Mercurial > emacs
annotate lisp/international/mule-conf.el @ 89573:6b5d42f51038
(x_get_font_repertory): Handle the case that the
encoding of font is other than Unicode.
author | Kenichi Handa <handa@m17n.org> |
---|---|
date | Mon, 06 Oct 2003 11:23:25 +0000 |
parents | 2f877ed80fa6 |
children | b1e7c4bffed1 |
rev | line source |
---|---|
17070 | 1 ;;; mule-conf.el --- configure multilingual environment |
2 | |
3 ;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN. | |
89483 | 4 ;; Licensed to the Free Software Foundation. |
5 ;; Copyright (C) 2002, 2003 Free Software Foundation, Inc. | |
6 ;; Copyright (C) 2003 | |
88411 | 7 ;; National Institute of Advanced Industrial Science and Technology (AIST) |
8 ;; Registration Number H13PRO009 | |
17070 | 9 |
88486 | 10 ;; Keywords: i18n, mule, multilingual, character set, coding system |
17070 | 11 |
12 ;; This file is part of GNU Emacs. | |
13 | |
14 ;; GNU Emacs is free software; you can redistribute it and/or modify | |
15 ;; it under the terms of the GNU General Public License as published by | |
16 ;; the Free Software Foundation; either version 2, or (at your option) | |
17 ;; any later version. | |
18 | |
19 ;; GNU Emacs is distributed in the hope that it will be useful, | |
20 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of | |
21 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
22 ;; GNU General Public License for more details. | |
23 | |
24 ;; You should have received a copy of the GNU General Public License | |
25 ;; along with GNU Emacs; see the file COPYING. If not, write to the | |
26 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330, | |
27 ;; Boston, MA 02111-1307, USA. | |
28 | |
29 ;;; Commentary: | |
30 | |
88575 | 31 ;; This file defines the Emacs charsets and some basic coding systems. |
32 ;; Other coding systems are defined in the files in directory | |
33 ;; lisp/language. | |
17070 | 34 |
35 ;;; Code: | |
36 | |
88666 | 37 ;;; Remarks |
38 | |
88575 | 39 ;; The ISO-IR registry is at http://www.itscj.ipsj.or.jp/ISO-IR/. |
40 ;; Standards docs equivalent to iso-2022 and iso-8859 are at | |
41 ;; http://www.ecma.ch/. | |
42 | |
88717 | 43 ;; FWIW, http://www.microsoft.com/globaldev/ lists the following for |
44 ;; MS Windows, which are presumably the only charsets we really need | |
45 ;; to worry about on such systems: | |
88666 | 46 ;; `OEM codepages': 437, 720, 737, 775, 850, 852, 855, 857, 858, 862, 866 |
47 ;; `Windows codepages': 1250, 1251, 1252, 1253, 1254, 1255, 1256, 1257, | |
48 ;; 1258, 874, 932, 936, 949, 950 | |
49 | |
17070 | 50 ;;; Definitions of character sets. |
51 | |
89089 | 52 ;; The charsets `ascii', `unicode' and `eight-bit' are already defined |
53 ;; in charset.c as below: | |
88411 | 54 ;; |
55 ;; (define-charset 'ascii | |
56 ;; "" | |
57 ;; :dimension 1 | |
58 ;; :code-space [0 127] | |
89089 | 59 ;; :iso-final-char ?B |
88411 | 60 ;; :ascii-compatible-p t |
61 ;; :emacs-mule-id 0 | |
62 ;; :code-offset 0) | |
63 ;; | |
64 ;; (define-charset 'unicode | |
65 ;; "" | |
66 ;; :dimension 3 | |
67 ;; :code-space [0 255 0 255 0 16] | |
68 ;; :ascii-compatible-p t | |
69 ;; :code-offset 0) | |
70 ;; | |
89089 | 71 ;; (define-charset 'eight-bit |
72 ;; "" | |
73 ;; :dimension 1 | |
74 ;; :code-space [128 255] | |
75 ;; :code-offset #x3FFF80) | |
76 ;; | |
88411 | 77 ;; We now set :docstring, :short-name, and :long-name properties. |
78 | |
79 (put-charset-property | |
80 'ascii :docstring "ASCII (ISO646 IRV)") | |
81 (put-charset-property | |
82 'ascii :short-name "ASCII") | |
83 (put-charset-property | |
84 'ascii :long-name "ASCII (ISO646 IRV)") | |
85 (put-charset-property | |
89050
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
86 'iso-8859-1 :docstring "Latin-1 (ISO/IEC 8859-1)") |
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
87 (put-charset-property |
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
88 'iso-8859-1 :short-name "Latin-1") |
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
89 (put-charset-property |
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
90 'iso-8859-1 :long-name "Latin-1") |
c00be25be9ad
Don't define the charset iso-8859-1 here, just setup its properties.
Kenichi Handa <handa@m17n.org>
parents:
89041
diff
changeset
|
91 (put-charset-property |
88411 | 92 'unicode :docstring "Unicode (ISO10646)") |
93 (put-charset-property | |
94 'unicode :short-name "Unicode") | |
95 (put-charset-property | |
96 'unicode :long-name "Unicode (ISO10646)") | |
89089 | 97 (put-charset-property 'eight-bit :docstring "Raw bytes 0-255") |
98 (put-charset-property 'eight-bit :short-name "Raw bytes") | |
17070 | 99 |
88411 | 100 (define-charset-alias 'ucs 'unicode) |
101 | |
102 (define-charset 'emacs | |
88647 | 103 "Full Emacs characters" |
88411 | 104 :ascii-compatible-p t |
105 :code-space [ 0 255 0 255 0 63 ] | |
106 :code-offset 0 | |
107 :supplementary-p t) | |
108 | |
109 (define-charset 'latin-iso8859-1 | |
110 "Right-Hand Part of ISO/IEC 8859/1 (Latin-1): ISO-IR-100" | |
111 :short-name "RHP of Latin-1" | |
112 :long-name "RHP of ISO/IEC 8859/1 (Latin-1): ISO-IR-100" | |
113 :iso-final-char ?A | |
114 :emacs-mule-id 129 | |
115 :code-space [32 127] | |
116 :code-offset 160) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
117 |
88735 | 118 ;; Name perhaps not ideal, but is XEmacs-compatible. |
119 (define-charset 'control-1 | |
88411 | 120 "8-bit control code (0x80..0x9F)" |
121 :short-name "8-bit control code" | |
122 :code-space [128 159] | |
123 :code-offset 128) | |
124 | |
88735 | 125 (define-charset 'eight-bit-control |
126 "Raw bytes in the range 0x80..0x9F (usually produced from invalid encodings)" | |
127 :short-name "Raw bytes 0x80..0x9F" | |
128 :code-space [128 159] | |
129 :code-offset #x3FFF80) ; see character.h | |
130 | |
88411 | 131 (define-charset 'eight-bit-graphic |
88735 | 132 "Raw bytes in the range 0xA0..0xFF (usually produced from invalid encodings)" |
133 :short-name "Raw bytes 0xA0..0xFF" | |
88411 | 134 :code-space [160 255] |
88735 | 135 :code-offset #x3FFFA0) ; see character.h |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
136 |
88411 | 137 (defmacro define-iso-single-byte-charset (symbol iso-symbol name nickname |
138 iso-ir iso-final | |
139 emacs-mule-id map) | |
140 `(progn | |
141 (define-charset ,symbol | |
142 ,name | |
143 :short-name ,nickname | |
144 :long-name ,name | |
145 :ascii-compatible-p t | |
146 :code-space [0 255] | |
147 :map ,map) | |
148 (if ,iso-symbol | |
149 (define-charset ,iso-symbol | |
150 (if ,iso-ir | |
151 (format "Right-Hand Part of %s (%s): ISO-IR-%d" | |
152 ,name ,nickname ,iso-ir) | |
153 (format "Right-Hand Part of %s (%s)" ,name ,nickname)) | |
154 :short-name (format "RHP of %s" ,name) | |
155 :long-name (format "RHP of %s (%s)" ,name ,nickname) | |
156 :iso-final-char ,iso-final | |
88486 | 157 :emacs-mule-id ,emacs-mule-id |
88411 | 158 :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
|
159 :subset (list ,symbol 160 255 -128))))) |
88411 | 160 |
161 (define-iso-single-byte-charset 'iso-8859-2 'latin-iso8859-2 | |
162 "ISO/IEC 8859/2" "Latin-2" 101 ?B 130 "8859-2") | |
163 | |
164 (define-iso-single-byte-charset 'iso-8859-3 'latin-iso8859-3 | |
165 "ISO/IEC 8859/3" "Latin-3" 109 ?C 131 "8859-3") | |
166 | |
167 (define-iso-single-byte-charset 'iso-8859-4 'latin-iso8859-4 | |
168 "ISO/IEC 8859/4" "Latin-4" 110 ?D 132 "8859-4") | |
169 | |
170 (define-iso-single-byte-charset 'iso-8859-5 'cyrillic-iso8859-5 | |
171 "ISO/IEC 8859/5" "Latin/Cyrillic" 144 ?L 140 "8859-5") | |
172 | |
173 (define-iso-single-byte-charset 'iso-8859-6 'arabic-iso8859-6 | |
174 "ISO/IEC 8859/6" "Latin/Arabic" 127 ?G 135 "8859-6") | |
175 | |
176 (define-iso-single-byte-charset 'iso-8859-7 'greek-iso8859-7 | |
177 "ISO/IEC 8859/7" "Latin/Greek" 126 ?F 134 "8859-7") | |
178 | |
179 (define-iso-single-byte-charset 'iso-8859-8 'hebrew-iso8859-8 | |
180 "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H 136 "8859-8") | |
181 | |
182 (define-iso-single-byte-charset 'iso-8859-9 'latin-iso8859-9 | |
183 "ISO/IEC 8859/9" "Latin-5" 148 ?M 141 "8859-9") | |
184 | |
88575 | 185 (define-iso-single-byte-charset 'iso-8859-10 'latin-iso8859-10 |
88671 | 186 "ISO/IEC 8859/10" "Latin-6" 157 ?V nil "8859-10") |
88575 | 187 |
88671 | 188 ;; http://www.nectec.or.th/it-standards/iso8859-11/ |
189 ;; http://www.cwi.nl/~dik/english/codes/8859.html says this is tis-620 | |
190 ;; plus nbsp | |
191 (define-iso-single-byte-charset 'iso-8859-11 'thai-iso8859-11 | |
192 "ISO/IEC 8859/11" "Latin/Thai" 166 ?T nil "8859-11") | |
193 | |
194 ;; 8859-12 doesn't (yet?) exist. | |
88575 | 195 |
88411 | 196 (define-iso-single-byte-charset 'iso-8859-13 'latin-iso8859-13 |
88575 | 197 "ISO/IEC 8859/13" "Latin-7" 179 ?Y nil "8859-13") |
88411 | 198 |
199 (define-iso-single-byte-charset 'iso-8859-14 'latin-iso8859-14 | |
200 "ISO/IEC 8859/14" "Latin-8" 199 ?_ 143 "8859-14") | |
201 | |
202 (define-iso-single-byte-charset 'iso-8859-15 'latin-iso8859-15 | |
203 "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
|
204 |
88565 | 205 (define-iso-single-byte-charset 'iso-8859-16 'latin-iso8859-16 |
88638 | 206 "ISO/IEC 8859/16" "Latin-10" 226 ?f nil "8859-16") |
88565 | 207 |
88647 | 208 ;; No point in keeping it around. |
209 (fmakunbound 'define-iso-single-byte-charset) | |
210 | |
88671 | 211 ;; Can this be shared with 8859-11? |
89089 | 212 ;; N.b. not all of these are defined unicodes. |
