on decoding and |
97cf1cae1971
Change term unification to
Kenichi Handa <handa@m17n.org>
parents:
21713
diff
changeset
|
1159 ;; encoding. |
88760 | 1160 ;; Fixme: these aren't used now -- should they be? |
88411 | 1161 (setq standard-translation-table-for-decode nil) |
17760
b3d62674b210
Delete code for alternate-charset-table.
Kenichi Handa <handa@m17n.org>
parents:
17541
diff
changeset
|
1162 |
22186
fc4aaf1b1772
Change term "character translation table" to "translation table".
Kenichi Handa <handa@m17n.org>
parents:
22126
diff
changeset
|
1163 (setq standard-translation-table-for-encode nil) |
17760
b3d62674b210
Delete code for alternate-charset-table.
Kenichi Handa <handa@m17n.org>
parents:
17541
diff
changeset
|
1164 |
17070 | 1165 ;;; Make fundamental coding systems. |
1166 | |
90039
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1167 ;; 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
|
1168 ;; defined in coding.c as below: |
88411 | 1169 ;; |
1170 ;; (define-coding-system 'no-conversion | |
90039
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1171 ;; "..." |
88411 | 1172 ;; :coding-type 'raw-text |
90039
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1173 ;; ...) |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1174 ;; (define-coding-system 'undecided |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1175 ;; "..." |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1176 ;; :coding-type 'undecided |
67146244da43
New coding system aliases unix, dos, and mac.
Kenichi Handa <handa@m17n.org>
parents:
90009
diff
changeset
|
1177 ;; ...) |
17070 | 1178 |
18529
8e293f1a19a9
(binary): Define as coding system alias.
Richard M. Stallman <rms@gnu.org>
parents:
18519
diff
changeset
|
1179 (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
|
1180 (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
|
1181 (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
|
1182 (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
|
1183 |
88411 | 1184 (define-coding-system 'raw-text |
89483 | 1185 "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
|
1186 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
|
1187 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
|
1188 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
|
1189 byte. |
9688519d51d6
(no-conversion): Fix docstring.
Kenichi Handa <handa@m17n.org>
parents:
36518
diff
changeset
|
1190 |
9688519d51d6
(no-conversion): Fix docstring.
Kenichi Handa <handa@m17n.org>
parents:
36518
diff
changeset
|
1191 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
|
1192 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
|
1193 is treated as a character." |
89483 | 1194 :coding-type 'raw-text |
1195 :for-unibyte t | |
1196 :mnemonic ?t) | |
88411 | 1197 |
89483 | 1198 (define-coding-system 'no-conversion-multibyte |
1199 "Like `no-conversion' but don't read a file into a unibyte buffer." | |
1200 :coding-type 'raw-text | |
1201 :eol-type 'unix | |
1202 :mnemonic ?=) | |
1203 | |
88411 | 1204 (define-coding-system 'iso-latin-1 |
1205 "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)." | |
89091 | 1206 :coding-type 'charset |
88411 | 1207 :mnemonic ?1 |
89091 | 1208 :charset-list '(iso-8859-1) |
88411 | 1209 :mime-charset 'iso-8859-1) |
1210 | |
1211 (define-coding-system-alias 'iso-8859-1 'iso-latin-1) | |
1212 (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
|
1213 |
88411 | 1214 ;; Coding systems not specific to each language environment. |
1215 | |
1216 (define-coding-system 'emacs-mule | |
1217 "Emacs 21 internal format used in buffer and string." | |
1218 :coding-type 'emacs-mule | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1219 :charset-list 'emacs-mule |
88411 | 1220 :mnemonic ?M) |
19607
ea0964347a40
(raw-text): New coding system. Set
Kenichi Handa <handa@m17n.org>
parents:
19372
diff
changeset
|
1221 |
88411 | 1222 (define-coding-system 'utf-8 |
1223 "UTF-8." | |
1224 :coding-type 'utf-8 | |
1225 :mnemonic ?U | |
89041
2ce9656d788b
(utf-8): Give :mime-charset property.
