Commit | Line | Data |
---|---|---|
9542cb1f | 1 | /* Coding system handler (conversion, detection, etc). |
4a2f9c6a | 2 | Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN. |
8f924df7 | 3 | Licensed to the Free Software Foundation. |
6f197c07 | 4 | Copyright (C) 2001, 2002 Free Software Foundation, Inc. |
8f924df7 | 5 | Copyright (C) 2003 |
df7492f9 KH |
6 | National Institute of Advanced Industrial Science and Technology (AIST) |
7 | Registration Number H13PRO009 | |
4ed46869 | 8 | |
369314dc KH |
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. | |
4ed46869 | 15 | |
369314dc KH |
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. | |
4ed46869 | 20 | |
369314dc KH |
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 | |
23 | the Free Software Foundation, Inc., 59 Temple Place - Suite 330, | |
24 | Boston, MA 02111-1307, USA. */ | |
4ed46869 KH |
25 | |
26 | /*** TABLE OF CONTENTS *** | |
27 | ||
b73bfc1c | 28 | 0. General comments |
4ed46869 | 29 | 1. Preamble |
df7492f9 KH |
30 | 2. Emacs' internal format (emacs-utf-8) handlers |
31 | 3. UTF-8 handlers | |
32 | 4. UTF-16 handlers | |
33 | 5. Charset-base coding systems handlers | |
34 | 6. emacs-mule (old Emacs' internal format) handlers | |
35 | 7. ISO2022 handlers | |
36 | 8. Shift-JIS and BIG5 handlers | |
37 | 9. CCL handlers | |
38 | 10. C library functions | |
39 | 11. Emacs Lisp library functions | |
40 | 12. Postamble | |
4ed46869 KH |
41 | |
42 | */ | |
43 | ||
df7492f9 | 44 | /*** 0. General comments *** |
b73bfc1c KH |
45 | |
46 | ||
df7492f9 | 47 | CODING SYSTEM |
4ed46869 | 48 | |
5bad0796 DL |
49 | A coding system is an object for an encoding mechanism that contains |
50 | information about how to convert byte sequences to character | |
e19c3639 KH |
51 | sequences and vice versa. When we say "decode", it means converting |
52 | a byte sequence of a specific coding system into a character | |
53 | sequence that is represented by Emacs' internal coding system | |
54 | `emacs-utf-8', and when we say "encode", it means converting a | |
55 | character sequence of emacs-utf-8 to a byte sequence of a specific | |
0ef69138 | 56 | coding system. |
4ed46869 | 57 | |
e19c3639 KH |
58 | In Emacs Lisp, a coding system is represented by a Lisp symbol. In |
59 | C level, a coding system is represented by a vector of attributes | |
5bad0796 | 60 | stored in the hash table Vcharset_hash_table. The conversion from |
e19c3639 KH |
61 | coding system symbol to attributes vector is done by looking up |
62 | Vcharset_hash_table by the symbol. | |
4ed46869 | 63 | |
e19c3639 | 64 | Coding systems are classified into the following types depending on |
5bad0796 | 65 | the encoding mechanism. Here's a brief description of the types. |
4ed46869 | 66 | |
df7492f9 KH |
67 | o UTF-8 |
68 | ||
69 | o UTF-16 | |
70 | ||
71 | o Charset-base coding system | |
72 | ||
73 | A coding system defined by one or more (coded) character sets. | |
5bad0796 | 74 | Decoding and encoding are done by a code converter defined for each |
df7492f9 KH |
75 | character set. |
76 | ||
5bad0796 | 77 | o Old Emacs internal format (emacs-mule) |
df7492f9 | 78 | |
5bad0796 | 79 | The coding system adopted by old versions of Emacs (20 and 21). |
4ed46869 | 80 | |
df7492f9 | 81 | o ISO2022-base coding system |
4ed46869 KH |
82 | |
83 | The most famous coding system for multiple character sets. X's | |
df7492f9 KH |
84 | Compound Text, various EUCs (Extended Unix Code), and coding systems |
85 | used in the Internet communication such as ISO-2022-JP are all | |
86 | variants of ISO2022. | |
4ed46869 | 87 | |
df7492f9 | 88 | o SJIS (or Shift-JIS or MS-Kanji-Code) |
93dec019 | 89 | |
4ed46869 KH |
90 | A coding system to encode character sets: ASCII, JISX0201, and |
91 | JISX0208. Widely used for PC's in Japan. Details are described in | |
df7492f9 | 92 | section 8. |
4ed46869 | 93 | |
df7492f9 | 94 | o BIG5 |
4ed46869 | 95 | |
df7492f9 | 96 | A coding system to encode character sets: ASCII and Big5. Widely |
cfb43547 | 97 | used for Chinese (mainly in Taiwan and Hong Kong). Details are |
df7492f9 KH |
98 | described in section 8. In this file, when we write "big5" (all |
99 | lowercase), we mean the coding system, and when we write "Big5" | |
100 | (capitalized), we mean the character set. | |
4ed46869 | 101 | |
df7492f9 | 102 | o CCL |
27901516 | 103 | |
5bad0796 | 104 | If a user wants to decode/encode text encoded in a coding system |
df7492f9 KH |
105 | not listed above, he can supply a decoder and an encoder for it in |
106 | CCL (Code Conversion Language) programs. Emacs executes the CCL | |
107 | program while decoding/encoding. | |
27901516 | 108 | |
df7492f9 | 109 | o Raw-text |
4ed46869 | 110 | |
5a936b46 | 111 | A coding system for text containing raw eight-bit data. Emacs |
5bad0796 | 112 | treats each byte of source text as a character (except for |
df7492f9 | 113 | end-of-line conversion). |
4ed46869 | 114 | |
df7492f9 KH |
115 | o No-conversion |
116 | ||
117 | Like raw text, but don't do end-of-line conversion. | |
4ed46869 | 118 | |
4ed46869 | 119 | |
df7492f9 | 120 | END-OF-LINE FORMAT |
4ed46869 | 121 | |
5bad0796 | 122 | How text end-of-line is encoded depends on operating system. For |
df7492f9 | 123 | instance, Unix's format is just one byte of LF (line-feed) code, |
f4dee582 | 124 | whereas DOS's format is two-byte sequence of `carriage-return' and |
d46c5b12 KH |
125 | `line-feed' codes. MacOS's format is usually one byte of |
126 | `carriage-return'. | |
4ed46869 | 127 | |
cfb43547 | 128 | Since text character encoding and end-of-line encoding are |
df7492f9 KH |
129 | independent, any coding system described above can take any format |
130 | of end-of-line (except for no-conversion). | |
4ed46869 | 131 | |
e19c3639 KH |
132 | STRUCT CODING_SYSTEM |
133 | ||
134 | Before using a coding system for code conversion (i.e. decoding and | |
135 | encoding), we setup a structure of type `struct coding_system'. | |
136 | This structure keeps various information about a specific code | |
5bad0796 | 137 | conversion (e.g. the location of source and destination data). |
4ed46869 KH |
138 | |
139 | */ | |
140 | ||
df7492f9 KH |
141 | /* COMMON MACROS */ |
142 | ||
143 | ||
4ed46869 KH |
144 | /*** GENERAL NOTES on `detect_coding_XXX ()' functions *** |
145 | ||
df7492f9 | 146 | These functions check if a byte sequence specified as a source in |
ff0dacd7 KH |
147 | CODING conforms to the format of XXX, and update the members of |
148 | DETECT_INFO. | |
df7492f9 | 149 | |
ff0dacd7 | 150 | Return 1 if the byte sequence conforms to XXX, otherwise return 0. |
df7492f9 KH |
151 | |
152 | Below is the template of these functions. */ | |
153 | ||
4ed46869 | 154 | #if 0 |
df7492f9 | 155 | static int |
ff0dacd7 | 156 | detect_coding_XXX (coding, detect_info) |
df7492f9 | 157 | struct coding_system *coding; |
ff0dacd7 | 158 | struct coding_detection_info *detect_info; |
4ed46869 | 159 | { |
df7492f9 KH |
160 | unsigned char *src = coding->source; |
161 | unsigned char *src_end = coding->source + coding->src_bytes; | |
162 | int multibytep = coding->src_multibyte; | |
ff0dacd7 | 163 | int consumed_chars = 0; |
df7492f9 KH |
164 | int found = 0; |
165 | ...; | |
166 | ||
167 | while (1) | |
168 | { | |
169 | /* Get one byte from the source. If the souce is exausted, jump | |
170 | to no_more_source:. */ | |
171 | ONE_MORE_BYTE (c); | |
ff0dacd7 KH |
172 | |
