Commit | Line | Data |
---|---|---|
55535639 | 1 | ;;; codepage.el --- MS-DOS/MS-Windows specific coding systems |
75e98450 EZ |
2 | |
3 | ;; Copyright (C) 1998 Free Software Foundation, Inc. | |
4 | ||
5 | ;; Author: Eli Zaretskii | |
6 | ;; Maintainer: FSF | |
0ac646aa | 7 | ;; Keywords: i18n ms-dos ms-windows codepage |
75e98450 EZ |
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 | ||
0ac646aa | 28 | ;; Special coding systems for DOS/Windows codepage support. |
75e98450 | 29 | ;; |
0ac646aa EZ |
30 | ;; These coding systems perform conversion from the DOS/Windows |
31 | ;; codepage encoding to one of the ISO-8859 character sets. Each | |
32 | ;; codepage has its corresponding ISO-8859 charset, chosen so as to be | |
33 | ;; able to convert all (or most) of the characters. The idea is that | |
34 | ;; Emacs internally works with the usual MULE charsets, and the | |
35 | ;; conversion to and from the DOS codepage is performed on I/O only. | |
36 | ;; See term/internal.el for the complementary setup of the DOS | |
37 | ;; terminal display and input methods. | |
75e98450 EZ |
38 | ;; |
39 | ;; Thanks to Ken'ichi Handa <handa@etl.go.jp> for writing the CCL | |
a1506d29 | 40 | ;; encoders/decoders, and for help in debugging this code. |
75e98450 EZ |
41 | |
42 | ;;; Code: | |
43 | ||
44 | (defun cp-coding-system-for-codepage-1 (coding mnemonic iso-name | |
45 | decoder encoder) | |
46 | "Make coding system CODING for a DOS codepage using translation tables. | |
47 | MNEMONIC is a character to be displayed on mode line for the coding system. | |
48 | ISO-NAME is the name of the ISO-8859 charset which corresponds to this | |
49 | codepage. | |
50 | DECODER is a translation table for converting characters in the DOS codepage | |
51 | encoding to Emacs multibyte characters. | |
52 | ENCODER is a translation table for encoding Emacs multibyte characters into | |
0ac646aa | 53 | external DOS codepage codes." |
75e98450 EZ |
54 | (save-match-data |
55 | (let* ((coding-name (symbol-name coding)) | |
a7bc7c2a EZ |
56 | (undef (if (eq system-type 'ms-dos) |
57 | (if dos-unsupported-char-glyph | |
58 | (logand dos-unsupported-char-glyph 255) | |
59 | 127) | |
60 | ??)) | |
ba2a2753 | 61 | (safe-chars (make-char-table 'safe-chars)) |
7bd53962 | 62 | (ccl-decoder |
776ca83d | 63 | (ccl-compile |
7bd53962 KH |
64 | ;; The 4 here supplies the buf_magnification parameter |
65 | ;; for the CCL program. A multibyte character may take | |
0ac646aa | 66 | ;; at most 4-bytes. |
776ca83d EZ |
67 | `(4 (loop (read r1) |
68 | (if (r1 >= 128) | |
69 | ((r0 = ,(charset-id 'ascii)) | |
70 | (translate-character ,decoder r0 r1) | |
7bd53962 | 71 | (write-multibyte-character r0 r1)) |
776ca83d EZ |
72 | (write r1)) |
73 | (repeat))))) | |
7bd53962 | 74 | (ccl-encoder |
776ca83d | 75 | (ccl-compile |
07a96c46 AI |
76 | ;; The 2 here supplies the buf_magnification parameter for |
77 | ;; the CCL program. Since the -dos coding system generates | |
78 | ;; \r\n for each \n, a factor of 2 covers even the worst case | |
79 | ;; of empty lines with a single \n. | |
80 | `(2 (loop (read-multibyte-character r0 r1) | |
776ca83d EZ |
81 | (if (r0 != ,(charset-id 'ascii)) |
82 | ((translate-character ,encoder r0 r1) | |
83 | (if (r0 == ,(charset-id 'japanese-jisx0208)) | |
a7bc7c2a | 84 | ((r1 = ,undef) |
776ca83d EZ |
85 | (write r1))))) |
86 | (write-repeat r1)))))) | |
776ca83d | 87 | |
ba2a2753 KH |
88 | ;; Set elements of safe multibyte characters for this codepage |
89 | ;; to t in the char-table safe-chars. | |
90 | (let ((tbl (get decoder 'translation-table)) | |
91 | (i 128) | |
92 | ch) | |
93 | (while (< i 256) | |
94 | (setq ch (aref tbl i)) | |
95 | (if ch (aset safe-chars ch t)) | |
96 | (setq i (1+ i)))) | |
97 | ||
776ca83d | 98 | ;; Make coding system CODING. |
75e98450 EZ |
99 | (make-coding-system |
100 | coding 4 mnemonic | |
101 | (concat "8-bit encoding of " (symbol-name iso-name) | |
776ca83d | 102 | " characters using IBM codepage " coding-name) |
7bd53962 | 103 | (cons ccl-decoder ccl-encoder) |
a205e32a | 104 | `((safe-charsets ascii eight-bit-control eight-bit-graphic ,iso-name) |
ba2a2753 | 105 | (safe-chars . ,safe-chars) |
7bd53962 | 106 | (valid-codes (0 . 255))))))) |
75e98450 EZ |
107 | |
