Commit | Line | Data |
---|---|---|
0a10297a | 1 | ;;; mule-conf.el --- configure multilingual environment -*- no-byte-compile: t -*- |
08c19a27 | 2 | |
08c19a27 | 3 | ;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN. |
fa526c4a | 4 | ;; Licensed to the Free Software Foundation. |
c791cb54 | 5 | ;; Copyright (C) 2005 Free Software Foundation, Inc. |
08c19a27 KH |
6 | |
7 | ;; Keywords: mule, multilingual, character set, coding system | |
8 | ||
9 | ;; This file is part of GNU Emacs. | |
10 | ||
11 | ;; GNU Emacs is free software; you can redistribute it and/or modify | |
12 | ;; it under the terms of the GNU General Public License as published by | |
13 | ;; the Free Software Foundation; either version 2, or (at your option) | |
14 | ;; any later version. | |
15 | ||
16 | ;; GNU Emacs is distributed in the hope that it will be useful, | |
17 | ;; but WITHOUT ANY WARRANTY; without even the implied warranty of | |
18 | ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
19 | ;; GNU General Public License for more details. | |
20 | ||
21 | ;; You should have received a copy of the GNU General Public License | |
22 | ;; along with GNU Emacs; see the file COPYING. If not, write to the | |
23 | ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330, | |
24 | ;; Boston, MA 02111-1307, USA. | |
25 | ||
26 | ;;; Commentary: | |
27 | ||
28 | ;; Don't byte-compile this file. | |
29 | ||
30 | ;;; Code: | |
31 | ||
32 | ;;; Definitions of character sets. | |
33 | ||
34 | ;; Basic (official) character sets. These character sets are treated | |
7a860cf2 | 35 | ;; efficiently with respect to buffer memory. |
08c19a27 KH |
36 | |
37 | ;; Syntax: | |
38 | ;; (define-charset CHARSET-ID CHARSET | |
39 | ;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE | |
40 | ;; SHORT-NAME LONG-NAME DESCRIPTION ]) | |
41 | ;; ASCII charset is defined in src/charset.c as below. | |
42 | ;; (define-charset 0 ascii | |
43 | ;; [1 94 1 0 ?B 0 "ASCII" "ASCII" "ASCII (ISO646 IRV)"]) | |
44 | ||
7153b1f1 KH |
45 | ;; 1-byte charsets. Valid range of CHARSET-ID is 128..143. |
46 | ||
47 | ;; CHARSET-ID 128 is not used. | |
48 | ||
08c19a27 | 49 | (define-charset 129 'latin-iso8859-1 |
cead26f6 | 50 | [1 96 1 0 ?A 1 "RHP of Latin-1" "RHP of Latin-1 (ISO 8859-1): ISO-IR-100" |
5a6b038a | 51 | "Right-Hand Part of Latin Alphabet 1 (ISO/IEC 8859-1): ISO-IR-100."]) |
08c19a27 | 52 | (define-charset 130 'latin-iso8859-2 |
cead26f6 | 53 | [1 96 1 0 ?B 1 "RHP of Latin-2" "RHP of Latin-2 (ISO 8859-2): ISO-IR-101" |
5a6b038a | 54 | "Right-Hand Part of Latin Alphabet 2 (ISO/IEC 8859-2): ISO-IR-101."]) |
08c19a27 | 55 | (define-charset 131 'latin-iso8859-3 |
cead26f6 | 56 | [1 96 1 0 ?C 1 "RHP of Latin-3" "RHP of Latin-3 (ISO 8859-3): ISO-IR-109" |
5a6b038a | 57 | "Right-Hand Part of Latin Alphabet 3 (ISO/IEC 8859-3): ISO-IR-109."]) |
08c19a27 | 58 | (define-charset 132 'latin-iso8859-4 |
cead26f6 | 59 | [1 96 1 0 ?D 1 "RHP of Latin-4" "RHP of Latin-4 (ISO 8859-4): ISO-IR-110" |
5a6b038a | 60 | "Right-Hand Part of Latin Alphabet 4 (ISO/IEC 8859-4): ISO-IR-110."]) |
08c19a27 | 61 | (define-charset 133 'thai-tis620 |
cead26f6 | 62 | [1 96 1 0 ?T 1 "RHP of TIS620" "RHP of Thai (TIS620): ISO-IR-166" |
5a6b038a | 63 | "Right-Hand Part of TIS620.2533 (Thai): ISO-IR-166."]) |
08c19a27 | 64 | (define-charset 134 'greek-iso8859-7 |
cead26f6 | 65 | [1 96 1 0 ?F 1 "RHP of ISO8859/7" "RHP of Greek (ISO 8859-7): ISO-IR-126" |
5a6b038a | 66 | "Right-Hand Part of Latin/Greek Alphabet (ISO/IEC 8859-7): ISO-IR-126."]) |
08c19a27 | 67 | (define-charset 135 'arabic-iso8859-6 |
cead26f6 | 68 | [1 96 1 1 ?G 1 "RHP of ISO8859/6" "RHP of Arabic (ISO 8859-6): ISO-IR-127" |