Kenichi Handa <handa@m17n.org>
parents:
88894
diff
changeset
|
1226 :charset-list '(unicode) |
2ce9656d788b
(utf-8): Give :mime-charset property.
Kenichi Handa <handa@m17n.org>
parents:
88894
diff
changeset
|
1227 :mime-charset 'utf-8) |
88411 | 1228 |
1229 (define-coding-system-alias 'mule-utf-8 'utf-8) | |
1230 | |
1231 (define-coding-system 'utf-8-emacs | |
88468 | 1232 "Support for all Emacs characters (including non-Unicode characters)." |
88411 | 1233 :coding-type 'utf-8 |
1234 :mnemonic ?U | |
89244
bf10578caec8
(utf-8-emacs): Delete :mime-charset.
Dave Love <fx@gnu.org>
parents:
89200
diff
changeset
|
1235 :charset-list '(emacs)) |
88411 | 1236 |
89436 | 1237 (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
|
1238 "UTF-16LE (little endian, no signature (BOM))." |
88411 | 1239 :coding-type 'utf-16 |
1240 :mnemonic ?U | |
88503 | 1241 :charset-list '(unicode) |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1242 :endian 'little |
89436 | 1243 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1244 :mime-charset 'utf-16le) |
17070 | 1245 |
89436 | 1246 (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
|
1247 "UTF-16BE (big endian, no signature (BOM))." |
88411 | 1248 :coding-type 'utf-16 |
1249 :mnemonic ?U | |
1250 :charset-list '(unicode) | |
89422 | 1251 :endian 'big |
89436 | 1252 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1253 :mime-charset 'utf-16be) |
17070 | 1254 |
89436 | 1255 (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
|
1256 "UTF-16 (little endian, with signature (BOM))." |
88411 | 1257 :coding-type 'utf-16 |
1258 :mnemonic ?U | |
1259 :charset-list '(unicode) | |
88440
5b1dd2e30f16
(utf-16-le): Use :bom attribute instead of :signature.
Kenichi Handa <handa@m17n.org>
parents:
88411
diff
changeset
|
1260 :bom t |
88503 | 1261 :endian 'little |
89436 | 1262 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1263 :mime-charset 'utf-16) |
17070 | 1264 |
89436 | 1265 (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
|
1266 "UTF-16 (big endian, with signature)." |
88411 | 1267 :coding-type 'utf-16 |
1268 :mnemonic ?U | |
1269 :charset-list '(unicode) | |
88440
5b1dd2e30f16
(utf-16-le): Use :bom attribute instead of :signature.
Kenichi Handa <handa@m17n.org>
parents:
88411
diff
changeset
|
1270 :bom t |
89422 | 1271 :endian 'big |
89436 | 1272 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1273 :mime-charset 'utf-16) |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1274 |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1275 (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
|
1276 "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
|
1277 :coding-type 'utf-16 |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1278 :mnemonic ?U |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1279 :charset-list '(unicode) |
89436 | 1280 :bom '(utf-16le-with-signature . utf-16be-with-signature) |
89422 | 1281 :endian 'big |
89436 | 1282 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1283 :mime-charset 'utf-16) |
17070 | 1284 |
89436 | 1285 ;; Backwards compatibility (old names, also used by Mule-UCS). We |
1286 ;; 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
|
1287 (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
|
1288 (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
|
1289 |
89436 | 1290 |
88411 | 1291 (define-coding-system 'iso-2022-7bit |
88647 | 1292 "ISO 2022 based 7-bit encoding using only G0." |
88411 | 1293 :coding-type 'iso-2022 |
1294 :mnemonic ?J | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1295 :charset-list 'iso-2022 |
88411 | 1296 :designation [(ascii t) nil nil nil] |
1297 :flags '(short ascii-at-eol ascii-at-cntl 7-bit designation composition)) | |
1298 | |
1299 (define-coding-system 'iso-2022-7bit-ss2 | |
88647 | 1300 "ISO 2022 based 7-bit encoding using SS2 for 96-charset." |
88411 | 1301 :coding-type 'iso-2022 |
1302 :mnemonic ?$ | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1303 :charset-list 'iso-2022 |
88411 | 1304 :designation [(ascii 94) nil (nil 96) nil] |
1305 :flags '(short ascii-at-eol ascii-at-cntl 7-bit | |
1306 designation single-shift composition)) | |
1307 | |
1308 (define-coding-system 'iso-2022-7bit-lock | |
88647 | 1309 "ISO-2022 coding system using Locking-Shift for 96-charset." |
88411 | 1310 :coding-type 'iso-2022 |
1311 :mnemonic ?& | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1312 :charset-list 'iso-2022 |
