|
771
|
1 /* Win32 internationalization functions.
|
|
|
2 Copyright (C) 2000, 2001, 2002 Ben Wing.
|
|
|
3 Copyright (C) 2000 IKEYAMA Tomonori.
|
|
|
4
|
|
|
5 This file is part of XEmacs.
|
|
|
6
|
|
|
7 XEmacs is free software; you can redistribute it and/or modify it
|
|
|
8 under the terms of the GNU General Public License as published by the
|
|
|
9 Free Software Foundation; either version 2, or (at your option) any
|
|
|
10 later version.
|
|
|
11
|
|
|
12 XEmacs is distributed in the hope that it will be useful, but WITHOUT
|
|
|
13 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
|
14 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
|
|
15 for more details.
|
|
|
16
|
|
|
17 You should have received a copy of the GNU General Public License
|
|
|
18 along with XEmacs; see the file COPYING. If not, write to
|
|
|
19 the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
|
20 Boston, MA 02111-1307, USA. */
|
|
|
21
|
|
|
22 /* Synched up with: Not in FSF. */
|
|
|
23
|
|
|
24 /* Authorship:
|
|
|
25
|
|
|
26 Current primary author: Ben Wing <ben@xemacs.org>
|
|
|
27
|
|
|
28 Created summer 2000 by Ben Wing. Almost completely written by Ben Wing.
|
|
|
29 Little bits of code in some of the Lisp primitives from FSF Emacs.
|
|
|
30 Versions of wcscpy, wcsncpy from Cygwin newlib.
|
|
|
31
|
|
|
32 Coding systems written by Ben Wing in file-coding.c; moved here Sep 2001.
|
|
|
33 */
|
|
|
34
|
|
|
35 #include <config.h>
|
|
|
36 #include "lisp.h"
|
|
|
37
|
|
|
38 #include "elhash.h"
|
|
|
39 #include "faces.h"
|
|
|
40 #include "file-coding.h"
|
|
|
41 #include "frame.h"
|
|
|
42 #include "window.h"
|
|
|
43
|
|
|
44 #include "console-msw.h"
|
|
|
45 #include "objects-msw.h"
|
|
|
46
|
|
|
47 #ifndef CYGWIN_HEADERS
|
|
|
48 # include <mbctype.h>
|
|
|
49 #elif defined (MINGW)
|
|
|
50 int _setmbcp (int);
|
|
|
51 int _getmbcp (void);
|
|
|
52 #else
|
|
|
53 # define NO_EXT_MULTIBYTE_FEATURES
|
|
|
54 #endif
|
|
|
55
|
|
|
56 Lisp_Object Qmswindows_multibyte, Qmswindows_multibyte_to_unicode;
|
|
|
57 Lisp_Object Qmswindows_tstr, Qmswindows_unicode;
|
|
|
58 Lisp_Object Qmswindows_multibyte_system_default;
|
|
|
59
|
|
|
60 Lisp_Object Qansi, Qoem, Qmac, Qebcdic;
|
|
|
61 /* Qcode_page, Qlocale, Qcurrent, Quser_default, Qsystem_default in
|
|
|
62 general-slots.h */
|
|
|
63
|
|
|
64 #ifdef MULE
|
|
|
65
|
|
|
66 static Lisp_Object Vmswindows_charset_code_page_table;
|
|
|
67
|
|
|
68 LCID current_locale;
|
|
|
69
|
|
|
70
|
|
|
71 /************************************************************************/
|
|
|
72 /* Language/locale/code page conversion functions */
|
|
|
73 /************************************************************************/
|
|
|
74
|
|
|
75 /* There are various different ways of representing the vague concept
|
|
|
76 of "language", and it can be very confusing. So:
|
|
|
77
|
|
|
78 -- The C library has the concept of "locale", which is a
|
|
|
79 combination of language and country, and which controls the way
|
|
|
80 currency and dates are displayed, the encoding of data, etc.
|
|
|
81
|
|
|
82 -- XEmacs has the concept of "language environment", more or less
|
|
|
83 like a locale; although currently in most cases it just refers to
|
|
|
84 the language, and no sub-language distinctions are
|
|
|
85 made. (Exceptions are with Chinese, which has different language
|
|
|
86 environments for Taiwan and mainland China, due to the different
|
|
|
87 encodings and writing systems.)
|
|
|
88
|
|
|
89 -- Windows has a number of different language concepts:
|
|
|
90
|
|
|
91 1. There are "languages" and "sublanguages", which correspond to
|
|
|
92 the languages and countries of the C library -- e.g. LANG_ENGLISH
|
|
|
93 and SUBLANG_ENGLISH_US. These are identified by 8-bit integers,
|
|
|
94 called the "primary language identifier" and "sublanguage
|
|
|
95 identifier", respectively. These are combined into a 16-bit
|
|
|
96 integer or "language identifier" by MAKELANGID().
|
|
|
97
|
|
|
98 2. The language identifier in turn is combined with a "sort
|
|
|
99 identifier" (and optionally a "sort version") to yield a 32-bit
|
|
|
100 integer called a "locale identifier" (type LCID), which identifies
|
|
|
101 locales -- the primary means of distinguishing language/regional
|
|
|
102 settings and similar to C library locales.
|
|
|
103
|
|
|
104 3. "Code pages" identify different text encodings (i.e. a set of
|
|
|
105 supported characters, an enumeration of those characters [i.e. an
|
|
|
106 association of character with number or number pair; there may be
|
|
|
107 disjoint ranges of numbers supported]), and a way of encoding a
|
|
|
108 stream of those characters into an 8-bit data stream). All of the
|
|
|
109 encodings are either one-byte or mixed one-byte/two-byte encodings,
|
|
|
110 all non-modal; in the mixed encodings, two-byte characters have the
|
|
|
111 first byte >= 128, although the second byte may or may not be
|
|
|
112 restricted to this range, depending on the encoding. Code pages
|
|
|
113 are similar to XEmacs "charsets"; the latter also define a set of
|
|
|
114 supported characters and an enumeration of those characters (but
|
|
|
115 code pages in additionally define an encoding, which charsets don't
|
|
|
116 do). Code pages often function in Windows like charsets in XEmacs.
|
|
|
117
|
|
|
118 4. Every Windows locale has a specific code page associated with
|
|
|
119 it; more than one locale can share a code page -- e.g. all the
|
|
|
120 Western European languages, including English, do.
|
|
|
121
|
|
|
122 5. Windows also has an "input locale identifier" (aka "keyboard
|
|
|
123 layout id") or HKL, which is a 32-bit integer composed of the
|
|
|
124 16-bit language identifier and a 16-bit "device identifier", which
|
|
|
125 originally specified a particular keyboard layout (e.g. the locale
|
|
|
126 "US English" can have the QWERTY layout, the Dvorak layout, etc.),
|
|
|
127 but has been expanded to include speech-to-text converters and
|
|
|
128 other non-keyboard ways of inputting text. Note that both the HKL
|
|
|
129 and LCID share the language identifier in the lower 16 bits, and in
|
|
|
130 both cases a 0 in the upper 16 bits means "default" (sort order or
|
|
|
131 device), providing a way to convert between HKL's, LCID's, and
|
|
|
132 language identifiers (i.e. language/sublanguage pairs). The
|
|
|
133 default keyboard layout for a language is (as far as I can
|
|
|
134 determine) established using the Regional Settings control panel
|
|
|
135 applet, where you can add input locales as combinations of language
|
|
|
136 (actually language/sublanguage) and layout; presumably if you list
|
|
|
137 only one input locale with a particular language, the corresponding
|
|
|
138 layout is the default for that language. But what if you list more
|
|
|
139 than one? You can specify a single default input locale, but there
|
|
|
140 appears to be no way to do so on a per-language basis.
|
|
|
141 */
|
|
|
142
|
|
|
143 struct lang_to_string
|
|
|
144 {
|
|
|
145 int code;
|
|
|
146 char *string;
|
|
|
147 };
|
|
|
148
|
|
|
149 struct lang_to_string lang_to_string_table[] =
|
|
|
150 {
|
|
|
151 /* These names change from version to version of VC++, so it's easiest
|
|
|
152 just to bracket them all with ifdefs. */
|
|
|
153 #ifdef LANG_AFRIKAANS
|
|
|
154 { LANG_AFRIKAANS, "AFRIKAANS" },
|
|
|
155 #endif
|
|
|
156 #ifdef LANG_ALBANIAN
|
|
|
157 { LANG_ALBANIAN, "ALBANIAN" },
|
|
|
158 #endif
|
|
|
159 #ifdef LANG_ARABIC
|
|
|
160 { LANG_ARABIC, "ARABIC" },
|
|
|
161 #endif
|
|
|
162 #ifdef LANG_ARMENIAN
|
|
|
163 { LANG_ARMENIAN, "ARMENIAN" },
|
|
|
164 #endif
|
|
|
165 #ifdef LANG_ASSAMESE
|
|
|
166 { LANG_ASSAMESE, "ASSAMESE" },
|
|
|
167 #endif
|
|
|
168 #ifdef LANG_AZERI
|
|
|
169 { LANG_AZERI, "AZERI" },
|
|
|
170 #endif
|
|
|
171 #ifdef LANG_BASQUE
|
|
|
172 { LANG_BASQUE, "BASQUE" },
|
|
|
173 #endif
|
|
|
174 #ifdef LANG_BELARUSIAN
|
|
|
175 { LANG_BELARUSIAN, "BELARUSIAN" },
|
|
|
176 #endif
|
|
|
177 #ifdef LANG_BENGALI
|
|
|
178 { LANG_BENGALI, "BENGALI" },
|
|
|
179 #endif
|
|
|
180 #ifdef LANG_BULGARIAN
|
|
|
181 { LANG_BULGARIAN, "BULGARIAN" },
|
|
|
182 #endif
|
|
|
183 #ifdef LANG_CATALAN
|
|
|
184 { LANG_CATALAN, "CATALAN" },
|
|
|
185 #endif
|
|
|
186 #ifdef LANG_CHINESE
|
|
|
187 { LANG_CHINESE, "CHINESE" },
|
|
|
188 #endif
|
|
|
189 #ifdef LANG_CROATIAN
|
|
|
190 { LANG_CROATIAN, "CROATIAN" },
|
|
|
191 #endif
|
|
|
192 #ifdef LANG_CZECH
|
|
|
193 { LANG_CZECH, "CZECH" },
|
|
|
194 #endif
|
|
|
195 #ifdef LANG_DANISH
|
|
|
196 { LANG_DANISH, "DANISH" },
|
|
|
197 #endif
|
|
|
198 #ifdef LANG_DUTCH
|
|
|
199 { LANG_DUTCH, "DUTCH" },
|
|
|
200 #endif
|
|
|
201 #ifdef LANG_ENGLISH
|
|
|
202 { LANG_ENGLISH, "ENGLISH" },
|
|
|
203 #endif
|
|
|
204 #ifdef LANG_ESTONIAN
|
|
|
205 { LANG_ESTONIAN, "ESTONIAN" },
|
|
|
206 #endif
|
|
|
207 #ifdef LANG_FAEROESE
|
|
|
208 { LANG_FAEROESE, "FAEROESE" },
|
|
|
209 #endif
|
|
|
210 #ifdef LANG_FARSI
|
|
|
211 { LANG_FARSI, "FARSI" },
|
|
|
212 #endif
|
|
|
213 #ifdef LANG_FINNISH
|
|
|
214 { LANG_FINNISH, "FINNISH" },
|
|
|
215 #endif
|
|
|
216 #ifdef LANG_FRENCH
|
|
|
217 { LANG_FRENCH, "FRENCH" },
|
|
|
218 #endif
|
|
|
219 #ifdef LANG_GEORGIAN
|
|
|
220 { LANG_GEORGIAN, "GEORGIAN" },
|
|
|
221 #endif
|
|
|
222 #ifdef LANG_GERMAN
|
|
|
223 { LANG_GERMAN, "GERMAN" },
|
|
|
224 #endif
|
|
|
225 #ifdef LANG_GREEK
|
|
|
226 { LANG_GREEK, "GREEK" },
|
|
|
227 #endif
|
|
|
228 #ifdef LANG_GUJARATI
|
|
|
229 { LANG_GUJARATI, "GUJARATI" },
|
|
|
230 #endif
|
|
|
231 #ifdef LANG_HEBREW
|
|
|
232 { LANG_HEBREW, "HEBREW" },
|
|
|
233 #endif
|
|
|
234 #ifdef LANG_HINDI
|
|
|
235 { LANG_HINDI, "HINDI" },
|
|
|
236 #endif
|
|
|
237 #ifdef LANG_HUNGARIAN
|
|
|
238 { LANG_HUNGARIAN, "HUNGARIAN" },
|
|
|
239 #endif
|
|
|
240 #ifdef LANG_ICELANDIC
|
|
|
241 { LANG_ICELANDIC, "ICELANDIC" },