5a6b038a | 69 | "Right-Hand Part of Latin/Arabic Alphabet (ISO/IEC 8859-6): ISO-IR-127."]) |
08c19a27 | 70 | (define-charset 136 'hebrew-iso8859-8 |
cead26f6 | 71 | [1 96 1 1 ?H 1 "RHP of ISO8859/8" "RHP of Hebrew (ISO 8859-8): ISO-IR-138" |
5a6b038a | 72 | "Right-Hand Part of Latin/Hebrew Alphabet (ISO/IEC 8859-8): ISO-IR-138."]) |
08c19a27 | 73 | (define-charset 137 'katakana-jisx0201 |
cead26f6 | 74 | [1 94 1 0 ?I 1 "JISX0201 Katakana" "Japanese Katakana (JISX0201.1976)" |
5a6b038a | 75 | "Katakana Part of JISX0201.1976."]) |
08c19a27 | 76 | (define-charset 138 'latin-jisx0201 |
cead26f6 | 77 | [1 94 1 0 ?J 0 "JISX0201 Roman" "Japanese Roman (JISX0201.1976)" |
5a6b038a | 78 | "Roman Part of JISX0201.1976."]) |
7153b1f1 KH |
79 | |
80 | ;; CHARSET-ID is not used 139. | |
81 | ||
08c19a27 | 82 | (define-charset 140 'cyrillic-iso8859-5 |
cead26f6 | 83 | [1 96 1 0 ?L 1 "RHP of ISO8859/5" "RHP of Cyrillic (ISO 8859-5): ISO-IR-144" |
5a6b038a | 84 | "Right-Hand Part of Latin/Cyrillic Alphabet (ISO/IEC 8859-5): ISO-IR-144."]) |
08c19a27 | 85 | (define-charset 141 'latin-iso8859-9 |
cead26f6 | 86 | [1 96 1 0 ?M 1 "RHP of Latin-5" "RHP of Latin-5 (ISO 8859-9): ISO-IR-148" |
5a6b038a | 87 | "Right-Hand Part of Latin Alphabet 5 (ISO/IEC 8859-9): ISO-IR-148."]) |
7a860cf2 | 88 | (define-charset 142 'latin-iso8859-15 |
cead26f6 | 89 | [1 96 1 0 ?b 1 "RHP of Latin-9" "RHP of Latin-9 (ISO 8859-15): ISO-IR-203" |
5a6b038a | 90 | "Right-Hand Part of Latin Alphabet 9 (ISO/IEC 8859-15): ISO-IR-203."]) |
7a860cf2 | 91 | (define-charset 143 'latin-iso8859-14 |
bdf74bef | 92 | [1 96 1 0 ?_ 1 "RHP of Latin-8" "RHP of Latin-8 (ISO 8859-14): ISO-IR-199" |
5a6b038a | 93 | "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14): ISO-IR-199."]) |
7153b1f1 KH |
94 | |
95 | ;; 2-byte charsets. Valid range of CHARSET-ID is 144..153. | |
96 | ||
08c19a27 | 97 | (define-charset 144 'japanese-jisx0208-1978 |
cead26f6 | 98 | [2 94 2 0 ?@ 0 "JISX0208.1978" "JISX0208.1978 (Japanese): ISO-IR-42" |
5a6b038a | 99 | "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42."]) |
08c19a27 | 100 | (define-charset 145 'chinese-gb2312 |
cead26f6 | 101 | [2 94 2 0 ?A 0 "GB2312" "GB2312: ISO-IR-58" |
5a6b038a | 102 | "GB2312 Chinese simplified: ISO-IR-58."]) |
08c19a27 | 103 | (define-charset 146 'japanese-jisx0208 |
cead26f6 | 104 | [2 94 2 0 ?B 0 "JISX0208" "JISX0208.1983/1990 (Japanese): ISO-IR-87" |
5a6b038a | 105 | "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87."]) |
08c19a27 | 106 | (define-charset 147 'korean-ksc5601 |
cead26f6 | 107 | [2 94 2 0 ?C 0 "KSC5601" "KSC5601 (Korean): ISO-IR-149" |
5a6b038a | 108 | "KSC5601 Korean Hangul and Hanja: ISO-IR-149."]) |
08c19a27 | 109 | (define-charset 148 'japanese-jisx0212 |
cead26f6 | 110 | [2 94 2 0 ?D 0 "JISX0212" "JISX0212 (Japanese): ISO-IR-159" |
5a6b038a | 111 | "JISX0212 Japanese supplement: ISO-IR-159."]) |
08c19a27 | 112 | (define-charset 149 'chinese-cns11643-1 |
cead26f6 | 113 | [2 94 2 0 ?G 0 "CNS11643-1" "CNS11643-1 (Chinese traditional): ISO-IR-171" |
5a6b038a | 114 | "CNS11643 Plane 1 Chinese traditional: ISO-IR-171."]) |
08c19a27 | 115 | (define-charset 150 'chinese-cns11643-2 |
cead26f6 | 116 | [2 94 2 0 ?H 0 "CNS11643-2" "CNS11643-2 (Chinese traditional): ISO-IR-172" |
5a6b038a | 117 | "CNS11643 Plane 2 Chinese traditional: ISO-IR-172."]) |
7153b1f1 KH |
118 | (define-charset 151 'japanese-jisx0213-1 |
119 | [2 94 2 0 ?O 0 "JISX0213-1" "JISX0213-1" "JISX0213 Plane 1 (Japanese)"]) | |
08c19a27 | 120 | (define-charset 152 'chinese-big5-1 |
cead26f6 | 121 | [2 94 2 0 ?0 0 "Big5 (Level-1)" "Big5 (Level-1) A141-C67F" |
5a6b038a | 122 | "Frequently used part (A141-C67F) of Big5 (Chinese traditional)."]) |
08c19a27 | 123 | (define-charset 153 'chinese-big5-2 |