173 | if (! __C_conforms_to_XXX___ (c)) | |
174 | break; | |
175 | if (! __C_strongly_suggests_XXX__ (c)) | |
176 | found = CATEGORY_MASK_XXX; | |
df7492f9 | 177 | } |
ff0dacd7 KH |
178 | /* The byte sequence is invalid for XXX. */ |
179 | detect_info->rejected |= CATEGORY_MASK_XXX; | |
df7492f9 | 180 | return 0; |
ff0dacd7 | 181 | |
df7492f9 | 182 | no_more_source: |
ff0dacd7 KH |
183 | /* The source exausted successfully. */ |
184 | detect_info->found |= found; | |
df7492f9 | 185 | return 1; |
4ed46869 KH |
186 | } |
187 | #endif | |
188 | ||
189 | /*** GENERAL NOTES on `decode_coding_XXX ()' functions *** | |
190 | ||
df7492f9 KH |
191 | These functions decode a byte sequence specified as a source by |
192 | CODING. The resulting multibyte text goes to a place pointed to by | |
193 | CODING->charbuf, the length of which should not exceed | |
194 | CODING->charbuf_size; | |
d46c5b12 | 195 | |
df7492f9 KH |
196 | These functions set the information of original and decoded texts in |
197 | CODING->consumed, CODING->consumed_char, and CODING->charbuf_used. | |
198 | They also set CODING->result to one of CODING_RESULT_XXX indicating | |
199 | how the decoding is finished. | |
d46c5b12 | 200 | |
df7492f9 | 201 | Below is the template of these functions. */ |
d46c5b12 | 202 | |
4ed46869 | 203 | #if 0 |
b73bfc1c | 204 | static void |
df7492f9 | 205 | decode_coding_XXXX (coding) |
4ed46869 | 206 | struct coding_system *coding; |
4ed46869 | 207 | { |
df7492f9 KH |
208 | unsigned char *src = coding->source + coding->consumed; |
209 | unsigned char *src_end = coding->source + coding->src_bytes; | |
210 | /* SRC_BASE remembers the start position in source in each loop. | |
211 | The loop will be exited when there's not enough source code, or | |
212 | when there's no room in CHARBUF for a decoded character. */ | |
213 | unsigned char *src_base; | |
214 | /* A buffer to produce decoded characters. */ | |
215 | int *charbuf = coding->charbuf; | |
216 | int *charbuf_end = charbuf + coding->charbuf_size; | |
217 | int multibytep = coding->src_multibyte; | |
218 | ||
219 | while (1) | |
220 | { | |
221 | src_base = src; | |
222 | if (charbuf < charbuf_end) | |
223 | /* No more room to produce a decoded character. */ | |
224 | break; | |
225 | ONE_MORE_BYTE (c); | |
226 | /* Decode it. */ | |
227 | } | |
228 | ||
229 | no_more_source: | |
230 | if (src_base < src_end | |
231 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
232 | /* If the source ends by partial bytes to construct a character, | |
233 | treat them as eight-bit raw data. */ | |
234 | while (src_base < src_end && charbuf < charbuf_end) | |
235 | *charbuf++ = *src_base++; | |
236 | /* Remember how many bytes and characters we consumed. If the | |
237 | source is multibyte, the bytes and chars are not identical. */ | |
238 | coding->consumed = coding->consumed_char = src_base - coding->source; | |
239 | /* Remember how many characters we produced. */ | |
240 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
241 | } |
242 | #endif | |
243 | ||
244 | /*** GENERAL NOTES on `encode_coding_XXX ()' functions *** | |
245 | ||
df7492f9 KH |
246 | These functions encode SRC_BYTES length text at SOURCE of Emacs' |
247 | internal multibyte format by CODING. The resulting byte sequence | |
b73bfc1c KH |
248 | goes to a place pointed to by DESTINATION, the length of which |
249 | should not exceed DST_BYTES. | |
d46c5b12 | 250 | |
df7492f9 KH |
251 | These functions set the information of original and encoded texts in |
252 | the members produced, produced_char, consumed, and consumed_char of | |
253 | the structure *CODING. They also set the member result to one of | |
254 | CODING_RESULT_XXX indicating how the encoding finished. | |
d46c5b12 | 255 | |
df7492f9 KH |
256 | DST_BYTES zero means that source area and destination area are |
257 | overlapped, which means that we can produce a encoded text until it | |
258 | reaches at the head of not-yet-encoded source text. | |
d46c5b12 | 259 | |
df7492f9 | 260 | Below is a template of these functions. */ |
4ed46869 | 261 | #if 0 |
b73bfc1c | 262 | static void |
df7492f9 | 263 | encode_coding_XXX (coding) |
4ed46869 | 264 | struct coding_system *coding; |
4ed46869 | 265 | { |
df7492f9 KH |
266 | int multibytep = coding->dst_multibyte; |
267 | int *charbuf = coding->charbuf; | |
268 | int *charbuf_end = charbuf->charbuf + coding->charbuf_used; | |
269 | unsigned char *dst = coding->destination + coding->produced; | |
270 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
271 | unsigned char *adjusted_dst_end = dst_end - _MAX_BYTES_PRODUCED_IN_LOOP_; | |
272 | int produced_chars = 0; | |
273 | ||
274 | for (; charbuf < charbuf_end && dst < adjusted_dst_end; charbuf++) | |
275 | { | |
276 | int c = *charbuf; | |
277 | /* Encode C into DST, and increment DST. */ | |
278 | } | |
279 | label_no_more_destination: | |
280 | /* How many chars and bytes we produced. */ | |
281 | coding->produced_char += produced_chars; | |
282 | coding->produced = dst - coding->destination; | |
4ed46869 KH |
283 | } |
284 | #endif | |
285 | ||
4ed46869 KH |
286 | \f |
287 | /*** 1. Preamble ***/ | |
288 | ||
68c45bf0 | 289 | #include <config.h> |
4ed46869 KH |
290 | #include <stdio.h> |
291 | ||
4ed46869 KH |
292 | #include "lisp.h" |
293 | #include "buffer.h" | |
df7492f9 | 294 | #include "character.h" |
4ed46869 KH |
295 | #include "charset.h" |
296 | #include "ccl.h" | |
df7492f9 | 297 | #include "composite.h" |
4ed46869 KH |
298 | #include "coding.h" |
299 | #include "window.h" | |
4ed46869 | 300 | |
df7492f9 | 301 | Lisp_Object Vcoding_system_hash_table; |
4ed46869 | 302 | |
df7492f9 | 303 | Lisp_Object Qcoding_system, Qcoding_aliases, Qeol_type; |
1965cb73 DL |
304 | Lisp_Object Qunix, Qdos; |
305 | extern Lisp_Object Qmac; /* frame.c */ | |
4ed46869 KH |
306 | Lisp_Object Qbuffer_file_coding_system; |
307 | Lisp_Object Qpost_read_conversion, Qpre_write_conversion; | |
df7492f9 | 308 | Lisp_Object Qdefault_char; |
27901516 | 309 | Lisp_Object Qno_conversion, Qundecided; |
df7492f9 | 310 | Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5; |
b49a1807 | 311 | Lisp_Object Qbig, Qlittle; |
bb0115a2 | 312 | Lisp_Object Qcoding_system_history; |
1397dc18 | 313 | Lisp_Object Qvalid_codes; |
01378f49 | 314 | Lisp_Object QCcategory; |
4ed46869 KH |
315 | |
316 | extern Lisp_Object Qinsert_file_contents, Qwrite_region; | |
317 | Lisp_Object Qcall_process, Qcall_process_region, Qprocess_argument; | |
318 | Lisp_Object Qstart_process, Qopen_network_stream; | |
319 | Lisp_Object Qtarget_idx; | |
320 | ||
5d5bf4d8 KH |
321 | int coding_system_require_warning; |
322 | ||
d46c5b12 KH |
323 | Lisp_Object Vselect_safe_coding_system_function; |
324 | ||
7722baf9 EZ |
325 | /* Mnemonic string for each format of end-of-line. */ |
326 | Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; | |
327 | /* Mnemonic string to indicate format of end-of-line is not yet | |
4ed46869 | 328 | decided. */ |
7722baf9 | 329 | Lisp_Object eol_mnemonic_undecided; |
4ed46869 KH |
330 | |
331 | #ifdef emacs | |
332 | ||
4608c386 KH |
333 | Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
334 | ||
335 | Lisp_Object Qcoding_system_p, Qcoding_system_error; | |
4ed46869 | 336 | |
d46c5b12 KH |
337 | /* Coding system emacs-mule and raw-text are for converting only |
338 | end-of-line format. */ | |
339 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 340 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 341 | |