88411 | 213 (define-charset 'thai-tis620 |
214 "TIS620.2533" | |
215 :short-name "TIS620.2533" | |
216 :iso-final-char ?T | |
217 :emacs-mule-id 133 | |
218 :code-space [32 127] | |
219 :code-offset #x0E00) | |
220 | |
88671 | 221 ;; Fixme: doc for this, c.f. above |
88411 | 222 (define-charset 'tis620-2533 |
223 "TIS620.2533" | |
224 :short-name "TIS620.2533" | |
225 :ascii-compatible-p t | |
226 :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
|
227 :superset '(ascii eight-bit-control (thai-tis620 . 128))) |
88411 | 228 |
229 (define-charset 'jisx0201 | |
230 "JISX0201" | |
231 :short-name "JISX0201" | |
89483 | 232 :code-space [0 #xDF] |
233 :map "JISX0201") | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
234 |
88411 | 235 (define-charset 'latin-jisx0201 |
236 "Roman Part of JISX0201.1976" | |
237 :short-name "JISX0201 Roman" | |
238 :long-name "Japanese Roman (JISX0201.1976)" | |
239 :iso-final-char ?J | |
240 :emacs-mule-id 138 | |
241 :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
|
242 :subset '(jisx0201 33 126 0)) |
88411 | 243 |
244 (define-charset 'katakana-jisx0201 | |
245 "Katakana Part of JISX0201.1976" | |
246 :short-name "JISX0201 Katakana" | |
247 :long-name "Japanese Katakana (JISX0201.1976)" | |
248 :iso-final-char ?I | |
249 :emacs-mule-id 137 | |
250 :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
|
251 :subset '(jisx0201 161 254 -128)) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
252 |
88411 | 253 (define-charset 'chinese-gb2312 |
254 "GB2312 Chinese simplified: ISO-IR-58" | |
255 :short-name "GB2312" | |
256 :long-name "GB2312: ISO-IR-58" | |
257 :iso-final-char ?A | |
258 :emacs-mule-id 145 | |
259 :code-space [33 126 33 126] | |
260 :code-offset #x110000 | |
89483 | 261 :unify-map "GB2312") |
88411 | 262 |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
263 (define-charset 'chinese-gbk |
88486 | 264 "GBK Chinese simplified." |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
265 :short-name "GBK" |
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
266 :code-space [#x40 #xFE #x81 #xFE] |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
267 :code-offset #x160000 |
89483 | 268 :unify-map "GBK") |
88666 | 269 (define-charset-alias 'cp936 'chinese-gbk) |
88717 | 270 (define-charset-alias 'windows-936 'chinese-gbk) |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
271 |
88411 | 272 (define-charset 'chinese-cns11643-1 |
273 "CNS11643 Plane 1 Chinese traditional: ISO-IR-171" | |
274 :short-name "CNS11643-1" | |
275 :long-name "CNS11643-1 (Chinese traditional): ISO-IR-171" | |
276 :iso-final-char ?G | |
277 :emacs-mule-id 149 | |
278 :code-space [33 126 33 126] | |
279 :code-offset #x114000 | |
89483 | 280 :unify-map "CNS-1") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
281 |
88411 | 282 (define-charset 'chinese-cns11643-2 |
283 "CNS11643 Plane 2 Chinese traditional: ISO-IR-172" | |
284 :short-name "CNS11643-2" | |
285 :long-name "CNS11643-2 (Chinese traditional): ISO-IR-172" | |
286 :iso-final-char ?H | |
287 :emacs-mule-id 150 | |
288 :code-space [33 126 33 126] | |
289 :code-offset #x118000 | |
89483 | 290 :unify-map "CNS-2") |
88411 | 291 |
292 (define-charset 'chinese-cns11643-3 | |
293 "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183" | |
294 :short-name "CNS11643-3" | |
295 :long-name "CNS11643-3 (Chinese traditional): ISO-IR-183" | |
296 :iso-final-char ?I | |
297 :code-space [33 126 33 126] | |
298 :emacs-mule-id 246 | |
89483 | 299 :code-offset #x11C000 |
300 :unify-map "CNS-3") | |
88411 | 301 |
302 (define-charset 'chinese-cns11643-4 | |
303 "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184" | |
304 :short-name "CNS11643-4" | |
305 :long-name "CNS11643-4 (Chinese traditional): ISO-IR-184" | |
306 :iso-final-char ?J | |
307 :emacs-mule-id 247 | |
308 :code-space [33 126 33 126] | |
89483 | 309 :code-offset #x120000 |
310 :unify-map "CNS-4") | |
88411 | 311 |
312 (define-charset 'chinese-cns11643-5 | |
313 "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185" | |
314 :short-name "CNS11643-5" | |
315 :long-name "CNS11643-5 (Chinese traditional): ISO-IR-185" | |
316 :iso-final-char ?K | |
317 :emacs-mule-id 248 | |
318 :code-space [33 126 33 126] | |
89483 | 319 :code-offset #x124000 |
320 :unify-map "CNS-5") | |
88411 | 321 |
322 (define-charset 'chinese-cns11643-6 | |
323 "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186" | |
324 :short-name "CNS11643-6" | |
325 :long-name "CNS11643-6 (Chinese traditional): ISO-IR-186" | |
326 :iso-final-char ?L | |
327 :emacs-mule-id 249 | |
328 :code-space [33 126 33 126] | |
89483 | 329 :code-offset #x128000 |
330 :unify-map "CNS-6") | |
88411 | 331 |
332 (define-charset 'chinese-cns11643-7 | |
333 "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187" | |
334 :short-name "CNS11643-7" | |
335 :long-name "CNS11643-7 (Chinese traditional): ISO-IR-187" | |
336 :iso-final-char ?M | |
337 :emacs-mule-id 250 | |
338 :code-space [33 126 33 126] | |
89483 | 339 :code-offset #x12C000 |
340 :unify-map "CNS-7") | |
88411 | 341 |
342 (define-charset 'big5 | |
343 "Big5 (Chinese traditional)" | |
344 :short-name "Big5" | |
345 :code-space [#x40 #xFE #xA1 #xFE] | |
346 :code-offset #x130000 | |
89483 | 347 :unify-map "BIG5") |
88666 | 348 ;; Fixme: AKA cp950 according to |
349 ;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>. Is | |
350 ;; that correct? | |
88411 | 351 |
352 (define-charset 'chinese-big5-1 | |
88486 | 353 "Frequently used part (A141-C67E) of Big5 (Chinese traditional)" |
88411 | 354 :short-name "Big5 (Level-1)" |
355 :long-name "Big5 (Level-1) A141-C67F" | |
356 :iso-final-char ?0 | |
357 :emacs-mule-id 152 | |
358 :code-space [#x21 #x7E #x21 #x7E] | |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
359 :code-offset #x135000 |
89483 | 360 :unify-map "BIG5-1") |
88411 | 361 |
362 (define-charset 'chinese-big5-2 | |
88486 | 363 "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)" |
88411 | 364 :short-name "Big5 (Level-2)" |
365 :long-name "Big5 (Level-2) C940-FEFE" | |
366 :iso-final-char ?1 | |
367 :emacs-mule-id 153 | |
368 :code-space [#x21 #x7E #x21 #x7E] | |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
369 :code-offset #x137800 |
89483 | 370 :unify-map "BIG5-2") |
88411 | 371 |
372 (define-charset 'japanese-jisx0208 | |
373 "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87" | |
374 :short-name "JISX0208" | |
375 :long-name "JISX0208.1983/1990 (Japanese): ISO-IR-87" | |
376 :iso-final-char ?B | |
377 :emacs-mule-id 146 | |
378 :code-space [33 126 33 126] | |
379 :code-offset #x140000 | |
89483 | 380 :unify-map "JISX0208") |
88411 | 381 |
382 (define-charset 'japanese-jisx0208-1978 | |
383 "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42" | |
384 :short-name "JISX0208.1978" | |
89483 | 385 :long-name "JISX0208.1978 (JISC6226.1978): ISO-IR-42" |
88411 | 386 :iso-final-char ?@ |
387 :emacs-mule-id 144 | |
388 :code-space [33 126 33 126] | |
389 :code-offset #x144000 | |
89483 | 390 :unify-map "JISC6226") |
17070 | 391 |
88411 | 392 (define-charset 'japanese-jisx0212 |
393 "JISX0212 Japanese supplement: ISO-IR-159" | |
394 :short-name "JISX0212" | |
395 :long-name "JISX0212 (Japanese): ISO-IR-159" | |
396 :iso-final-char ?D | |
397 :emacs-mule-id 148 | |
398 :code-space [33 126 33 126] | |
399 :code-offset #x148000 | |
89483 | 400 :unify-map "JISX0212") |
88411 | 401 |
89426 | 402 ;; Note that jisx0213 contains characters not in Unicode (3.2?). It's |
403 ;; arguable whether it should have a unify-map. | |
88411 | 404 (define-charset 'japanese-jisx0213-1 |
405 "JISX0213 Plane 1 (Japanese)" | |
406 :short-name "JISX0213-1" | |
407 :iso-final-char ?O | |
408 :emacs-mule-id 151 | |
89483 | 409 :unify-map "JISX2131" |
88411 | 410 :code-space [33 126 33 126] |
411 :code-offset #x14C000) | |
17070 | 412 |
88411 | 413 (define-charset 'japanese-jisx0213-2 |
414 "JISX0213 Plane 2 (Japanese)" | |
415 :short-name "JISX0213-2" | |
416 :iso-final-char ?P | |
417 :emacs-mule-id 254 | |
89483 | 418 :unify-map "JISX2132" |
88411 | 419 :code-space [33 126 33 126] |
420 :code-offset #x150000) | |
17070 | 421 |
88411 | 422 (define-charset 'korean-ksc5601 |
423 "KSC5601 Korean Hangul and Hanja: ISO-IR-149" | |
424 :short-name "KSC5601" | |
425 :long-name "KSC5601 (Korean): ISO-IR-149" | |
426 :iso-final-char ?C | |
427 :emacs-mule-id 147 | |
428 :code-space [33 126 33 126] | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
429 :code-offset #x279f94 ; ... #x27c217 |
89483 | 430 :unify-map "KSC5601") |
17070 | 431 |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
432 (define-charset 'big5-hkscs |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
433 "Big5-HKSCS (Chinese traditional, Hong Kong supplement)" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
434 :short-name "Big5" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
435 :code-space [#x40 #xFE #xA1 #xFE] |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
436 :code-offset #x27c218 ; ... #x280839 |
89483 | 437 :unify-map "BIG5-HKSCS") |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
438 |
88666 | 439 ;; Fixme: Korean cp949/UHC |
440 | |
88411 | 441 (define-charset 'chinese-sisheng |
442 "SiSheng characters for PinYin/ZhuYin" | |
443 :short-name "SiSheng" | |
444 :long-name "SiSheng (PinYin/ZhuYin)" | |
445 :iso-final-char ?0 | |
446 :emacs-mule-id 160 | |