108 | (defun cp-decoding-vector-for-codepage (table charset offset) | |
109 | "Create a vector for decoding IBM PC characters using conversion table | |
110 | TABLE into an ISO-8859 character set CHARSET whose first non-ASCII | |
e714d2cf | 111 | character is generated by (make-char CHARSET OFFSET)." |
75e98450 EZ |
112 | (let* ((len (length table)) |
113 | (undefined-char | |
114 | (if (eq system-type 'ms-dos) | |
115 | (if dos-unsupported-char-glyph | |
116 | (logand dos-unsupported-char-glyph 255) | |
117 | 127) | |
118 | 32)) | |
119 | (vec1 (make-vector 256 undefined-char)) | |
120 | (i 0)) | |
14028d57 | 121 | (while (< i 256) |
75e98450 EZ |
122 | (aset vec1 i i) |
123 | (setq i (1+ i))) | |
124 | (setq i 0) | |
125 | (while (< i len) | |
126 | (if (aref table i) | |
127 | (aset vec1 (aref table i) (make-char charset (+ i offset)))) | |
128 | (setq i (1+ i))) | |
129 | vec1)) | |
130 | ||
131 | ;;; You don't think I created all these tables below by hand, do you? | |
132 | ;;; The following Awk script will create the table for cp850-to-Latin-1 | |
133 | ;;; conversion from the RFC 1345 file (the other tables are left as an | |
134 | ;;; excercise): | |
135 | ;;; BEGIN { n_pages = 11; | |
136 | ;;; pn["IBM437"] = 0; pn["IBM850"] = 1; pn["IBM851"] = 2; | |
137 | ;;; pn["IBM852"] = 3; pn["IBM855"] = 4; pn["IBM860"] = 5; | |
138 | ;;; pn["IBM861"] = 6; pn["IBM862"] = 7; pn["IBM863"] = 8; | |
139 | ;;; pn["IBM864"] = 9; pn["IBM865"] = 10; | |
140 | ;;; } | |
141 | ;;; $1 == "&charset" { charset = $2; } | |
142 | ;;; $1 == "&code" { code = $2; } | |
143 | ;;; /^ [^&]/ { | |
144 | ;;; if ((charset ~ /^IBM(437|8(5[0125]|6[0-5]))$/) || (charset ~ /^ISO_8859-1/)) | |
145 | ;;; { | |
146 | ;;; for (i = 1; i <= NF; i++) | |
147 | ;;; chars[charset,code++] = $i; | |
148 | ;;; } | |
149 | ;;; } | |
150 | ;;; | |
151 | ;;; END { | |
152 | ;;; for (i = 160; i < 256; i++) | |
153 | ;;; { | |
154 | ;;; c = chars["ISO_8859-1:1987",i]; | |
155 | ;;; if (c == "??") # skip unused positions | |
156 | ;;; { | |
157 | ;;; printf " nil"; | |
158 | ;;; if ((i - 159)%16 == 0) | |
159 | ;;; printf "\n"; | |
160 | ;;; continue; | |
161 | ;;; } | |
162 | ;;; found = 0; | |
163 | ;;; for (j in pn) | |
164 | ;;; map[j] = "nil"; | |
165 | ;;; for (combined in chars) | |
166 | ;;; { | |
167 | ;;; candidate = chars[combined]; | |
168 | ;;; split (combined, separate, SUBSEP); | |
169 | ;;; if (separate[1] == "IBM850" && candidate == c) | |
170 | ;;; { | |
171 | ;;; found = 1; | |
172 | ;;; map[separate[1]] = separate[2]; | |
173 | ;;; } | |
174 | ;;; } | |
175 | ;;; printf " %s", map["IBM850"]; | |
176 | ;;; if ((i - 159)%16 == 0) | |
177 | ;;; printf "\n"; | |
178 | ;;; } | |
179 | ;;; } | |
180 | ||
181 | ;;; WARNING WARNING WARNING!!! | |
182 | ;;; | |
183 | ;;; If you want to get fancy with these tables, remember that the inverse | |
184 | ;;; tables, created by `cp-decoding-vector-for-codepage' above, are installed | |
185 | ;;; on MS-DOS as nonascii-translation-table (see `dos-codepage-setup' on | |
186 | ;;; internal.el). Therefore, you should NOT put any codes below 128 in | |
187 | ;;; these tables! Otherwise, various Emacs commands and functions will | |
188 | ;;; mysteriously fail! For example, a typical screwup is to map the Latin-N | |
189 | ;;; acute accent character to the apostrophe, and have all regexps which | |
190 | ;;; end with "\\'" begin to fail (e.g., the automatic setting of the major | |
191 | ;;; mode by file name extension will stop working). | |
192 | ;;; | |
193 | ;;; You HAVE BEEN warned! | |
194 | ||
195 | ;; US/English/PC-8/IBM-2. This doesn't support Latin-1 characters very | |
196 | ;; well, but why not use what we can salvage? | |
197 | (defvar cp437-decode-table | |
198 | ;; Nth element is the code of a cp437 glyph for the multibyte | |
199 | ;; character created by (make-char 'latin-iso8859-1 (+ N 160)). | |
d3fcfdea | 200 | ;; The element nil means there's no corresponding cp437 glyph. |
75e98450 EZ |
201 | [ |
202 | 255 173 155 156 nil 157 179 nil nil nil 166 174 170 196 nil nil | |
203 | 248 241 253 nil nil nil nil 249 nil nil 167 175 172 171 nil 168 | |
204 | nil nil nil nil 142 143 146 128 nil 144 nil nil nil nil nil nil | |
205 | nil 165 nil nil nil nil 153 nil nil nil nil nil 154 nil nil 225 | |
206 | 133 160 131 nil 132 134 145 135 138 130 136 137 141 161 140 139 | |