|
|
|
242 #endif
|
|
|
243 #ifdef LANG_INDONESIAN
|
|
|
244 { LANG_INDONESIAN, "INDONESIAN" },
|
|
|
245 #endif
|
|
|
246 #ifdef LANG_ITALIAN
|
|
|
247 { LANG_ITALIAN, "ITALIAN" },
|
|
|
248 #endif
|
|
|
249 #ifdef LANG_JAPANESE
|
|
|
250 { LANG_JAPANESE, "JAPANESE" },
|
|
|
251 #endif
|
|
|
252 #ifdef LANG_KANNADA
|
|
|
253 { LANG_KANNADA, "KANNADA" },
|
|
|
254 #endif
|
|
|
255 #ifdef LANG_KASHMIRI
|
|
|
256 { LANG_KASHMIRI, "KASHMIRI" },
|
|
|
257 #endif
|
|
|
258 #ifdef LANG_KAZAK
|
|
|
259 { LANG_KAZAK, "KAZAK" },
|
|
|
260 #endif
|
|
|
261 #ifdef LANG_KONKANI
|
|
|
262 { LANG_KONKANI, "KONKANI" },
|
|
|
263 #endif
|
|
|
264 #ifdef LANG_KOREAN
|
|
|
265 { LANG_KOREAN, "KOREAN" },
|
|
|
266 #endif
|
|
|
267 #ifdef LANG_LATVIAN
|
|
|
268 { LANG_LATVIAN, "LATVIAN" },
|
|
|
269 #endif
|
|
|
270 #ifdef LANG_LITHUANIAN
|
|
|
271 { LANG_LITHUANIAN, "LITHUANIAN" },
|
|
|
272 #endif
|
|
|
273 #ifdef LANG_MACEDONIAN
|
|
|
274 { LANG_MACEDONIAN, "MACEDONIAN" },
|
|
|
275 #endif
|
|
|
276 #ifdef LANG_MALAY
|
|
|
277 { LANG_MALAY, "MALAY" },
|
|
|
278 #endif
|
|
|
279 #ifdef LANG_MALAYALAM
|
|
|
280 { LANG_MALAYALAM, "MALAYALAM" },
|
|
|
281 #endif
|
|
|
282 #ifdef LANG_MANIPURI
|
|
|
283 { LANG_MANIPURI, "MANIPURI" },
|
|
|
284 #endif
|
|
|
285 #ifdef LANG_MARATHI
|
|
|
286 { LANG_MARATHI, "MARATHI" },
|
|
|
287 #endif
|
|
|
288 #ifdef LANG_NEPALI
|
|
|
289 { LANG_NEPALI, "NEPALI" },
|
|
|
290 #endif
|
|
|
291 #ifdef LANG_NEUTRAL
|
|
|
292 { LANG_NEUTRAL, "NEUTRAL" },
|
|
|
293 #endif
|
|
|
294 #ifdef LANG_NORWEGIAN
|
|
|
295 { LANG_NORWEGIAN, "NORWEGIAN" },
|
|
|
296 #endif
|
|
|
297 #ifdef LANG_ORIYA
|
|
|
298 { LANG_ORIYA, "ORIYA" },
|
|
|
299 #endif
|
|
|
300 #ifdef LANG_POLISH
|
|
|
301 { LANG_POLISH, "POLISH" },
|
|
|
302 #endif
|
|
|
303 #ifdef LANG_PORTUGUESE
|
|
|
304 { LANG_PORTUGUESE, "PORTUGUESE" },
|
|
|
305 #endif
|
|
|
306 #ifdef LANG_PUNJABI
|
|
|
307 { LANG_PUNJABI, "PUNJABI" },
|
|
|
308 #endif
|
|
|
309 #ifdef LANG_ROMANIAN
|
|
|
310 { LANG_ROMANIAN, "ROMANIAN" },
|
|
|
311 #endif
|
|
|
312 #ifdef LANG_RUSSIAN
|
|
|
313 { LANG_RUSSIAN, "RUSSIAN" },
|
|
|
314 #endif
|
|
|
315 #ifdef LANG_SANSKRIT
|
|
|
316 { LANG_SANSKRIT, "SANSKRIT" },
|
|
|
317 #endif
|
|
|
318 #ifdef LANG_SERBIAN
|
|
|
319 { LANG_SERBIAN, "SERBIAN" },
|
|
|
320 #endif
|
|
|
321 #ifdef LANG_SINDHI
|
|
|
322 { LANG_SINDHI, "SINDHI" },
|
|
|
323 #endif
|
|
|
324 #ifdef LANG_SLOVAK
|
|
|
325 { LANG_SLOVAK, "SLOVAK" },
|
|
|
326 #endif
|
|
|
327 #ifdef LANG_SLOVENIAN
|
|
|
328 { LANG_SLOVENIAN, "SLOVENIAN" },
|
|
|
329 #endif
|
|
|
330 #ifdef LANG_SPANISH
|
|
|
331 { LANG_SPANISH, "SPANISH" },
|
|
|
332 #endif
|
|
|
333 #ifdef LANG_SWAHILI
|
|
|
334 { LANG_SWAHILI, "SWAHILI" },
|
|
|
335 #endif
|
|
|
336 #ifdef LANG_SWEDISH
|
|
|
337 { LANG_SWEDISH, "SWEDISH" },
|
|
|
338 #endif
|
|
|
339 #ifdef LANG_TAMIL
|
|
|
340 { LANG_TAMIL, "TAMIL" },
|
|
|
341 #endif
|
|
|
342 #ifdef LANG_TATAR
|
|
|
343 { LANG_TATAR, "TATAR" },
|
|
|
344 #endif
|
|
|
345 #ifdef LANG_TELUGU
|
|
|
346 { LANG_TELUGU, "TELUGU" },
|
|
|
347 #endif
|
|
|
348 #ifdef LANG_THAI
|
|
|
349 { LANG_THAI, "THAI" },
|
|
|
350 #endif
|
|
|
351 #ifdef LANG_TURKISH
|
|
|
352 { LANG_TURKISH, "TURKISH" },
|
|
|
353 #endif
|
|
|
354 #ifdef LANG_UKRAINIAN
|
|
|
355 { LANG_UKRAINIAN, "UKRAINIAN" },
|
|
|
356 #endif
|
|
|
357 #ifdef LANG_URDU
|
|
|
358 { LANG_URDU, "URDU" },
|
|
|
359 #endif
|
|
|
360 #ifdef LANG_UZBEK
|
|
|
361 { LANG_UZBEK, "UZBEK" },
|
|
|
362 #endif
|
|
|
363 #ifdef LANG_VIETNAMESE
|
|
|
364 { LANG_VIETNAMESE, "VIETNAMESE" },
|
|
|
365 #endif
|
|
|
366 };
|
|
|
367
|
|
|
368 struct lang_to_string sublang_to_string_table[] =
|
|
|
369 {
|
|
|
370 { LANG_ARABIC, 0 },
|
|
|
371 #ifdef SUBLANG_ARABIC_ALGERIA
|
|
|
372 { SUBLANG_ARABIC_ALGERIA, "ARABIC_ALGERIA" },
|
|
|
373 #endif
|
|
|
374 #ifdef SUBLANG_ARABIC_BAHRAIN
|
|
|
375 { SUBLANG_ARABIC_BAHRAIN, "ARABIC_BAHRAIN" },
|
|
|
376 #endif
|
|
|
377 #ifdef SUBLANG_ARABIC_EGYPT
|
|
|
378 { SUBLANG_ARABIC_EGYPT, "ARABIC_EGYPT" },
|
|
|
379 #endif
|
|
|
380 #ifdef SUBLANG_ARABIC_IRAQ
|
|
|
381 { SUBLANG_ARABIC_IRAQ, "ARABIC_IRAQ" },
|
|
|
382 #endif
|
|
|
383 #ifdef SUBLANG_ARABIC_JORDAN
|
|
|
384 { SUBLANG_ARABIC_JORDAN, "ARABIC_JORDAN" },
|
|
|
385 #endif
|
|
|
386 #ifdef SUBLANG_ARABIC_KUWAIT
|
|
|
387 { SUBLANG_ARABIC_KUWAIT, "ARABIC_KUWAIT" },
|
|
|
388 #endif
|
|
|
389 #ifdef SUBLANG_ARABIC_LEBANON
|
|
|
390 { SUBLANG_ARABIC_LEBANON, "ARABIC_LEBANON" },
|
|
|
391 #endif
|
|
|
392 #ifdef SUBLANG_ARABIC_LIBYA
|
|
|
393 { SUBLANG_ARABIC_LIBYA, "ARABIC_LIBYA" },
|
|
|
394 #endif
|
|
|
395 #ifdef SUBLANG_ARABIC_MOROCCO
|
|
|
396 { SUBLANG_ARABIC_MOROCCO, "ARABIC_MOROCCO" },
|
|
|
397 #endif
|
|
|
398 #ifdef SUBLANG_ARABIC_OMAN
|
|
|
399 { SUBLANG_ARABIC_OMAN, "ARABIC_OMAN" },
|
|
|
400 #endif
|
|
|
401 #ifdef SUBLANG_ARABIC_QATAR
|
|
|
402 { SUBLANG_ARABIC_QATAR, "ARABIC_QATAR" },
|
|
|
403 #endif
|
|
|
404 #ifdef SUBLANG_ARABIC_SAUDI_ARABIA
|
|
|
405 { SUBLANG_ARABIC_SAUDI_ARABIA, "ARABIC_SAUDI_ARABIA" },
|
|
|
406 #endif
|
|
|
407 #ifdef SUBLANG_ARABIC_SYRIA
|
|
|
408 { SUBLANG_ARABIC_SYRIA, "ARABIC_SYRIA" },
|
|
|
409 #endif
|
|
|
410 #ifdef SUBLANG_ARABIC_TUNISIA
|
|
|
411 { SUBLANG_ARABIC_TUNISIA, "ARABIC_TUNISIA" },
|
|
|
412 #endif
|
|
|
413 #ifdef SUBLANG_ARABIC_UAE
|
|
|
414 { SUBLANG_ARABIC_UAE, "ARABIC_UAE" },
|
|
|
415 #endif
|
|
|
416 #ifdef SUBLANG_ARABIC_YEMEN
|
|
|
417 { SUBLANG_ARABIC_YEMEN, "ARABIC_YEMEN" },
|
|
|
418 #endif
|
|
|
419 { LANG_AZERI, 0 },
|
|
|
420 #ifdef SUBLANG_AZERI_CYRILLIC
|
|
|
421 { SUBLANG_AZERI_CYRILLIC, "AZERI_CYRILLIC" },
|
|
|
422 #endif
|
|
|
423 #ifdef SUBLANG_AZERI_LATIN
|
|
|
424 { SUBLANG_AZERI_LATIN, "AZERI_LATIN" },
|
|
|
425 #endif
|
|
|
426 { LANG_CHINESE, 0 },
|
|
|
427 #ifdef SUBLANG_CHINESE_HONGKONG
|
|
|
428 { SUBLANG_CHINESE_HONGKONG, "CHINESE_HONGKONG" },
|
|
|
429 #endif
|
|
|
430 #ifdef SUBLANG_CHINESE_MACAU
|
|
|
431 { SUBLANG_CHINESE_MACAU, "CHINESE_MACAU" },
|
|
|
432 #endif
|
|
|
433 #ifdef SUBLANG_CHINESE_SIMPLIFIED
|
|
|
434 { SUBLANG_CHINESE_SIMPLIFIED, "CHINESE_SIMPLIFIED" },
|
|
|
435 #endif
|
|
|
436 #ifdef SUBLANG_CHINESE_SINGAPORE
|
|
|
437 { SUBLANG_CHINESE_SINGAPORE, "CHINESE_SINGAPORE" },
|
|
|
438 #endif
|
|
|
439 #ifdef SUBLANG_CHINESE_TRADITIONAL
|
|
|
440 { SUBLANG_CHINESE_TRADITIONAL, "CHINESE_TRADITIONAL" },
|
|
|
441 #endif
|
|
|
442 { LANG_DUTCH, 0 },
|
|
|
443 #ifdef SUBLANG_DUTCH
|
|
|
444 { SUBLANG_DUTCH, "DUTCH" },
|
|
|
445 #endif
|
|
|
446 #ifdef SUBLANG_DUTCH_BELGIAN
|
|
|
447 { SUBLANG_DUTCH_BELGIAN, "DUTCH_BELGIAN" },
|
|
|
448 #endif
|
|
|
449 { LANG_ENGLISH, 0 },
|
|
|
450 #ifdef SUBLANG_ENGLISH_AUS
|
|
|
451 { SUBLANG_ENGLISH_AUS, "ENGLISH_AUS" },
|
|
|
452 #endif
|
|
|
453 #ifdef SUBLANG_ENGLISH_BELIZE
|
|
|
454 { SUBLANG_ENGLISH_BELIZE, "ENGLISH_BELIZE" },
|
|
|
455 #endif
|
|
|
456 #ifdef SUBLANG_ENGLISH_CAN
|
|
|
457 { SUBLANG_ENGLISH_CAN, "ENGLISH_CAN" },
|
|
|
458 #endif
|
|
|
459 #ifdef SUBLANG_ENGLISH_CARIBBEAN
|
|
|
460 { SUBLANG_ENGLISH_CARIBBEAN, "ENGLISH_CARIBBEAN" },
|
|
|
461 #endif
|
|
|
462 #ifdef SUBLANG_ENGLISH_EIRE
|
|
|
463 { SUBLANG_ENGLISH_EIRE, "ENGLISH_EIRE" },
|
|
|
464 #endif
|
|
|
465 #ifdef SUBLANG_ENGLISH_JAMAICA
|
|
|
466 { SUBLANG_ENGLISH_JAMAICA, "ENGLISH_JAMAICA" },
|
|
|
467 #endif
|
|
|
468 #ifdef SUBLANG_ENGLISH_NZ
|
|
|
469 { SUBLANG_ENGLISH_NZ, "ENGLISH_NZ" },
|
|
|
470 #endif
|
|
|
471 #ifdef SUBLANG_ENGLISH_PHILIPPINES
|
|
|
472 { SUBLANG_ENGLISH_PHILIPPINES, "ENGLISH_PHILIPPINES" },
|
|
|
473 #endif
|
|
|
474 #ifdef SUBLANG_ENGLISH_SOUTH_AFRICA
|
|
|
475 { SUBLANG_ENGLISH_SOUTH_AFRICA, "ENGLISH_SOUTH_AFRICA" },
|
|
|
476 #endif
|
|
|
477 #ifdef SUBLANG_ENGLISH_TRINIDAD
|
|
|
478 { SUBLANG_ENGLISH_TRINIDAD, "ENGLISH_TRINIDAD" },
|
|
|
479 #endif
|
|
|
480 #ifdef SUBLANG_ENGLISH_UK
|
|
|
481 { SUBLANG_ENGLISH_UK, "ENGLISH_UK" },
|
|
|
482 #endif
|
|
|
483 #ifdef SUBLANG_ENGLISH_US
|
|
|
484 { SUBLANG_ENGLISH_US, "ENGLISH_US" },
|
|
|
485 #endif
|
|
|
486 #ifdef SUBLANG_ENGLISH_ZIMBABWE
|
|
|
487 { SUBLANG_ENGLISH_ZIMBABWE, "ENGLISH_ZIMBABWE" },
|
|
|
488 #endif
|
|
|
489 { LANG_FRENCH, 0 },
|
|
|
490 #ifdef SUBLANG_FRENCH
|
|
|
491 { SUBLANG_FRENCH, "FRENCH" },
|
|
|
492 #endif
|
|
|
493 #ifdef SUBLANG_FRENCH_BELGIAN
|
|
|
494 { SUBLANG_FRENCH_BELGIAN, "FRENCH_BELGIAN" },
|
|
|
495 #endif
|
|
|
496 #ifdef SUBLANG_FRENCH_CANADIAN
|
|
|
497 { SUBLANG_FRENCH_CANADIAN, "FRENCH_CANADIAN" },
|
|
|
498 #endif
|
|
|
499 #ifdef SUBLANG_FRENCH_LUXEMBOURG
|
|
|
500 { SUBLANG_FRENCH_LUXEMBOURG, "FRENCH_LUXEMBOURG" },
|
|
|
501 #endif
|
|
|
502 #ifdef SUBLANG_FRENCH_MONACO
|
|
|
503 { SUBLANG_FRENCH_MONACO, "FRENCH_MONACO" },
|
|
|
504 #endif
|
|
|
505 #ifdef SUBLANG_FRENCH_SWISS
|
|
|
506 { SUBLANG_FRENCH_SWISS, "FRENCH_SWISS" },
|
|
|
507 #endif
|
|
|
508 { LANG_GERMAN, 0 },
|
|
|
509 #ifdef SUBLANG_GERMAN
|
|
|
510 { SUBLANG_GERMAN, "GERMAN" },
|
|
|
511 #endif
|
|
|
512 #ifdef SUBLANG_GERMAN_AUSTRIAN
|
|
|
513 { SUBLANG_GERMAN_AUSTRIAN, "GERMAN_AUSTRIAN" },
|
|
|
514 #endif
|
|
|
515 #ifdef SUBLANG_GERMAN_LIECHTENSTEIN
|
|
|
516 { SUBLANG_GERMAN_LIECHTENSTEIN, "GERMAN_LIECHTENSTEIN" },
|
|
|
517 #endif
|
|
|
518 #ifdef SUBLANG_GERMAN_LUXEMBOURG
|
|
|
519 { SUBLANG_GERMAN_LUXEMBOURG, "GERMAN_LUXEMBOURG" },
|
|
|
520 #endif
|
|
|
521 #ifdef SUBLANG_GERMAN_SWISS
|
|
|
522 { SUBLANG_GERMAN_SWISS, "GERMAN_SWISS" },
|
|
|
523 #endif
|
|
|
524 { LANG_ITALIAN, 0 },
|
|
|
525 #ifdef SUBLANG_ITALIAN
|
|
|
526 { SUBLANG_ITALIAN, "ITALIAN" },
|
|
|
527 #endif
|
|
|
528 #ifdef SUBLANG_ITALIAN_SWISS
|
|
|
529 { SUBLANG_ITALIAN_SWISS, "ITALIAN_SWISS" },
|
|
|
530 #endif
|
|
|
531 { LANG_KASHMIRI, 0 },
|
|
|
532 #ifdef SUBLANG_KASHMIRI_INDIA
|
|
|
533 { SUBLANG_KASHMIRI_INDIA, "KASHMIRI_INDIA" },
|
|
|
534 #endif
|
|
|
535 { LANG_KOREAN, 0 },
|
|
|
536 #ifdef SUBLANG_KOREAN
|
|
|
537 { SUBLANG_KOREAN, "KOREAN" },
|
|
|
538 #endif
|
|
|
539 #ifdef SUBLANG_KOREAN_JOHAB
|
|
|