cead26f6 | 124 | [2 94 2 0 ?1 0 "Big5 (Level-2)" "Big5 (Level-2) C940-FEFE" |
5a6b038a | 125 | "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)."]) |
08c19a27 KH |
126 | |
127 | ;; Additional (private) character sets. These character sets are | |
7a860cf2 | 128 | ;; treated less space-efficiently in the buffer. |
08c19a27 KH |
129 | |
130 | ;; Syntax: | |
7153b1f1 | 131 | ;; (define-charset CHARSET-ID CHARSET |
08c19a27 KH |
132 | ;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE |
133 | ;; SHORT-NAME LONG-NAME DESCRIPTION ]) | |
134 | ||
135 | ;; ISO-2022 allows a use of character sets not registered in ISO with | |
136 | ;; final characters `0' (0x30) through `?' (0x3F). Among them, Emacs | |
137 | ;; reserves `0' through `9' to support several private character sets. | |
138 | ;; The remaining final characters `:' through `?' are for users. | |
139 | ||
7153b1f1 KH |
140 | ;; 1-byte 1-column charsets. Valid range of CHARSET-ID is 160..223. |
141 | ||
142 | (define-charset 160 'chinese-sisheng | |
08c19a27 | 143 | [1 94 1 0 ?0 0 "SiSheng" "SiSheng (PinYin/ZhuYin)" |
5a6b038a | 144 | "Sisheng characters (vowels with tone marks) for Pinyin/Zhuyin."]) |
08c19a27 KH |
145 | |
146 | ;; IPA characters for phonetic symbols. | |
7153b1f1 | 147 | (define-charset 161 'ipa |
5a6b038a WL |
148 | [1 96 1 0 ?0 1 "IPA" "IPA" |
149 | "IPA (International Phonetic Association) characters."]) | |
08c19a27 KH |
150 | |
151 | ;; Vietnamese VISCII. VISCII is 1-byte character set which contains | |
152 | ;; more than 96 characters. Since Emacs can't handle it as one | |
153 | ;; character set, it is divided into two: lower case letters and upper | |
154 | ;; case letters. | |
7153b1f1 | 155 | (define-charset 162 'vietnamese-viscii-lower |
5a6b038a WL |
156 | [1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case" |
157 | "Vietnamese VISCII1.1 lower-case characters."]) | |
7153b1f1 | 158 | (define-charset 163 'vietnamese-viscii-upper |
5a6b038a WL |
159 | [1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case" |
160 | "Vietnamese VISCII1.1 upper-case characters."]) | |
08c19a27 KH |
161 | |
162 | ;; For Arabic, we need three different types of character sets. | |
163 | ;; Digits are of direction left-to-right and of width 1-column. | |
164 | ;; Others are of direction right-to-left and of width 1-column or | |
165 | ;; 2-column. | |
7153b1f1 | 166 | (define-charset 164 'arabic-digit |
5a6b038a WL |
167 | [1 94 1 0 ?2 0 "Arabic digit" "Arabic digit" |
168 | "Arabic digits."]) | |
7153b1f1 | 169 | (define-charset 165 'arabic-1-column |
5a6b038a WL |
170 | [1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column" |
171 | "Arabic 1-column width glyphs."]) | |
7153b1f1 KH |
172 | |
173 | ;; ASCII with right-to-left direction. | |
174 | (define-charset 166 'ascii-right-to-left | |
175 | [1 94 1 1 ?B 0 "rev ASCII" "ASCII with right-to-left direction" | |
5a6b038a | 176 | "ASCII (left half of ISO 8859-1) with right-to-left direction."]) |
7153b1f1 KH |
177 | |
178 | ;; Lao script. | |
179 | ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F. | |
180 | (define-charset 167 'lao | |
5a6b038a WL |
181 | [1 94 1 0 ?1 0 "Lao" "Lao" |
182 | "Lao characters (U+0E80..U+0EDF)."]) | |
7153b1f1 | 183 | |
e7f614fc | 184 | ;; CHARSET-IDs 168..223 are not used. |
7153b1f1 KH |
185 | |
186 | ;; 1-byte 2-column charsets. Valid range of CHARSET-ID is 224..239. | |
187 | ||
188 | (define-charset 224 'arabic-2-column | |
5a6b038a WL |
189 | [1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column" |
190 | "Arabic 2-column glyphs."]) | |
08c19a27 | 191 | |
7153b1f1 KH |
192 | ;; Indian scripts. Symbolic charset for data exchange. Glyphs are |