207 | nil 164 149 162 147 nil 148 246 nil 151 163 150 129 nil nil 152] | |
208 | "Table for converting ISO-8859-1 characters into codepage 437 glyphs.") | |
209 | (setplist 'cp437-decode-table | |
210 | '(charset latin-iso8859-1 language "Latin-1" offset 160)) | |
211 | ||
212 | ;; Multilingual (Latin-1) | |
213 | (defvar cp850-decode-table | |
214 | ;; Nth element is the code of a cp850 glyph for the multibyte | |
215 | ;; character created by (make-char 'latin-iso8859-1 (+ N 160)). | |
216 | ;; The element nil means there's no corresponding cp850 glyph. | |
217 | [ | |
6752f598 | 218 | 255 173 189 156 207 190 221 245 249 184 166 174 170 240 169 nil |
dd73abe6 | 219 | 248 241 253 252 239 230 244 250 247 251 167 175 172 171 243 168 |
75e98450 EZ |
220 | 183 181 182 199 142 143 146 128 212 144 210 211 222 214 215 216 |
221 | 209 165 227 224 226 229 153 158 157 235 233 234 154 237 231 225 | |
222 | 133 160 131 198 132 134 145 135 138 130 136 137 141 161 140 139 | |
223 | 208 164 149 162 147 228 148 246 155 151 163 150 129 236 232 152] | |
224 | "Table for converting ISO-8859-1 characters into codepage 850 glyphs.") | |
225 | (setplist 'cp850-decode-table | |
226 | '(charset latin-iso8859-1 language "Latin-1" offset 160)) | |
227 | ||
228 | ;; Greek | |
229 | (defvar cp851-decode-table | |
230 | [ | |
231 | 255 nil nil 156 nil nil nil 245 249 nil nil 174 nil 240 nil nil | |
232 | 248 241 nil nil 239 nil 134 nil 141 143 144 175 146 171 149 152 | |
233 | 161 164 165 166 167 168 169 170 172 173 181 182 184 183 189 190 | |
234 | 198 199 nil 207 208 209 210 211 212 213 nil nil 155 157 158 159 | |
235 | 252 214 215 216 221 222 224 225 226 227 228 229 230 231 232 233 | |
236 | 234 235 237 236 238 242 243 244 246 250 160 251 162 163 253 nil] | |
237 | "Table for converting ISO-8859-7 characters into codepage 851 glyphs.") | |
238 | (setplist 'cp851-decode-table | |
239 | '(charset greek-iso8859-7 language "Greek" offset 160)) | |
240 | ||
241 | ;; Slavic/Eastern Europe (Latin-2) | |
242 | (defvar cp852-decode-table | |
243 | [ | |
244 | 255 164 244 157 207 149 151 245 249 230 184 155 141 240 166 189 | |
245 | 248 165 247 136 239 150 152 243 242 231 173 156 171 241 167 190 | |
795537a2 | 246 | 232 181 182 198 142 145 143 128 172 144 168 211 183 214 215 210 |
75e98450 EZ |
247 | 209 227 213 224 226 138 153 158 252 222 233 235 154 237 221 225 |
248 | 234 160 131 199 132 146 134 135 159 130 169 137 216 161 140 212 | |
249 | 208 228 229 162 147 139 148 246 253 133 163 251 129 236 238 250] | |
250 | "Table for converting ISO-8859-2 characters into codepage 852 glyphs.") | |
251 | (setplist 'cp852-decode-table | |
252 | '(charset latin-iso8859-2 language "Latin-2" offset 160)) | |
253 | ||
254 | ;; Russian | |
255 | (defvar cp855-decode-table | |
256 | [ | |
dd73abe6 | 257 | 255 133 129 131 135 137 139 141 143 145 147 149 151 240 153 155 |
75e98450 EZ |
258 | 161 163 236 173 167 169 234 244 184 190 199 209 211 213 215 221 |
259 | 226 228 230 232 171 182 165 252 246 250 159 242 238 248 157 224 | |
260 | 160 162 235 172 166 168 233 243 183 189 198 208 210 212 214 216 | |
261 | 225 227 229 231 170 181 164 251 245 249 158 241 237 247 156 222 | |
dd73abe6 | 262 | 239 132 128 130 134 136 138 140 142 144 146 148 150 253 152 154] |
75e98450 EZ |
263 | "Table for converting ISO-8859-5 characters into codepage 855 glyphs.") |
264 | (setplist 'cp855-decode-table | |
265 | '(charset cyrillic-iso8859-5 language "Cyrillic-ISO" offset 160)) | |
266 | ||
267 | ;; Turkish | |
268 | (defvar cp857-decode-table | |
269 | [ | |
270 | 255 nil nil 156 207 nil 245 249 152 158 166 nil 240 nil | |
271 | 248 nil 253 252 239 nil nil nil nil 141 159 167 nil 171 nil | |
272 | 183 181 182 142 nil nil 128 212 144 210 211 222 214 215 216 | |
273 | 165 227 224 226 nil 153 232 nil 235 233 234 154 nil nil 225 | |
274 | 133 160 131 132 nil nil 135 138 130 136 137 236 161 140 139 | |
275 | 164 149 162 147 nil 148 246 nil 151 163 150 129 nil nil 250] | |
276 | "Table for converting ISO-8859-3 characters into codepage 857 glyphs.") | |
277 | (setplist 'cp857-decode-table | |
278 | '(charset latin-iso8859-3 language "Latin-3" offset 160)) | |
279 | ||
280 | ;; Portuguese | |
281 | (defvar cp860-decode-table | |
282 | [ | |