447 :code-space [33 126] | |
89483 | 448 :unify-map "MULE-sisheng" |
88411 | 449 :code-offset #x200000) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
450 |
88735 | 451 ;; A subset of the 1989 version of IPA. It consists of the consonant |
452 ;; signs used in English, French, German and Italian, and all vowels | |
453 ;; signs in the table. [says old MULE doc] | |
88411 | 454 (define-charset 'ipa |
455 "IPA (International Phonetic Association)" | |
456 :short-name "IPA" | |
457 :iso-final-char ?0 | |
458 :emacs-mule-id 161 | |
89483 | 459 :unify-map "MULE-ipa" |
88411 | 460 :code-space [32 127] |
461 :code-offset #x200080) | |
17070 | 462 |
88411 | 463 (define-charset 'viscii |
464 "VISCII1.1" | |
465 :short-name "VISCII" | |
466 :long-name "VISCII 1.1" | |
467 :code-space [0 255] | |
89483 | 468 :map "VISCII") |
88411 | 469 |
470 (define-charset 'vietnamese-viscii-lower | |
471 "VISCII1.1 lower-case" | |
472 :short-name "VISCII lower" | |
473 :long-name "VISCII lower-case" | |
474 :iso-final-char ?1 | |
475 :emacs-mule-id 162 | |
476 :code-space [32 127] | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
477 :code-offset #x200200 |
89483 | 478 :unify-map "MULE-lviscii") |
17070 | 479 |
88411 | 480 (define-charset 'vietnamese-viscii-upper |
481 "VISCII1.1 upper-case" | |
482 :short-name "VISCII upper" | |
483 :long-name "VISCII upper-case" | |
484 :iso-final-char ?2 | |
485 :emacs-mule-id 163 | |
486 :code-space [32 127] | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
487 :code-offset #x200280 |
89483 | 488 :unify-map "MULE-uviscii") |
88411 | 489 |
490 (define-charset 'vscii | |
89483 | 491 "VSCII1.1 (TCVN-5712 VN1)" |
88411 | 492 :short-name "VSCII" |
493 :code-space [0 255] | |
89483 | 494 :map "VSCII") |
495 | |
496 (define-charset-alias 'tcvn-5712 'vscii) | |
88411 | 497 |
88727 | 498 ;; Fixme: see note in tcvn.map about combining characters |
89483 | 499 (define-charset 'vscii-2 |
500 "VSCII-2 (TCVN-5712 VN2)" | |
88727 | 501 :code-space [0 255] |
89483 | 502 :map "VSCII-2") |
88727 | 503 |
88411 | 504 (define-charset 'koi8-r |
505 "KOI8-R" | |
506 :short-name "KOI8-R" | |
507 :ascii-compatible-p t | |
508 :code-space [0 255] | |
89483 | 509 :map "KOI8-R") |
88411 | 510 |
511 (define-charset-alias 'koi8 'koi8-r) | |
512 | |
513 (define-charset 'alternativnyj | |
514 "ALTERNATIVNYJ" | |
515 :short-name "alternativnyj" | |
516 :ascii-compatible-p t | |
517 :code-space [0 255] | |
89483 | 518 :map "ALTERNATIVNYJ") |
89200 | 519 |
520 (define-charset 'cp866 | |
521 "CP866" | |
522 :short-name "cp866" | |
523 :ascii-compatible-p t | |
524 :code-space [0 255] | |
89483 | 525 :map "IBM866") |
89200 | 526 (define-charset-alias 'ibm866 'cp866) |
17070 | 527 |
88533 | 528 (define-charset 'koi8-u |
529 "KOI8-U" | |
530 :short-name "KOI8-U" | |
531 :ascii-compatible-p t | |
532 :code-space [0 255] | |
89483 | 533 :map "KOI8-U") |
88533 | 534 |
535 (define-charset 'koi8-t | |
536 "KOI8-T" | |
537 :short-name "KOI8-T" | |
538 :ascii-compatible-p t | |
539 :code-space [0 255] | |
89483 | 540 :map "KOI8-T") |
88533 | 541 |
542 (define-charset 'georgian-ps | |
543 "GEORGIAN-PS" | |
544 :short-name "GEORGIAN-PS" | |
545 :ascii-compatible-p t | |
546 :code-space [0 255] | |
89483 | 547 :map "KA-PS") |
88533 | 548 |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
549 (define-charset 'georgian-academy |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
550 "GEORGIAN-ACADEMY" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
551 :short-name "GEORGIAN-ACADEMY" |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
552 :ascii-compatible-p t |
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
553 :code-space [0 255] |
89483 | 554 :map "KA-ACADEMY") |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
555 |
88533 | 556 (define-charset 'windows-1250 |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
557 "WINDOWS-1250 (Central Europe)" |
88533 | 558 :short-name "WINDOWS-1250" |
559 :ascii-compatible-p t | |
560 :code-space [0 255] | |
89483 | 561 :map "CP1250") |
88533 | 562 (define-charset-alias 'cp1250 'windows-1250) |
563 | |
564 (define-charset 'windows-1251 | |
88666 | 565 "WINDOWS-1251 (Cyrillic)" |
88533 | 566 :short-name "WINDOWS-1251" |
567 :ascii-compatible-p t | |
568 :code-space [0 255] | |
89483 | 569 :map "CP1251") |
88533 | 570 (define-charset-alias 'cp1251 'windows-1251) |
571 | |
572 (define-charset 'windows-1252 | |
88666 | 573 "WINDOWS-1252 (Latin I)" |
88533 | 574 :short-name "WINDOWS-1252" |
575 :ascii-compatible-p t | |
576 :code-space [0 255] | |
89483 | 577 :map "CP1252") |
88533 | 578 (define-charset-alias 'cp1252 'windows-1252) |
579 | |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
580 (define-charset 'windows-1253 |
88666 | 581 "WINDOWS-1253 (Greek)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
582 :short-name "WINDOWS-1253" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
583 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
584 :code-space [0 255] |
89483 | 585 :map "CP1253") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
586 (define-charset-alias 'cp1253 'windows-1253) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
587 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
588 (define-charset 'windows-1254 |
88666 | 589 "WINDOWS-1254 (Turkish)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
590 :short-name "WINDOWS-1254" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
591 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
592 :code-space [0 255] |
89483 | 593 :map "CP1254") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
594 (define-charset-alias 'cp1254 'windows-1254) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
595 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
596 (define-charset 'windows-1255 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
597 "WINDOWS-1255 (Hebrew)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
598 :short-name "WINDOWS-1255" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
599 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
600 :code-space [0 255] |
89483 | 601 :map "CP1255") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
602 (define-charset-alias 'cp1255 'windows-1255) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
603 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
604 (define-charset 'windows-1256 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
605 "WINDOWS-1256 (Arabic)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
606 :short-name "WINDOWS-1256" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
607 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
608 :code-space [0 255] |
89483 | 609 :map "CP1256") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
610 (define-charset-alias 'cp1256 'windows-1256) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
611 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
612 (define-charset 'windows-1257 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
613 "WINDOWS-1257 (Baltic)" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
614 :short-name "WINDOWS-1257" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
615 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
616 :code-space [0 255] |
89483 | 617 :map "CP1257") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
618 (define-charset-alias 'cp1257 'windows-1257) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
619 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
620 (define-charset 'windows-1258 |
88666 | 621 "WINDOWS-1258 (Viet Nam)" |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
622 :short-name "WINDOWS-1258" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
623 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
624 :code-space [0 255] |
89483 | 625 :map "CP1258") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
626 (define-charset-alias 'cp1258 'windows-1258) |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
627 |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
628 (define-charset 'next |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
629 "NEXT" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
630 :short-name "NEXT" |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
631 :ascii-compatible-p t |
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
632 :code-space [0 255] |
89483 | 633 :map "NEXTSTEP") |
88555
e52f0de0d5d1
(ebcdic-us, ebcdic-uk): Change map
Dave Love <fx@gnu.org>
parents:
88533
diff
changeset
|
634 |
88533 | 635 (define-charset 'cp1125 |
636 "CP1125" | |
637 :short-name "CP1125" | |
638 :code-space [0 255] | |
89483 | 639 :map "CP1125") |
88533 | 640 (define-charset-alias 'ruscii 'cp1125) |
641 ;; Original name for cp1125, says Serhii Hlodin <hlodin@lutsk.bank.gov.ua> | |
642 (define-charset-alias 'cp866u 'cp1125) | |
643 | |
88671 | 644 ;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html |
645 ;; shows this as not ASCII comptaible, with various graphics in | |
646 ;; 0x01-0x1F. | |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
647 (define-charset 'cp437 |
88671 | 648 "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
|
649 :short-name "CP437" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
650 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
651 :ascii-compatible-p t |
89483 | 652 :map "IBM437") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
653 |