193 | ;; not assigned. They are automatically converted to each Indian | |
194 | ;; script which IS-13194 supports. | |
195 | ||
196 | (define-charset 225 'indian-is13194 | |
197 | [1 94 2 0 ?5 1 "IS 13194" "Indian IS 13194" | |
5a6b038a | 198 | "Generic Indian character set for data exchange with IS 13194."]) |
7153b1f1 KH |
199 | |
200 | ;; CHARSET-IDs 226..239 are not used. | |
201 | ||
16808556 RS |
202 | (define-charset 240 'indian-glyph |
203 | [2 96 1 0 ?4 0 "Indian glyph" "Indian glyph" | |
204 | "Glyphs for Indian characters."]) | |
205 | ;; 240 used to be [2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column"] | |
206 | ||
7153b1f1 KH |
207 | ;; 2-byte 1-column charsets. Valid range of CHARSET-ID is 240..244. |
208 | ||
209 | ;; Actual Glyph for 1-column width. | |
7153b1f1 | 210 | (define-charset 241 'tibetan-1-column |
5a6b038a WL |
211 | [2 94 1 0 ?8 0 "Tibetan 1-col" "Tibetan 1 column" |
212 | "Tibetan 1-column glyphs."]) | |
7153b1f1 | 213 | |
e98a6f1c KH |
214 | ;; Subsets of Unicode. |
215 | ||
216 | (define-charset 242 'mule-unicode-2500-33ff | |
217 | [2 96 1 0 ?2 0 "Unicode subset 2" "Unicode subset (U+2500..U+33FF)" | |
218 | "Unicode characters of the range U+2500..U+33FF."]) | |
219 | ||
220 | (define-charset 243 'mule-unicode-e000-ffff | |
221 | [2 96 1 0 ?3 0 "Unicode subset 3" "Unicode subset (U+E000+FFFF)" | |
222 | "Unicode characters of the range U+E000..U+FFFF."]) | |
7153b1f1 | 223 | |
7153b1f1 KH |
224 | (define-charset 244 'mule-unicode-0100-24ff |
225 | [2 96 1 0 ?1 0 "Unicode subset" "Unicode subset (U+0100..U+24FF)" | |
226 | "Unicode characters of the range U+0100..U+24FF."]) | |
227 | ||
228 | ;; 2-byte 2-column charsets. Valid range of CHARSET-ID is 245..254. | |
229 | ||
7a362b93 | 230 | ;; Ethiopic characters (Amharic and Tigrigna). |
7153b1f1 | 231 | (define-charset 245 'ethiopic |
5a6b038a WL |
232 | [2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters" |
233 | "Ethiopic characters."]) | |
08c19a27 KH |
234 | |
235 | ;; Chinese CNS11643 Plane3 thru Plane7. Although these are official | |
236 | ;; character sets, the use is rare and don't have to be treated | |
7a860cf2 | 237 | ;; space-efficiently in the buffer. |
7153b1f1 | 238 | (define-charset 246 'chinese-cns11643-3 |
cead26f6 | 239 | [2 94 2 0 ?I 0 "CNS11643-3" "CNS11643-3 (Chinese traditional): ISO-IR-183" |
5a6b038a | 240 | "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183."]) |
7153b1f1 | 241 | (define-charset 247 'chinese-cns11643-4 |
cead26f6 | 242 | [2 94 2 0 ?J 0 "CNS11643-4" "CNS11643-4 (Chinese traditional): ISO-IR-184" |
5a6b038a | 243 | "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184."]) |
7153b1f1 | 244 | (define-charset 248 'chinese-cns11643-5 |
cead26f6 | 245 | [2 94 2 0 ?K 0 "CNS11643-5" "CNS11643-5 (Chinese traditional): ISO-IR-185" |
5a6b038a | 246 | "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185."]) |
7153b1f1 | 247 | (define-charset 249 'chinese-cns11643-6 |
cead26f6 | 248 | [2 94 2 0 ?L 0 "CNS11643-6" "CNS11643-6 (Chinese traditional): ISO-IR-186" |
5a6b038a | 249 | "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186."]) |
7153b1f1 | 250 | (define-charset 250 'chinese-cns11643-7 |
cead26f6 | 251 | [2 94 2 0 ?M 0 "CNS11643-7" "CNS11643-7 (Chinese traditional): ISO-IR-187" |
5a6b038a | 252 | "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187."]) |
08c19a27 | 253 | |
08c19a27 | 254 | ;; Actual Glyph for 2-column width. |
7153b1f1 | 255 | (define-charset 251 'indian-2-column |
2aa72de7 | 256 | [2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column" |
5a6b038a | 257 | "Indian character set for 2-column width glyphs."]) |
16808556 RS |
258 | ;; old indian-1-column characters will be translated to indian-2-column. |