283 | 255 173 155 156 nil nil 179 nil nil nil 166 174 170 nil nil nil | |
284 | nil 241 253 nil nil nil nil 249 nil nil 167 175 172 171 nil 168 | |
285 | 145 134 143 142 nil nil nil 128 146 144 137 nil 152 nil 139 nil | |
286 | nil 165 159 169 140 153 nil nil nil 157 150 nil 154 nil nil nil | |
287 | 133 160 131 132 nil nil nil 135 138 130 136 nil 141 161 nil nil | |
288 | nil 164 149 162 147 148 nil 246 nil 151 163 nil 129 nil nil nil] | |
289 | "Table for converting ISO-8859-1 characters into codepage 860 glyphs.") | |
290 | (setplist 'cp860-decode-table | |
291 | '(charset latin-iso8859-1 language "Latin-1" offset 160)) | |
292 | ||
293 | ;; Icelandic | |
294 | (defvar cp861-decode-table | |
295 | [ | |
296 | 255 173 nil 156 nil nil nil nil nil nil nil 174 170 nil nil nil | |
297 | nil 241 253 nil nil nil nil 249 nil nil nil 175 172 171 nil 168 | |
298 | nil 164 nil nil 142 143 146 128 nil 144 nil nil nil 165 nil nil | |
299 | 139 nil 159 166 nil nil 153 nil 157 nil 167 nil 154 151 141 nil | |
300 | 133 160 131 nil 132 134 145 135 138 130 136 137 nil 161 nil nil | |
301 | 140 nil nil 162 147 nil 148 246 155 nil 163 150 129 152 149 nil] | |
302 | "Table for converting ISO-8859-1 characters into codepage 861 glyphs.") | |
303 | (setplist 'cp861-decode-table | |
304 | '(charset latin-iso8859-1 language "Latin-1" offset 160)) | |
305 | ||
306 | ;; Hebrew | |
307 | (defvar cp862-decode-table | |
308 | ;; Nth element is the code of a cp862 glyph for the multibyte | |
309 | ;; character created by (make-char 'hebrew-iso8859-8 (+ N 160)). | |
0ac646aa | 310 | ;; The element nil means there's no corresponding cp862 glyph. |
75e98450 EZ |
311 | [ |
312 | 255 173 155 156 nil 157 179 nil nil nil nil 174 170 196 nil nil | |
313 | 248 241 253 nil nil 230 nil 249 nil nil 246 175 172 171 nil nil | |
314 | nil nil nil nil nil nil nil nil nil nil nil nil nil nil nil nil | |
315 | nil nil nil nil nil nil nil nil nil nil nil nil nil nil nil 205 | |
316 | 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 | |
317 | 144 145 146 147 148 149 150 151 152 153 154 nil nil nil nil nil] | |
318 | "Table for converting ISO-8859-8 characters into codepage 862 glyphs.") | |
319 | (setplist 'cp862-decode-table | |
320 | '(charset hebrew-iso8859-8 language "Hebrew" offset 160)) | |
321 | ||
322 | ;; French Canadian | |
323 | (defvar cp863-decode-table | |
324 | [ | |
325 | 255 nil 155 156 152 nil 160 143 164 nil nil 174 170 nil nil 167 | |
326 | nil 241 253 166 161 nil 134 249 165 nil nil 175 172 171 173 nil | |
327 | 142 nil 132 nil nil nil nil 128 145 144 146 148 nil nil 168 149 | |
328 | nil nil nil nil 153 nil nil nil nil 157 nil 158 154 nil nil nil | |
329 | 133 nil 131 nil nil nil nil 135 138 130 136 137 141 nil 140 139 | |
330 | nil nil nil 162 147 nil nil 246 nil 151 163 150 129 nil nil nil] | |
331 | "Table for converting ISO-8859-1 characters into codepage 863 glyphs.") | |
332 | (setplist 'cp863-decode-table | |
333 | '(charset latin-iso8859-1 language "Latin-1" offset 160)) | |
334 | ||
335 | ;; Arabic | |
336 | ;; FIXME: Emacs doesn't seem to support the "Arabic" language | |
337 | ;; environment yet. So this is only partially usable, for now | |
338 | (defvar cp864-decode-table | |
339 | [ | |
340 | 255 nil nil nil 164 nil nil nil nil nil nil nil 172 161 nil nil | |
341 | nil nil nil nil nil nil nil nil nil nil nil 187 nil nil nil 191 | |
342 | nil 193 194 195 196 nil 198 199 169 201 170 171 173 174 175 207 | |
343 | 208 209 210 188 189 190 235 215 216 223 238 nil nil nil nil nil | |
344 | 224 247 248 252 251 239 242 243 232 233 253 nil nil nil nil nil | |
345 | nil 241 nil nil nil nil nil nil nil nil nil nil nil nil nil nil] | |
0ac646aa | 346 | "Table for converting ISO-8859-6 characters into codepage 864 glyphs.") |
75e98450 EZ |
347 | (setplist 'cp864-decode-table |
348 | '(charset arabic-iso8859-6 language nil offset 160)) | |
349 | ||
0ac646aa EZ |
350 | ;; Arabic OEM codepage used by Windows |
351 | ;; FIXME: Emacs doesn't seem to support the "Arabic" language | |
352 | ;; environment yet. So this is only partially usable, for now | |
353 | (defvar cp720-decode-table | |
354 | [ | |
355 | 255 nil nil nil 148 nil nil nil nil nil nil nil nil 196 nil nil | |
356 | nil nil nil nil nil nil nil nil nil nil nil nil nil nil nil nil | |