88411 | 1313 :designation [(ascii 94) (nil 96) nil nil] |
1314 :flags '(ascii-at-eol ascii-at-cntl 7-bit | |
1315 designation locking-shift composition)) | |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1316 |
18519
b6badf3614ea
Fix calls to define-coding-system-alias.
Richard M. Stallman <rms@gnu.org>
parents:
18377
diff
changeset
|
1317 (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
|
1318 |
88411 | 1319 (define-coding-system 'iso-2022-7bit-lock-ss2 |
88647 | 1320 "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN." |
88411 | 1321 :coding-type 'iso-2022 |
1322 :mnemonic ?i | |
1323 :charset-list '(ascii | |
1324 japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201 | |
1325 korean-ksc5601 | |
1326 chinese-gb2312 | |
1327 chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3 | |
1328 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6 | |
1329 chinese-cns11643-7) | |
1330 :designation [(ascii 94) | |
1331 (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 96) | |
1332 (nil chinese-cns11643-2) | |
1333 (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5 | |
1334 chinese-cns11643-6 chinese-cns11643-7)] | |
1335 :flags '(short ascii-at-eol ascii-at-cntl 7-bit locking-shift | |
1336 single-shift init-bol)) | |
17070 | 1337 |
18519
b6badf3614ea
Fix calls to define-coding-system-alias.
Richard M. Stallman <rms@gnu.org>
parents:
18377
diff
changeset
|
1338 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2) |
17070 | 1339 |
88411 | 1340 (define-coding-system 'iso-2022-8bit-ss2 |
88647 | 1341 "ISO 2022 based 8-bit encoding using SS2 for 96-charset." |
88411 | 1342 :coding-type 'iso-2022 |
1343 :mnemonic ?@ | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1344 :charset-list 'iso-2022 |
88411 | 1345 :designation [(ascii 94) nil (nil 96) nil] |
1346 :flags '(ascii-at-eol ascii-at-cntl designation single-shift composition)) | |
17070 | 1347 |
88411 | 1348 (define-coding-system 'compound-text |
1349 "Compound text based generic encoding for decoding unknown messages. | |
17070 | 1350 |
89483 | 1351 This coding system does not support extended segments of CTEXT." |
88411 | 1352 :coding-type 'iso-2022 |
1353 :mnemonic ?x | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1354 :charset-list 'iso-2022 |
88411 | 1355 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] |
90352 | 1356 :flags '(ascii-at-eol ascii-at-cntl long-form |
88411 | 1357 designation locking-shift single-shift composition) |
88503 | 1358 ;; Fixme: this isn't a valid MIME charset and has to be |
1359 ;; special-cased elsewhere -- fx | |
88411 | 1360 :mime-charset 'x-ctext) |
24619
6057f7a48050
(x-ctext): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
24308
diff
changeset
|
1361 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1362 (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
|
1363 (define-coding-system-alias 'ctext 'compound-text) |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1364 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1365 ;; 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
|
1366 ;; 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
|
1367 ;; 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
|
1368 ;; 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
|
1369 ;; 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
|
1370 (define-coding-system 'ctext-no-compositions |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1371 "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
|
1372 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1373 Like `compound-text', but does not produce escape sequences for compositions." |
88411 | 1374 :coding-type 'iso-2022 |
1375 :mnemonic ?x | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1376 :charset-list 'iso-2022 |
88411 | 1377 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] |
1378 :flags '(ascii-at-eol ascii-at-cntl | |
1379 designation locking-shift single-shift)) | |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1380 |
88411 | 1381 (define-coding-system 'compound-text-with-extensions |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1382 "Compound text encoding with ICCCM Extended Segment extensions. |
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1383 |
53241
b5acb6a7d79b
(compound-text-with-extensions): Change the type to 2 (iso-2022 base).