259 | (declare-equiv-charset 2 94 ?6 'indian-2-column) | |
08c19a27 | 260 | |
2aa72de7 | 261 | ;; Tibetan script. |
7153b1f1 | 262 | (define-charset 252 'tibetan |
5a6b038a WL |
263 | [2 94 2 0 ?7 0 "Tibetan 2-col" "Tibetan 2 column" |
264 | "Tibetan 2-column width glyphs."]) | |
7153b1f1 KH |
265 | |
266 | ;; CHARSET-ID 253 is not used. | |
267 | ||
268 | ;; JISX0213 Plane 2 | |
269 | (define-charset 254 'japanese-jisx0213-2 | |
5a6b038a WL |
270 | [2 94 2 0 ?P 0 "JISX0213-2" "JISX0213-2" |
271 | "JISX0213 Plane 2 (Japanese)."]) | |
2aa72de7 | 272 | |
85f789f7 KH |
273 | ;; Tell C code charset ID's of several charsets. |
274 | (setup-special-charsets) | |
08c19a27 | 275 | |
85f789f7 | 276 | \f |
d2a1ee18 KH |
277 | ;; These are tables for translating characters on decoding and |
278 | ;; encoding. | |
f967223b | 279 | (define-translation-table |
40e98681 KH |
280 | 'oldjis-newjis-jisroman-ascii |
281 | (list (cons (make-char 'japanese-jisx0208-1978) | |
282 | (make-char 'japanese-jisx0208)) | |
283 | (cons (make-char 'latin-jisx0201) (make-char 'ascii)))) | |
3cd01a6c KH |
284 | (aset (get 'oldjis-newjis-jisroman-ascii 'translation-table) |
285 | (make-char 'latin-jisx0201 92) (make-char 'latin-jisx0201 92)) | |
286 | (aset (get 'oldjis-newjis-jisroman-ascii 'translation-table) | |
287 | (make-char 'latin-jisx0201 126) (make-char 'latin-jisx0201 126)) | |
40e98681 | 288 | |
f967223b KH |
289 | (setq standard-translation-table-for-decode |
290 | (get 'oldjis-newjis-jisroman-ascii 'translation-table)) | |
08c19a27 | 291 | |
f967223b | 292 | (setq standard-translation-table-for-encode nil) |
08c19a27 KH |
293 | \f |
294 | ;;; Make fundamental coding systems. | |
295 | ||
296 | ;; Miscellaneous coding systems which can't be made by | |
297 | ;; `make-coding-system'. | |
298 | ||
299 | (put 'no-conversion 'coding-system | |
bc6a0946 KH |
300 | (vector nil ?= "Do no conversion. |
301 | ||
302 | When you visit a file with this coding, the file is read into a | |
303 | unibyte buffer as is, thus each byte of a file is treated as a | |
304 | character." | |
3fcbab9a | 305 | (list 'coding-category 'coding-category-binary |
701117d5 KH |
306 | 'alias-coding-systems '(no-conversion) |
307 | 'safe-charsets t 'safe-chars t) | |
3fcbab9a | 308 | nil)) |
08c19a27 | 309 | (put 'no-conversion 'eol-type 0) |
3fcbab9a KH |
310 | (put 'coding-category-binary 'coding-systems '(no-conversion)) |
311 | (setq coding-system-list '(no-conversion)) | |
312 | (setq coding-system-alist '(("no-conversion"))) | |
701117d5 | 313 | (define-coding-system-internal 'no-conversion) |
08c19a27 | 314 | |
8da035d0 RS |
315 | (define-coding-system-alias 'binary 'no-conversion) |
316 | ||
426591c3 | 317 | (put 'undecided 'coding-system |
76810f60 | 318 | (vector t ?- "No conversion on encoding, automatic conversion on decoding" |
08dcf825 KH |
319 | (list 'alias-coding-systems '(undecided) |
320 | 'safe-charsets '(ascii)) | |
3fcbab9a KH |
321 | nil)) |
322 | (setq coding-system-list (cons 'undecided coding-system-list)) | |
323 | (setq coding-system-alist (cons '("undecided") coding-system-alist)) | |
426591c3 | 324 | (put 'undecided 'eol-type |
3fcbab9a | 325 | (make-subsidiary-coding-system 'undecided)) |
08c19a27 | 326 | |
8d969bf6 | 327 | (define-coding-system-alias 'unix 'undecided-unix) |
1c445211 RS |
328 | (define-coding-system-alias 'dos 'undecided-dos) |
329 | (define-coding-system-alias 'mac 'undecided-mac) | |
330 | ||
08c19a27 KH |
331 | ;; Coding systems not specific to each language environment. |
332 | ||
333 | (make-coding-system | |
426591c3 | 334 | 'emacs-mule 0 ?= |
695ac440 | 335 | "Emacs internal format used in buffer and string. |
bc6a0946 | 336 | |
695ac440 KH |