540 /* NOTE: Omitted in more recent versions of VC++ (e.g. v6.0) */
|
|
|
541 { SUBLANG_KOREAN_JOHAB, "KOREAN_JOHAB" },
|
|
|
542 #endif
|
|
|
543 { LANG_LITHUANIAN, 0 },
|
|
|
544 #ifdef SUBLANG_LITHUANIAN
|
|
|
545 { SUBLANG_LITHUANIAN, "LITHUANIAN" },
|
|
|
546 #endif
|
|
|
547 #ifdef SUBLANG_LITHUANIAN_CLASSIC
|
|
|
548 { SUBLANG_LITHUANIAN_CLASSIC, "LITHUANIAN_CLASSIC" },
|
|
|
549 #endif
|
|
|
550 { LANG_MALAY, 0 },
|
|
|
551 #ifdef SUBLANG_MALAY_BRUNEI_DARUSSALAM
|
|
|
552 { SUBLANG_MALAY_BRUNEI_DARUSSALAM, "MALAY_BRUNEI_DARUSSALAM" },
|
|
|
553 #endif
|
|
|
554 #ifdef SUBLANG_MALAY_MALAYSIA
|
|
|
555 { SUBLANG_MALAY_MALAYSIA, "MALAY_MALAYSIA" },
|
|
|
556 #endif
|
|
|
557 { LANG_NEPALI, 0 },
|
|
|
558 #ifdef SUBLANG_NEPALI_INDIA
|
|
|
559 { SUBLANG_NEPALI_INDIA, "NEPALI_INDIA" },
|
|
|
560 #endif
|
|
|
561 { LANG_NEUTRAL, 0 },
|
|
|
562 #ifdef SUBLANG_NEUTRAL
|
|
|
563 { SUBLANG_NEUTRAL, "NEUTRAL" },
|
|
|
564 #endif
|
|
|
565 { LANG_NORWEGIAN, 0 },
|
|
|
566 #ifdef SUBLANG_NORWEGIAN_BOKMAL
|
|
|
567 { SUBLANG_NORWEGIAN_BOKMAL, "NORWEGIAN_BOKMAL" },
|
|
|
568 #endif
|
|
|
569 #ifdef SUBLANG_NORWEGIAN_NYNORSK
|
|
|
570 { SUBLANG_NORWEGIAN_NYNORSK, "NORWEGIAN_NYNORSK" },
|
|
|
571 #endif
|
|
|
572 { LANG_PORTUGUESE, 0 },
|
|
|
573 #ifdef SUBLANG_PORTUGUESE
|
|
|
574 { SUBLANG_PORTUGUESE, "PORTUGUESE" },
|
|
|
575 #endif
|
|
|
576 #ifdef SUBLANG_PORTUGUESE_BRAZILIAN
|
|
|
577 { SUBLANG_PORTUGUESE_BRAZILIAN, "PORTUGUESE_BRAZILIAN" },
|
|
|
578 #endif
|
|
|
579 { LANG_SERBIAN, 0 },
|
|
|
580 #ifdef SUBLANG_SERBIAN_CYRILLIC
|
|
|
581 { SUBLANG_SERBIAN_CYRILLIC, "SERBIAN_CYRILLIC" },
|
|
|
582 #endif
|
|
|
583 #ifdef SUBLANG_SERBIAN_LATIN
|
|
|
584 { SUBLANG_SERBIAN_LATIN, "SERBIAN_LATIN" },
|
|
|
585 #endif
|
|
|
586 { LANG_SPANISH, 0 },
|
|
|
587 #ifdef SUBLANG_SPANISH
|
|
|
588 { SUBLANG_SPANISH, "SPANISH" },
|
|
|
589 #endif
|
|
|
590 #ifdef SUBLANG_SPANISH_ARGENTINA
|
|
|
591 { SUBLANG_SPANISH_ARGENTINA, "SPANISH_ARGENTINA" },
|
|
|
592 #endif
|
|
|
593 #ifdef SUBLANG_SPANISH_BOLIVIA
|
|
|
594 { SUBLANG_SPANISH_BOLIVIA, "SPANISH_BOLIVIA" },
|
|
|
595 #endif
|
|
|
596 #ifdef SUBLANG_SPANISH_CHILE
|
|
|
597 { SUBLANG_SPANISH_CHILE, "SPANISH_CHILE" },
|
|
|
598 #endif
|
|
|
599 #ifdef SUBLANG_SPANISH_COLOMBIA
|
|
|
600 { SUBLANG_SPANISH_COLOMBIA, "SPANISH_COLOMBIA" },
|
|
|
601 #endif
|
|
|
602 #ifdef SUBLANG_SPANISH_COSTA_RICA
|
|
|
603 { SUBLANG_SPANISH_COSTA_RICA, "SPANISH_COSTA_RICA" },
|
|
|
604 #endif
|
|
|
605 #ifdef SUBLANG_SPANISH_DOMINICAN_REPUBLIC
|
|
|
606 { SUBLANG_SPANISH_DOMINICAN_REPUBLIC, "SPANISH_DOMINICAN_REPUBLIC" },
|
|
|
607 #endif
|
|
|
608 #ifdef SUBLANG_SPANISH_ECUADOR
|
|
|
609 { SUBLANG_SPANISH_ECUADOR, "SPANISH_ECUADOR" },
|
|
|
610 #endif
|
|
|
611 #ifdef SUBLANG_SPANISH_EL_SALVADOR
|
|
|
612 { SUBLANG_SPANISH_EL_SALVADOR, "SPANISH_EL_SALVADOR" },
|
|
|
613 #endif
|
|
|
614 #ifdef SUBLANG_SPANISH_GUATEMALA
|
|
|
615 { SUBLANG_SPANISH_GUATEMALA, "SPANISH_GUATEMALA" },
|
|
|
616 #endif
|
|
|
617 #ifdef SUBLANG_SPANISH_HONDURAS
|
|
|
618 { SUBLANG_SPANISH_HONDURAS, "SPANISH_HONDURAS" },
|
|
|
619 #endif
|
|
|
620 #ifdef SUBLANG_SPANISH_MEXICAN
|
|
|
621 { SUBLANG_SPANISH_MEXICAN, "SPANISH_MEXICAN" },
|
|
|
622 #endif
|
|
|
623 #ifdef SUBLANG_SPANISH_MODERN
|
|
|
624 { SUBLANG_SPANISH_MODERN, "SPANISH_MODERN" },
|
|
|
625 #endif
|
|
|
626 #ifdef SUBLANG_SPANISH_NICARAGUA
|
|
|
627 { SUBLANG_SPANISH_NICARAGUA, "SPANISH_NICARAGUA" },
|
|
|
628 #endif
|
|
|
629 #ifdef SUBLANG_SPANISH_PANAMA
|
|
|
630 { SUBLANG_SPANISH_PANAMA, "SPANISH_PANAMA" },
|
|
|
631 #endif
|
|
|
632 #ifdef SUBLANG_SPANISH_PARAGUAY
|
|
|
633 { SUBLANG_SPANISH_PARAGUAY, "SPANISH_PARAGUAY" },
|
|
|
634 #endif
|
|
|
635 #ifdef SUBLANG_SPANISH_PERU
|
|
|
636 { SUBLANG_SPANISH_PERU, "SPANISH_PERU" },
|
|
|
637 #endif
|
|
|
638 #ifdef SUBLANG_SPANISH_PUERTO_RICO
|
|
|
639 { SUBLANG_SPANISH_PUERTO_RICO, "SPANISH_PUERTO_RICO" },
|
|
|
640 #endif
|
|
|
641 #ifdef SUBLANG_SPANISH_URUGUAY
|
|
|
642 { SUBLANG_SPANISH_URUGUAY, "SPANISH_URUGUAY" },
|
|
|
643 #endif
|
|
|
644 #ifdef SUBLANG_SPANISH_VENEZUELA
|
|
|
645 { SUBLANG_SPANISH_VENEZUELA, "SPANISH_VENEZUELA" },
|
|
|
646 #endif
|
|
|
647 { LANG_SWEDISH, 0 },
|
|
|
648 #ifdef SUBLANG_SWEDISH
|
|
|
649 { SUBLANG_SWEDISH, "SWEDISH" },
|
|
|
650 #endif
|
|
|
651 #ifdef SUBLANG_SWEDISH_FINLAND
|
|
|
652 { SUBLANG_SWEDISH_FINLAND, "SWEDISH_FINLAND" },
|
|
|
653 #endif
|
|
|
654 { LANG_URDU, 0 },
|
|
|
655 #ifdef SUBLANG_URDU_INDIA
|
|
|
656 { SUBLANG_URDU_INDIA, "URDU_INDIA" },
|
|
|
657 #endif
|
|
|
658 #ifdef SUBLANG_URDU_PAKISTAN
|
|
|
659 { SUBLANG_URDU_PAKISTAN, "URDU_PAKISTAN" },
|
|
|
660 #endif
|
|
|
661 { LANG_UZBEK, 0 },
|
|
|
662 #ifdef SUBLANG_UZBEK_CYRILLIC
|
|
|
663 { SUBLANG_UZBEK_CYRILLIC, "UZBEK_CYRILLIC" },
|
|
|
664 #endif
|
|
|
665 #ifdef SUBLANG_UZBEK_LATIN
|
|
|
666 { SUBLANG_UZBEK_LATIN, "UZBEK_LATIN" },
|
|
|
667 #endif
|
|
|
668 };
|
|
|
669
|
|
|
670 static int
|
|
|
671 lang_to_langcode (Lisp_Object lang, struct lang_to_string *table,
|
|
|
672 int table_size)
|
|
|
673 {
|
|
|
674 int i;
|
|
|
675
|
|
|
676 for (i = 0; i < table_size; i++)
|
|
|
677 if (!strcmp ((char *) XSTRING_DATA (lang), table[i].string))
|
|
|
678 return table[i].code;
|
|
|
679 return -1;
|
|
|
680 }
|
|
|
681
|
|
|
682 static int
|
|
|
683 sublang_to_langcode (Lisp_Object lang, struct lang_to_string *table,
|
|
|
684 int table_size)
|
|
|
685 {
|
|
|
686 int i;
|
|
|
687
|
|
|
688 for (i = 0; i < table_size; i++)
|
|
|
689 if (table[i].string &&
|
|
|
690 !strcmp ((char *) XSTRING_DATA (lang), table[i].string))
|
|
|
691 return table[i].code;
|
|
|
692
|
|
|
693 if (!strcmp ((char *) XSTRING_DATA (lang), "NEUTRAL"))
|
|
|
694 return SUBLANG_NEUTRAL;
|
|
|
695 if (!strcmp ((char *) XSTRING_DATA (lang), "DEFAULT"))
|
|
|
696 return SUBLANG_DEFAULT;
|
|
|
697 if (!strcmp ((char *) XSTRING_DATA (lang), "SYS_DEFAULT"))
|
|
|
698 return SUBLANG_SYS_DEFAULT;
|
|
|
699
|
|
|
700 return -1;
|
|
|
701 }
|
|
|
702
|
|
|
703 static Lisp_Object
|
|
|
704 langcode_to_lang (int code, struct lang_to_string *table,
|
|
|
705 int table_size)
|
|
|
706 {
|
|
|
707 int i;
|
|
|
708
|
|
|
709 for (i = 0; i < table_size; i++)
|
|
|
710 if (code == table[i].code)
|
|
|
711 return build_string (table[i].string);
|
|
|
712 return Qnil;
|
|
|
713 }
|
|
|
714
|
|
|
715 static Lisp_Object
|
|
|
716 sublangcode_to_lang (int lang, int sublang, struct lang_to_string *table,
|
|
|
717 int table_size)
|
|
|
718 {
|
|
|
719 int i;
|
|
|
720 int found_lang = 0;
|
|
|
721
|
|
|
722 for (i = 0; i < table_size; i++)
|
|
|
723 {
|
|
|
724 if (found_lang)
|
|
|
725 {
|
|
|
726 if (!table[i].string)
|
|
|
727 break;
|
|
|
728 if (sublang == table[i].code)
|
|
|
729 return build_string (table[i].string);
|
|
|
730 }
|
|
|
731 else if (!table[i].string && lang == table[i].code)
|
|
|
732 found_lang = 1;
|
|
|
733 }
|
|
|
734
|
|
|
735 switch (sublang)
|
|
|
736 {
|
|
|
737 case SUBLANG_NEUTRAL:
|
|
|
738 return build_string ("NEUTRAL");
|
|
|
739 case SUBLANG_DEFAULT:
|
|
|
740 return build_string ("DEFAULT");
|
|
|
741 case SUBLANG_SYS_DEFAULT:
|
|
|
742 return build_string ("SYS_DEFAULT");
|
|
|
743 }
|
|
|
744
|
|
|
745 return Qnil;
|
|
|
746 }
|
|
|
747
|
|
|
748 static LCID
|
|
|
749 locale_to_lcid (Lisp_Object locale)
|
|
|
750 {
|
|
|
751 int langcode, sublangcode;
|
|
|
752 Lisp_Object lang, sublang;
|
|
|
753
|
|
|
754 if (STRINGP (locale))
|
|
|
755 {
|
|
|
756 lang = locale;
|
|
|
757 sublang = Qnil;
|
|
|
758 }
|
|
|
759 else if (CONSP (locale))
|
|
|
760 {
|
|
|
761 CHECK_STRING (XCAR (locale));
|
|
|
762 CHECK_STRING (XCDR (locale));
|
|
|
763 lang = XCAR (locale);
|
|
|
764 sublang = XCDR (locale);
|
|
|
765 }
|
|
|
766 else
|
|
|
767 invalid_argument ("Locale must be LANG or (LANG . SUBLANG)", locale);
|
|
|
768
|
|
|
769 langcode = lang_to_langcode (lang, lang_to_string_table,
|
|
|
770 countof (lang_to_string_table));
|
|
|
771
|
|
|
772 if (langcode < 0)
|
|
|
773 invalid_constant ("Unrecognized language", lang);
|
|
|
774
|
|
|
775 if (!NILP (sublang))
|
|
|
776 {
|
|
|
777 sublangcode = sublang_to_langcode (sublang, sublang_to_string_table,
|
|
|
778 countof (sublang_to_string_table));
|
|
|
779 if (sublangcode < 0)
|
|
|
780 invalid_constant ("Unrecognized sublanguage", sublang);
|
|
|
781 }
|
|
|
782 else
|
|
|
783 sublangcode = SUBLANG_DEFAULT;
|
|
|
784
|
|
|
785 return MAKELCID (MAKELANGID (langcode, sublangcode),
|
|
|
786 SORT_DEFAULT);
|
|
|
787 }
|
|
|
788
|
|
|
789 static Lisp_Object
|
|
|
790 lcid_to_locale (LCID lcid)
|
|
|
791 {
|
|
|
792 int langid = LANGIDFROMLCID (lcid);
|
|
|
793 int langcode = PRIMARYLANGID (langid);
|
|
|
794 int sublangcode = SUBLANGID (langid);
|
|
|
795
|
|
|
796 return Fcons (langcode_to_lang (langcode, lang_to_string_table,
|
|
|
797 countof (lang_to_string_table)),
|
|
|
798 sublangcode_to_lang (langcode, sublangcode,
|
|
|
799 sublang_to_string_table,
|
|
|
800 countof (sublang_to_string_table)));
|
|
|
801 }
|
|
|
802
|
|
|
803 int
|
|
|
804 mswindows_locale_to_code_page (LCID lcid)
|
|
|
805 {
|
|
|
806 char codepagestr[10];
|
|
|
807
|
|
|
808 GetLocaleInfoA (lcid, LOCALE_IDEFAULTANSICODEPAGE, codepagestr, 10);
|
|
|
809 return atoi (codepagestr);
|
|
|
810 }
|
|
|
811
|
|
|
812 int
|
|
|
813 mswindows_locale_to_oem_code_page (LCID lcid)
|
|
|
814 {
|
|
|
815 char codepagestr[10];
|
|
|
816
|
|
|
817 GetLocaleInfoA (lcid, LOCALE_IDEFAULTCODEPAGE, codepagestr, 10);
|
|
|
818 return atoi (codepagestr);
|
|
|
819 }
|
|
|
820
|
|
|
821 static void
|
|
|
822 set_current_lcid (LCID lcid)
|
|
|
823 {
|
|
|
824 int cp;
|
|
|
825
|
|
|
826 /* This will fail under Win9x, so we remember our own locale rather than
|
|
|
827 consulting GetThreadLocale. */
|
|
|
828 SetThreadLocale (lcid);
|
|
|
829 current_locale = lcid;
|
|
|
830 cp = mswindows_locale_to_code_page (lcid);
|
|
|
831 #ifndef NO_EXT_MULTIBYTE_FEATURES
|
|
|
832 _setmbcp (cp);