88666 | 654 (define-charset 'cp720 |
655 "CP720 (Arabic)" | |
656 :short-name "CP720" | |
657 :code-space [0 255] | |
658 :ascii-compatible-p t | |
89483 | 659 :map "CP720") |
88666 | 660 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
661 (define-charset 'cp737 |
88671 | 662 "CP737 (PC Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
663 :short-name "CP737" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
664 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
665 :ascii-compatible-p t |
89483 | 666 :map "CP737") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
667 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
668 (define-charset 'cp775 |
88671 | 669 "CP775 (PC Baltic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
670 :short-name "CP775" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
671 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
672 :ascii-compatible-p t |
89483 | 673 :map "CP775") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
674 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
675 (define-charset 'cp851 |
89089 | 676 "CP851 (Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
677 :short-name "CP851" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
678 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
679 :ascii-compatible-p t |
89483 | 680 :map "IBM851") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
681 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
682 (define-charset 'cp852 |
88671 | 683 "CP852 (MS-DOS Latin-2)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
684 :short-name "CP852" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
685 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
686 :ascii-compatible-p t |
89483 | 687 :map "IBM852") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
688 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
689 (define-charset 'cp855 |
88671 | 690 "CP855 (IBM Cyrillic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
691 :short-name "CP855" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
692 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
693 :ascii-compatible-p t |
89483 | 694 :map "IBM855") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
695 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
696 (define-charset 'cp857 |
88671 | 697 "CP857 (IBM Turkish)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
698 :short-name "CP857" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
699 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
700 :ascii-compatible-p t |
89483 | 701 :map "IBM857") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
702 |
88666 | 703 (define-charset 'cp858 |
704 "CP858 (Multilingual Latin I + Euro)" | |
705 :short-name "CP858" | |
706 :code-space [0 255] | |
707 :ascii-compatible-p t | |
89483 | 708 :map "CP858") |
88671 | 709 (define-charset-alias 'cp00858 'cp858) ; IANA has IBM00858/CP00858 |
88666 | 710 |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
711 (define-charset 'cp860 |
88671 | 712 "CP860 (MS-DOS Portuguese)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
713 :short-name "CP860" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
714 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
715 :ascii-compatible-p t |
89483 | 716 :map "IBM860") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
717 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
718 (define-charset 'cp861 |
88671 | 719 "CP861 (MS-DOS Icelandic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
720 :short-name "CP861" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
721 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
722 :ascii-compatible-p t |
89483 | 723 :map "IBM861") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
724 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
725 (define-charset 'cp862 |
88671 | 726 "CP862 (PC Hebrew)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
727 :short-name "CP862" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
728 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
729 :ascii-compatible-p t |
89483 | 730 :map "IBM862") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
731 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
732 (define-charset 'cp863 |
88671 | 733 "CP863 (MS-DOS Canadian French)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
734 :short-name "CP863" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
735 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
736 :ascii-compatible-p t |
89483 | 737 :map "IBM863") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
738 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
739 (define-charset 'cp864 |
88671 | 740 "CP864 (PC Arabic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
741 :short-name "CP864" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
742 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
743 :ascii-compatible-p t |
89483 | 744 :map "IBM864") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
745 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
746 (define-charset 'cp865 |
88671 | 747 "CP865 (MS-DOS Nordic)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
748 :short-name "CP865" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
749 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
750 :ascii-compatible-p t |
89483 | 751 :map "IBM865") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
752 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
753 (define-charset 'cp869 |
88671 | 754 "CP869 (IBM Modern Greek)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
755 :short-name "CP869" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
756 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
757 :ascii-compatible-p t |
89483 | 758 :map "IBM869") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
759 |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
760 (define-charset 'cp874 |
88671 | 761 "CP874 (IBM Thai)" |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
762 :short-name "CP874" |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
763 :code-space [0 255] |
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
764 :ascii-compatible-p t |
89483 | 765 :map "IBM874") |
88613
cb347c3671eb
Avoid decode-char in top-level code
Dave Love <fx@gnu.org>
parents:
88600
diff
changeset
|
766 |
17070 | 767 ;; For Arabic, we need three different types of character sets. |
768 ;; Digits are of direction left-to-right and of width 1-column. | |
769 ;; Others are of direction right-to-left and of width 1-column or | |
770 ;; 2-column. | |
88411 | 771 (define-charset 'arabic-digit |
772 "Arabic digit" | |
773 :short-name "Arabic digit" | |
774 :iso-final-char ?2 | |
775 :emacs-mule-id 164 | |
776 :code-space [34 42] | |
777 :code-offset #x0600) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
778 |
88411 | 779 (define-charset 'arabic-1-column |
780 "Arabic 1-column" | |
781 :short-name "Arabic 1-col" | |
782 :long-name "Arabic 1-column" | |
783 :iso-final-char ?3 | |
784 :emacs-mule-id 165 | |
785 :code-space [33 126] | |
786 :code-offset #x200100) | |
787 | |
788 (define-charset 'arabic-2-column | |
789 "Arabic 2-column" | |
790 :short-name "Arabic 2-col" | |
791 :long-name "Arabic 2-column" | |
792 :iso-final-char ?4 | |
793 :emacs-mule-id 224 | |
794 :code-space [33 126] | |
795 :code-offset #x200180) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
796 |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
797 ;; Lao script. |
88411 | 798 ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF. |
89089 | 799 ;; Not all of them are defined unicodes. |
88411 | 800 (define-charset 'lao |
801 "Lao characters (ISO10646 0E81..0EDF)" | |
802 :short-name "Lao" | |
803 :iso-final-char ?1 | |
804 :emacs-mule-id 167 | |
805 :code-space [33 126] | |
806 :code-offset #x0E81) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
807 |
88411 | 808 (define-charset 'mule-lao |
809 "Lao characters (ISO10646 0E81..0EDF)" | |
810 :short-name "Lao" | |
811 :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
|
812 :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
|
813 |
17070 | 814 |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
815 ;; 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
|
816 ;; 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
|
817 ;; script which IS-13194 supports. |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
818 |
88411 | 819 (define-charset 'indian-is13194 |
820 "Generic Indian charset for data exchange with IS 13194" | |
821 :short-name "IS 13194" | |
822 :long-name "Indian IS 13194" | |
823 :iso-final-char ?5 | |
824 :emacs-mule-id 225 | |
825 :code-space [33 126] | |
826 :code-offset #x180000) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
827 |
89483 | 828 (let ((code-offset #x180100)) |
829 (dolist (script '(devanagari sanskrit bengali tamil telugu assamese | |
830 oriya kannada malayalam gujarati punjabi)) | |
831 (define-charset (intern (format "%s-cdac" script)) | |
832 (format "Glyphs of %s script for CDAC font. Subset of `indian-glyph'." | |
833 (capitalize (symbol-name script))) | |
834 :short-name (format "CDAC %s glyphs" (capitalize (symbol-name script))) | |
835 :code-space [0 255] | |
836 :code-offset code-offset) | |
837 (setq code-offset (+ code-offset #x100))) | |
89257
6435a79c2d95
(malayalam-glyph): New charset.