357 | nil 152 153 154 155 157 158 159 160 161 162 163 164 165 166 167 | |
358 | 168 169 170 171 172 173 224 225 226 227 228 nil nil nil nil nil | |
359 | 149 229 231 232 233 234 235 236 237 238 239 241 242 243 244 245 | |
360 | 246 145 146 nil nil nil nil nil nil nil nil nil nil nil nil nil] | |
361 | "Table for converting ISO-8859-6 characters into codepage 720 glyphs.") | |
362 | (setplist 'cp720-decode-table | |
363 | '(charset arabic-iso8859-6 language nil offset 160)) | |
364 | ||
365 | ||
75e98450 EZ |
366 | ;; Nordic (Norwegian/Danish) |
367 | (defvar cp865-decode-table | |
368 | [ | |
369 | 255 173 nil 156 nil nil nil nil nil nil 166 174 170 nil nil nil | |
370 | nil 241 253 nil nil nil nil 249 nil nil 167 175 172 171 nil 168 | |
371 | nil nil nil nil 142 143 146 128 nil 144 nil nil nil nil nil nil | |
372 | nil 165 nil nil nil nil 153 nil 157 nil nil nil 154 nil nil nil | |
373 | 133 160 131 nil 132 134 145 135 138 130 136 137 141 161 140 139 | |
374 | nil 164 149 162 147 nil 148 246 155 151 163 150 129 nil nil 152] | |
375 | "Table for converting ISO-8859-1 characters into codepage 865 glyphs.") | |
376 | (setplist 'cp865-decode-table | |
377 | '(charset latin-iso8859-1 language "Latin-1" offset 160)) | |
378 | ||
573191a1 EZ |
379 | ;; Russian (Yes, another one! This one's supposed to be used |
380 | ;; on Windows as the Russian OEM code page.) | |
381 | (defvar cp866-decode-table | |
382 | [ | |
383 | 255 240 nil nil 242 nil nil 244 nil nil nil nil nil nil 246 nil | |
384 | 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 | |
385 | 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | |
386 | 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 | |
ffd5cede | 387 | 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 |
573191a1 EZ |
388 | 252 241 nil nil 243 nil nil 245 nil nil nil nil nil nil 247 nil] |
389 | "Table for converting ISO-8859-5 characters into codepage 866 glyphs.") | |
390 | (setplist 'cp866-decode-table | |
391 | '(charset cyrillic-iso8859-5 language "Cyrillic-ISO" offset 160)) | |
392 | ||
75e98450 EZ |
393 | ;; Greek (yes, another one!) |
394 | (defvar cp869-decode-table | |
395 | [ | |
396 | 255 139 140 156 nil nil 138 245 249 151 nil 174 137 240 nil 142 | |
397 | 248 241 153 154 239 247 134 136 141 143 144 175 146 171 149 152 | |
398 | 161 164 165 166 167 168 169 170 172 173 181 182 183 184 189 190 | |
399 | 198 199 nil 207 208 209 210 211 212 213 145 150 155 157 158 159 | |
400 | 252 214 215 216 221 222 224 225 226 227 228 229 230 231 232 233 | |
401 | 234 235 237 236 238 242 243 244 246 250 160 251 162 163 253 nil] | |
402 | "Table for converting ISO-8859-7 characters into codepage 869 glyphs.") | |
403 | (setplist 'cp869-decode-table | |
404 | '(charset greek-iso8859-7 language "Greek" offset 160)) | |
405 | ||
0ac646aa EZ |
406 | ;; Greek OEM codepage used by Windows |
407 | (defvar cp737-decode-table | |
408 | [ | |
409 | 255 nil nil nil nil nil 179 nil nil nil nil nil nil 196 nil nil | |
410 | 248 241 253 nil nil nil 234 250 235 236 237 nil 238 nil 239 240 | |
411 | nil 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | |
412 | 143 144 nil 145 146 147 148 149 150 151 244 245 225 226 227 229 | |
413 | nil 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 | |
414 | 167 168 170 169 171 172 173 174 175 224 228 232 230 231 233 nil] | |
415 | "Table for converting ISO-8859-7 characters into codepage 737 glyphs.") | |
416 | (setplist 'cp737-decode-table | |
417 | '(charset greek-iso8859-7 language "Greek" offset 160)) | |
418 | ||
106e96bd EZ |
419 | ;; Conversion from codepages 770-775 to Latin-4 for Baltic countries. |
420 | ;; FIXME: Once we support Latin-7, these should be remapped into it. | |
421 | (defvar cp770-decode-table | |
422 | [ | |
423 | 255 143 nil nil 155 nil 156 nil 157 159 137 168 nil 196 146 nil | |
424 | 248 133 nil nil nil nil 134 nil nil 158 136 152 nil nil 145 nil | |
425 | 160 nil nil nil 142 nil nil 173 128 nil 139 nil 144 nil nil 161 | |
426 | nil nil nil 163 nil 149 153 nil nil 167 nil nil 154 nil 166 225 | |
427 | 131 nil nil nil 132 nil nil 141 135 nil 138 nil 130 nil nil 140 | |
428 | nil nil nil 162 nil 147 148 247 nil 151 nil nil 129 nil 150 nil] | |
429 | "Table for converting ISO-8859-4 characters into codepage 770 glyphs.") | |
430 | (setplist 'cp770-decode-table | |