4ed46869 KH |
342 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
343 | routines by the following three variables. */ | |
344 | /* Coding-system for reading files and receiving data from process. */ | |
345 | Lisp_Object Vcoding_system_for_read; | |
346 | /* Coding-system for writing files and sending data to process. */ | |
347 | Lisp_Object Vcoding_system_for_write; | |
348 | /* Coding-system actually used in the latest I/O. */ | |
349 | Lisp_Object Vlast_coding_system_used; | |
350 | ||
c4825358 | 351 | /* A vector of length 256 which contains information about special |
94487c4e | 352 | Latin codes (especially for dealing with Microsoft codes). */ |
3f003981 | 353 | Lisp_Object Vlatin_extra_code_table; |
c4825358 | 354 | |
9ce27fde KH |
355 | /* Flag to inhibit code conversion of end-of-line format. */ |
356 | int inhibit_eol_conversion; | |
357 | ||
74383408 KH |
358 | /* Flag to inhibit ISO2022 escape sequence detection. */ |
359 | int inhibit_iso_escape_detection; | |
360 | ||
ed29121d EZ |
361 | /* Flag to make buffer-file-coding-system inherit from process-coding. */ |
362 | int inherit_process_coding_system; | |
363 | ||
c4825358 | 364 | /* Coding system to be used to encode text for terminal display. */ |
4ed46869 KH |
365 | struct coding_system terminal_coding; |
366 | ||
c4825358 KH |
367 | /* Coding system to be used to encode text for terminal display when |
368 | terminal coding system is nil. */ | |
369 | struct coding_system safe_terminal_coding; | |
370 | ||
371 | /* Coding system of what is sent from terminal keyboard. */ | |
4ed46869 KH |
372 | struct coding_system keyboard_coding; |
373 | ||
02ba4723 KH |
374 | Lisp_Object Vfile_coding_system_alist; |
375 | Lisp_Object Vprocess_coding_system_alist; | |
376 | Lisp_Object Vnetwork_coding_system_alist; | |
4ed46869 | 377 | |
68c45bf0 PE |
378 | Lisp_Object Vlocale_coding_system; |
379 | ||
4ed46869 KH |
380 | #endif /* emacs */ |
381 | ||
f967223b KH |
382 | /* Flag to tell if we look up translation table on character code |
383 | conversion. */ | |
84fbb8a0 | 384 | Lisp_Object Venable_character_translation; |
f967223b KH |
385 | /* Standard translation table to look up on decoding (reading). */ |
386 | Lisp_Object Vstandard_translation_table_for_decode; | |
387 | /* Standard translation table to look up on encoding (writing). */ | |
388 | Lisp_Object Vstandard_translation_table_for_encode; | |
84fbb8a0 | 389 | |
f967223b KH |
390 | Lisp_Object Qtranslation_table; |
391 | Lisp_Object Qtranslation_table_id; | |
392 | Lisp_Object Qtranslation_table_for_decode; | |
393 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 KH |
394 | |
395 | /* Alist of charsets vs revision number. */ | |
df7492f9 | 396 | static Lisp_Object Vcharset_revision_table; |
4ed46869 | 397 | |
02ba4723 KH |
398 | /* Default coding systems used for process I/O. */ |
399 | Lisp_Object Vdefault_process_coding_system; | |
400 | ||
002fdb44 DL |
401 | /* Char table for translating Quail and self-inserting input. */ |
402 | Lisp_Object Vtranslation_table_for_input; | |
403 | ||
df7492f9 KH |
404 | /* Two special coding systems. */ |
405 | Lisp_Object Vsjis_coding_system; | |
406 | Lisp_Object Vbig5_coding_system; | |
407 | ||
408 | ||
ff0dacd7 KH |
409 | static int detect_coding_utf_8 P_ ((struct coding_system *, |
410 | struct coding_detection_info *info)); | |
df7492f9 KH |
411 | static void decode_coding_utf_8 P_ ((struct coding_system *)); |
412 | static int encode_coding_utf_8 P_ ((struct coding_system *)); | |
413 | ||
ff0dacd7 KH |
414 | static int detect_coding_utf_16 P_ ((struct coding_system *, |
415 | struct coding_detection_info *info)); | |
df7492f9 KH |
416 | static void decode_coding_utf_16 P_ ((struct coding_system *)); |
417 | static int encode_coding_utf_16 P_ ((struct coding_system *)); | |
418 | ||
ff0dacd7 KH |
419 | static int detect_coding_iso_2022 P_ ((struct coding_system *, |
420 | struct coding_detection_info *info)); | |
df7492f9 KH |
421 | static void decode_coding_iso_2022 P_ ((struct coding_system *)); |
422 | static int encode_coding_iso_2022 P_ ((struct coding_system *)); | |
423 | ||
ff0dacd7 KH |
424 | static int detect_coding_emacs_mule P_ ((struct coding_system *, |
425 | struct coding_detection_info *info)); | |
df7492f9 KH |
426 | static void decode_coding_emacs_mule P_ ((struct coding_system *)); |
427 | static int encode_coding_emacs_mule P_ ((struct coding_system *)); | |
428 | ||
ff0dacd7 KH |
429 | static int detect_coding_sjis P_ ((struct coding_system *, |
430 | struct coding_detection_info *info)); | |
df7492f9 KH |
431 | static void decode_coding_sjis P_ ((struct coding_system *)); |
432 | static int encode_coding_sjis P_ ((struct coding_system *)); | |
433 | ||
ff0dacd7 KH |
434 | static int detect_coding_big5 P_ ((struct coding_system *, |
435 | struct coding_detection_info *info)); | |
df7492f9 KH |
436 | static void decode_coding_big5 P_ ((struct coding_system *)); |
437 | static int encode_coding_big5 P_ ((struct coding_system *)); | |
438 | ||
ff0dacd7 KH |
439 | static int detect_coding_ccl P_ ((struct coding_system *, |
440 | struct coding_detection_info *info)); | |
df7492f9 KH |
441 | static void decode_coding_ccl P_ ((struct coding_system *)); |
442 | static int encode_coding_ccl P_ ((struct coding_system *)); | |
443 | ||
444 | static void decode_coding_raw_text P_ ((struct coding_system *)); | |
445 | static int encode_coding_raw_text P_ ((struct coding_system *)); | |
446 | ||
447 | ||
448 | /* ISO2022 section */ | |
449 | ||
450 | #define CODING_ISO_INITIAL(coding, reg) \ | |
451 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
452 | coding_attr_iso_initial), \ | |
453 | reg))) | |
454 | ||
455 | ||
456 | #define CODING_ISO_REQUEST(coding, charset_id) \ | |
457 | ((charset_id <= (coding)->max_charset_id \ | |
458 | ? (coding)->safe_charsets[charset_id] \ | |
459 | : -1)) | |
460 | ||
461 | ||
462 | #define CODING_ISO_FLAGS(coding) \ | |
463 | ((coding)->spec.iso_2022.flags) | |
464 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
465 | ((coding)->spec.iso_2022.current_designation[reg]) | |
466 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
467 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
468 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
469 | ((coding)->spec.iso_2022.single_shifting) | |
470 | #define CODING_ISO_BOL(coding) \ | |
471 | ((coding)->spec.iso_2022.bol) | |
472 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
473 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
474 | ||
475 | /* Control characters of ISO2022. */ | |
476 | /* code */ /* function */ | |
477 | #define ISO_CODE_LF 0x0A /* line-feed */ | |
478 | #define ISO_CODE_CR 0x0D /* carriage-return */ | |
479 | #define ISO_CODE_SO 0x0E /* shift-out */ | |
480 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
481 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
482 | #define ISO_CODE_ESC 0x1B /* escape */ | |
483 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
484 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
485 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
486 | ||
487 | /* All code (1-byte) of ISO2022 is classified into one of the | |
488 | followings. */ | |
489 | enum iso_code_class_type | |
490 | { | |
491 | ISO_control_0, /* Control codes in the range | |
492 | 0x00..0x1F and 0x7F, except for the | |