|
|
|
833 #endif
|
|
|
834 }
|
|
|
835
|
|
|
836 DEFUN ("mswindows-set-current-locale", Fmswindows_set_current_locale,
|
|
|
837 1, 1, 0, /*
|
|
|
838 Set the current MS Windows locale.
|
|
|
839
|
|
|
840 LOCALE should a language string, or a cons (LANG . SUBLANG).
|
|
|
841 If SUBLANG is omitted, "SUBLANG_DEFAULT" is used.
|
|
|
842
|
|
|
843 Recognized language names are
|
|
|
844 (some may not be recognized if the compiler is older than VC++ 6.0)
|
|
|
845
|
|
|
846 "AFRIKAANS"
|
|
|
847 "ALBANIAN"
|
|
|
848 "ARABIC"
|
|
|
849 "ARMENIAN"
|
|
|
850 "ASSAMESE"
|
|
|
851 "AZERI"
|
|
|
852 "BASQUE"
|
|
|
853 "BELARUSIAN"
|
|
|
854 "BENGALI"
|
|
|
855 "BULGARIAN"
|
|
|
856 "CATALAN"
|
|
|
857 "CHINESE"
|
|
|
858 "CROATIAN"
|
|
|
859 "CZECH"
|
|
|
860 "DANISH"
|
|
|
861 "DUTCH"
|
|
|
862 "ENGLISH"
|
|
|
863 "ESTONIAN"
|
|
|
864 "FAEROESE"
|
|
|
865 "FARSI"
|
|
|
866 "FINNISH"
|
|
|
867 "FRENCH"
|
|
|
868 "GEORGIAN"
|
|
|
869 "GERMAN"
|
|
|
870 "GREEK"
|
|
|
871 "GUJARATI"
|
|
|
872 "HEBREW"
|
|
|
873 "HINDI"
|
|
|
874 "HUNGARIAN"
|
|
|
875 "ICELANDIC"
|
|
|
876 "INDONESIAN"
|
|
|
877 "ITALIAN"
|
|
|
878 "JAPANESE"
|
|
|
879 "KANNADA"
|
|
|
880 "KASHMIRI"
|
|
|
881 "KAZAK"
|
|
|
882 "KONKANI"
|
|
|
883 "KOREAN"
|
|
|
884 "LATVIAN"
|
|
|
885 "LITHUANIAN"
|
|
|
886 "MACEDONIAN"
|
|
|
887 "MALAY"
|
|
|
888 "MALAYALAM"
|
|
|
889 "MANIPURI"
|
|
|
890 "MARATHI"
|
|
|
891 "NEPALI"
|
|
|
892 "NEUTRAL"
|
|
|
893 "NORWEGIAN"
|
|
|
894 "ORIYA"
|
|
|
895 "POLISH"
|
|
|
896 "PORTUGUESE"
|
|
|
897 "PUNJABI"
|
|
|
898 "ROMANIAN"
|
|
|
899 "RUSSIAN"
|
|
|
900 "SANSKRIT"
|
|
|
901 "SERBIAN"
|
|
|
902 "SINDHI"
|
|
|
903 "SLOVAK"
|
|
|
904 "SLOVENIAN"
|
|
|
905 "SPANISH"
|
|
|
906 "SWAHILI"
|
|
|
907 "SWEDISH"
|
|
|
908 "TAMIL"
|
|
|
909 "TATAR"
|
|
|
910 "TELUGU"
|
|
|
911 "THAI"
|
|
|
912 "TURKISH"
|
|
|
913 "UKRAINIAN"
|
|
|
914 "URDU"
|
|
|
915 "UZBEK"
|
|
|
916 "VIETNAMESE"
|
|
|
917
|
|
|
918 Recognized sub-language names are
|
|
|
919 (some may not be recognized if the compiler is older than VC++ 6.0)
|
|
|
920
|
|
|
921 "ARABIC_ALGERIA"
|
|
|
922 "ARABIC_BAHRAIN"
|
|
|
923 "ARABIC_EGYPT"
|
|
|
924 "ARABIC_IRAQ"
|
|
|
925 "ARABIC_JORDAN"
|
|
|
926 "ARABIC_KUWAIT"
|
|
|
927 "ARABIC_LEBANON"
|
|
|
928 "ARABIC_LIBYA"
|
|
|
929 "ARABIC_MOROCCO"
|
|
|
930 "ARABIC_OMAN"
|
|
|
931 "ARABIC_QATAR"
|
|
|
932 "ARABIC_SAUDI_ARABIA"
|
|
|
933 "ARABIC_SYRIA"
|
|
|
934 "ARABIC_TUNISIA"
|
|
|
935 "ARABIC_UAE"
|
|
|
936 "ARABIC_YEMEN"
|
|
|
937 "AZERI_CYRILLIC"
|
|
|
938 "AZERI_LATIN"
|
|
|
939 "CHINESE_HONGKONG"
|
|
|
940 "CHINESE_MACAU"
|
|
|
941 "CHINESE_SIMPLIFIED"
|
|
|
942 "CHINESE_SINGAPORE"
|
|
|
943 "CHINESE_TRADITIONAL"
|
|
|
944 "DEFAULT"
|
|
|
945 "DUTCH"
|
|
|
946 "DUTCH_BELGIAN"
|
|
|
947 "ENGLISH_AUS"
|
|
|
948 "ENGLISH_BELIZE"
|
|
|
949 "ENGLISH_CAN"
|
|
|
950 "ENGLISH_CARIBBEAN"
|
|
|
951 "ENGLISH_EIRE"
|
|
|
952 "ENGLISH_JAMAICA"
|
|
|
953 "ENGLISH_NZ"
|
|
|
954 "ENGLISH_PHILIPPINES"
|
|
|
955 "ENGLISH_SOUTH_AFRICA"
|
|
|
956 "ENGLISH_TRINIDAD"
|
|
|
957 "ENGLISH_UK"
|
|
|
958 "ENGLISH_US"
|
|
|
959 "ENGLISH_ZIMBABWE"
|
|
|
960 "FRENCH"
|
|
|
961 "FRENCH_BELGIAN"
|
|
|
962 "FRENCH_CANADIAN"
|
|
|
963 "FRENCH_LUXEMBOURG"
|
|
|
964 "FRENCH_MONACO"
|
|
|
965 "FRENCH_SWISS"
|
|
|
966 "GERMAN"
|
|
|
967 "GERMAN_AUSTRIAN"
|
|
|
968 "GERMAN_LIECHTENSTEIN"
|
|
|
969 "GERMAN_LUXEMBOURG"
|
|
|
970 "GERMAN_SWISS"
|
|
|
971 "ITALIAN"
|
|
|
972 "ITALIAN_SWISS"
|
|
|
973 "KASHMIRI_INDIA"
|
|
|
974 "KOREAN"
|
|
|
975 "KOREAN_JOHAB" (NOTE: omitted in Visual C++ 6.0 and later)
|
|
|
976 "LITHUANIAN"
|
|
|
977 "LITHUANIAN_CLASSIC"
|
|
|
978 "MALAY_BRUNEI_DARUSSALAM"
|
|
|
979 "MALAY_MALAYSIA"
|
|
|
980 "NEPALI_INDIA"
|
|
|
981 "NEUTRAL"
|
|
|
982 "NORWEGIAN_BOKMAL"
|
|
|
983 "NORWEGIAN_NYNORSK"
|
|
|
984 "PORTUGUESE"
|
|
|
985 "PORTUGUESE_BRAZILIAN"
|
|
|
986 "SERBIAN_CYRILLIC"
|
|
|
987 "SERBIAN_LATIN"
|
|
|
988 "SPANISH"
|
|
|
989 "SPANISH_ARGENTINA"
|
|
|
990 "SPANISH_BOLIVIA"
|
|
|
991 "SPANISH_CHILE"
|
|
|
992 "SPANISH_COLOMBIA"
|
|
|
993 "SPANISH_COSTA_RICA"
|
|
|
994 "SPANISH_DOMINICAN_REPUBLIC"
|
|
|
995 "SPANISH_ECUADOR"
|
|
|
996 "SPANISH_EL_SALVADOR"
|
|
|
997 "SPANISH_GUATEMALA"
|
|
|
998 "SPANISH_HONDURAS"
|
|
|
999 "SPANISH_MEXICAN"
|
|
|
1000 "SPANISH_MODERN"
|
|
|
1001 "SPANISH_NICARAGUA"
|
|
|
1002 "SPANISH_PANAMA"
|
|
|
1003 "SPANISH_PARAGUAY"
|
|
|
1004 "SPANISH_PERU"
|
|
|
1005 "SPANISH_PUERTO_RICO"
|
|
|
1006 "SPANISH_URUGUAY"
|
|
|
1007 "SPANISH_VENEZUELA"
|
|
|
1008 "SWEDISH"
|
|
|
1009 "SWEDISH_FINLAND"
|
|
|
1010 "SYS_DEFAULT"
|
|
|
1011 "URDU_INDIA"
|
|
|
1012 "URDU_PAKISTAN"
|
|
|
1013 "UZBEK_CYRILLIC"
|
|
|
1014 "UZBEK_LATIN"
|
|
|
1015 */
|
|
|
1016 (locale))
|
|
|
1017 {
|
|
|
1018 LCID lcid = locale_to_lcid (locale);
|
|
|
1019
|
|
|
1020 set_current_lcid (lcid);
|
|
|
1021 return Qnil;
|
|
|
1022 }
|
|
|
1023
|
|
|
1024 #ifdef DEBUG_XEMACS
|
|
|
1025
|
|
|
1026 static int getacp (void);
|
|
|
1027 int
|
|
|
1028 getacp (void)
|
|
|
1029 {
|
|
|
1030 return GetACP ();
|
|
|
1031 }
|
|
|
1032
|
|
|
1033 #endif /* DEBUG_XEMACS */
|
|
|
1034
|
|
|
1035 LCID
|
|
|
1036 mswindows_current_locale (void)
|
|
|
1037 {
|
|
|
1038 /* Even if SetThreadLocale() failed, return the right locale anyway */
|
|
|
1039 return current_locale;
|
|
|
1040 }
|
|
|
1041
|
|
|
1042 DEFUN ("mswindows-current-locale", Fmswindows_current_locale,
|
|
|
1043 0, 0, 0, /*
|
|
|
1044 Return the current MS Windows locale.
|
|
|
1045
|
|
|
1046 The return value will be a cons (LANG . SUBLANG). See
|
|
|
1047 `mswindows-set-current-locale' for more info.
|
|
|
1048 */
|
|
|
1049 ())
|
|
|
1050 {
|
|
|
1051 return lcid_to_locale (mswindows_current_locale ());
|
|
|
1052 }
|
|
|
1053
|
|
|
1054 DEFUN ("mswindows-user-default-locale", Fmswindows_user_default_locale,
|
|
|
1055 0, 0, 0, /*
|
|
|
1056 Return the MS Windows user-default locale.
|
|
|
1057 */
|
|
|
1058 ())
|
|
|
1059 {
|
|
|
1060 return lcid_to_locale (GetUserDefaultLCID ());
|
|
|
1061 }
|
|
|
1062
|
|
|
1063 DEFUN ("mswindows-system-default-locale", Fmswindows_system_default_locale,
|
|
|
1064 0, 0, 0, /*
|
|
|
1065 Return the MS Windows system-default locale.
|
|
|
1066 */
|
|
|
1067 ())
|
|
|
1068 {
|
|
|
1069 return lcid_to_locale (GetSystemDefaultLCID ());
|
|
|
1070 }
|
|
|
1071
|
|
|
1072 DEFUN ("mswindows-locale-code-page", Fmswindows_locale_code_page,
|
|
|
1073 0, 1, 0, /*
|
|
|
1074 Return the (ANSI) code page of the specified MS Windows locale.
|
|
|
1075 If LOCALE is nil or omitted, the current locale is used.
|
|
|
1076 */
|
|
|
1077 (locale))
|
|
|
1078 {
|
|
|
1079 LCID lcid = NILP (locale) ? current_locale : locale_to_lcid (locale);
|
|
|
1080 return make_int (mswindows_locale_to_code_page (lcid));
|
|
|
1081 }
|
|
|
1082
|
|
|
1083 DEFUN ("mswindows-locale-oem-code-page", Fmswindows_locale_oem_code_page,
|
|
|
1084 0, 1, 0, /*
|
|
|
1085 Return the OEM code page of the specified MS Windows locale.
|
|
|
1086 If LOCALE is nil or omitted, the current locale is used.
|
|
|
1087 */
|
|
|
1088 (locale))
|
|
|
1089 {
|
|
|
1090 LCID lcid = NILP (locale) ? current_locale : locale_to_lcid (locale);
|
|
|
1091 return make_int (mswindows_locale_to_oem_code_page (lcid));
|
|
|
1092 }
|
|
|
1093
|
|
|
1094 static DWORD
|
|
|
1095 int_from_hex (Char_ASCII *s)
|
|
|
1096 {
|
|
|
1097 DWORD val = 0;
|
|
|
1098 static Char_ASCII hex[] = "0123456789abcdefABCDEF";
|
|
|
1099 Char_ASCII *p;
|
|
|
1100
|
|
|
1101 while (*s && (p = strchr (hex, *s)) != NULL)
|
|
|
1102 {
|
|
|
1103 int digit = p - hex;
|
|
|
1104 if (digit > 15)
|
|
|
1105 digit -= 6;
|
|
|
1106 val = val * 16 + digit;
|
|
|
1107 s++;
|
|
|
1108 }
|
|
|
1109 return val;
|
|
|
1110 }
|
|
|
1111
|
|
|
1112 /* We need to build a global list, since the EnumSystemLocale callback
|
|
|
1113 function isn't given a context pointer. */
|
|
|
1114 static Lisp_Object Vmswindows_valid_locales;
|
|
|
1115
|
|
|
1116 static BOOL CALLBACK
|
|
|
1117 enum_locale_fn (Char_ASCII *localeNum)
|
|
|
1118 {
|
|
|
1119 DWORD id = int_from_hex (localeNum);
|
|
|
1120 Vmswindows_valid_locales =
|
|
|
1121 Fcons (lcid_to_locale ((LCID) id), Vmswindows_valid_locales);
|
|
|
1122 return TRUE;
|
|
|
1123 }
|
|
|
1124
|
|
|
1125 DEFUN ("mswindows-supported-locales", Fmswindows_supported_locales,
|
|
|
1126 0, 0, 0, /*
|
|
|
1127 Return a list of the supported MS Windows locales on this system.
|
|
|
1128 */
|
|
|
1129 ())
|
|
|
1130 {
|
|
|
1131 Vmswindows_valid_locales = Qnil;
|
|
|
1132
|
|
|
1133 /* Use the ANSI version because the return value is just a hex number. */
|
|
|
1134 EnumSystemLocalesA (enum_locale_fn, LCID_SUPPORTED);
|
|
|
1135
|
|
|
1136 Vmswindows_valid_locales = Fnreverse (Vmswindows_valid_locales);
|
|
|
1137 return Vmswindows_valid_locales;
|
|
|
1138 }
|
|
|
1139
|
|
|
1140 /************************************************************************/
|
|
|
1141 /* Mule functions */
|
|
|
1142 /************************************************************************/
|
|
|
1143
|
|
|
1144 DEFUN ("mswindows-charset-code-page",
|
|
|
1145 Fmswindows_charset_code_page, 1, 1, 0, /*
|
|
|
1146 Return the code page for the CHARSET.
|
|
|
1147
|
|
|
1148 #### This function may be changed in the near future.