431 | '(charset latin-iso8859-4 language "Latin-4" offset 160)) | |
432 | ||
433 | (defvar cp773-decode-table | |
434 | [ | |
435 | 255 220 nil 138 150 nil 234 190 166 246 237 149 173 196 252 nil | |
436 | 208 nil nil 139 239 nil 235 nil nil 247 137 133 136 nil 253 nil | |
437 | 160 nil nil nil 142 143 146 244 222 144 240 nil 242 nil nil 161 | |
438 | nil 238 226 232 nil 229 153 158 157 248 nil nil 154 nil 250 225 | |
439 | 131 nil nil nil 132 134 145 245 223 130 241 nil 243 nil nil 140 | |
440 | nil 236 147 233 nil 228 148 198 155 249 nil nil 129 nil 251 nil] | |
441 | "Table for converting ISO-8859-4 characters into codepage 773 glyphs.") | |
442 | (setplist 'cp773-decode-table | |
443 | '(charset latin-iso8859-4 language "Latin-4" offset 160)) | |
444 | ||
445 | (defvar cp774-decode-table | |
446 | [ | |
447 | 255 181 nil nil 155 nil nil nil 245 190 nil nil nil 196 207 nil | |
448 | 248 208 nil nil nil nil nil nil nil 213 nil nil nil nil 216 nil | |
449 | nil nil nil nil 142 143 146 189 182 144 183 nil 184 nil nil nil | |
450 | nil nil nil nil nil nil 153 nil nil 198 nil nil 154 nil 199 225 | |
451 | nil 160 nil nil 132 134 145 212 209 130 210 137 211 161 140 nil | |
452 | nil nil nil nil 147 nil 148 246 237 214 163 150 129 nil 215 248] | |
453 | "Table for converting ISO-8859-4 characters into codepage 774 glyphs.") | |
454 | (setplist 'cp774-decode-table | |
455 | '(charset latin-iso8859-4 language "Latin-4" offset 160)) | |
456 | ||
75e98450 EZ |
457 | (defvar cp775-decode-table |
458 | [ | |
459 | 255 181 nil 138 150 nil 234 245 166 190 237 149 173 240 207 nil | |
106e96bd | 460 | 248 208 nil 139 239 nil 235 nil nil 213 137 133 136 nil 216 nil |
75e98450 EZ |
461 | 160 nil nil nil 142 143 146 189 182 144 183 nil 184 nil nil 161 |
462 | nil 238 226 232 nil 229 153 158 157 198 nil nil 154 nil 199 225 | |
463 | 131 nil nil nil 132 134 145 212 209 130 210 nil 211 nil nil 140 | |
106e96bd | 464 | nil 236 147 233 nil 228 148 247 155 214 nil nil 129 nil 215 nil] |
75e98450 EZ |
465 | "Table for converting ISO-8859-4 characters into codepage 775 glyphs.") |
466 | (setplist 'cp775-decode-table | |
467 | '(charset latin-iso8859-4 language "Latin-4" offset 160)) | |
468 | ||
7e37faa3 EZ |
469 | ;; Support for the Windows 12xx series of codepages that MS has |
470 | ;; butchered from the ISO-8859 specs. This does not add support for | |
471 | ;; the extended characters that MS has added in the 128 - 159 coding | |
472 | ;; range, only translates those characters that can be expressed in | |
0ac646aa | 473 | ;; the corresponding iso-8859 charset. |
7e37faa3 EZ |
474 | |
475 | ;; Codepage Mapping: | |
476 | ;; | |
477 | ;; Windows-1250: ISO-8859-2 (Central Europe) - differs in some positions | |
478 | ;; Windows-1251: ISO-8859-5 (Cyrillic) - differs wildly | |
479 | ;; Windows-1252: ISO-8859-1 (West Europe) - exact match | |
480 | ;; Windows-1253: ISO-8859-7 (Greek) - differs in some positions | |
481 | ;; Windows-1254: ISO-8859-9 (Turkish) - exact match | |
482 | ;; Windows-1255: ISO-8859-8 (Hebrew) - exact match | |
483 | ;; Windows-1256: ISO-8859-6 (Arabic) - half match | |
484 | ;; Windows-1257: ISO-8859-4 (Baltic) - differs, future Latin-7 | |
485 | ;; Windows-1258: VISCII (Vietnamese) - Completely different | |
486 | ||
487 | (defvar cp1250-decode-table | |
488 | [ | |
489 | 160 165 162 163 164 188 140 167 168 138 170 141 143 173 142 175 | |
490 | 176 185 178 179 180 190 156 161 184 154 186 157 159 189 158 191 | |
491 | 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | |
492 | 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 | |
493 | 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 | |
494 | 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 ] | |
adab83c8 | 495 | "ISO-8859-2 to Windows-1250 (Central Europe) codepage decoding table.") |
7e37faa3 EZ |
496 | (setplist 'cp1250-decode-table |
497 | '(charset latin-iso8859-2 language "Latin-2" offset 160)) | |
498 | ||
499 | (defvar cp1251-decode-table | |
500 | [ | |
501 | 160 168 128 129 170 189 178 175 163 138 140 142 141 173 161 143 | |
502 | 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | |
503 | 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 | |
504 | 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 | |