337 | Encoding text with this coding system produces the actual byte |
338 | sequence of the text in buffers and strings. An exception is made for | |
339 | eight-bit-control characters. Each of them is encoded into a single | |
340 | byte." | |
40e98681 | 341 | nil |
06859d9e KH |
342 | '((safe-charsets . t) |
343 | (composition . t))) | |
08c19a27 | 344 | |
2cb30410 KH |
345 | (make-coding-system |
346 | 'raw-text 5 ?t | |
695ac440 KH |
347 | "Raw text, which means text contains random 8-bit codes. |
348 | Encoding text with this coding system produces the actual byte | |
349 | sequence of the text in buffers and strings. An exception is made for | |
350 | eight-bit-control characters. Each of them is encoded into a single | |
bc6a0946 KH |
351 | byte. |
352 | ||
353 | When you visit a file with this coding, the file is read into a | |
354 | unibyte buffer as is (except for EOL format), thus each byte of a file | |
355 | is treated as a character." | |
40e98681 KH |
356 | nil |
357 | '((safe-charsets . t))) | |
2cb30410 | 358 | |
08c19a27 | 359 | (make-coding-system |
4951a271 KH |
360 | 'iso-2022-7bit 2 ?J |
361 | "ISO 2022 based 7-bit encoding using only G0" | |
08c19a27 | 362 | '((ascii t) nil nil nil |
fec0e02d | 363 | short ascii-eol ascii-cntl seven) |
ccac3d77 KH |
364 | '((safe-charsets . t) |
365 | (composition . t))) | |
08c19a27 KH |
366 | |
367 | (make-coding-system | |
2792ce16 | 368 | 'iso-2022-7bit-ss2 2 ?$ |
4951a271 KH |
369 | "ISO 2022 based 7-bit encoding using SS2 for 96-charset" |
370 | '((ascii t) nil t nil | |
fec0e02d | 371 | short ascii-eol ascii-cntl seven nil single-shift) |
ccac3d77 KH |
372 | '((safe-charsets . t) |
373 | (composition . t))) | |
4951a271 KH |
374 | |
375 | (make-coding-system | |
2792ce16 | 376 | 'iso-2022-7bit-lock 2 ?& |
4951a271 KH |
377 | "ISO-2022 coding system using Locking-Shift for 96-charset" |
378 | '((ascii t) t nil nil | |
fec0e02d | 379 | nil ascii-eol ascii-cntl seven locking-shift) |
ccac3d77 KH |
380 | '((safe-charsets . t) |
381 | (composition . t))) | |
4951a271 | 382 | |
2e21aa27 | 383 | (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock) |
08c19a27 KH |
384 | |
385 | (make-coding-system | |
4951a271 | 386 | 'iso-2022-7bit-lock-ss2 2 ?i |
d0c5d809 | 387 | "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN" |
08c19a27 KH |
388 | '((ascii t) |
389 | (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 t) | |
390 | (nil chinese-cns11643-2) | |
391 | (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5 | |
392 | chinese-cns11643-6 chinese-cns11643-7) | |
d0c5d809 | 393 | short ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil |
fec0e02d | 394 | init-bol) |
3374b353 | 395 | '((safe-charsets ascii japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201 |
40e98681 KH |
396 | korean-ksc5601 chinese-gb2312 chinese-cns11643-1 |
397 | chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4 | |
ccac3d77 KH |
398 | chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7) |
399 | (composition . t))) | |
08c19a27 | 400 | |
2e21aa27 | 401 | (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2) |
08c19a27 KH |
402 | |
403 | (make-coding-system | |
4951a271 KH |
404 | 'iso-2022-8bit-ss2 2 ?@ |
405 | "ISO 2022 based 8-bit encoding using SS2 for 96-charset" | |
08c19a27 | 406 | '((ascii t) nil t nil |
fec0e02d | 407 | nil ascii-eol ascii-cntl nil nil single-shift) |
ccac3d77 KH |
408 | '((safe-charsets . t) |
409 | (composition . t))) | |
08c19a27 | 410 | |
d49a4835 | 411 | (make-coding-system |
cb5be6c9 | 412 | 'compound-text 2 ?x |
73066974 EZ |
413 | "Compound text based generic encoding for decoding unknown messages. |
414 | ||