|
|
|
1149
|
|
|
1150 Currently defined Windows code pages include (along with their status
|
|
|
1151 as Ansi, OEM, Mac, EBCDIC, or some combination):
|
|
|
1152
|
|
|
1153 EBCDIC 037 EBCDIC
|
|
|
1154 OEM 437 MS-DOS United States
|
|
|
1155 EBCDIC 500 EBCDIC "500V1"
|
|
|
1156 OEM 708 Arabic (ASMO 708)
|
|
|
1157 OEM 709 Arabic (ASMO 449+, BCON V4)
|
|
|
1158 OEM 710 Arabic (Transparent Arabic)
|
|
|
1159 OEM 720 Arabic (Transparent ASMO)
|
|
|
1160 OEM 737 Greek (formerly 437G)
|
|
|
1161 OEM 775 Baltic
|
|
|
1162 OEM 850 MS-DOS Multilingual (Latin I)
|
|
|
1163 OEM 852 MS-DOS Slavic (Latin II)
|
|
|
1164 OEM 855 IBM Cyrillic (primarily Russian)
|
|
|
1165 OEM 857 IBM Turkish
|
|
|
1166 OEM 860 MS-DOS Portuguese
|
|
|
1167 OEM 861 MS-DOS Icelandic
|
|
|
1168 OEM 862 Hebrew
|
|
|
1169 OEM 863 MS-DOS Canadian-French
|
|
|
1170 OEM 864 Arabic
|
|
|
1171 OEM 865 MS-DOS Nordic
|
|
|
1172 OEM 866 MS-DOS Russian
|
|
|
1173 OEM 869 IBM Modern Greek
|
|
|
1174 Ansi/OEM 874 Thai
|
|
|
1175 EBCDIC 875 EBCDIC
|
|
|
1176 Ansi/OEM 932 Japanese
|
|
|
1177 Ansi/OEM 936 Chinese (PRC, Singapore)
|
|
|
1178 Ansi/OEM 949 Korean
|
|
|
1179 Ansi/OEM 950 Chinese (Taiwan; Hong Kong SAR, PRC)
|
|
|
1180 EBCDIC 1026 EBCDIC
|
|
|
1181 ANSI 1200 Unicode (BMP of ISO 10646)
|
|
|
1182 ANSI 1250 Windows 3.1 Eastern European
|
|
|
1183 ANSI 1251 Windows 3.1 Cyrillic
|
|
|
1184 ANSI 1252 Windows 3.1 US (ANSI)
|
|
|
1185 ANSI 1253 Windows 3.1 Greek
|
|
|
1186 ANSI 1254 Windows 3.1 Turkish
|
|
|
1187 ANSI 1255 Hebrew
|
|
|
1188 ANSI 1256 Arabic
|
|
|
1189 ANSI 1257 Baltic
|
|
|
1190 ANSI 1258 VietNam
|
|
|
1191 Ansi/OEM 1361 Korean (Johab)
|
|
|
1192 Mac 10000 Macintosh Roman
|
|
|
1193 Mac 10001 Macintosh Japanese
|
|
|
1194 Mac 10006 Macintosh Greek I
|
|
|
1195 Mac 10007 Macintosh Cyrillic
|
|
|
1196 Mac 10029 Macintosh Latin 2
|
|
|
1197 Mac 10079 Macintosh Icelandic
|
|
|
1198 Mac 10081 Macintosh Turkish
|
|
|
1199
|
|
|
1200 A code page is a set of characters, along with an enumeration of these
|
|
|
1201 characters and an encoding of them in a byte stream. Thus, in XEmacs
|
|
|
1202 parlance it defines both a "charset" and a "coding system" for this
|
|
|
1203 charset. Traditional encodings are either simple one-byte encodings, or
|
|
|
1204 combination one-byte/two-byte encodings (aka MBCS encodings, where MBCS
|
|
|
1205 stands for "Multibyte Character Set") with the following properties:
|
|
|
1206
|
|
|
1207 -- all characters are encoded as a one-byte or two-byte sequence
|
|
|
1208 -- the encoding is stateless (non-modal)
|
|
|
1209 -- the lower 128 bytes are compatible with ASCII
|
|
|
1210 -- in the higher bytes, the value of the first byte ("lead byte")
|
|
|
1211 determines whether a second byte follows
|
|
|
1212 -- the values used for second bytes may overlap those used for first bytes,
|
|
|
1213 and (in some encodings) include values in the low half; thus, moving
|
|
|
1214 backwards is hard, and pure-ASCII algorithms (e.g. finding the next slash)
|
|
|
1215 will fail unless rewritten to be MBCS-aware (neither of these problems
|
|
|
1216 exist in UTF-8 or in the XEmacs internal string encoding)
|
|
|
1217
|
|
|
1218 Recent code pages, however, do not necessarily follow these properties --
|
|
|
1219 code pages have been expanded to include arbitrary encodings, such as UTF-8
|
|
|
1220 \(may have more than two bytes per character) and ISO-2022-JP (complex modal
|
|
|
1221 encoding).
|
|
|
1222
|
|
|
1223 Every locale has four associated code pages: ANSI (an international
|
|
|
1224 standard or some Microsoft-created approximation; the native code page
|
|
|
1225 under Windows), OEM (a DOS encoding, still used in the FAT file system),
|
|
|
1226 Mac (an encoding used on the Macintosh) and EBCDIC (a non-ASCII-compatible
|
|
|
1227 encoding used on IBM mainframes, originally based on the BCD or
|
|
|
1228 "binary-coded decimal" encoding of numbers). All code pages associated
|
|
|
1229 with a locale follow (as far as I know) the properties listed above for
|
|
|
1230 traditional code pages.
|
|
|
1231 */
|
|
|
1232 (charset))
|
|
|
1233 {
|
|
|
1234 charset = Fget_charset (charset);
|
|
|
1235 return Fgethash (charset, Vmswindows_charset_code_page_table, Qnil);
|
|
|
1236 }
|
|
|
1237
|
|
|
1238 DEFUN ("mswindows-set-charset-code-page",
|
|
|
1239 Fmswindows_set_charset_code_page, 2, 2, 0, /*
|
|
|
1240 Set the CODE-PAGE for the CHARSET.
|
|
|
1241
|
|
|
1242 #### This function may be changed once full Unicode support is present.
|
|
|
1243 */
|
|
|
1244 (charset, code_page))
|
|
|
1245 {
|
|
|
1246 charset = Fget_charset (charset);
|
|
|
1247 CHECK_INT (code_page);
|
|
|
1248 Fputhash (charset, code_page, Vmswindows_charset_code_page_table);
|
|
|
1249 return Qnil;
|
|
|
1250 }
|
|
|
1251
|
|
|
1252 Lisp_Object
|
|
|
1253 mswindows_get_code_page_charset (int code_page)
|
|
|
1254 {
|
|
|
1255 Lisp_Object charset_tail;
|
|
|
1256 Lisp_Object charset = Qunbound;
|
|
|
1257
|
|
|
1258 LIST_LOOP (charset_tail, Fcharset_list ())
|
|
|
1259 {
|
|
|
1260 Lisp_Object charset_code_page;
|
|
|
1261
|
|
|
1262 charset_code_page = Fmswindows_charset_code_page (XCAR (charset_tail));
|
|
|
1263 if (INTP (charset_code_page) &&
|
|
|
1264 code_page == XINT (charset_code_page))
|
|
|
1265 {
|
|
|
1266 charset = Fget_charset (XCAR (charset_tail));
|
|
|
1267 break;
|
|
|
1268 }
|
|
|
1269 }
|
|
|
1270 return charset;
|
|
|
1271 }
|
|
|
1272
|
|
|
1273
|
|
|
1274
|
|
|
1275 #if 0 /* #### from Emacs 20.6; consider porting */
|
|
|
1276
|
|
|
1277 xxDEFUN ("mswindows-get-locale-info", Fmswindows_get_locale_info, 1, 2, 0, /*
|
|
|
1278 Return information about the Windows locale LCID.
|
|
|
1279 By default, return a three letter locale code which encodes the default
|
|
|
1280 language as the first two characters, and the country or regionial variant
|
|
|
1281 as the third letter. For example, ENU refers to `English (United States)',
|
|
|
1282 while ENC means `English (Canadian)'.
|
|
|
1283
|
|
|
1284 If the optional argument LONGFORM is t, the long form of the locale
|
|
|
1285 name is returned, e.g. `English (United States)' instead; if LONGFORM
|
|
|
1286 is a number, it is interpreted as an LCTYPE constant and the corresponding
|
|
|
1287 locale information is returned.
|
|
|
1288
|
|
|
1289 If LCID (a 16-bit number) is not a valid locale, the result is nil.
|
|
|
1290 */
|
|
|
1291 (lcid, longform))
|
|
|
1292 {
|
|
|
1293 int got_abbrev;
|
|
|
1294 int got_full;
|
|
|
1295 char abbrev_name[32] = { 0 };
|
|
|
1296 char full_name[256] = { 0 };
|
|
|
1297
|
|
|
1298 CHECK_INT (lcid);
|
|
|
1299
|
|
|
1300 if (!IsValidLocale (XINT (lcid), LCID_SUPPORTED))
|
|
|
1301 return Qnil;
|
|
|
1302
|
|
|
1303 if (NILP (longform))
|
|
|
1304 {
|
|
|
1305 got_abbrev = GetLocaleInfo (XINT (lcid),
|
|
|
1306 LOCALE_SABBREVLANGNAME | LOCALE_USE_CP_ACP,
|
|
|
1307 abbrev_name, sizeof (abbrev_name));
|
|
|
1308 if (got_abbrev)
|
|
|
1309 return build_string (abbrev_name);
|
|
|
1310 }
|
|
|
1311 else if (EQ (longform, Qt))
|
|
|
1312 {
|
|
|
1313 got_full = GetLocaleInfo (XINT (lcid),
|
|
|
1314 LOCALE_SLANGUAGE | LOCALE_USE_CP_ACP,
|
|
|
1315 full_name, sizeof (full_name));
|
|
|
1316 if (got_full)
|
|
|
1317 return build_string (full_name);
|
|
|
1318 }
|
|
|
1319 else if (NUMBERP (longform))
|
|
|
1320 {
|
|
|
1321 got_full = GetLocaleInfo (XINT (lcid),
|
|
|
1322 XINT (longform),
|
|
|
1323 full_name, sizeof (full_name));
|
|
|
1324 if (got_full)
|
|
|
1325 return make_unibyte_string (full_name, got_full);
|
|
|
1326 }
|
|
|
1327
|
|
|
1328 return Qnil;
|
|
|
1329 }
|
|
|
1330
|
|
|
1331 /* We need to build a global list, since the EnumCodePages callback
|
|
|
1332 function isn't given a context pointer. */
|
|
|
1333 Lisp_Object Vmswindows_valid_code_pages;
|
|
|
1334
|
|
|
1335 BOOL CALLBACK enum_code_page_fn (LPTSTR codepageNum)
|
|
|
1336 {
|
|
|
1337 DWORD id = atoi (codepageNum);
|
|
|
1338 Vmswindows_valid_code_pages = Fcons (make_int (id), Vmswindows_valid_code_pages);
|
|
|
1339 return TRUE;
|
|
|
1340 }
|
|
|
1341
|
|
|
1342 xxDEFUN ("mswindows-get-valid-code-pages", Fmswindows_get_valid_code_pages, 0, 0, 0, /*
|
|
|
1343 Return list of all valid Windows code pages.
|
|
|
1344 */
|
|
|
1345 ())
|
|
|
1346 {
|
|
|
1347 Vmswindows_valid_code_pages = Qnil;
|
|
|
1348
|
|
|
1349 EnumSystemCodePages (enum_code_page_fn, CP_SUPPORTED);
|
|
|
1350
|
|
|
1351 Vmswindows_valid_code_pages = Fnreverse (Vmswindows_valid_code_pages);
|
|
|
1352 return Vmswindows_valid_code_pages;
|
|
|
1353 }
|
|
|
1354
|
|
|
1355 xxDEFUN ("mswindows-get-console-code-page", Fmswindows_get_console_code_page, 0, 0, 0, /*
|
|
|
1356 Return current Windows code page for console input.
|
|
|
1357 */
|
|
|
1358 ())
|
|
|
1359 {
|
|
|
1360 return make_int (GetConsoleCP ());
|
|
|
1361 }
|
|
|
1362
|
|
|
1363 xxDEFUN ("mswindows-set-console-code-page", Fmswindows_set_console_code_page, 1, 1, 0, /*
|
|
|
1364 Make Windows code page CP be the current code page setting for Emacs.
|
|
|
1365 The code page setting affects keyboard input and display in tty mode.
|
|
|
1366 If successful, the new CP is returned, otherwise nil.
|
|
|
1367 */
|
|
|
1368 (cp))
|
|
|
1369 {
|
|
|
1370 CHECK_INT (cp);
|
|
|
1371
|
|
|
1372 if (!IsValidCodePage (XINT (cp)))
|
|
|
1373 return Qnil;
|
|
|
1374
|
|
|
1375 if (!SetConsoleCP (XINT (cp)))
|
|
|
1376 return Qnil;
|
|
|
1377
|
|
|
1378 return make_int (GetConsoleCP ());
|
|
|
1379 }
|
|
|
1380
|
|
|
1381 xxDEFUN ("mswindows-get-console-output-code-page", Fmswindows_get_console_output_code_page, 0, 0, 0, /*