505 | 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 | |
506 | 185 184 144 131 186 190 179 191 188 154 156 158 157 167 162 159 ] | |
adab83c8 | 507 | "ISO-8859-5 to Windows-1251 (Cyrillic) codepage decoding table.") |
7e37faa3 EZ |
508 | (setplist 'cp1251-decode-table |
509 | '(charset cyrillic-iso8859-5 language "Cyrillic-ISO" offset 160)) | |
510 | ||
511 | ;; cp1253 is missing nbsp so we cannot quite translate perfectly. It | |
512 | ;; also has two micro/mu characters which would require more complex | |
513 | ;; processing to accomodate. | |
514 | (defvar cp1253-decode-table | |
515 | [ | |
516 | nil 145 146 163 nil nil 166 167 168 169 nil 171 172 173 nil 151 | |
517 | 176 177 178 179 180 161 162 183 184 185 186 187 188 189 190 191 | |
518 | 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | |
519 | 208 209 nil 211 212 213 214 215 216 217 218 219 220 221 222 223 | |
520 | 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 | |
521 | 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 nil ] | |
adab83c8 | 522 | "ISO-8859-7 to Windows-1253 (Greek) codepage decoding table.") |
7e37faa3 EZ |
523 | (setplist 'cp1253-decode-table |
524 | '(charset greek-iso8859-7 language "Greek" offset 160)) | |
525 | ||
526 | ;; Since Latin-7 is not yet official, and Emacs does not support it, | |
527 | ;; provide translation between Windows-1257 and Latin-4 the best we | |
528 | ;; can. | |
529 | (defvar cp1257-decode-table | |
530 | [ | |
531 | 160 192 nil 170 164 nil 207 167 nil 208 199 204 nil 173 222 nil | |
532 | 176 224 nil 186 nil nil 239 nil nil 240 231 236 nil nil 254 nil | |
533 | 194 nil nil nil 196 197 175 193 200 201 198 nil 203 nil nil 206 | |
534 | nil 210 212 205 nil 213 214 215 168 216 nil nil 220 nil 219 223 | |
535 | 226 nil nil nil 228 229 191 225 232 233 230 nil 235 nil nil 238 | |
536 | nil 242 244 237 nil 245 246 247 184 248 nil nil 252 nil 251 nil ] | |
adab83c8 | 537 | "ISO-8859-4 to Windows-1257 (Baltic) codepage decoding table.") |
7e37faa3 EZ |
538 | (setplist 'cp1257-decode-table |
539 | '(charset latin-iso8859-4 language "Latin-4" offset 160)) | |
540 | ||
75e98450 EZ |
541 | ;;;###autoload |
542 | (defun cp-make-coding-systems-for-codepage (codepage iso-name offset) | |
708b0815 | 543 | "Create a coding system to convert IBM CODEPAGE into charset ISO-NAME |
75e98450 EZ |
544 | whose first character is at offset OFFSET from the beginning of 8-bit |
545 | ASCII table. | |
546 | ||
708b0815 EZ |
547 | The created coding system has the usual 3 subsidiary systems: for Unix-, |
548 | DOS- and Mac-style EOL conversion. However, unlike built-in coding | |
549 | systems, the Mac-style EOL conversion is currently not supported by the | |
550 | decoder and encoder created by this function." | |
75e98450 EZ |
551 | (let* ((decode-table (intern (format "%s-decode-table" codepage))) |
552 | (nonascii-table | |
553 | (intern (format "%s-nonascii-translation-table" codepage))) | |
554 | (decode-translation | |
555 | (intern (format "%s-decode-translation-table" codepage))) | |
556 | (encode-translation | |
776ca83d | 557 | (intern (format "%s-encode-translation-table" codepage)))) |
75e98450 EZ |
558 | (set nonascii-table |
559 | (make-translation-table-from-vector | |
560 | (cp-decoding-vector-for-codepage | |
561 | (symbol-value decode-table) iso-name offset))) | |
562 | (define-translation-table encode-translation | |
563 | (char-table-extra-slot (symbol-value nonascii-table) 0)) | |
0d35b92b EZ |
564 | ;; For charsets other than ascii, eight-bit-* and ISO-NAME, set |
565 | ;; `?' for one-column charsets, and some Japanese character for | |
75e98450 | 566 | ;; wide-column charsets. CCL encoder convert that Japanese |
a7bc7c2a | 567 | ;; character to either dos-unsupported-char-glyph or "??". |
75e98450 | 568 | (let ((tbl (char-table-extra-slot (symbol-value nonascii-table) 0)) |
a7bc7c2a EZ |
569 | (undef (if (eq system-type 'ms-dos) |
570 | (if dos-unsupported-char-glyph | |
571 | (logand dos-unsupported-char-glyph 255) | |
572 | 127) | |
573 | ??)) | |
0d35b92b EZ |
574 | (charsets (delq 'ascii |
575 | (delq 'eight-bit-control | |
576 | (delq 'eight-bit-graphic | |
577 | (delq iso-name | |
578 | (copy-sequence charset-list)))))) | |
75e98450 EZ |
579 | (wide-column-char (make-char 'japanese-jisx0208 32 32))) |
580 | (while charsets | |