Kenichi Handa <handa@m17n.org>
parents:
89244
diff
changeset
|
838 |
89483 | 839 (dolist (script '(devanagari bengali punjabi gujarati |
840 oriya tamil telugu kannada malayalam)) | |
841 (define-charset (intern (format "%s-akruti" script)) | |
842 (format "Glyphs of %s script for AKRUTI font. Subset of `indian-glyph'." | |
843 (capitalize (symbol-name script))) | |
844 :short-name (format "AKRUTI %s glyphs" (capitalize (symbol-name script))) | |
845 :code-space [0 255] | |
846 :code-offset code-offset) | |
847 (setq code-offset (+ code-offset #x100)))) | |
89091 | 848 |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
849 (define-charset 'indian-glyph |
88411 | 850 "Glyphs for Indian characters." |
851 :short-name "Indian glyph" | |
852 :iso-final-char ?4 | |
853 :emacs-mule-id 240 | |
854 :code-space [32 127 32 127] | |
855 :code-offset #x180100) | |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
856 |
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
857 ;; Actual Glyph for 1-column width. |
88411 | 858 (define-charset 'indian-1-column |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
859 "Indian charset for 1-column width glyphs." |
88411 | 860 :short-name "Indian 1-col" |
861 :long-name "Indian 1 Column" | |
862 :iso-final-char ?6 | |
863 :emacs-mule-id 240 | |
864 :code-space [33 126 33 126] | |
865 :code-offset #x184000) | |
866 | |
867 ;; Actual Glyph for 2-column width. | |
868 (define-charset 'indian-2-column | |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
869 "Indian charset for 2-column width glyphs." |
88411 | 870 :short-name "Indian 2-col" |
871 :long-name "Indian 2 Column" | |
872 :iso-final-char ?5 | |
873 :emacs-mule-id 251 | |
874 :code-space [33 126 33 126] | |
89267
a9df91935aa0
(indian-is13194): Delete :unify-map
Kenichi Handa <handa@m17n.org>
parents:
89257
diff
changeset
|
875 :code-offset #x184000) |
88411 | 876 |
877 (define-charset 'tibetan | |
878 "Tibetan characters" | |
879 :iso-final-char ?7 | |
880 :short-name "Tibetan 2-col" | |
88486 | 881 :long-name "Tibetan 2 column" |
88411 | 882 :iso-final-char ?7 |
883 :emacs-mule-id 252 | |
89483 | 884 :unify-map "MULE-tibetan" |
89292
1bc1e30ea8d5
(tibetan): Fix :code-space property.
Kenichi Handa <handa@m17n.org>
parents:
89267
diff
changeset
|
885 :code-space [33 126 33 37] |
88411 | 886 :code-offset #x190000) |
887 | |
888 (define-charset 'tibetan-1-column | |
889 "Tibetan 1 column glyph" | |
890 :short-name "Tibetan 1-col" | |
891 :long-name "Tibetan 1 column" | |
892 :iso-final-char ?8 | |
893 :emacs-mule-id 241 | |
894 :code-space [33 126 33 37] | |
89292
1bc1e30ea8d5
(tibetan): Fix :code-space property.
Kenichi Handa <handa@m17n.org>
parents:
89267
diff
changeset
|
895 :code-offset #x190000) |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
896 |
33044
7878d85aef6d
New charsets mule-unicode-2500-33ff and mule-unicode-e000-ffff.
Kenichi Handa <handa@m17n.org>
parents:
32786
diff
changeset
|
897 ;; Subsets of Unicode. |
88411 | 898 (define-charset 'mule-unicode-2500-33ff |
899 "Unicode characters of the range U+2500..U+33FF." | |
900 :short-name "Unicode subset 2" | |
901 :long-name "Unicode subset (U+2500..U+33FF)" | |
902 :iso-final-char ?2 | |
903 :emacs-mule-id 242 | |
904 :code-space [#x20 #x7f #x20 #x47] | |
905 :code-offset #x2500) | |
33044
7878d85aef6d
New charsets mule-unicode-2500-33ff and mule-unicode-e000-ffff.