|
|
|
1382 Return current Windows code page for console output.
|
|
|
1383 */
|
|
|
1384 ())
|
|
|
1385 {
|
|
|
1386 return make_int (GetConsoleOutputCP ());
|
|
|
1387 }
|
|
|
1388
|
|
|
1389 xxDEFUN ("mswindows-set-console-output-code-page", Fmswindows_set_console_output_code_page, 1, 1, 0, /*
|
|
|
1390 Make Windows code page CP be the current code page setting for Emacs.
|
|
|
1391 The code page setting affects keyboard input and display in tty mode.
|
|
|
1392 If successful, the new CP is returned, otherwise nil.
|
|
|
1393 */
|
|
|
1394 (cp))
|
|
|
1395 {
|
|
|
1396 CHECK_INT (cp);
|
|
|
1397
|
|
|
1398 if (!IsValidCodePage (XINT (cp)))
|
|
|
1399 return Qnil;
|
|
|
1400
|
|
|
1401 if (!SetConsoleOutputCP (XINT (cp)))
|
|
|
1402 return Qnil;
|
|
|
1403
|
|
|
1404 return make_int (GetConsoleOutputCP ());
|
|
|
1405 }
|
|
|
1406
|
|
|
1407 xxDEFUN ("mswindows-get-code-page-charset", Fmswindows_get_code_page_charset, 1, 1, 0, /*
|
|
|
1408 Return charset of code page CP.
|
|
|
1409 Returns nil if the code page is not valid.
|
|
|
1410 */
|
|
|
1411 (cp))
|
|
|
1412 {
|
|
|
1413 CHARSETINFO info;
|
|
|
1414
|
|
|
1415 CHECK_INT (cp);
|
|
|
1416
|
|
|
1417 if (!IsValidCodePage (XINT (cp)))
|
|
|
1418 return Qnil;
|
|
|
1419
|
|
|
1420 if (TranslateCharsetInfo ((DWORD *) XINT (cp), &info, TCI_SRCCODEPAGE))
|
|
|
1421 return make_int (info.ciCharset);
|
|
|
1422
|
|
|
1423 return Qnil;
|
|
|
1424 }
|
|
|
1425
|
|
|
1426 xxDEFUN ("mswindows-get-valid-keyboard-layouts", Fmswindows_get_valid_keyboard_layouts, 0, 0, 0, /*
|
|
|
1427 Return list of Windows keyboard languages and layouts.
|
|
|
1428 The return value is a list of pairs of language id and layout id.
|
|
|
1429 */
|
|
|
1430 ())
|
|
|
1431 {
|
|
|
1432 int num_layouts = GetKeyboardLayoutList (0, NULL);
|
|
|
1433 HKL * layouts = (HKL *) alloca (num_layouts * sizeof (HKL));
|
|
|
1434 Lisp_Object obj = Qnil;
|
|
|
1435
|
|
|
1436 if (GetKeyboardLayoutList (num_layouts, layouts) == num_layouts)
|
|
|
1437 {
|
|
|
1438 while (--num_layouts >= 0)
|
|
|
1439 {
|
|
|
1440 DWORD kl = (DWORD) layouts[num_layouts];
|
|
|
1441
|
|
|
1442 obj = Fcons (Fcons (make_int (kl & 0xffff),
|
|
|
1443 make_int ((kl >> 16) & 0xffff)),
|
|
|
1444 obj);
|
|
|
1445 }
|
|
|
1446 }
|
|
|
1447
|
|
|
1448 return obj;
|
|
|
1449 }
|
|
|
1450
|
|
|
1451 xxDEFUN ("mswindows-get-keyboard-layout", Fmswindows_get_keyboard_layout, 0, 0, 0, /*
|
|
|
1452 Return current Windows keyboard language and layout.
|
|
|
1453 The return value is the cons of the language id and the layout id.
|
|
|
1454 */
|
|
|
1455 ())
|
|
|
1456 {
|
|
|
1457 DWORD kl = (DWORD) GetKeyboardLayout (dwWindowsThreadId);
|
|
|
1458
|
|
|
1459 return Fcons (make_int (kl & 0xffff),
|
|
|
1460 make_int ((kl >> 16) & 0xffff));
|
|
|
1461 }
|
|
|
1462
|
|
|
1463 xxDEFUN ("mswindows-set-keyboard-layout", Fmswindows_set_keyboard_layout, 1, 1, 0, /*
|
|
|
1464 Make LAYOUT be the current keyboard layout for Emacs.
|
|
|
1465 The keyboard layout setting affects interpretation of keyboard input.
|
|
|
1466 If successful, the new layout id is returned, otherwise nil.
|
|
|
1467 */
|
|
|
1468 (layout))
|
|
|
1469 {
|
|
|
1470 DWORD kl;
|
|
|
1471
|
|
|
1472 CHECK_CONS (layout);
|
|
|
1473 CHECK_INT (XCAR (layout)));
|
|
|
1474 CHECK_INT (XCDR (layout)));
|
|
|
1475
|
|
|
1476 kl = (XINT (XCAR (layout))) & 0xffff)
|
|
|
1477 | (XINT (XCDR (layout))) << 16);
|
|
|
1478
|
|
|
1479 if (!ActivateKeyboardLayout ((HKL) kl, 0))
|
|
|
1480 return Qnil;
|
|
|
1481
|
|
|
1482 return Fmswindows_get_keyboard_layout ();
|
|
|
1483 }
|
|
|
1484
|
|
|
1485 #endif /* 0 */
|
|
|
1486
|
|
|
1487
|
|
|
1488 /* input method functions. */
|
|
|
1489
|
|
|
1490 #ifdef HAVE_MS_WINDOWS
|
|
|
1491
|
|
|
1492 void
|
|
|
1493 mswindows_start_ime_composition (struct frame *f)
|
|
|
1494 {
|
|
|
1495 COMPOSITIONFORM form;
|
|
|
1496 HWND hwnd = FRAME_MSWINDOWS_HANDLE (f);
|
|
|
1497 HIMC himc = ImmGetContext (hwnd);
|
|
|
1498
|
|
|
1499 /* Set a position of composition window. */
|
|
|
1500 xzero (form);
|
|
|
1501 form.dwStyle = CFS_POINT;
|
|
|
1502 form.ptCurrentPos.x = FRAME_MSWINDOWS_CURSOR_X (f);
|
|
|
1503 form.ptCurrentPos.y = FRAME_MSWINDOWS_CURSOR_Y (f);
|
|
|
1504 ImmSetCompositionWindow (himc, &form);
|
|
|
1505
|
|
|
1506 /* Set composition window font same as current face one. */
|
|
|
1507 {
|
|
|
1508 LOGFONTW old_logfont;
|
|
|
1509 CHARSETINFO info;
|
|
|
1510 Lisp_Object charset;
|
|
|
1511
|
|
|
1512 /* Get Mule charset from current ime font charset. */
|
|
|
1513 qxeImmGetCompositionFont (himc, &old_logfont);
|
|
|
1514 TranslateCharsetInfo ((DWORD *) (DWORD) old_logfont.lfCharSet, &info,
|
|
|
1515 TCI_SRCCHARSET);
|
|
|
1516 charset = mswindows_get_code_page_charset (info.ciACP);
|
|
|
1517
|
|
|
1518 if (CHARSETP (charset))
|
|
|
1519 {
|
|
|
1520 Lisp_Object window = FRAME_SELECTED_WINDOW (f);
|
|
|
1521 struct window *w = XWINDOW (window);
|
|
|
1522 face_index findex = FRAME_MSWINDOWS_CURSOR_FINDEX (f);
|
|
|
1523 struct face_cachel *cachel = WINDOW_FACE_CACHEL (w, findex);
|
|
|
1524 Lisp_Object face_font = FACE_CACHEL_FONT (cachel, charset);
|
|
|
1525
|
|
|
1526 if (!FONT_INSTANCEP (face_font))
|
|
|
1527 face_font =
|
|
|
1528 ensure_face_cachel_contains_charset (cachel, window, charset);
|
|
|
1529
|
|
|
1530 if (!EQ (face_font, Vthe_null_font_instance))
|
|
|
1531 {
|
|
|
1532 LOGFONTW new_logfont;
|
|
|
1533
|
|
|
1534 /* Get LOGFONT from the face font */
|
|
|
1535 if (qxeGetObject (FONT_INSTANCE_MSWINDOWS_HFONT_VARIANT
|
|
|
1536 (XFONT_INSTANCE (face_font),
|
|
|
1537 cachel->underline, cachel->strikethru),
|
|
|
1538 sizeof (LOGFONTW), (void*) &new_logfont))
|
|
|
1539 qxeImmSetCompositionFont (himc, &new_logfont);
|
|
|
1540 }
|
|
|
1541 }
|
|
|
1542 }
|
|
|
1543 ImmReleaseContext (hwnd, himc);
|
|
|
1544 return;
|
|
|
1545 }
|
|
|
1546
|
|
|
1547 #endif /* HAVE_MS_WINDOWS */
|
|
|
1548
|
|
|
1549 #else /* not MULE */
|
|
|
1550
|
|
|
1551 int
|
|
|
1552 mswindows_locale_to_code_page (LCID lcid)
|
|
|
1553 {
|
|
|
1554 return CP_ACP;
|
|
|
1555 }
|
|
|
1556
|
|
|
1557 #endif /* MULE */
|
|
|
1558
|
|
|
1559
|
|
|
1560 #ifdef CYGWIN
|
|
|
1561
|
|
|
1562 /* based on newlib strncpy, strcpy */
|
|
|
1563
|
|
|
1564 wchar_t *
|
|
|
1565 wcsncpy (wchar_t *dst0, const wchar_t *src0, size_t count)
|
|
|
1566 {
|
|
|
1567 wchar_t *dscan;
|
|
|
1568 const wchar_t *sscan;
|
|
|
1569
|
|
|
1570 dscan = dst0;
|
|
|
1571 sscan = src0;
|
|
|
1572 while (count > 0)
|
|
|
1573 {
|
|
|
1574 --count;
|
|
|
1575 if ((*dscan++ = *sscan++) == '\0')
|
|
|
1576 break;
|
|
|
1577 }
|
|
|
1578 while (count-- > 0)
|
|
|
1579 *dscan++ = '\0';
|
|
|
1580
|
|
|
1581 return dst0;
|
|
|
1582 }
|
|
|
1583
|
|
|
1584 wchar_t *
|
|
|
1585 wcscpy (wchar_t *dst0, const wchar_t *src0)
|
|
|
1586 {
|
|
|
1587 wchar_t *s = dst0;
|
|
|
1588
|
|
|
1589 while ((*dst0++ = *src0++))
|
|
|
1590 ;
|
|
|
1591
|
|
|
1592 return s;
|
|
|
1593 }
|
|
|
1594
|
|
|
1595 wchar_t *
|
|
|
1596 wcsdup (const wchar_t *str)
|
|
|
1597 {
|
|
|
1598 int len = wcslen (str) + 1;
|
|
|
1599 void *val = xmalloc (len * sizeof (wchar_t));
|
|
|
1600
|
|
|
1601 if (val == 0) return 0;
|
|
|
1602 return (wchar_t *) memcpy (val, str, len * sizeof (wchar_t));
|
|
|
1603 }
|
|
|
1604
|
|
|
1605 #endif /* CYGWIN */
|
|
|
1606
|
|
|
1607
|
|
|
1608 /************************************************************************/
|
|
|
1609 /* MS Windows multibyte-to-unicode methods */
|
|
|
1610 /************************************************************************/
|
|
|
1611
|
|
|
1612 DEFINE_CODING_SYSTEM_TYPE (mswindows_multibyte_to_unicode);
|
|
|
1613
|
|
|
1614 enum mswindows_multibyte_cp_type
|
|
|
1615 {
|
|
|
1616 MULTIBYTE_ANSI,
|
|
|
1617 MULTIBYTE_OEM,
|
|
|
1618 MULTIBYTE_EBCDIC,
|
|
|
1619 MULTIBYTE_MAC
|
|
|
1620 };
|
|
|
1621
|
|
|
1622 enum mswindows_multibyte_locale_type
|
|
|
1623 {
|
|
|
1624 MULTIBYTE_SPECIFIED_LOCALE,
|
|
|
1625 MULTIBYTE_SPECIFIED_CODE_PAGE,
|
|
|
1626 MULTIBYTE_CURRENT,
|
|
|
1627 MULTIBYTE_USER_DEFAULT,
|
|
|
1628 MULTIBYTE_SYSTEM_DEFAULT
|
|
|
1629 };
|
|
|
1630
|
|
|
1631 struct mswindows_multibyte_to_unicode_coding_system
|
|
|
1632 {
|
|
|
1633 enum mswindows_multibyte_cp_type cp_type;
|
|
|
1634 enum mswindows_multibyte_locale_type locale_type;
|
|
|
1635 LCID locale; /* if locale_type is MULTIBYTE_SPECIFIED_LOCALE */
|
|
|
1636 int cp; /* if locale_type is MULTIBYTE_SPECIFIED_CODE_PAGE */
|
|
|
1637 };
|
|
|
1638
|
|
|
1639 struct mswindows_multibyte_to_unicode_coding_stream
|
|
|
1640 {
|
|
|
1641 int partial_byte;
|
|
|
1642 int partial_byte_present;
|
|
|
1643 int cp;
|
|
|
1644 };
|
|
|
1645
|
|
|
1646 static const struct lrecord_description
|
|
|
1647 mswindows_multibyte_to_unicode_coding_system_description[] = {
|
|
|
1648 { XD_END }
|
|
|
1649 };
|
|
|
1650
|
|
|
1651 static void
|
|
|
1652 mswindows_multibyte_to_unicode_init (Lisp_Object codesys)
|
|
|
1653 {
|
|
|
1654 struct mswindows_multibyte_to_unicode_coding_system *data =
|
|
|
1655 XCODING_SYSTEM_TYPE_DATA (codesys, mswindows_multibyte_to_unicode);
|
|
|
1656
|
|
|
1657 data->cp_type = MULTIBYTE_ANSI;
|
|
|
1658 data->locale_type = MULTIBYTE_CURRENT;
|
|
|
1659 }
|
|
|
1660
|
|
|
1661 static Lisp_Object
|
|
|
1662 lcid_to_locale_mule_or_no (LCID lcid)
|
|
|
1663 {
|
|
|
1664 #ifdef MULE
|
|
|
1665 return lcid_to_locale (lcid);
|
|
|
1666 #else
|
|
|
1667 return Fcons (build_string ("NEUTRAL"), build_string ("DEFAULT"));
|
|
|
1668 #endif
|
|
|
1669 }
|
|
|
1670
|
|
|
1671 static int
|
|
|
1672 determine_code_page (Lisp_Object codesys)
|
|
|
1673 {
|
|
|
1674 #ifdef MULE
|
|
|
1675 LCID locale;
|
|
|
1676 struct mswindows_multibyte_to_unicode_coding_system *data =
|
|
|
1677 XCODING_SYSTEM_TYPE_DATA (codesys, mswindows_multibyte_to_unicode);
|
|
|
1678
|
|
|
1679 switch (data->locale_type)
|
|
|
1680 {
|
|
|
1681 case MULTIBYTE_SPECIFIED_CODE_PAGE:
|
|
|
1682 return data->cp;
|
|
|
1683 case MULTIBYTE_SPECIFIED_LOCALE:
|
|
|
1684 locale = data->locale; break;
|
|
|
1685 case MULTIBYTE_CURRENT:
|
|
|
1686 locale = mswindows_current_locale (); break;
|
|
|
1687 case MULTIBYTE_USER_DEFAULT:
|
|
|
1688 locale = GetUserDefaultLCID (); break;
|
|
|
1689 case MULTIBYTE_SYSTEM_DEFAULT:
|
|
|
1690 locale = GetSystemDefaultLCID (); break;
|
|
|
1691 default:
|
|
|
1692 abort (); locale = 0;
|
|
|
1693 }
|
|
|
1694
|
|
|
1695 switch (data->cp_type)
|
|
|
1696 {
|
|
|
1697 case MULTIBYTE_ANSI:
|
|
|
1698 return mswindows_locale_to_code_page (locale);
|
|
|