Kenichi Handa <handa@m17n.org>
parents:
52401
diff
changeset
|
1384 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
|
1385 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
|
1386 |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1387 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
|
1388 for decoding and encoding files, process I/O, etc." |
89909 | 1389 :coding-type 'iso-2022 |
88411 | 1390 :mnemonic ?x |
89909 | 1391 :charset-list 'iso-2022 |
1392 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] | |
90352 | 1393 :flags '(ascii-at-eol ascii-at-cntl long-form |
89909 | 1394 designation locking-shift single-shift) |
88411 | 1395 :post-read-conversion 'ctext-post-read-conversion |
1396 :pre-write-conversion 'ctext-pre-write-conversion) | |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1397 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1398 (define-coding-system-alias |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1399 '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
|
1400 (define-coding-system-alias |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1401 '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
|
1402 |
88411 | 1403 (define-coding-system 'us-ascii |
89483 | 1404 "Encode ASCII as-is and encode non-ASCII characters to `?'." |
88411 | 1405 :coding-type 'charset |
1406 :mnemonic ?- | |
1407 :charset-list '(ascii) | |
1408 :default-char ?? | |
1409 :mime-charset 'us-ascii) | |
19266
a042f26b7a4c
(iso-safe): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
19005
diff
changeset
|
1410 |
88411 | 1411 (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
|
1412 |
89426 | 1413 (define-coding-system 'utf-7 |
1414 "UTF-7 encoding of Unicode (RFC 2152)." | |
1415 :coding-type 'utf-8 | |
1416 :mnemonic ?U | |
1417 :mime-charset 'utf-7 | |
1418 :charset-list '(unicode) | |
1419 :pre-write-conversion 'utf-7-pre-write-conversion | |
1420 :post-read-conversion 'utf-7-post-read-conversion) | |
50118
c38bf27db0aa
(iso-latin-1): Moved from european.el.
Kenichi Handa <handa@m17n.org>
parents:
49598
diff
changeset
|
1421 |
91116
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1422 (define-coding-system 'utf-7-imap |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1423 "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
|
1424 :coding-type 'utf-8 |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1425 :mnemonic ?u |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1426 :charset-list '(unicode) |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1427 :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
|
1428 :post-read-conversion 'utf-7-imap-post-read-conversion) |
ec7b5eef2638
(utf-7-imap): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
90996
diff
changeset
|
1429 |
88411 | 1430 ;; Use us-ascii for terminal output if some other coding system is not |
23196 | 1431 ;; specified explicitly. |
88411 | 1432 (set-safe-terminal-coding-system-internal 'us-ascii) |
19266
a042f26b7a4c
(iso-safe): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
19005
diff
changeset
|
1433 |
17070 | 1434 ;; The other coding-systems are defined in each language specific |
88411 | 1435 ;; files under lisp/language. |
17070 | 1436 |
21713
aa160e4358ac
(file-coding-system-alist): Use emacs-mule for .elc files.