493 | following 5 codes. */ | |
494 | ISO_carriage_return, /* ISO_CODE_CR (0x0D) */ | |
495 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ | |
496 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
497 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
498 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
499 | ISO_control_1, /* Control codes in the range | |
500 | 0x80..0x9F, except for the | |
501 | following 3 codes. */ | |
502 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
503 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
504 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
505 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
506 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
507 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
508 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
509 | }; | |
05e6f5dc | 510 | |
df7492f9 KH |
511 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
512 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 513 | |
df7492f9 KH |
514 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
515 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
516 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 517 | |
df7492f9 KH |
518 | /* If set, reset graphic planes and registers at end-of-line to the |
519 | initial state. */ | |
520 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 521 | |
df7492f9 KH |
522 | /* If set, reset graphic planes and registers before any control |
523 | characters to the initial state. */ | |
524 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 525 | |
df7492f9 KH |
526 | /* If set, encode by 7-bit environment. */ |
527 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 528 | |
df7492f9 KH |
529 | /* If set, use locking-shift function. */ |
530 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 531 | |
df7492f9 KH |
532 | /* If set, use single-shift function. Overwrite |
533 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
534 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 535 | |
df7492f9 KH |
536 | /* If set, use designation escape sequence. */ |
537 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 538 | |
df7492f9 KH |
539 | /* If set, produce revision number sequence. */ |
540 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 541 | |
df7492f9 KH |
542 | /* If set, produce ISO6429's direction specifying sequence. */ |
543 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 544 | |
df7492f9 KH |
545 | /* If set, assume designation states are reset at beginning of line on |
546 | output. */ | |
547 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 548 | |
df7492f9 KH |
549 | /* If set, designation sequence should be placed at beginning of line |
550 | on output. */ | |
551 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 552 | |
df7492f9 KH |
553 | /* If set, do not encode unsafe charactes on output. */ |
554 | #define CODING_ISO_FLAG_SAFE 0x0800 | |
aa72b389 | 555 | |
df7492f9 KH |
556 | /* If set, extra latin codes (128..159) are accepted as a valid code |
557 | on input. */ | |
558 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 559 | |
df7492f9 | 560 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 561 | |
df7492f9 | 562 | #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 |
aa72b389 | 563 | |
bf16eb23 | 564 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 565 | |
bf16eb23 | 566 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 567 | |
bf16eb23 | 568 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 569 | |
df7492f9 KH |
570 | /* A character to be produced on output if encoding of the original |
571 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
572 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 573 | |
4ed46869 | 574 | |
df7492f9 KH |
575 | /* UTF-16 section */ |
576 | #define CODING_UTF_16_BOM(coding) \ | |
577 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 578 | |
df7492f9 KH |
579 | #define CODING_UTF_16_ENDIAN(coding) \ |
580 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 581 | |
df7492f9 KH |
582 | #define CODING_UTF_16_SURROGATE(coding) \ |
583 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 584 | |
4ed46869 | 585 | |
df7492f9 KH |
586 | /* CCL section */ |
587 | #define CODING_CCL_DECODER(coding) \ | |
588 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
589 | #define CODING_CCL_ENCODER(coding) \ | |
590 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
591 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 592 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 593 | |
5a936b46 | 594 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 595 | |
df7492f9 KH |
596 | enum coding_category |
597 | { | |
598 | coding_category_iso_7, | |
599 | coding_category_iso_7_tight, | |
600 | coding_category_iso_8_1, | |
601 | coding_category_iso_8_2, | |
602 | coding_category_iso_7_else, | |
603 | coding_category_iso_8_else, | |
604 | coding_category_utf_8, | |
605 | coding_category_utf_16_auto, | |
606 | coding_category_utf_16_be, | |
607 | coding_category_utf_16_le, | |
608 | coding_category_utf_16_be_nosig, | |
609 | coding_category_utf_16_le_nosig, | |
610 | coding_category_charset, | |
611 | coding_category_sjis, | |
612 | coding_category_big5, | |
613 | coding_category_ccl, | |
614 | coding_category_emacs_mule, | |
615 | /* All above are targets of code detection. */ | |
616 | coding_category_raw_text, | |
617 | coding_category_undecided, | |
618 | coding_category_max | |
619 | }; | |
620 | ||
621 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
622 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
623 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
624 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
625 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
626 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
627 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
628 | #define CATEGORY_MASK_UTF_8 (1 << coding_category_utf_8) | |
b49a1807 | 629 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
630 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
631 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
632 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
633 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
634 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
635 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
636 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
637 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
638 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 639 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
640 | |
641 | /* This value is returned if detect_coding_mask () find nothing other | |
642 | than ASCII characters. */ | |
643 | #define CATEGORY_MASK_ANY \ | |
644 | (CATEGORY_MASK_ISO_7 \ | |
645 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
646 | | CATEGORY_MASK_ISO_8_1 \ | |
647 | | CATEGORY_MASK_ISO_8_2 \ | |
648 | | CATEGORY_MASK_ISO_7_ELSE \ | |
649 | | CATEGORY_MASK_ISO_8_ELSE \ | |
650 | | CATEGORY_MASK_UTF_8 \ | |
651 | | CATEGORY_MASK_UTF_16_BE \ | |
652 | | CATEGORY_MASK_UTF_16_LE \ | |
653 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
654 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
655 | | CATEGORY_MASK_CHARSET \ | |
656 | | CATEGORY_MASK_SJIS \ | |
657 | | CATEGORY_MASK_BIG5 \ | |
658 | | CATEGORY_MASK_CCL \ | |