1699 case MULTIBYTE_OEM:
|
|
|
1700 return mswindows_locale_to_oem_code_page (locale);
|
|
|
1701 case MULTIBYTE_EBCDIC:
|
|
|
1702 #ifdef LOCALE_IDEFAULTEBCDICCODEPAGE /* Doesn't exist under Cygwin */
|
|
|
1703 {
|
|
|
1704 char codepagestr[10];
|
|
|
1705 GetLocaleInfoA (locale, LOCALE_IDEFAULTEBCDICCODEPAGE, codepagestr,
|
|
|
1706 10);
|
|
|
1707 return atoi (codepagestr);
|
|
|
1708 }
|
|
|
1709 #else
|
|
|
1710 invalid_operation ("Unable to determine EBCDIC code page for locale",
|
|
|
1711 lcid_to_locale (locale));
|
|
|
1712 return 0;
|
|
|
1713 #endif
|
|
|
1714 case MULTIBYTE_MAC:
|
|
|
1715 #ifdef LOCALE_IDEFAULTMACCODEPAGE /* Doesn't exist under Cygwin */
|
|
|
1716 {
|
|
|
1717 char codepagestr[10];
|
|
|
1718 GetLocaleInfoA (locale, LOCALE_IDEFAULTMACCODEPAGE, codepagestr,
|
|
|
1719 10);
|
|
|
1720 return atoi (codepagestr);
|
|
|
1721 }
|
|
|
1722 #else
|
|
|
1723 invalid_operation ("Unable to determine Mac code page for locale",
|
|
|
1724 lcid_to_locale (locale));
|
|
|
1725 return 0;
|
|
|
1726 #endif
|
|
|
1727 default:
|
|
|
1728 abort (); return 0;
|
|
|
1729 }
|
|
|
1730 #else /* not MULE */
|
|
|
1731 return CP_ACP;
|
|
|
1732 #endif
|
|
|
1733 }
|
|
|
1734
|
|
|
1735 static int
|
|
|
1736 mswindows_multibyte_to_unicode_putprop (Lisp_Object codesys,
|
|
|
1737 Lisp_Object key,
|
|
|
1738 Lisp_Object value)
|
|
|
1739 {
|
|
|
1740 struct mswindows_multibyte_to_unicode_coding_system *data =
|
|
|
1741 XCODING_SYSTEM_TYPE_DATA (codesys, mswindows_multibyte_to_unicode);
|
|
|
1742
|
|
|
1743 if (EQ (key, Qcode_page))
|
|
|
1744 {
|
|
|
1745 if (EQ (value, Qansi))
|
|
|
1746 data->cp_type = MULTIBYTE_ANSI;
|
|
|
1747 else if (EQ (value, Qoem))
|
|
|
1748 data->cp_type = MULTIBYTE_OEM;
|
|
|
1749 else if (EQ (value, Qebcdic))
|
|
|
1750 data->cp_type = MULTIBYTE_EBCDIC;
|
|
|
1751 else if (EQ (value, Qmac))
|
|
|
1752 data->cp_type = MULTIBYTE_MAC;
|
|
|
1753 else
|
|
|
1754 {
|
|
|
1755 CHECK_NATNUM (value);
|
|
|
1756 data->locale_type = MULTIBYTE_SPECIFIED_CODE_PAGE;
|
|
|
1757 data->cp = XINT (value);
|
|
|
1758 }
|
|
|
1759 }
|
|
|
1760 else if (EQ (key, Qlocale))
|
|
|
1761 {
|
|
|
1762 if (EQ (value, Qcurrent))
|
|
|
1763 data->locale_type = MULTIBYTE_CURRENT;
|
|
|
1764 else if (EQ (value, Quser_default))
|
|
|
1765 data->locale_type = MULTIBYTE_USER_DEFAULT;
|
|
|
1766 else if (EQ (value, Qsystem_default))
|
|
|
1767 data->locale_type = MULTIBYTE_SYSTEM_DEFAULT;
|
|
|
1768 else
|
|
|
1769 {
|
|
|
1770 data->locale_type = MULTIBYTE_SPECIFIED_LOCALE;
|
|
|
1771 #ifdef MULE
|
|
|
1772 data->locale = locale_to_lcid (value);
|
|
|
1773 #else
|
|
|
1774 data->locale = 0;
|
|
|
1775 #endif
|
|
|
1776 }
|
|
|
1777 }
|
|
|
1778 else
|
|
|
1779 return 0;
|
|
|
1780 return 1;
|
|
|
1781 }
|
|
|
1782
|
|
|
1783 static Lisp_Object
|
|
|
1784 mswindows_multibyte_to_unicode_getprop (Lisp_Object coding_system,
|
|
|
1785 Lisp_Object prop)
|
|
|
1786 {
|
|
|
1787 struct mswindows_multibyte_to_unicode_coding_system *data =
|
|
|
1788 XCODING_SYSTEM_TYPE_DATA (coding_system, mswindows_multibyte_to_unicode);
|
|
|
1789
|
|
|
1790 if (EQ (prop, Qcode_page))
|
|
|
1791 {
|
|
|
1792 if (data->locale_type == MULTIBYTE_SPECIFIED_CODE_PAGE)
|
|
|
1793 return make_int (data->cp);
|
|
|
1794 else
|
|
|
1795 switch (data->cp_type)
|
|
|
1796 {
|
|
|
1797 case MULTIBYTE_ANSI: return Qansi;
|
|
|
1798 case MULTIBYTE_OEM: return Qoem;
|
|
|
1799 case MULTIBYTE_EBCDIC: return Qebcdic;
|
|
|
1800 case MULTIBYTE_MAC: return Qmac;
|
|
|
1801 default: abort ();
|
|
|
1802 }
|
|
|
1803 }
|
|
|
1804 else if (EQ (prop, Qlocale))
|
|
|
1805 {
|
|
|
1806 switch (data->locale_type)
|
|
|
1807 {
|
|
|
1808 case MULTIBYTE_CURRENT: return Qcurrent;
|
|
|
1809 case MULTIBYTE_USER_DEFAULT: return Quser_default;
|
|
|
1810 case MULTIBYTE_SYSTEM_DEFAULT: return Qsystem_default;
|
|
|
1811 case MULTIBYTE_SPECIFIED_LOCALE:
|
|
|
1812 return lcid_to_locale_mule_or_no (data->locale);
|
|
|
1813
|
|
|
1814 case MULTIBYTE_SPECIFIED_CODE_PAGE:
|
|
|
1815 return Qnil;
|
|
|
1816 default: abort ();
|
|
|
1817 }
|
|
|
1818 }
|
|
|
1819
|
|
|
1820 return Qunbound;
|
|
|
1821 }
|
|
|
1822
|
|
|
1823 static void
|
|
|
1824 mswindows_multibyte_to_unicode_print (Lisp_Object cs,
|
|
|
1825 Lisp_Object printcharfun, int escapeflag)
|
|
|
1826 {
|
|
|
1827 struct mswindows_multibyte_to_unicode_coding_system *data =
|
|
|
1828 XCODING_SYSTEM_TYPE_DATA (cs, mswindows_multibyte_to_unicode);
|
|
|
1829
|
|
|
1830 write_c_string ("(", printcharfun);
|
|
|
1831 if (data->locale_type == MULTIBYTE_SPECIFIED_CODE_PAGE)
|
|
|
1832 print_internal (make_int (data->cp), printcharfun, 1);
|
|
|
1833 else
|
|
|
1834 {
|
|
|
1835 print_internal (mswindows_multibyte_to_unicode_getprop (cs, Qlocale),
|
|
|
1836 printcharfun, 0);
|
|
|
1837 write_c_string (", ", printcharfun);
|
|
|
1838 print_internal (mswindows_multibyte_to_unicode_getprop (cs, Qcode_page),
|
|
|
1839 printcharfun, 0);
|
|
|
1840 }
|
|
|
1841 write_c_string (")", printcharfun);
|
|
|
1842 }
|
|
|
1843
|
|
|
1844 /* Convert multibyte to Unicode according to the specified code page
|
|
|
1845 and return the value as a malloc()ed string. This currently exists
|
|
|
1846 because the TO_INTERNAL_FORMAT() mechanism -- the normal way to do
|
|
|
1847 such conversions -- has no way of passing in a parameter to control
|
|
|
1848 the operation. We could use a global variable to pass this value
|
|
|
1849 in, but that runs the risk of causing problems due to reentrancy.
|
|
|
1850 (You might say, yeah, right, how can TO_INTERNAL_FORMAT() get
|
|
|
1851 called recursively merely when I'm doing a simple conversion
|
|
|
1852 operation? It turns out this can and does happen, consistently, as
|
|
|
1853 a result of calling QUIT -- it happens consistently for complicated
|
|
|
1854 reasons outlined in event-msw.c, WM_KEYDOWN handling.) */
|
|
|
1855
|
|
|
1856 Extbyte *
|
|
|
1857 convert_multibyte_to_unicode_malloc (const Extbyte *src, Bytecount n,
|
|
|
1858 int cp, Bytecount *size_out)
|
|
|
1859 {
|
|
|
1860 Bytecount nout = MultiByteToWideChar (cp, 0, src, n, 0, 0);
|
|
|
1861 Extbyte *outp = xnew_array (Extbyte, nout * sizeof (WCHAR));
|
|
|
1862
|
|
|
1863 MultiByteToWideChar (cp, 0, src, n, (LPWSTR) outp, nout);
|
|
|
1864 if (size_out)
|
|
|
1865 *size_out = nout * sizeof (WCHAR);
|
|
|
1866 return outp;
|
|
|
1867 }
|
|
|
1868
|
|
|
1869 /* Convert MS Windows multibyte to internal, with specified code page.
|
|
|
1870 See above for why this exists, and the TO_INTERNAL_FORMAT() macros
|
|
|
1871 aren't just used. */
|
|
|
1872
|
|
|
1873 Intbyte *
|
|
|
1874 convert_multibyte_to_internal_malloc (const Extbyte *src, Bytecount n,
|
|
|
1875 int cp, Bytecount *size_out)
|
|
|
1876 {
|
|
|
1877 Bytecount size;
|
|
|
1878 Extbyte *unidata = convert_multibyte_to_unicode_malloc (src, n, cp, &size);
|
|
|
1879 Intbyte *intdata;
|
|
|
1880
|
|
|
1881 TO_INTERNAL_FORMAT (DATA, (unidata, size), MALLOC, (intdata, size),
|
|
|
1882 Qmswindows_unicode);
|
|
|
1883
|
|
|
1884 xfree (unidata);
|
|
|
1885
|
|
|
1886 if (size_out)
|
|
|
1887 *size_out = size;
|
|
|
1888
|
|
|
1889 return intdata;
|
|
|
1890 }
|
|
|
1891
|
|
|
1892 /* Convert multibyte to Unicode according to the specified code page
|
|
|
1893 and append the results onto the specified Dynarr. See above. */
|
|
|
1894
|
|
|
1895 void
|
|
|
1896 convert_multibyte_to_unicode_dynarr (const Extbyte *src, Bytecount n,
|
|
|
1897 int cp, unsigned_char_dynarr *dst)
|
|
|
1898 {
|
|
|
1899 Bytecount nout = MultiByteToWideChar (cp, 0, src, n, 0, 0);
|
|
|
1900 void *outp;
|
|
|
1901
|
|
|
1902 Dynarr_add_many (dst, 0, nout * sizeof (WCHAR));
|
|
|
1903 /* dynarr's buffer may be realloc()ed by call above, so access it after */
|
|
|
1904 outp = Dynarr_atp (dst, Dynarr_length (dst) - nout * sizeof (WCHAR));
|
|
|
1905 MultiByteToWideChar (cp, 0, src, n, (LPWSTR) outp, nout);
|
|
|
1906 }
|
|
|
1907
|
|
|
1908 /* Convert MS Windows multibyte to Unicode. */
|
|
|
1909
|
|
|
1910 static Bytecount
|
|
|
1911 mswindows_multibyte_to_unicode_convert (struct coding_stream *str,
|
|
|
1912 const unsigned char *src,
|
|
|
1913 unsigned_char_dynarr *dst,
|
|
|
1914 Bytecount n)
|
|
|
1915 {
|
|
|
1916 unsigned char *new_src = (unsigned char *) src;
|
|
|
1917 int i;
|
|
|
1918 struct mswindows_multibyte_to_unicode_coding_stream *data =
|
|
|
1919 CODING_STREAM_TYPE_DATA (str, mswindows_multibyte_to_unicode);
|
|
|
1920 Bytecount orign = n;
|
|
|
1921
|
|
|
1922 if (data->cp == 0)
|
|
|
1923 data->cp = determine_code_page (str->codesys);
|
|
|
1924 if (data->partial_byte_present)
|
|
|
1925 {
|
|
|
1926 new_src = alloca_array (unsigned char, n + 1);
|
|
|
1927 memcpy (new_src + 1, src, n);
|
|
|
1928 new_src[0] =
|
|
|
1929 (unsigned char) data->partial_byte;
|
|
|
1930 n++;
|
|
|
1931 }
|
|
|
1932
|
|
|
1933 if (str->direction == CODING_DECODE)
|
|
|
1934 {
|
|
|
1935 for (i = n - 1; i >= 0; i--)
|
|
|
1936 {
|
|
|
1937 if (!IsDBCSLeadByteEx (data->cp, new_src[i]))
|
|
|
1938 break;
|
|
|
1939 }
|
|
|
1940
|
|
|
1941 i++;
|
|
|
1942
|
|
|
1943 for (; i < n; i++)
|
|
|
1944 {
|
|
|
1945 if (IsDBCSLeadByteEx (data->cp, new_src[i]))
|
|
|
1946 i++;
|
|
|
1947 }
|
|
|
1948
|
|
|
1949 if (i > n)
|
|
|
1950 {
|
|
|
1951 /* a char is split across the boundary */
|
|
|
1952 data->partial_byte = new_src[n - 1];
|
|
|
1953 data->partial_byte_present = 1;
|
|
|
1954 n--;
|
|
|
1955 }
|
|
|
1956 else
|
|
|
1957 data->partial_byte_present = 0;
|
|
|
1958
|
|
|
1959 convert_multibyte_to_unicode_dynarr ((Extbyte *) new_src, n, data->cp,
|
|
|
1960 dst);
|
|
|
1961 }
|
|
|
1962 else
|
|
|
1963 {
|
|
|
1964 if (n & 1)
|
|
|
1965 {
|
|
|
1966 /* a char is split across the boundary */
|
|
|
1967 data->partial_byte = new_src[n - 1];
|
|
|
1968 data->partial_byte_present = 1;
|
|
|
1969 n--;
|
|
|
1970 }
|
|
|
1971 else
|
|
|
1972 data->partial_byte_present = 0;
|
|
|
1973
|
|
|
1974 {
|
|
|
1975 int nout = WideCharToMultiByte (data->cp, WC_COMPOSITECHECK,
|
|
|
1976 (LPWSTR) new_src, n / sizeof (WCHAR),
|
|
|
1977 0, 0, "~", 0);
|
|
|
1978 void *outp;
|
|
|
1979
|
|
|
1980 Dynarr_add_many (dst, 0, nout);
|
|
|
1981 /* dynarr's buffer may be realloc()ed by call above, so access it
|
|
|
1982 after */
|
|
|
1983 outp = Dynarr_atp (dst, Dynarr_length (dst) - nout);
|
|
|
1984 WideCharToMultiByte (data->cp, WC_COMPOSITECHECK, (LPWSTR) new_src,
|
|
|
1985 n / sizeof (WCHAR),
|
|
|
1986 (LPSTR) outp, nout, "~", 0);
|
|
|
1987 }
|
|
|
1988 }
|
|
|
1989 return orign;
|
|
|