e11cf111 | 415 | This coding system does not support extended segments." |
5259f34b | 416 | '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) t t |
d49a4835 KH |
417 | nil ascii-eol ascii-cntl nil locking-shift single-shift nil nil nil |
418 | init-bol nil nil) | |
419 | '((safe-charsets . t) | |
ccac3d77 KH |
420 | (mime-charset . x-ctext) |
421 | (composition . t))) | |
d49a4835 | 422 | |
cb5be6c9 EZ |
423 | (define-coding-system-alias 'x-ctext 'compound-text) |
424 | (define-coding-system-alias 'ctext 'compound-text) | |
73066974 | 425 | |
cb5be6c9 EZ |
426 | ;; Same as compound-text, but doesn't produce composition escape |
427 | ;; sequences. Used in post-read and pre-write conversions of | |
428 | ;; compound-text-with-extensions, see mule.el. Note that this should | |
429 | ;; not have a mime-charset property, to prevent it from showing up | |
430 | ;; close to the beginning of coding systems ordered by priority. | |
73066974 EZ |
431 | (make-coding-system |
432 | 'ctext-no-compositions 2 ?x | |
433 | "Compound text based generic encoding for decoding unknown messages. | |
434 | ||
cb5be6c9 | 435 | Like `compound-text', but does not produce escape sequences for compositions." |
73066974 EZ |
436 | '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) t t |
437 | nil ascii-eol ascii-cntl nil locking-shift single-shift nil nil nil | |
438 | init-bol nil nil) | |
cb5be6c9 | 439 | '((safe-charsets . t))) |
73066974 EZ |
440 | |
441 | (make-coding-system | |
1e056d48 | 442 | 'compound-text-with-extensions 2 ?x |
e11cf111 | 443 | "Compound text encoding with extended segments. |
73066974 | 444 | |
1e056d48 KH |
445 | See the variable `ctext-non-standard-encodings-alist' for the |
446 | detail about how extended segments are handled. | |
447 | ||
73066974 EZ |
448 | This coding system should be used only for X selections. It is inappropriate |
449 | for decoding and encoding files, process I/O, etc." | |
1e056d48 KH |
450 | '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) t t |
451 | nil ascii-eol ascii-cntl) | |
73066974 EZ |
452 | '((post-read-conversion . ctext-post-read-conversion) |
453 | (pre-write-conversion . ctext-pre-write-conversion))) | |
454 | ||
cb5be6c9 EZ |
455 | (define-coding-system-alias |
456 | 'x-ctext-with-extensions 'compound-text-with-extensions) | |
457 | (define-coding-system-alias | |
458 | 'ctext-with-extensions 'compound-text-with-extensions) | |
75b6fb58 | 459 | |
f6eb8ace KH |
460 | (make-coding-system |
461 | 'iso-safe 2 ?- | |
e11cf111 | 462 | "Encode ASCII asis and encode non-ASCII characters to `?'." |
f6eb8ace | 463 | '(ascii nil nil nil |
fec0e02d | 464 | nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil t) |
40e98681 | 465 | '((safe-charsets ascii))) |
f6eb8ace | 466 | |
9f13685a KH |
467 | (define-coding-system-alias |
468 | 'us-ascii 'iso-safe) | |
469 | ||
435c388e KH |
470 | (make-coding-system |
471 | 'iso-latin-1 2 ?1 | |
472 | "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)." | |
473 | '(ascii latin-iso8859-1 nil nil | |
474 | nil nil nil nil nil nil nil nil nil nil nil t t) | |
475 | '((safe-charsets ascii latin-iso8859-1) | |
476 | (mime-charset . iso-8859-1))) | |
477 | ||
478 | (define-coding-system-alias 'iso-8859-1 'iso-latin-1) | |
479 | (define-coding-system-alias 'latin-1 'iso-latin-1) | |
480 | ||
5b984695 | 481 | ;; Use iso-safe for terminal output if some other coding system is not |
e8dd0160 | 482 | ;; specified explicitly. |
f6eb8ace KH |
483 | (set-safe-terminal-coding-system-internal 'iso-safe) |
484 | ||
08c19a27 KH |
485 | ;; The other coding-systems are defined in each language specific |
486 | ;; section of languages.el. | |
487 | ||
678dc7ec RS |
488 | ;; Normally, set coding system to `undecided' before reading a file. |