659 | | CATEGORY_MASK_EMACS_MULE) | |
660 | ||
661 | ||
662 | #define CATEGORY_MASK_ISO_7BIT \ | |
663 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
664 | ||
665 | #define CATEGORY_MASK_ISO_8BIT \ | |
666 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
667 | ||
668 | #define CATEGORY_MASK_ISO_ELSE \ | |
669 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
670 | ||
671 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
672 | (CATEGORY_MASK_ISO_7 \ | |
673 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
674 | | CATEGORY_MASK_ISO_7_ELSE \ | |
675 | | CATEGORY_MASK_ISO_8_ELSE) | |
676 | ||
677 | #define CATEGORY_MASK_ISO \ | |
678 | ( CATEGORY_MASK_ISO_7BIT \ | |
679 | | CATEGORY_MASK_ISO_8BIT \ | |
680 | | CATEGORY_MASK_ISO_ELSE) | |
681 | ||
682 | #define CATEGORY_MASK_UTF_16 \ | |
683 | (CATEGORY_MASK_UTF_16_BE \ | |
684 | | CATEGORY_MASK_UTF_16_LE \ | |
685 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
686 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
687 | ||
688 | ||
689 | /* List of symbols `coding-category-xxx' ordered by priority. This | |
690 | variable is exposed to Emacs Lisp. */ | |
691 | static Lisp_Object Vcoding_category_list; | |
692 | ||
693 | /* Table of coding categories (Lisp symbols). This variable is for | |
694 | internal use oly. */ | |
695 | static Lisp_Object Vcoding_category_table; | |
696 | ||
697 | /* Table of coding-categories ordered by priority. */ | |
698 | static enum coding_category coding_priorities[coding_category_max]; | |
699 | ||
700 | /* Nth element is a coding context for the coding system bound to the | |
701 | Nth coding category. */ | |
702 | static struct coding_system coding_categories[coding_category_max]; | |
703 | ||
df7492f9 KH |
704 | /*** Commonly used macros and functions ***/ |
705 | ||
706 | #ifndef min | |
707 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
708 | #endif | |
709 | #ifndef max | |
710 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
711 | #endif | |
4ed46869 | 712 | |
df7492f9 KH |
713 | #define CODING_GET_INFO(coding, attrs, eol_type, charset_list) \ |
714 | do { \ | |
715 | attrs = CODING_ID_ATTRS (coding->id); \ | |
716 | eol_type = CODING_ID_EOL_TYPE (coding->id); \ | |
717 | if (VECTORP (eol_type)) \ | |
718 | eol_type = Qunix; \ | |
719 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); \ | |
720 | } while (0) | |
4ed46869 | 721 | |
4ed46869 | 722 | |
df7492f9 KH |
723 | /* Safely get one byte from the source text pointed by SRC which ends |
724 | at SRC_END, and set C to that byte. If there are not enough bytes | |
725 | in the source, it jumps to `no_more_source'. The caller | |
726 | should declare and set these variables appropriately in advance: | |
727 | src, src_end, multibytep | |
728 | */ | |
aa72b389 | 729 | |
df7492f9 | 730 | #define ONE_MORE_BYTE(c) \ |
aa72b389 | 731 | do { \ |
df7492f9 KH |
732 | if (src == src_end) \ |
733 | { \ | |
734 | if (src_base < src) \ | |
735 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; \ | |
736 | goto no_more_source; \ | |
737 | } \ | |
738 | c = *src++; \ | |
739 | if (multibytep && (c & 0x80)) \ | |
740 | { \ | |
741 | if ((c & 0xFE) != 0xC0) \ | |
742 | error ("Undecodable char found"); \ | |
743 | c = ((c & 1) << 6) | *src++; \ | |
744 | } \ | |
745 | consumed_chars++; \ | |
aa72b389 KH |
746 | } while (0) |
747 | ||
aa72b389 | 748 | |
df7492f9 KH |
749 | #define ONE_MORE_BYTE_NO_CHECK(c) \ |
750 | do { \ | |
751 | c = *src++; \ | |
752 | if (multibytep && (c & 0x80)) \ | |
753 | { \ | |
754 | if ((c & 0xFE) != 0xC0) \ | |
755 | error ("Undecodable char found"); \ | |
756 | c = ((c & 1) << 6) | *src++; \ | |
757 | } \ | |
781d7a48 | 758 | consumed_chars++; \ |
aa72b389 KH |
759 | } while (0) |
760 | ||
aa72b389 | 761 | |
df7492f9 KH |
762 | /* Store a byte C in the place pointed by DST and increment DST to the |
763 | next free point, and increment PRODUCED_CHARS. The caller should | |
764 | assure that C is 0..127, and declare and set the variable `dst' | |
765 | appropriately in advance. | |
766 | */ | |
aa72b389 KH |
767 | |
768 | ||
df7492f9 KH |
769 | #define EMIT_ONE_ASCII_BYTE(c) \ |
770 | do { \ | |
771 | produced_chars++; \ | |
772 | *dst++ = (c); \ | |
b6871cc7 | 773 | } while (0) |
aa72b389 KH |
774 | |
775 | ||
df7492f9 | 776 | /* Like EMIT_ONE_ASCII_BYTE byt store two bytes; C1 and C2. */ |
aa72b389 | 777 | |
df7492f9 KH |
778 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
779 | do { \ | |
780 | produced_chars += 2; \ | |
781 | *dst++ = (c1), *dst++ = (c2); \ | |
782 | } while (0) | |
aa72b389 KH |
783 | |
784 | ||
df7492f9 KH |
785 | /* Store a byte C in the place pointed by DST and increment DST to the |
786 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is | |
787 | nonzero, store in an appropriate multibyte from. The caller should | |
788 | declare and set the variables `dst' and `multibytep' appropriately | |
789 | in advance. */ | |
790 | ||
791 | #define EMIT_ONE_BYTE(c) \ | |
792 | do { \ | |
793 | produced_chars++; \ | |
794 | if (multibytep) \ | |
795 | { \ | |
796 | int ch = (c); \ | |
797 | if (ch >= 0x80) \ | |
798 | ch = BYTE8_TO_CHAR (ch); \ | |
799 | CHAR_STRING_ADVANCE (ch, dst); \ | |
800 | } \ | |
801 | else \ | |
802 | *dst++ = (c); \ | |
aa72b389 | 803 | } while (0) |
aa72b389 | 804 | |
aa72b389 | 805 | |
df7492f9 | 806 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 807 | |
e19c3639 KH |
808 | #define EMIT_TWO_BYTES(c1, c2) \ |
809 | do { \ | |
810 | produced_chars += 2; \ | |
811 | if (multibytep) \ | |
812 | { \ | |
813 | int ch; \ | |
814 | \ | |
815 | ch = (c1); \ | |
816 | if (ch >= 0x80) \ | |
817 | ch = BYTE8_TO_CHAR (ch); \ | |
818 | CHAR_STRING_ADVANCE (ch, dst); \ | |
819 | ch = (c2); \ | |
820 | if (ch >= 0x80) \ | |
821 | ch = BYTE8_TO_CHAR (ch); \ | |
822 | CHAR_STRING_ADVANCE (ch, dst); \ | |
823 | } \ | |
824 | else \ | |
825 | { \ | |
826 | *dst++ = (c1); \ | |
827 | *dst++ = (c2); \ | |
828 | } \ | |
aa72b389 KH |
829 | } while (0) |
830 | ||
831 | ||
df7492f9 KH |
832 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
833 | do { \ | |
834 | EMIT_ONE_BYTE (c1); \ | |
835 | EMIT_TWO_BYTES (c2, c3); \ | |
836 | } while (0) | |
aa72b389 | 837 | |
aa72b389 | 838 | |
df7492f9 KH |
839 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
840 | do { \ | |
841 | EMIT_TWO_BYTES (c1, c2); \ | |
842 | EMIT_TWO_BYTES (c3, c4); \ | |
843 | } while (0) | |
aa72b389 | 844 | |
aa72b389 | 845 | |
df7492f9 KH |
846 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
847 | do { \ | |
848 | charset_map_loaded = 0; \ | |
849 | c = DECODE_CHAR (charset, code); \ | |
850 | if (charset_map_loaded) \ | |
851 | { \ | |
8f924df7 | 852 | const unsigned char *orig = coding->source; \ |
df7492f9 KH |
853 | EMACS_INT offset; \ |
854 | \ | |
855 | coding_set_source (coding); \ | |
856 | offset = coding->source - orig; \ | |
857 | src += offset; \ | |
858 | src_base += offset; \ | |
859 | src_end += offset; \ | |
860 | } \ | |
aa72b389 KH |
861 | } while (0) |
862 | ||
863 | ||
df7492f9 KH |
864 | #define ASSURE_DESTINATION(bytes) \ |
865 | do { \ | |
866 | if (dst + (bytes) >= dst_end) \ | |
867 | { \ | |
868 | int more_bytes = charbuf_end - charbuf + (bytes); \ | |
869 | \ | |
870 | dst = alloc_destination (coding, more_bytes, dst); \ | |
871 | dst_end = coding->destination + coding->dst_bytes; \ | |
872 | } \ | |
873 | } while (0) | |
aa72b389 | 874 | |
aa72b389 | 875 | |