1990 }
|
|
|
1991
|
|
|
1992 static enum source_sink_type
|
|
|
1993 mswindows_multibyte_to_unicode_conversion_end_type (Lisp_Object codesys)
|
|
|
1994 {
|
|
|
1995 return DECODES_BYTE_TO_BYTE;
|
|
|
1996 }
|
|
|
1997
|
|
|
1998
|
|
|
1999 /************************************************************************/
|
|
|
2000 /* MS Windows Multibyte methods */
|
|
|
2001 /************************************************************************/
|
|
|
2002
|
|
|
2003 DEFINE_CODING_SYSTEM_TYPE (mswindows_multibyte);
|
|
|
2004
|
|
|
2005 struct mswindows_multibyte_coding_system
|
|
|
2006 {
|
|
|
2007 Lisp_Object code_page;
|
|
|
2008 Lisp_Object locale;
|
|
|
2009 };
|
|
|
2010
|
|
|
2011 struct mswindows_multibyte_coding_stream
|
|
|
2012 {
|
|
|
2013 int dummy;
|
|
|
2014 };
|
|
|
2015
|
|
|
2016 static const struct lrecord_description
|
|
|
2017 mswindows_multibyte_coding_system_description[] = {
|
|
|
2018 { XD_LISP_OBJECT,
|
|
|
2019 coding_system_data_offset +
|
|
|
2020 offsetof (struct mswindows_multibyte_coding_system, code_page) },
|
|
|
2021 { XD_LISP_OBJECT,
|
|
|
2022 coding_system_data_offset +
|
|
|
2023 offsetof (struct mswindows_multibyte_coding_system, locale) },
|
|
|
2024 { XD_END }
|
|
|
2025 };
|
|
|
2026
|
|
|
2027 static Bytecount
|
|
|
2028 mswindows_multibyte_convert (struct coding_stream *str,
|
|
|
2029 const UExtbyte *src,
|
|
|
2030 unsigned_char_dynarr *dst, Bytecount n)
|
|
|
2031 {
|
|
|
2032 Bytecount orign = n;
|
|
|
2033 /* should never be called; is preprocessed away in the
|
|
|
2034 canonicalize method */
|
|
|
2035 abort ();
|
|
|
2036 return orign;
|
|
|
2037 }
|
|
|
2038
|
|
|
2039 static void
|
|
|
2040 mswindows_multibyte_init (Lisp_Object codesys)
|
|
|
2041 {
|
|
|
2042 struct mswindows_multibyte_coding_system *data =
|
|
|
2043 XCODING_SYSTEM_TYPE_DATA (codesys, mswindows_multibyte);
|
|
|
2044
|
|
|
2045 data->code_page = Qnil;
|
|
|
2046 data->locale = Qnil;
|
|
|
2047 }
|
|
|
2048
|
|
|
2049 static void
|
|
|
2050 mswindows_multibyte_mark (Lisp_Object codesys)
|
|
|
2051 {
|
|
|
2052 struct mswindows_multibyte_coding_system *data =
|
|
|
2053 XCODING_SYSTEM_TYPE_DATA (codesys, mswindows_multibyte);
|
|
|
2054
|
|
|
2055 mark_object (data->code_page);
|
|
|
2056 mark_object (data->locale);
|
|
|
2057 }
|
|
|
2058
|
|
|
2059 static int
|
|
|
2060 mswindows_multibyte_putprop (Lisp_Object codesys,
|
|
|
2061 Lisp_Object key,
|
|
|
2062 Lisp_Object value)
|
|
|
2063 {
|
|
|
2064 struct mswindows_multibyte_coding_system *data =
|
|
|
2065 XCODING_SYSTEM_TYPE_DATA (codesys, mswindows_multibyte);
|
|
|
2066
|
|
|
2067 if (EQ (key, Qcode_page))
|
|
|
2068 data->code_page = value;
|
|
|
2069 else if (EQ (key, Qlocale))
|
|
|
2070 data->locale = value;
|
|
|
2071 else
|
|
|
2072 return 0;
|
|
|
2073 return 1;
|
|
|
2074 }
|
|
|
2075
|
|
|
2076 static Lisp_Object
|
|
|
2077 mswindows_multibyte_getprop (Lisp_Object coding_system,
|
|
|
2078 Lisp_Object prop)
|
|
|
2079 {
|
|
|
2080 struct mswindows_multibyte_coding_system *data =
|
|
|
2081 XCODING_SYSTEM_TYPE_DATA (coding_system, mswindows_multibyte);
|
|
|
2082
|
|
|
2083 if (EQ (prop, Qcode_page))
|
|
|
2084 return data->code_page;
|
|
|
2085 else if (EQ (prop, Qlocale))
|
|
|
2086 return data->locale;
|
|
|
2087 else
|
|
|
2088 return Qunbound;
|
|
|
2089 }
|
|
|
2090
|
|
|
2091 /* Convert this coding system into the proper chain. */
|
|
|
2092
|
|
|
2093 static Lisp_Object
|
|
|
2094 mswindows_multibyte_canonicalize (Lisp_Object codesys)
|
|
|
2095 {
|
|
|
2096 struct mswindows_multibyte_coding_system *data =
|
|
|
2097 XCODING_SYSTEM_TYPE_DATA (codesys, mswindows_multibyte);
|
|
|
2098 Lisp_Object m2u;
|
|
|
2099
|
|
|
2100 m2u =
|
|
|
2101 make_internal_coding_system
|
|
|
2102 (Qnil,
|
|
|
2103 "internal-mswindows-multibyte-to-unicode",
|
|
|
2104 Qmswindows_multibyte_to_unicode,
|
|
|
2105 Qnil, NILP (data->locale) ?
|
|
|
2106 list2 (Qcode_page, data->code_page) :
|
|
|
2107 list4 (Qcode_page, data->code_page, Qlocale, data->locale));
|
|
|
2108
|
|
|
2109 return make_internal_coding_system (codesys,
|
|
|
2110 "internal-mswindows-multibyte-chain",
|
|
|
2111 Qchain, Qunbound,
|
|
|
2112 list4 (Qchain,
|
|
|
2113 list2 (m2u, Qmswindows_unicode),
|
|
|
2114 Qcanonicalize_after_coding,
|
|
|
2115 codesys));
|
|
|
2116 }
|
|
|
2117
|
|
|
2118
|
|
|
2119 void
|
|
|
2120 syms_of_intl_win32 (void)
|
|
|
2121 {
|
|
|
2122 #ifdef MULE
|
|
|
2123 DEFSUBR (Fmswindows_set_current_locale);
|
|
|
2124 DEFSUBR (Fmswindows_current_locale);
|
|
|
2125 DEFSUBR (Fmswindows_user_default_locale);
|
|
|
2126 DEFSUBR (Fmswindows_system_default_locale);
|
|
|
2127 DEFSUBR (Fmswindows_locale_code_page);
|
|
|
2128 DEFSUBR (Fmswindows_locale_oem_code_page);
|
|
|
2129 DEFSUBR (Fmswindows_supported_locales);
|
|
|
2130 DEFSUBR (Fmswindows_charset_code_page);
|
|
|
2131 DEFSUBR (Fmswindows_set_charset_code_page);
|
|
|
2132
|
|
|
2133 #if 0
|
|
|
2134 DEFSUBR (Fmswindows_get_locale_info);
|
|
|
2135 DEFSUBR (Fmswindows_get_current_locale_id);
|
|
|
2136 DEFSUBR (Fmswindows_get_default_locale_id);
|
|
|
2137 DEFSUBR (Fmswindows_get_valid_locale_ids);
|
|
|
2138 DEFSUBR (Fmswindows_set_current_locale);
|
|
|
2139
|
|
|
2140 DEFSUBR (Fmswindows_get_console_code_page);
|
|
|
2141 DEFSUBR (Fmswindows_set_console_code_page);
|
|
|
2142 DEFSUBR (Fmswindows_get_console_output_code_page);
|
|
|
2143 DEFSUBR (Fmswindows_set_console_output_code_page);
|
|
|
2144 DEFSUBR (Fmswindows_get_valid_code_pages);
|
|
|
2145 DEFSUBR (Fmswindows_get_code_page_charset);
|
|
|
2146
|
|
|
2147 DEFSUBR (Fmswindows_get_valid_keyboard_layouts);
|
|
|
2148 DEFSUBR (Fmswindows_get_keyboard_layout);
|
|
|
2149 DEFSUBR (Fmswindows_set_keyboard_layout);
|
|
|
2150 #endif
|
|
|
2151 #endif /* MULE */
|
|
|
2152
|
|
|
2153 DEFSYMBOL (Qmswindows_tstr);
|
|
|
2154 DEFSYMBOL (Qmswindows_multibyte);
|
|
|
2155 DEFSYMBOL (Qmswindows_multibyte_to_unicode);
|
|
|
2156 DEFSYMBOL (Qmswindows_unicode);
|
|
|
2157 DEFSYMBOL (Qmswindows_multibyte_system_default);
|
|
|
2158
|
|
|
2159 DEFSYMBOL (Qansi);
|
|
|
2160 DEFSYMBOL (Qoem);
|
|
|
2161 DEFSYMBOL (Qmac);
|
|
|
2162 DEFSYMBOL (Qebcdic);
|
|
|
2163 }
|
|
|
2164
|
|
|
2165 void
|
|
|
2166 coding_system_type_create_intl_win32 (void)
|
|
|
2167 {
|
|
|
2168 INITIALIZE_CODING_SYSTEM_TYPE_WITH_DATA
|
|
|
2169 (mswindows_multibyte_to_unicode,
|
|
|
2170 "mswindows-multibyte-to-unicode-coding-system-p");
|
|
|
2171 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte_to_unicode, init);
|
|
|
2172 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte_to_unicode, print);
|
|
|
2173 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte_to_unicode, convert);
|
|
|
2174 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte_to_unicode, getprop);
|
|
|
2175 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte_to_unicode, putprop);
|
|
|
2176 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte_to_unicode,
|
|
|
2177 conversion_end_type);
|
|
|
2178
|
|
|
2179 INITIALIZE_CODING_SYSTEM_TYPE_WITH_DATA
|
|
|
2180 (mswindows_multibyte,
|
|
|
2181 "mswindows-multibyte-coding-system-p");
|
|
|
2182 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte, convert);
|
|
|
2183 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte, init);
|
|
|
2184 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte, mark);
|
|
|
2185 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte, getprop);
|
|
|
2186 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte, putprop);
|
|
|
2187 CODING_SYSTEM_HAS_METHOD (mswindows_multibyte, canonicalize);
|
|
|
2188 }
|
|
|
2189
|
|
|
2190 void
|
|
|
2191 reinit_coding_system_type_create_intl_win32 (void)
|
|
|
2192 {
|
|
|
2193 REINITIALIZE_CODING_SYSTEM_TYPE (mswindows_multibyte_to_unicode);
|
|
|
2194 REINITIALIZE_CODING_SYSTEM_TYPE (mswindows_multibyte);
|
|
|
2195 }
|
|
|
2196
|
|
|
2197 void
|
|
|
2198 vars_of_intl_win32 (void)
|
|
|
2199 {
|
|
|
2200 #ifdef MULE
|
|
|
2201 Vmswindows_charset_code_page_table =
|
|
|
2202 make_lisp_hash_table (50, HASH_TABLE_NON_WEAK, HASH_TABLE_EQ);
|
|
|
2203 staticpro (&Vmswindows_charset_code_page_table);
|
|
|
2204 #endif /* MULE */
|
|
|
2205 }
|
|
|
2206
|
|
|
2207 static void
|
|
|
2208 determine_if_using_unicode (void)
|
|
|
2209 {
|
|
|
2210 if (XEUNICODE_P)
|
|
|
2211 Fdefine_coding_system_alias (Qmswindows_tstr, Qmswindows_unicode);
|
|
|
2212 else
|
|
|
2213 Fdefine_coding_system_alias (Qmswindows_tstr,
|
|
|
2214 Qmswindows_multibyte_system_default);
|
|
|
2215 }
|
|
|
2216
|
|
|
2217 void
|
|
|
2218 complex_vars_of_intl_win32 (void)
|
|
|
2219 {
|
|
|
2220 Fmake_coding_system
|
|
|
2221 (Qmswindows_unicode, Qunicode,
|
|
|
2222 build_msg_string ("MS Windows Unicode"),
|
|
|
2223 nconc2 (list4 (Qdocumentation,
|
|
|
2224 build_msg_string (
|
|
|
2225 "Converts to the Unicode encoding for Windows API calls.\n"
|
|
|
2226 "This encoding is equivalent to standard UTF16, little-endian."
|
|
|
2227 ),
|
|
|
2228 Qmnemonic, build_string ("MSW-U")),
|
|
|
2229 list4 (Qtype, Qutf_16,
|
|
|
2230 Qlittle_endian, Qt)));
|
|
|
2231
|
|
|
2232 #ifdef MULE
|
|
|
2233 /* Just temporarily. This will get fixed in mule-msw-init.el. */
|
|
|
2234 Fdefine_coding_system_alias (Qmswindows_multibyte_system_default,
|
|
|
2235 Qraw_text);
|
|
|
2236 #else
|
|
|
2237 /* Not temporarily. These may be referenced by Lisp code so we need to
|
|
|
2238 define them. */
|
|
|
2239 Fdefine_coding_system_alias (Qmswindows_multibyte,
|
|
|
2240 Qraw_text);
|
|
|
2241 Fdefine_coding_system_alias (Qmswindows_multibyte_system_default,
|
|
|
2242 Qraw_text);
|
|
|
2243 Fdefine_coding_system_alias (intern ("mswindows-multibyte-user-default"),
|
|
|
2244 Qraw_text);
|
|
|
2245 Fdefine_coding_system_alias (intern ("mswindows-multibyte-oem"),
|
|
|
2246 Qraw_text);
|
|
|
2247 Fdefine_coding_system_alias (intern
|
|
|
2248 ("mswindows-multibyte-oem-system-default"),
|
|
|
2249 Qraw_text);
|
|
|
2250 Fdefine_coding_system_alias (intern ("mswindows-multibyte-oem-user-default"),
|
|
|
2251 Qraw_text);
|
|
|
2252 #endif /* MULE */
|
|
|
2253
|
|
|
2254 determine_if_using_unicode ();
|
|
|
2255 }
|
|
|
2256
|
|
|
2257 void
|
|
|
2258 init_intl_win32 (void)
|
|
|
2259 {
|
|
|
2260 #ifdef MULE
|
|
|
2261 set_current_lcid (GetUserDefaultLCID ());
|
|
|
2262 #endif /* MULE */
|
|
|
2263
|
|
|
2264 if (initialized)
|
|
|
2265 /* If not initialized, we also call this, but early -- see the
|
|
|
2266 previous function. */
|
|
|
2267 determine_if_using_unicode ();
|
|
|
2268 }
|