Richard M. Stallman <rms@gnu.org>
parents:
20732
diff
changeset
|
1437 ;; 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
|
1438 ;; 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
|
1439 ;; 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
|
1440 ;; Tar files are not decoded at all, but we treat them as raw bytes. |
17070 | 1441 |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1442 (setq file-coding-system-alist |
88776
805a3bb7daf4
(file-coding-system-alist): Change
Dave Love <fx@gnu.org>
parents:
88760
diff
changeset
|
1443 '(("\\.elc\\'" . utf-8-emacs) |
42047
83eb799f3657
(translation-table-for-input): New
Dave Love <fx@gnu.org>
parents:
41468
diff
changeset
|
1444 ("\\.utf\\(-8\\)?\\'" . utf-8) |
88575 | 1445 ;; This is the defined default for XML documents. It may be |
1446 ;; overridden by a charset specification in the header. That | |
1447 ;; should be grokked by the auto-coding mechanism, but rms | |
1448 ;; vetoed that. -- fx | |
1449 ("\\.xml\\'" . utf-8) | |
34264
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1450 ;; 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
|
1451 ;; 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
|
1452 ;; newlines. This is required to make the special treatment |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1453 ;; of the "\ newline" combination in loaddefs.el, which marks |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1454 ;; the beginning of a doc string, work. |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1455 ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix)) |
32228
6a5bae3ed1c1
file-coding-system-alist): Use \',
Dave Love <fx@gnu.org>
parents:
30260
diff
changeset
|
1456 ("\\.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
|
1457 ( "\\.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
|
1458 ("\\.\\(tex\\|ltx\\|dtx\\|drv\\)\\'" . latexenc-find-file-coding-system) |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1459 ("" . (undecided . nil)))) |
17070 | 1460 |
1461 | |
1462 ;;; Setting coding categories and their priorities. | |
1463 | |
1464 ;; This setting is just to read an Emacs Lisp source files which | |
1465 ;; 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
|
1466 ;; values are set by the command `set-language-environment' for each |
17070 | 1467 ;; language environment. |
1468 | |
88411 | 1469 (set-coding-system-priority |
1470 'iso-latin-1 | |
1471 'utf-8 | |
1472 'iso-2022-7bit | |
1473 ) | |
17070 | 1474 |
19372 | 1475 |
1476 ;;; Miscellaneous settings. | |
88411 | 1477 |
1478 ;; Make all multibyte characters self-insert. | |
1479 (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
|
1480 (cons 128 (max-char)) |
88411 | 1481 'self-insert-command) |
1482 | |
50511
5930672784ee
Register ?\221 and ?\226 in latin-extra-code-table.
Kenichi Handa <handa@m17n.org>
parents:
50488
diff
changeset
|
1483 (aset latin-extra-code-table ?\221 t) |
19372 | 1484 (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
|
1485 (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
|
1486 (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
|
1487 (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
|
1488 (aset latin-extra-code-table ?\226 t) |
19372 | 1489 |
88647 | 1490 ;; Move least specific charsets to end of priority list |
1491 | |
1492 (apply #'set-charset-priority | |
1493 (delq 'unicode (delq 'emacs (charset-priority-list)))) | |
1494 | |
88600 | 1495 ;; The old code-pages library is obsoleted by coding systems based on |
1496 ;; the charsets defined in this file but might be required by user | |
1497 ;; code. | |
1498 (provide 'code-pages) | |
1499 | |
88575 | 1500 ;; Local variables: |
1501 ;; no-byte-compile: t | |
1502 ;; End: | |
23260
1e8cac8d2c50
Call update-coding-systems-internal at the tail.
Kenichi Handa <handa@m17n.org>
parents:
23196
diff
changeset
|
1503 |
61698
19c94353380d
(translation-table-for-input): Remove redundant declaration.
Stefan Monnier <monnier@iro.umontreal.ca>
parents:
53241
diff
changeset
|
1504 ;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5 |
17070 | 1505 ;;; mule-conf.el ends here |