Kenichi Handa <handa@m17n.org>
parents:
32786
diff
changeset
|
906 |
88411 | 907 (define-charset 'mule-unicode-e000-ffff |
908 "Unicode characters of the range U+E000..U+FFFF." | |
909 :short-name "Unicode subset 3" | |
910 :long-name "Unicode subset (U+E000+FFFF)" | |
911 :iso-final-char ?3 | |
912 :emacs-mule-id 243 | |
913 :code-space [#x20 #x7F #x20 #x75] | |
88843 | 914 :code-offset #xE000 |
915 :max-code 30015) ; U+FFFF | |
17070 | 916 |
88411 | 917 (define-charset 'mule-unicode-0100-24ff |
918 "Unicode characters of the range U+0100..U+24FF." | |
919 :short-name "Unicode subset" | |
920 :long-name "Unicode subset (U+0100..U+24FF)" | |
921 :iso-final-char ?1 | |
922 :emacs-mule-id 244 | |
923 :code-space [#x20 #x7F #x20 #x7F] | |
924 :code-offset #x100) | |
17070 | 925 |
89089 | 926 (define-charset 'unicode-bmp |
927 "Unicode Basic Multilingual Plane" | |
928 :short-name "Unicode BMP" | |
929 :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
|
930 :code-offset 0) |
89091 | 931 |
88411 | 932 (define-charset 'ethiopic |
88486 | 933 "Ethiopic characters for Amharic and Tigrigna." |
88411 | 934 :short-name "Ethiopic" |
935 :long-name "Ethiopic characters" | |
936 :iso-final-char ?3 | |
937 :emacs-mule-id 245 | |
89483 | 938 :unify-map "MULE-ethiopic" |
88411 | 939 :code-space [33 126 33 126] |
940 :code-offset #x1A0000) | |
17070 | 941 |
88411 | 942 (define-charset 'mac-roman |
943 "Mac Roman charset" | |
944 :short-name "Mac Roman" | |
945 :ascii-compatible-p t | |
946 :code-space [0 255] | |
89483 | 947 :map "MACINTOSH") |
29167
7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
Kenichi Handa <handa@m17n.org>
parents:
28951
diff
changeset
|
948 |
88533 | 949 ;; Fixme: modern EBCDIC variants, e.g. IBM00924? |
950 (define-charset 'ebcdic-us | |
951 "US version of EBCDIC" | |
952 :short-name "EBCDIC-US" | |
953 :code-space [0 255] | |
954 :mime-charset 'ebcdic-us | |
89483 | 955 :map "EBCDICUS") |
88533 | 956 |
957 (define-charset 'ebcdic-uk | |
958 "UK version of EBCDIC" | |
959 :short-name "EBCDIC-UK" | |
960 :code-space [0 255] | |
961 :mime-charset 'ebcdic-uk | |
89483 | 962 :map "EBCDICUK") |
88533 | 963 |
89200 | 964 (define-charset 'ibm1047 |
965 ;; Says groff: | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
966 "IBM1047, `EBCDIC Latin 1/Open Systems' used by OS/390 Unix." |
89200 | 967 :short-name "IBM1047" |
968 :code-space [0 255] | |
969 :mime-charset 'ibm1047 | |
89483 | 970 :map "IBM1047") |
89200 | 971 (define-charset-alias 'cp1047 'ibm1047) |
972 | |
88575 | 973 (define-charset 'hp-roman8 |
974 "Encoding used by Hewlet-Packard printer software" | |
975 :short-name "HP-ROMAN8" | |
976 :ascii-compatible-p t | |
977 :code-space [0 255] | |
89483 | 978 :map "HP-ROMAN8") |
88575 | 979 |
88671 | 980 ;; To make a coding system with this, a pre-write-conversion should |
981 ;; account for the commented-out multi-valued code points in | |
982 ;; stdenc.map. | |
88575 | 983 (define-charset 'adobe-standard-encoding |
984 "Adobe `standard encoding' used in PostScript" | |
985 :short-name "ADOBE-STANDARD-ENCODING" | |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
986 :code-space [#x20 255] |
88575 | 987 :map "stdenc") |
988 | |
989 (define-charset 'symbol | |
990 "Adobe symbol encoding used in PostScript" | |
991 :short-name "ADOBE-SYMBOL" | |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
992 :code-space [#x20 255] |
88575 | 993 :map "symbol") |
994 | |
995 (define-charset 'ibm850 | |
88671 | 996 "DOS codepage 850 (Latin-1)" |
88575 | 997 :short-name "IBM850" |
88591
b8eb49355bfe
(adobe-standard-encoding, symbol):
Dave Love <fx@gnu.org>
parents:
88588
diff
changeset
|
998 :ascii-compatible-p t |
88575 | 999 :code-space [0 255] |
89483 | 1000 :map "IBM850") |
88575 | 1001 (define-charset-alias 'cp850 'ibm850) |
1002 | |
89318 | 1003 (define-charset 'mik |
1004 "Bulgarian DOS codepage" | |
1005 :short-name "MIK" | |
1006 :ascii-compatible-p t | |
1007 :code-space [0 255] | |
89483 | 1008 :map "MIK") |
89318 | 1009 |
89483 | 1010 (define-charset 'ptcp154 |
89318 | 1011 "`Paratype' codepage (Asian Cyrillic)" |
1012 :short-name "PT154" | |
1013 :ascii-compatible-p t | |
1014 :code-space [0 255] | |
89389
b6e224aa7da6
(big5-hkscs, georgian-academy): New
Dave Love <fx@gnu.org>
parents:
89356
diff
changeset
|
1015 :mime-charset 'pt154 |
89483 | 1016 :map "PTCP154") |
1017 (define-charset-alias 'pt154 'ptcp154) | |
1018 (define-charset-alias 'cp154 'ptcp154) | |
89318 | 1019 |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1020 (define-charset 'gb18030-2-byte |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1021 "GB18030 2-byte (0x814E..0xFEFE)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1022 :code-space [#x40 #xFE #x81 #xFE] |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1023 :supplementary-p t |
89483 | 1024 :map "GB180302") |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1025 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1026 (define-charset 'gb18030-4-byte-bmp |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1027 "GB18030 4-byte for BMP (0x81308130-0x8431A439)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1028 :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
|
1029 :supplementary-p t |
89483 | 1030 :map "GB180304") |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1031 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1032 (define-charset 'gb18030-4-byte-smp |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1033 "GB18030 4-byte for SMP (0x90308130-0xE3329A35)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1034 :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
|
1035 :min-code '(#x9030 . #x8130) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1036 :max-code '(#xE332 . #x9A35) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1037 :supplementary-p t |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1038 :code-offset #x10000) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1039 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1040 (define-charset 'gb18030-4-byte-ext-1 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1041 "GB18030 4-byte (0x8431A530-0x8F39FE39)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1042 :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
|
1043 :min-code '(#x8431 . #xA530) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1044 :max-code '(#x8F39 . #xFE39) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1045 :supplementary-p t |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1046 :code-offset #x200000 ; ... #x22484B |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1047 ) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1048 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1049 (define-charset 'gb18030-4-byte-ext-2 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1050 "GB18030 4-byte (0xE3329A36-0xFE39FE39)" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1051 :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
|
1052 :min-code '(#xE332 . #x9A36) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1053 :max-code '(#xFE39 . #xFE39) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1054 :supplementary-p t |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1055 :code-offset #X22484C ; ... #x279f93 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1056 ) |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1057 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1058 (define-charset 'gb18030 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1059 "GB18030" |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1060 :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
|
1061 :min-code 0 |
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1062 :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
|
1063 :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
|
1064 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
|
1065 gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)) |
88675
20cca396a8ee
(chinese-gbk): Change :code-offset to
Kenichi Handa <handa@m17n.org>
parents:
88671
diff
changeset
|
1066 |
88411 | 1067 (unify-charset 'chinese-gb2312) |
88451
33d9bd9d6aa7
(chinese-gbk): New charset.
Kenichi Handa <handa@m17n.org>
parents:
88440
diff
changeset
|
1068 (unify-charset 'chinese-gbk) |
88411 | 1069 (unify-charset 'chinese-cns11643-1) |
1070 (unify-charset 'chinese-cns11643-2) | |
89483 | 1071 (unify-charset 'chinese-cns11643-3) |
1072 (unify-charset 'chinese-cns11643-4) | |
1073 (unify-charset 'chinese-cns11643-5) | |
1074 (unify-charset 'chinese-cns11643-6) | |
1075 (unify-charset 'chinese-cns11643-7) | |
88411 | 1076 (unify-charset 'big5) |
1077 (unify-charset 'chinese-big5-1) | |
1078 (unify-charset 'chinese-big5-2) | |
89483 | 1079 (unify-charset 'big5-hkscs) |
1080 (unify-charset 'korean-ksc5601) | |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
1081 (unify-charset 'vietnamese-viscii-lower) |
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
1082 (unify-charset 'vietnamese-viscii-upper) |
88760 | 1083 (unify-charset 'chinese-sisheng) |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1084 (unify-charset 'ipa) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1085 (unify-charset 'tibetan) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1086 (unify-charset 'ethiopic) |
89483 | 1087 (unify-charset 'japanese-jisx0208-1978) |
88894
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1088 (unify-charset 'japanese-jisx0208) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1089 (unify-charset 'japanese-jisx0212) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1090 (unify-charset 'japanese-jisx0213-1) |
9eb791116de8
Unify these charses: korean-ksc5601, ipa, tibetan, ethiopic,
Kenichi Handa <handa@m17n.org>
parents:
88843
diff
changeset
|
1091 (unify-charset 'japanese-jisx0213-2) |
88588
2516c98d56d2
(vietnamese-viscii-lower, vietnamese-viscii-upper): Supply them
Kenichi Handa <handa@m17n.org>
parents:
88575
diff
changeset
|
1092 |
17070 | 1093 |
22126
97cf1cae1971
Change term unification to
Kenichi Handa <handa@m17n.org>
parents:
21713
diff
changeset
|
1094 ;; These are tables for translating characters on decoding and |
97cf1cae1971
Change term unification to
Kenichi Handa <handa@m17n.org>
parents:
21713
diff
changeset
|
1095 ;; encoding. |
88760 | 1096 ;; Fixme: these aren't used now -- should they be? |
88411 | 1097 (setq standard-translation-table-for-decode nil) |
17760
b3d62674b210
Delete code for alternate-charset-table.
Kenichi Handa <handa@m17n.org>
parents:
17541
diff
changeset
|
1098 |
22186
fc4aaf1b1772
Change term "character translation table" to "translation table".
Kenichi Handa <handa@m17n.org>
parents:
22126
diff
changeset
|
1099 (setq standard-translation-table-for-encode nil) |
17760
b3d62674b210
Delete code for alternate-charset-table.
Kenichi Handa <handa@m17n.org>
parents:
17541
diff
changeset
|
1100 |
88760 | 1101 ;; Fixme: should this be retained? I guess it could be useful for |
1102 ;; non-unified charsets. | |
42047
83eb799f3657
(translation-table-for-input): New
Dave Love <fx@gnu.org>
parents:
41468
diff
changeset
|
1103 (defvar translation-table-for-input nil |
83eb799f3657
(translation-table-for-input): New
Dave Love <fx@gnu.org>
parents:
41468
diff
changeset
|
1104 "If non-nil, a char table used to translate characters from input methods. |
83eb799f3657
(translation-table-for-input): New
Dave Love <fx@gnu.org>
parents:
41468
diff
changeset
|
1105 \(Currently only used by Quail.)") |
17760
b3d62674b210
Delete code for alternate-charset-table.