489 | ;; Compiled Emacs Lisp files (*.elc) are not decoded at all, | |
490 | ;; but we regard them as containing multibyte characters. | |
491 | ;; Tar files are not decoded at all, but we treat them as raw bytes. | |
08c19a27 | 492 | |
4951a271 | 493 | (setq file-coding-system-alist |
2238f751 | 494 | '(("\\.elc\\'" . (emacs-mule . emacs-mule)) |
bdf74bef | 495 | ("\\.utf\\(-8\\)?\\'" . utf-8) |
3e88bb50 EZ |
496 | ;; We use raw-text for reading loaddefs.el so that if it |
497 | ;; happens to have DOS or Mac EOLs, they are converted to | |
498 | ;; newlines. This is required to make the special treatment | |
499 | ;; of the "\ newline" combination in loaddefs.el, which marks | |
500 | ;; the beginning of a doc string, work. | |
501 | ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix)) | |
2238f751 | 502 | ("\\.tar\\'" . (no-conversion . no-conversion)) |
518a0981 | 503 | ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system) |
0b606bb2 | 504 | ("\\.tex\\|\\.ltx\\|\\.dtx\\|\\.drv\\'" . latexenc-find-file-coding-system) |
4951a271 | 505 | ("" . (undecided . nil)))) |
08c19a27 KH |
506 | |
507 | \f | |
508 | ;;; Setting coding categories and their priorities. | |
509 | ||
510 | ;; This setting is just to read an Emacs Lisp source files which | |
511 | ;; contain multilingual text while dumping Emacs. More appropriate | |
2792ce16 | 512 | ;; values are set by the command `set-language-environment' for each |
08c19a27 KH |
513 | ;; language environment. |
514 | ||
29742cb5 KH |
515 | (setq coding-category-emacs-mule 'emacs-mule |
516 | coding-category-sjis 'japanese-shift-jis | |
517 | coding-category-iso-7 'iso-2022-7bit | |
40e98681 | 518 | coding-category-iso-7-tight 'iso-2022-jp |
29742cb5 | 519 | coding-category-iso-8-1 'iso-latin-1 |
5b984695 | 520 | coding-category-iso-8-2 'iso-latin-1 |
29742cb5 KH |
521 | coding-category-iso-7-else 'iso-2022-7bit-lock |
522 | coding-category-iso-8-else 'iso-2022-8bit-ss2 | |
a1223d6c | 523 | coding-category-ccl nil |
f8499efb | 524 | coding-category-utf-8 'mule-utf-8 |
9ef9b28e KH |
525 | coding-category-utf-16-be 'mule-utf-16be-with-signature |
526 | coding-category-utf-16-le 'mule-utf-16le-with-signature | |
29742cb5 | 527 | coding-category-big5 'chinese-big5 |
2cb30410 | 528 | coding-category-raw-text 'raw-text |
29742cb5 | 529 | coding-category-binary 'no-conversion) |
08c19a27 KH |
530 | |
531 | (set-coding-priority | |
5b984695 | 532 | '(coding-category-iso-8-1 |
69b73c8a | 533 | coding-category-iso-8-2 |
60ec9367 KH |
534 | coding-category-utf-8 |
535 | coding-category-utf-16-be | |
536 | coding-category-utf-16-le | |
5b984695 KH |
537 | coding-category-iso-7-tight |
538 | coding-category-iso-7 | |
29742cb5 | 539 | coding-category-iso-7-else |
2cb30410 | 540 | coding-category-iso-8-else |
e4e6cfa0 | 541 | coding-category-emacs-mule |
2cb30410 | 542 | coding-category-raw-text |
a1506d29 | 543 | coding-category-sjis |
08c19a27 | 544 | coding-category-big5 |
a1223d6c | 545 | coding-category-ccl |
2c7794b0 | 546 | coding-category-binary |
60ec9367 | 547 | )) |
08c19a27 | 548 | |
c1b628eb KH |
549 | \f |
550 | ;;; Miscellaneous settings. | |
e97c2306 | 551 | (aset latin-extra-code-table ?\221 t) |
c1b628eb | 552 | (aset latin-extra-code-table ?\222 t) |
40232452 KH |
553 | (aset latin-extra-code-table ?\223 t) |
554 | (aset latin-extra-code-table ?\224 t) | |
b4026917 | 555 | (aset latin-extra-code-table ?\225 t) |
e97c2306 | 556 | (aset latin-extra-code-table ?\226 t) |
c1b628eb | 557 | |
4cb4b388 KH |
558 | (update-coding-systems-internal) |
559 | ||
c791cb54 | 560 | ;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5 |
08c19a27 | 561 | ;;; mule-conf.el ends here |