581 | (aset tbl (make-char (car charsets)) | |
a7bc7c2a | 582 | (if (= (charset-width (car charsets)) 1) undef wide-column-char)) |
75e98450 EZ |
583 | (setq charsets (cdr charsets)))) |
584 | (define-translation-table decode-translation | |
585 | (symbol-value nonascii-table)) | |
586 | (cp-coding-system-for-codepage-1 | |
776ca83d EZ |
587 | (intern codepage) ?D iso-name decode-translation encode-translation) |
588 | )) | |
75e98450 EZ |
589 | |
590 | (defun cp-codepage-decoder (codepage) | |
8157ac14 PJ |
591 | "If CODEPAGE is the name of a supported codepage, return its decode table. |
592 | Otherwise return nil." | |
75e98450 EZ |
593 | (let ((cp (if (symbolp codepage) (symbol-name codepage) codepage))) |
594 | (cond | |
595 | ((stringp cp) | |
596 | (intern-soft (format "%s-decode-table" cp))) | |
597 | (t nil)))) | |
598 | ||
599 | ;;;###autoload | |
600 | (defun cp-charset-for-codepage (codepage) | |
601 | "Return the charset for which there is a translation table to DOS CODEPAGE. | |
602 | CODEPAGE must be the name of a DOS codepage, a string." | |
603 | (let ((cp-decoder (cp-codepage-decoder codepage))) | |
604 | (if (null cp-decoder) | |
605 | (error "Unsupported codepage %s" codepage) | |
606 | (get cp-decoder 'charset)))) | |
607 | ||
608 | ;;;###autoload | |
609 | (defun cp-language-for-codepage (codepage) | |
610 | "Return the name of the MULE language environment for CODEPAGE. | |
611 | CODEPAGE must be the name of a DOS codepage, a string." | |
612 | (let ((cp-decoder (cp-codepage-decoder codepage))) | |
613 | (if (null cp-decoder) | |
614 | (error "Unsupported codepage %s" codepage) | |
615 | (get cp-decoder 'language)))) | |
616 | ||
617 | ;;;###autoload | |
618 | (defun cp-offset-for-codepage (codepage) | |
619 | "Return the offset to be used in setting up coding systems for CODEPAGE. | |
620 | CODEPAGE must be the name of a DOS codepage, a string." | |
621 | (let ((cp-decoder (cp-codepage-decoder codepage))) | |
622 | (if (null cp-decoder) | |
623 | (error "Unsupported codepage %s" codepage) | |
624 | (get cp-decoder 'offset)))) | |
625 | ||
626 | ;;;###autoload | |
627 | (defun cp-supported-codepages () | |
628 | "Return an alist of supported codepages. | |
629 | ||
630 | Each association in the alist has the form (NNN . CHARSET), where NNN is the | |
631 | codepage number, and CHARSET is the MULE charset which is the closest match | |
632 | for the character set supported by that codepage. | |
633 | ||
634 | A codepage NNN is supported if a variable called `cpNNN-decode-table' exists, | |
635 | is a vector, and has a charset property." | |
636 | (save-match-data | |
637 | (let (alist chset sname) | |
638 | (mapatoms | |
639 | (function | |
640 | (lambda (sym) | |
641 | (if (and (boundp sym) | |
7e37faa3 | 642 | (string-match "\\`cp\\([1-9][0-9][0-9][0-9]?\\)-decode-table\\'" |
75e98450 EZ |
643 | (setq sname (symbol-name sym))) |
644 | (vectorp (symbol-value sym)) | |
645 | (setq chset (get sym 'charset))) | |
646 | (setq alist | |
647 | (cons (cons (match-string 1 sname) chset) alist)))))) | |
648 | alist))) | |
649 | ||
650 | ;;;###autoload | |
651 | (defun codepage-setup (codepage) | |
e714d2cf | 652 | "Create a coding system cpCODEPAGE to support the IBM codepage CODEPAGE. |
75e98450 EZ |
653 | |
654 | These coding systems are meant for encoding and decoding 8-bit non-ASCII | |
655 | characters used by the IBM codepages, typically in conjunction with files | |
e714d2cf | 656 | read/written by MS-DOS software, or for display on the MS-DOS terminal." |
75e98450 EZ |
657 | (interactive |
658 | (let ((completion-ignore-case t) | |
659 | (candidates (cp-supported-codepages))) | |
660 | (list (completing-read "Setup DOS Codepage: (default 437) " candidates | |
661 | nil t nil nil "437")))) | |
7dd4fd43 EZ |
662 | (let* ((cp (format "cp%s" codepage)) |
663 | (cp-defined (intern-soft cp))) | |
664 | (or (and cp-defined ;; avoid defining if already defined | |
665 | (coding-system-p cp-defined)) | |
666 | (cp-make-coding-systems-for-codepage | |
667 | cp (cp-charset-for-codepage cp) (cp-offset-for-codepage cp))))) | |
75e98450 EZ |
668 | |
669 | (provide 'codepage) | |
670 | ||
ab5796a9 | 671 | ;;; arch-tag: 80328de8-b94e-4386-be26-5876105731f0 |
55535639 | 672 | ;;; codepage.el ends here |