aa72b389 | 876 | |
df7492f9 KH |
877 | static void |
878 | coding_set_source (coding) | |
aa72b389 | 879 | struct coding_system *coding; |
aa72b389 | 880 | { |
df7492f9 KH |
881 | if (BUFFERP (coding->src_object)) |
882 | { | |
2cb26057 | 883 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 884 | |
df7492f9 | 885 | if (coding->src_pos < 0) |
2cb26057 | 886 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 887 | else |
2cb26057 | 888 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 889 | } |
df7492f9 | 890 | else if (STRINGP (coding->src_object)) |
aa72b389 | 891 | { |
8f924df7 | 892 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 893 | } |
df7492f9 KH |
894 | else |
895 | /* Otherwise, the source is C string and is never relocated | |
896 | automatically. Thus we don't have to update anything. */ | |
897 | ; | |
898 | } | |
aa72b389 | 899 | |
df7492f9 KH |
900 | static void |
901 | coding_set_destination (coding) | |
902 | struct coding_system *coding; | |
903 | { | |
904 | if (BUFFERP (coding->dst_object)) | |
aa72b389 | 905 | { |
df7492f9 | 906 | if (coding->src_pos < 0) |
aa72b389 | 907 | { |
28f67a95 KH |
908 | coding->destination = BEG_ADDR + coding->dst_pos_byte - 1; |
909 | coding->dst_bytes = (GAP_END_ADDR | |
910 | - (coding->src_bytes - coding->consumed) | |
911 | - coding->destination); | |
aa72b389 | 912 | } |
df7492f9 | 913 | else |
28f67a95 KH |
914 | { |
915 | /* We are sure that coding->dst_pos_byte is before the gap | |
916 | of the buffer. */ | |
917 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
918 | + coding->dst_pos_byte - 1); | |
919 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) | |
920 | - coding->destination); | |
921 | } | |
df7492f9 KH |
922 | } |
923 | else | |
924 | /* Otherwise, the destination is C string and is never relocated | |
925 | automatically. Thus we don't have to update anything. */ | |
926 | ; | |
927 | } | |
928 | ||
929 | ||
930 | static void | |
931 | coding_alloc_by_realloc (coding, bytes) | |
932 | struct coding_system *coding; | |
933 | EMACS_INT bytes; | |
934 | { | |
935 | coding->destination = (unsigned char *) xrealloc (coding->destination, | |
936 | coding->dst_bytes + bytes); | |
937 | coding->dst_bytes += bytes; | |
938 | } | |
939 | ||
940 | static void | |
941 | coding_alloc_by_making_gap (coding, bytes) | |
942 | struct coding_system *coding; | |
943 | EMACS_INT bytes; | |
944 | { | |
2c78b7e1 KH |
945 | if (BUFFERP (coding->dst_object) |
946 | && EQ (coding->src_object, coding->dst_object)) | |
df7492f9 KH |
947 | { |
948 | EMACS_INT add = coding->src_bytes - coding->consumed; | |
949 | ||
950 | GAP_SIZE -= add; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
951 | make_gap (bytes); | |
952 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
953 | } | |
954 | else | |
955 | { | |
2c78b7e1 KH |
956 | Lisp_Object this_buffer; |
957 | ||
958 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
959 | set_buffer_internal (XBUFFER (coding->dst_object)); |
960 | make_gap (bytes); | |
961 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 962 | } |
df7492f9 | 963 | } |
8f924df7 | 964 | |
df7492f9 KH |
965 | |
966 | static unsigned char * | |
967 | alloc_destination (coding, nbytes, dst) | |
968 | struct coding_system *coding; | |
3e139625 | 969 | EMACS_INT nbytes; |
df7492f9 KH |
970 | unsigned char *dst; |
971 | { | |
972 | EMACS_INT offset = dst - coding->destination; | |
973 | ||
974 | if (BUFFERP (coding->dst_object)) | |
975 | coding_alloc_by_making_gap (coding, nbytes); | |
aa72b389 | 976 | else |
df7492f9 KH |
977 | coding_alloc_by_realloc (coding, nbytes); |
978 | coding->result = CODING_RESULT_SUCCESS; | |
979 | coding_set_destination (coding); | |
980 | dst = coding->destination + offset; | |
981 | return dst; | |
982 | } | |
aa72b389 | 983 | |
ff0dacd7 KH |
984 | /** Macros for annotations. */ |
985 | ||
986 | /* Maximum length of annotation data (sum of annotations for | |
987 | composition and charset). */ | |
988 | #define MAX_ANNOTATION_LENGTH (5 + (MAX_COMPOSITION_COMPONENTS * 2) - 1 + 5) | |
989 | ||
990 | /* An annotation data is stored in the array coding->charbuf in this | |
991 | format: | |
992 | [ -LENGTH ANNOTATION_MASK FROM TO ... ] | |
993 | LENGTH is the number of elements in the annotation. | |
994 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
995 | FROM and TO specify the range of text annotated. They are relative | |
996 | to coding->src_pos (on encoding) or coding->dst_pos (on decoding). | |
997 | ||
998 | The format of the following elements depend on ANNOTATION_MASK. | |
999 | ||
1000 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1001 | follows: | |
1002 | ... METHOD [ COMPOSITION-COMPONENTS ... ] | |
1003 | METHOD is one of enum composition_method. | |
1004 | Optionnal COMPOSITION-COMPONENTS are characters and composition | |
1005 | rules. | |
1006 | ||
1007 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
1008 | follows. */ | |
1009 | ||
1010 | #define ADD_ANNOTATION_DATA(buf, len, mask, from, to) \ | |
1011 | do { \ | |
1012 | *(buf)++ = -(len); \ | |
1013 | *(buf)++ = (mask); \ | |
1014 | *(buf)++ = (from); \ | |
1015 | *(buf)++ = (to); \ | |
1016 | coding->annotated = 1; \ | |
1017 | } while (0); | |
1018 | ||
1019 | #define ADD_COMPOSITION_DATA(buf, from, to, method) \ | |
1020 | do { \ | |
1021 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, from, to); \ | |
1022 | *buf++ = method; \ | |
1023 | } while (0) | |
1024 | ||
1025 | ||
1026 | #define ADD_CHARSET_DATA(buf, from, to, id) \ | |
1027 | do { \ | |
1028 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_CHARSET_MASK, from, to); \ | |
1029 | *buf++ = id; \ | |
1030 | } while (0) | |
1031 | ||
df7492f9 KH |
1032 | \f |
1033 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1034 | ||
1035 | ||
1036 | ||
1037 | \f | |
1038 | /*** 3. UTF-8 ***/ | |
1039 | ||
1040 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1041 | Check if a text is encoded in UTF-8. If it is, return 1, else |
1042 | return 0. */ | |
df7492f9 KH |
1043 | |
1044 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1045 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1046 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1047 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1048 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1049 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1050 | ||
1051 | static int | |
ff0dacd7 | 1052 | detect_coding_utf_8 (coding, detect_info) |
df7492f9 | 1053 | struct coding_system *coding; |
ff0dacd7 | 1054 | struct coding_detection_info *detect_info; |
df7492f9 | 1055 | { |
8f924df7 KH |
1056 | const unsigned char *src = coding->source, *src_base = src; |
1057 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
1058 | int multibytep = coding->src_multibyte; |
1059 | int consumed_chars = 0; | |
1060 | int found = 0; | |
89528eb3 | 1061 | int incomplete; |
df7492f9 | 1062 | |
ff0dacd7 | 1063 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1064 | /* A coding system of this category is always ASCII compatible. */ |
1065 | src += coding->head_ascii; | |
1066 | ||
1067 | while (1) | |
aa72b389 | 1068 | { |
df7492f9 | 1069 | int c, c1, c2, c3, c4; |
aa72b389 | 1070 | |
89528eb3 | 1071 | incomplete = 0; |
df7492f9 KH |
1072 | ONE_MORE_BYTE (c); |
1073 | if (UTF_8_1_OCTET_P (c)) | |
1074 | continue; | |
89528eb3 | 1075 | incomplete = 1; |
df7492f9 KH |