Kenichi Handa <handa@m17n.org>
parents:
17541
diff
changeset
|
1106 |
17070 | 1107 ;;; Make fundamental coding systems. |
1108 | |
88411 | 1109 ;; The coding system `no-conversion' is already defined in coding.c as |
1110 ;; below: | |
1111 ;; | |
1112 ;; (define-coding-system 'no-conversion | |
1113 ;; "Do no conversion." | |
1114 ;; :coding-type 'raw-text | |
1115 ;; :mnemonic ?=) | |
18529
8e293f1a19a9
(binary): Define as coding system alias.
Richard M. Stallman <rms@gnu.org>
parents:
18519
diff
changeset
|
1116 |
88647 | 1117 (define-coding-system-alias 'binary 'no-conversion) |
1118 | |
88411 | 1119 (define-coding-system 'raw-text |
89483 | 1120 "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
|
1121 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
|
1122 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
|
1123 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
|
1124 byte. |
9688519d51d6
(no-conversion): Fix docstring.
Kenichi Handa <handa@m17n.org>
parents:
36518
diff
changeset
|
1125 |
9688519d51d6
(no-conversion): Fix docstring.
Kenichi Handa <handa@m17n.org>
parents:
36518
diff
changeset
|
1126 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
|
1127 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
|
1128 is treated as a character." |
89483 | 1129 :coding-type 'raw-text |
1130 :for-unibyte t | |
1131 :mnemonic ?t) | |
88411 | 1132 |
89483 | 1133 (define-coding-system 'no-conversion-multibyte |
1134 "Like `no-conversion' but don't read a file into a unibyte buffer." | |
1135 :coding-type 'raw-text | |
1136 :eol-type 'unix | |
1137 :mnemonic ?=) | |
1138 | |
88411 | 1139 (define-coding-system 'undecided |
88647 | 1140 "No conversion on encoding, automatic conversion on decoding." |
88411 | 1141 :coding-type 'undecided |
1142 :mnemonic ?- | |
1143 :charset-list '(ascii)) | |
1144 | |
1145 (define-coding-system-alias 'unix 'undecided-unix) | |
1146 (define-coding-system-alias 'dos 'undecided-dos) | |
1147 (define-coding-system-alias 'mac 'undecided-mac) | |
1148 | |
1149 (define-coding-system 'iso-latin-1 | |
1150 "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)." | |
89091 | 1151 :coding-type 'charset |
88411 | 1152 :mnemonic ?1 |
89091 | 1153 :charset-list '(iso-8859-1) |
88411 | 1154 :mime-charset 'iso-8859-1) |
1155 | |
1156 (define-coding-system-alias 'iso-8859-1 'iso-latin-1) | |
1157 (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
|
1158 |
88411 | 1159 ;; Coding systems not specific to each language environment. |
1160 | |
1161 (define-coding-system 'emacs-mule | |
1162 "Emacs 21 internal format used in buffer and string." | |
1163 :coding-type 'emacs-mule | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1164 :charset-list 'emacs-mule |
88411 | 1165 :mnemonic ?M) |
1166 | |
1167 (define-coding-system 'utf-8 | |
1168 "UTF-8." | |
1169 :coding-type 'utf-8 | |
1170 :mnemonic ?U | |
89041
2ce9656d788b
(utf-8): Give :mime-charset property.
Kenichi Handa <handa@m17n.org>
parents:
88894
diff
changeset
|
1171 :charset-list '(unicode) |
2ce9656d788b
(utf-8): Give :mime-charset property.
Kenichi Handa <handa@m17n.org>
parents:
88894
diff
changeset
|
1172 :mime-charset 'utf-8) |
88411 | 1173 |
1174 (define-coding-system-alias 'mule-utf-8 'utf-8) | |
1175 | |
1176 (define-coding-system 'utf-8-emacs | |
88468 | 1177 "Support for all Emacs characters (including non-Unicode characters)." |
88411 | 1178 :coding-type 'utf-8 |
1179 :mnemonic ?U | |
89244
bf10578caec8
(utf-8-emacs): Delete :mime-charset.
Dave Love <fx@gnu.org>
parents:
89200
diff
changeset
|
1180 :charset-list '(emacs)) |
88411 | 1181 |
89436 | 1182 (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
|
1183 "UTF-16LE (little endian, no signature (BOM))." |
88411 | 1184 :coding-type 'utf-16 |
1185 :mnemonic ?U | |
88503 | 1186 :charset-list '(unicode) |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1187 :endian 'little |
89436 | 1188 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1189 :mime-charset 'utf-16le) |
17070 | 1190 |
89436 | 1191 (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
|
1192 "UTF-16BE (big endian, no signature (BOM))." |
88411 | 1193 :coding-type 'utf-16 |
1194 :mnemonic ?U | |
1195 :charset-list '(unicode) | |
89422 | 1196 :endian 'big |
89436 | 1197 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1198 :mime-charset 'utf-16be) |
88411 | 1199 |
89436 | 1200 (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
|
1201 "UTF-16 (little endian, with signature (BOM))." |
88411 | 1202 :coding-type 'utf-16 |
1203 :mnemonic ?U | |
1204 :charset-list '(unicode) | |
88440
5b1dd2e30f16
(utf-16-le): Use :bom attribute instead of :signature.
Kenichi Handa <handa@m17n.org>
parents:
88411
diff
changeset
|
1205 :bom t |
88503 | 1206 :endian 'little |
89436 | 1207 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1208 :mime-charset 'utf-16) |
17070 | 1209 |
89436 | 1210 (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
|
1211 "UTF-16 (big endian, with signature)." |
88411 | 1212 :coding-type 'utf-16 |
1213 :mnemonic ?U | |
1214 :charset-list '(unicode) | |
88440
5b1dd2e30f16
(utf-16-le): Use :bom attribute instead of :signature.
Kenichi Handa <handa@m17n.org>
parents:
88411
diff
changeset
|
1215 :bom t |
89422 | 1216 :endian 'big |
89436 | 1217 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1218 :mime-charset 'utf-16) |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1219 |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1220 (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
|
1221 "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
|
1222 :coding-type 'utf-16 |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1223 :mnemonic ?U |
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1224 :charset-list '(unicode) |
89436 | 1225 :bom '(utf-16le-with-signature . utf-16be-with-signature) |
89422 | 1226 :endian 'big |
89436 | 1227 :mime-text-unsuitable t |
89403
e7eb0fa7dce7
(utf-16-le): Renamed from utf-16-le-nosig.
Kenichi Handa <handa@m17n.org>
parents:
89389
diff
changeset
|
1228 :mime-charset 'utf-16) |
88411 | 1229 |
89436 | 1230 ;; Backwards compatibility (old names, also used by Mule-UCS). We |
1231 ;; 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
|
1232 (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
|
1233 (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
|
1234 |
89436 | 1235 |
88411 | 1236 (define-coding-system 'iso-2022-7bit |
88647 | 1237 "ISO 2022 based 7-bit encoding using only G0." |
88411 | 1238 :coding-type 'iso-2022 |
1239 :mnemonic ?J | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1240 :charset-list 'iso-2022 |
88411 | 1241 :designation [(ascii t) nil nil nil] |
1242 :flags '(short ascii-at-eol ascii-at-cntl 7-bit designation composition)) | |
1243 | |
1244 (define-coding-system 'iso-2022-7bit-ss2 | |
88647 | 1245 "ISO 2022 based 7-bit encoding using SS2 for 96-charset." |
88411 | 1246 :coding-type 'iso-2022 |
1247 :mnemonic ?$ | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1248 :charset-list 'iso-2022 |
88411 | 1249 :designation [(ascii 94) nil (nil 96) nil] |
1250 :flags '(short ascii-at-eol ascii-at-cntl 7-bit | |
1251 designation single-shift composition)) | |
1252 | |
1253 (define-coding-system 'iso-2022-7bit-lock | |
88647 | 1254 "ISO-2022 coding system using Locking-Shift for 96-charset." |
88411 | 1255 :coding-type 'iso-2022 |
1256 :mnemonic ?& | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1257 :charset-list 'iso-2022 |
88411 | 1258 :designation [(ascii 94) (nil 96) nil nil] |
1259 :flags '(ascii-at-eol ascii-at-cntl 7-bit | |
1260 designation locking-shift composition)) | |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1261 |
18519
b6badf3614ea
Fix calls to define-coding-system-alias.
Richard M. Stallman <rms@gnu.org>
parents:
18377
diff
changeset
|
1262 (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
|
1263 |
88411 | 1264 (define-coding-system 'iso-2022-7bit-lock-ss2 |
88647 | 1265 "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN." |
88411 | 1266 :coding-type 'iso-2022 |
1267 :mnemonic ?i | |
1268 :charset-list '(ascii | |
1269 japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201 | |
1270 korean-ksc5601 | |
1271 chinese-gb2312 | |
1272 chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3 | |
1273 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6 | |
1274 chinese-cns11643-7) | |
1275 :designation [(ascii 94) | |
1276 (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 96) | |
1277 (nil chinese-cns11643-2) | |
1278 (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5 | |
1279 chinese-cns11643-6 chinese-cns11643-7)] | |
1280 :flags '(short ascii-at-eol ascii-at-cntl 7-bit locking-shift | |
1281 single-shift init-bol)) | |
17070 | 1282 |
18519
b6badf3614ea
Fix calls to define-coding-system-alias.