1076 | ONE_MORE_BYTE (c1); |
1077 | if (! UTF_8_EXTRA_OCTET_P (c1)) | |
1078 | break; | |
1079 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1080 | { |
ff0dacd7 | 1081 | found = CATEGORY_MASK_UTF_8; |
df7492f9 | 1082 | continue; |
aa72b389 | 1083 | } |
df7492f9 KH |
1084 | ONE_MORE_BYTE (c2); |
1085 | if (! UTF_8_EXTRA_OCTET_P (c2)) | |
1086 | break; | |
1087 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1088 | { |
ff0dacd7 | 1089 | found = CATEGORY_MASK_UTF_8; |
df7492f9 | 1090 | continue; |
aa72b389 | 1091 | } |
df7492f9 KH |
1092 | ONE_MORE_BYTE (c3); |
1093 | if (! UTF_8_EXTRA_OCTET_P (c3)) | |
1094 | break; | |
1095 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1096 | { |
ff0dacd7 | 1097 | found = CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1098 | continue; |
1099 | } | |
1100 | ONE_MORE_BYTE (c4); | |
1101 | if (! UTF_8_EXTRA_OCTET_P (c4)) | |
1102 | break; | |
1103 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1104 | { | |
ff0dacd7 | 1105 | found = CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1106 | continue; |
1107 | } | |
1108 | break; | |
aa72b389 | 1109 | } |
ff0dacd7 | 1110 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1111 | return 0; |
aa72b389 | 1112 | |
df7492f9 | 1113 | no_more_source: |
89528eb3 | 1114 | if (incomplete && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1115 | { |
ff0dacd7 | 1116 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1117 | return 0; |
aa72b389 | 1118 | } |
ff0dacd7 KH |
1119 | detect_info->found |= found; |
1120 | return 1; | |
aa72b389 KH |
1121 | } |
1122 | ||
4ed46869 | 1123 | |
b73bfc1c | 1124 | static void |
df7492f9 | 1125 | decode_coding_utf_8 (coding) |
b73bfc1c | 1126 | struct coding_system *coding; |
b73bfc1c | 1127 | { |
8f924df7 KH |
1128 | const unsigned char *src = coding->source + coding->consumed; |
1129 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1130 | const unsigned char *src_base; | |
df7492f9 KH |
1131 | int *charbuf = coding->charbuf; |
1132 | int *charbuf_end = charbuf + coding->charbuf_size; | |
1133 | int consumed_chars = 0, consumed_chars_base; | |
1134 | int multibytep = coding->src_multibyte; | |
1135 | Lisp_Object attr, eol_type, charset_list; | |
4ed46869 | 1136 | |
df7492f9 KH |
1137 | CODING_GET_INFO (coding, attr, eol_type, charset_list); |
1138 | ||
1139 | while (1) | |
b73bfc1c | 1140 | { |
df7492f9 | 1141 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1142 | |
df7492f9 KH |
1143 | src_base = src; |
1144 | consumed_chars_base = consumed_chars; | |
4af310db | 1145 | |
df7492f9 KH |
1146 | if (charbuf >= charbuf_end) |
1147 | break; | |
1148 | ||
1149 | ONE_MORE_BYTE (c1); | |
1150 | if (UTF_8_1_OCTET_P(c1)) | |
1151 | { | |
1152 | c = c1; | |
1153 | if (c == '\r') | |
4af310db | 1154 | { |
df7492f9 | 1155 | if (EQ (eol_type, Qdos)) |
4af310db | 1156 | { |
df7492f9 | 1157 | if (src == src_end) |
98725083 KH |
1158 | { |
1159 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; | |
1160 | goto no_more_source; | |
1161 | } | |
df7492f9 KH |
1162 | if (*src == '\n') |
1163 | ONE_MORE_BYTE (c); | |
4af310db | 1164 | } |
df7492f9 KH |
1165 | else if (EQ (eol_type, Qmac)) |
1166 | c = '\n'; | |
4af310db | 1167 | } |
4af310db | 1168 | } |
df7492f9 | 1169 | else |
4af310db | 1170 | { |
df7492f9 KH |
1171 | ONE_MORE_BYTE (c2); |
1172 | if (! UTF_8_EXTRA_OCTET_P (c2)) | |
1173 | goto invalid_code; | |
1174 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1175 | { |
b0edb2c5 DL |
1176 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1177 | /* Reject overlong sequences here and below. Encoders | |
1178 | producing them are incorrect, they can be misleading, | |
1179 | and they mess up read/write invariance. */ | |
1180 | if (c < 128) | |
1181 | goto invalid_code; | |
4af310db | 1182 | } |
df7492f9 | 1183 | else |
aa72b389 | 1184 | { |
df7492f9 KH |
1185 | ONE_MORE_BYTE (c3); |
1186 | if (! UTF_8_EXTRA_OCTET_P (c3)) | |
1187 | goto invalid_code; | |
1188 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1189 | { |
1190 | c = (((c1 & 0xF) << 12) | |
1191 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1192 | if (c < 0x800 |
1193 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1194 | goto invalid_code; |
1195 | } | |
df7492f9 KH |
1196 | else |
1197 | { | |
1198 | ONE_MORE_BYTE (c4); | |
1199 | if (! UTF_8_EXTRA_OCTET_P (c4)) | |
1200 | goto invalid_code; | |
1201 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1202 | { |
df7492f9 KH |
1203 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1204 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1205 | if (c < 0x10000) |
1206 | goto invalid_code; | |
1207 | } | |
df7492f9 KH |
1208 | else |
1209 | { | |
1210 | ONE_MORE_BYTE (c5); | |
1211 | if (! UTF_8_EXTRA_OCTET_P (c5)) | |
1212 | goto invalid_code; | |
1213 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1214 | { | |
1215 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1216 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1217 | | (c5 & 0x3F)); | |
b0edb2c5 | 1218 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1219 | goto invalid_code; |
1220 | } | |
1221 | else | |
1222 | goto invalid_code; | |
1223 | } | |
1224 | } | |
aa72b389 | 1225 | } |
b73bfc1c | 1226 | } |
df7492f9 KH |
1227 | |
1228 | *charbuf++ = c; | |
1229 | continue; | |
1230 | ||
1231 | invalid_code: | |
1232 | src = src_base; | |
1233 | consumed_chars = consumed_chars_base; | |
1234 | ONE_MORE_BYTE (c); | |
1235 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1236 | coding->errors++; | |
aa72b389 KH |
1237 | } |
1238 | ||
df7492f9 KH |
1239 | no_more_source: |
1240 | coding->consumed_char += consumed_chars_base; | |
1241 | coding->consumed = src_base - coding->source; | |
1242 | coding->charbuf_used = charbuf - coding->charbuf; | |
1243 | } | |
1244 | ||
1245 | ||
1246 | static int | |
1247 | encode_coding_utf_8 (coding) | |
1248 | struct coding_system *coding; | |
1249 | { | |
1250 | int multibytep = coding->dst_multibyte; | |
1251 | int *charbuf = coding->charbuf; | |
1252 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1253 | unsigned char *dst = coding->destination + coding->produced; | |
1254 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
e19c3639 | 1255 | int produced_chars = 0; |
df7492f9 KH |
1256 | int c; |
1257 | ||
1258 | if (multibytep) | |
aa72b389 | 1259 | { |
df7492f9 KH |
1260 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1261 | ||
1262 | while (charbuf < charbuf_end) | |
b73bfc1c | 1263 | { |
df7492f9 | 1264 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1265 | |
df7492f9 KH |
1266 | ASSURE_DESTINATION (safe_room); |
1267 | c = *charbuf++; | |
28f67a95 KH |
1268 | if (CHAR_BYTE8_P (c)) |
1269 | { | |
1270 | c = CHAR_TO_BYTE8 (c); | |
1271 | EMIT_ONE_BYTE (c); | |
1272 | } | |
1273 | else | |
1274 | { | |
1275 | CHAR_STRING_ADVANCE (c, pend); | |
1276 | for (p = str; p < pend; p++) | |
1277 | EMIT_ONE_BYTE (*p); | |
1278 | } | |
b73bfc1c | 1279 | } |
aa72b389 | 1280 | } |
df7492f9 KH |
1281 | else |
1282 | { | |
1283 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1284 | ||
1285 | while (charbuf < charbuf_end) | |
b73bfc1c | 1286 | { |
df7492f9 KH |
1287 | ASSURE_DESTINATION (safe_room); |
1288 | c = *charbuf++; | |
1289 | dst += CHAR_STRING (c, dst); | |
1290 | produced_chars++; | |
4ed46869 KH |
1291 | } |
1292 | } | |
df7492f9 KH |
1293 | coding->result = CODING_RESULT_SUCCESS; |