Richard M. Stallman <rms@gnu.org>
parents:
18377
diff
changeset
|
1283 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2) |
17070 | 1284 |
88411 | 1285 (define-coding-system 'iso-2022-8bit-ss2 |
88647 | 1286 "ISO 2022 based 8-bit encoding using SS2 for 96-charset." |
88411 | 1287 :coding-type 'iso-2022 |
1288 :mnemonic ?@ | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1289 :charset-list 'iso-2022 |
88411 | 1290 :designation [(ascii 94) nil (nil 96) nil] |
1291 :flags '(ascii-at-eol ascii-at-cntl designation single-shift composition)) | |
17070 | 1292 |
88411 | 1293 (define-coding-system 'compound-text |
1294 "Compound text based generic encoding for decoding unknown messages. | |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1295 |
89483 | 1296 This coding system does not support extended segments of CTEXT." |
88411 | 1297 :coding-type 'iso-2022 |
1298 :mnemonic ?x | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1299 :charset-list 'iso-2022 |
88411 | 1300 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] |
1301 :flags '(ascii-at-eol ascii-at-cntl | |
1302 designation locking-shift single-shift composition) | |
88503 | 1303 ;; Fixme: this isn't a valid MIME charset and has to be |
1304 ;; special-cased elsewhere -- fx | |
88411 | 1305 :mime-charset 'x-ctext) |
24619
6057f7a48050
(x-ctext): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
24308
diff
changeset
|
1306 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1307 (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
|
1308 (define-coding-system-alias 'ctext 'compound-text) |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1309 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1310 ;; 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
|
1311 ;; 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
|
1312 ;; 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
|
1313 ;; 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
|
1314 ;; close to the beginning of coding systems ordered by priority. |
88411 | 1315 (define-coding-system 'ctext-no-compositions 2 ?x |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1316 "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
|
1317 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1318 Like `compound-text', but does not produce escape sequences for compositions." |
88411 | 1319 :coding-type 'iso-2022 |
1320 :mnemonic ?x | |
89102
1365cbd31156
(emacs-mule, iso-2022-7bit)
Kenichi Handa <handa@m17n.org>
parents:
89091
diff
changeset
|
1321 :charset-list 'iso-2022 |
88411 | 1322 :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil] |
1323 :flags '(ascii-at-eol ascii-at-cntl | |
1324 designation locking-shift single-shift)) | |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1325 |
88411 | 1326 (define-coding-system 'compound-text-with-extensions |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1327 "Compound text encoding with ICCCM Extended Segment extensions. |
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1328 |
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1329 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
|
1330 for decoding and encoding files, process I/O, etc." |
88411 | 1331 :coding-type 'raw-text |
1332 :mnemonic ?x | |
1333 :post-read-conversion 'ctext-post-read-conversion | |
1334 :pre-write-conversion 'ctext-pre-write-conversion) | |
43458
3dd402082e18
(ctext-no-compositions): New coding system.
Eli Zaretskii <eliz@gnu.org>
parents:
42112
diff
changeset
|
1335 |
43552
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1336 (define-coding-system-alias |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1337 '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
|
1338 (define-coding-system-alias |
52e76230bc9c
(compound-text): Renamed back from compound-text-no-extensions.
Eli Zaretskii <eliz@gnu.org>
parents:
43458
diff
changeset
|
1339 '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
|
1340 |
88411 | 1341 (define-coding-system 'us-ascii |
89483 | 1342 "Encode ASCII as-is and encode non-ASCII characters to `?'." |
88411 | 1343 :coding-type 'charset |
1344 :mnemonic ?- | |
1345 :charset-list '(ascii) | |
1346 :default-char ?? | |
1347 :mime-charset 'us-ascii) | |
19266
a042f26b7a4c
(iso-safe): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
19005
diff
changeset
|
1348 |
88411 | 1349 (define-coding-system-alias 'iso-safe 'us-ascii) |
1350 | |
89426 | 1351 (define-coding-system 'utf-7 |
1352 "UTF-7 encoding of Unicode (RFC 2152)." | |
1353 :coding-type 'utf-8 | |
1354 :mnemonic ?U | |
1355 :mime-charset 'utf-7 | |
1356 :charset-list '(unicode) | |
1357 :pre-write-conversion 'utf-7-pre-write-conversion | |
1358 :post-read-conversion 'utf-7-post-read-conversion) | |
1359 | |
88411 | 1360 ;; Use us-ascii for terminal output if some other coding system is not |
23196 | 1361 ;; specified explicitly. |
88411 | 1362 (set-safe-terminal-coding-system-internal 'us-ascii) |
19266
a042f26b7a4c
(iso-safe): New coding system.
Kenichi Handa <handa@m17n.org>
parents:
19005
diff
changeset
|
1363 |
17070 | 1364 ;; The other coding-systems are defined in each language specific |
88411 | 1365 ;; files under lisp/language. |
17070 | 1366 |
21713
aa160e4358ac
(file-coding-system-alist): Use emacs-mule for .elc files.
Richard M. Stallman <rms@gnu.org>
parents:
20732
diff
changeset
|
1367 ;; 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
|
1368 ;; 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
|
1369 ;; 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
|
1370 ;; Tar files are not decoded at all, but we treat them as raw bytes. |
17070 | 1371 |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1372 (setq file-coding-system-alist |
88776
805a3bb7daf4
(file-coding-system-alist): Change
Dave Love <fx@gnu.org>
parents:
88760
diff
changeset
|
1373 '(("\\.elc\\'" . utf-8-emacs) |
42047
83eb799f3657
(translation-table-for-input): New
Dave Love <fx@gnu.org>
parents:
41468
diff
changeset
|
1374 ("\\.utf\\(-8\\)?\\'" . utf-8) |
88575 | 1375 ;; This is the defined default for XML documents. It may be |
1376 ;; overridden by a charset specification in the header. That | |
1377 ;; should be grokked by the auto-coding mechanism, but rms | |
1378 ;; vetoed that. -- fx | |
1379 ("\\.xml\\'" . utf-8) | |
34264
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1380 ;; 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
|
1381 ;; 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
|
1382 ;; newlines. This is required to make the special treatment |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1383 ;; of the "\ newline" combination in loaddefs.el, which marks |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1384 ;; the beginning of a doc string, work. |
b0c17ac74953
(file-coding-system-alist): Use
Eli Zaretskii <eliz@gnu.org>
parents:
33933
diff
changeset
|
1385 ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix)) |
32228
6a5bae3ed1c1
file-coding-system-alist): Use \',
Dave Love <fx@gnu.org>
parents:
30260
diff
changeset
|
1386 ("\\.tar\\'" . (no-conversion . no-conversion)) |
89483 | 1387 ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system) |
18196
85354a726fa5
Coding system names changed.
Kenichi Handa <handa@m17n.org>
parents:
17992
diff
changeset
|
1388 ("" . (undecided . nil)))) |
17070 | 1389 |
1390 | |
1391 ;;; Setting coding categories and their priorities. | |
1392 | |
1393 ;; This setting is just to read an Emacs Lisp source files which | |
1394 ;; 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
|
1395 ;; values are set by the command `set-language-environment' for each |
17070 | 1396 ;; language environment. |
1397 | |
88411 | 1398 (set-coding-system-priority |
1399 'iso-latin-1 | |
1400 'utf-8 | |
1401 'iso-2022-7bit | |
1402 ) | |
17070 | 1403 |
19372 | 1404 |
1405 ;;; Miscellaneous settings. | |
88411 | 1406 |
1407 ;; Make all multibyte characters self-insert. | |
1408 (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
|
1409 (cons 128 (max-char)) |
88411 | 1410 'self-insert-command) |
1411 | |
50511
5930672784ee
Register ?\221 and ?\226 in latin-extra-code-table.
Kenichi Handa <handa@m17n.org>
parents:
50488
diff
changeset
|
1412 (aset latin-extra-code-table ?\221 t) |
19372 | 1413 (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
|
1414 (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
|
1415 (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
|
1416 (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
|
1417 (aset latin-extra-code-table ?\226 t) |
23260
1e8cac8d2c50
Call update-coding-systems-internal at the tail.
Kenichi Handa <handa@m17n.org>
parents:
23196
diff
changeset
|
1418 |
88647 | 1419 ;; Move least specific charsets to end of priority list |
1420 | |
1421 (apply #'set-charset-priority | |
1422 (delq 'unicode (delq 'emacs (charset-priority-list)))) | |
1423 | |
88600 | 1424 ;; The old code-pages library is obsoleted by coding systems based on |
1425 ;; the charsets defined in this file but might be required by user | |
1426 ;; code. | |
1427 (provide 'code-pages) | |
1428 | |
88575 | 1429 ;; Local variables: |
1430 ;; no-byte-compile: t | |
1431 ;; End: | |
1432 | |
17070 | 1433 ;;; mule-conf.el ends here |