1294 | coding->produced_char += produced_chars; | |
1295 | coding->produced = dst - coding->destination; | |
1296 | return 0; | |
4ed46869 KH |
1297 | } |
1298 | ||
b73bfc1c | 1299 | |
df7492f9 | 1300 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
1301 | Check if a text is encoded in one of UTF-16 based coding systems. |
1302 | If it is, return 1, else return 0. */ | |
aa72b389 | 1303 | |
df7492f9 KH |
1304 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1305 | (((val) & 0xFC00) == 0xD800) | |
1306 | ||
1307 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1308 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1309 | |
df7492f9 KH |
1310 | #define UTF_16_INVALID_P(val) \ |
1311 | (((val) == 0xFFFE) \ | |
1312 | || ((val) == 0xFFFF) \ | |
1313 | || UTF_16_LOW_SURROGATE_P (val)) | |
aa72b389 | 1314 | |
aa72b389 | 1315 | |
df7492f9 | 1316 | static int |
ff0dacd7 | 1317 | detect_coding_utf_16 (coding, detect_info) |
aa72b389 | 1318 | struct coding_system *coding; |
ff0dacd7 | 1319 | struct coding_detection_info *detect_info; |
aa72b389 | 1320 | { |
8f924df7 KH |
1321 | const unsigned char *src = coding->source, *src_base = src; |
1322 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
1323 | int multibytep = coding->src_multibyte; |
1324 | int consumed_chars = 0; | |
1325 | int c1, c2; | |
aa72b389 | 1326 | |
ff0dacd7 | 1327 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
aa72b389 | 1328 | |
ff0dacd7 KH |
1329 | if (coding->mode & CODING_MODE_LAST_BLOCK |
1330 | && (coding->src_bytes & 1)) | |
1331 | { | |
1332 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1333 | return 0; | |
1334 | } | |
df7492f9 KH |
1335 | ONE_MORE_BYTE (c1); |
1336 | ONE_MORE_BYTE (c2); | |
aa72b389 | 1337 | |
df7492f9 | 1338 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1339 | { |
b49a1807 KH |
1340 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1341 | | CATEGORY_MASK_UTF_16_AUTO); | |
ff0dacd7 | 1342 | detect_info->rejected |= CATEGORY_MASK_UTF_16_BE; |
aa72b389 | 1343 | } |
df7492f9 | 1344 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1345 | { |
b49a1807 KH |
1346 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1347 | | CATEGORY_MASK_UTF_16_AUTO); | |
ff0dacd7 KH |
1348 | detect_info->rejected |= CATEGORY_MASK_UTF_16_LE; |
1349 | } | |
df7492f9 | 1350 | no_more_source: |
ff0dacd7 | 1351 | return 1; |
df7492f9 | 1352 | } |
aa72b389 | 1353 | |
df7492f9 KH |
1354 | static void |
1355 | decode_coding_utf_16 (coding) | |
1356 | struct coding_system *coding; | |
1357 | { | |
8f924df7 KH |
1358 | const unsigned char *src = coding->source + coding->consumed; |
1359 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1360 | const unsigned char *src_base; | |
df7492f9 KH |
1361 | int *charbuf = coding->charbuf; |
1362 | int *charbuf_end = charbuf + coding->charbuf_size; | |
1363 | int consumed_chars = 0, consumed_chars_base; | |
1364 | int multibytep = coding->src_multibyte; | |
1365 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1366 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); | |
1367 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
1368 | Lisp_Object attr, eol_type, charset_list; | |
1369 | ||
1370 | CODING_GET_INFO (coding, attr, eol_type, charset_list); | |
1371 | ||
b49a1807 | 1372 | if (bom == utf_16_with_bom) |
aa72b389 | 1373 | { |
df7492f9 | 1374 | int c, c1, c2; |
4af310db | 1375 | |
aa72b389 | 1376 | src_base = src; |
df7492f9 KH |
1377 | ONE_MORE_BYTE (c1); |
1378 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1379 | c = (c1 << 8) | c2; |
aa72b389 | 1380 | |
b49a1807 KH |
1381 | if (endian == utf_16_big_endian |
1382 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1383 | { |
b49a1807 KH |
1384 | /* The first two bytes are not BOM. Treat them as bytes |
1385 | for a normal character. */ | |
1386 | src = src_base; | |
1387 | coding->errors++; | |
aa72b389 | 1388 | } |
b49a1807 KH |
1389 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1390 | } | |
1391 | else if (bom == utf_16_detect_bom) | |
1392 | { | |
1393 | /* We have already tried to detect BOM and failed in | |
1394 | detect_coding. */ | |
1395 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; | |
df7492f9 | 1396 | } |
aa72b389 | 1397 | |
df7492f9 KH |
1398 | while (1) |
1399 | { | |
1400 | int c, c1, c2; | |
1401 | ||
1402 | src_base = src; | |
1403 | consumed_chars_base = consumed_chars; | |
1404 | ||
1405 | if (charbuf + 2 >= charbuf_end) | |
1406 | break; | |
1407 | ||
1408 | ONE_MORE_BYTE (c1); | |
1409 | ONE_MORE_BYTE (c2); | |
1410 | c = (endian == utf_16_big_endian | |
e19c3639 | 1411 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
df7492f9 | 1412 | if (surrogate) |
fd3ae0b9 | 1413 | { |
df7492f9 | 1414 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1415 | { |
df7492f9 KH |
1416 | if (endian == utf_16_big_endian) |
1417 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1418 | else | |
1419 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1420 | *charbuf++ = c1; | |
1421 | *charbuf++ = c2; | |
1422 | coding->errors++; | |
1423 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1424 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1425 | else |
df7492f9 | 1426 | *charbuf++ = c; |
fd3ae0b9 KH |
1427 | } |
1428 | else | |
df7492f9 KH |
1429 | { |
1430 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1431 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
1432 | *charbuf++ = c; | |
1433 | } | |
fd3ae0b9 | 1434 | } |
aa72b389 | 1435 | else |
df7492f9 KH |
1436 | { |
1437 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1438 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1439 | else | |
1440 | *charbuf++ = c; | |
8f924df7 | 1441 | } |
aa72b389 | 1442 | } |
df7492f9 KH |
1443 | |
1444 | no_more_source: | |
1445 | coding->consumed_char += consumed_chars_base; | |
1446 | coding->consumed = src_base - coding->source; | |
1447 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1448 | } |
b73bfc1c | 1449 | |
df7492f9 KH |
1450 | static int |
1451 | encode_coding_utf_16 (coding) | |
1452 | struct coding_system *coding; | |
1453 | { | |
1454 | int multibytep = coding->dst_multibyte; | |
1455 | int *charbuf = coding->charbuf; | |
1456 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1457 | unsigned char *dst = coding->destination + coding->produced; | |
1458 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1459 | int safe_room = 8; | |
1460 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1461 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; | |
1462 | int produced_chars = 0; | |
1463 | Lisp_Object attrs, eol_type, charset_list; | |
1464 | int c; | |
4ed46869 | 1465 | |
df7492f9 KH |
1466 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
1467 | ||
b49a1807 | 1468 | if (bom != utf_16_without_bom) |
df7492f9 KH |
1469 | { |
1470 | ASSURE_DESTINATION (safe_room); | |
1471 | if (big_endian) | |
df7492f9 | 1472 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1473 | else |
1474 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
df7492f9 KH |
1475 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1476 | } | |
1477 | ||
1478 | while (charbuf < charbuf_end) | |
1479 | { | |
1480 | ASSURE_DESTINATION (safe_room); | |
1481 | c = *charbuf++; | |
e19c3639 KH |
1482 | if (c >= MAX_UNICODE_CHAR) |
1483 | c = coding->default_char; | |
df7492f9 KH |
1484 | |
1485 | if (c < 0x10000) | |
1486 | { | |
1487 | if (big_endian) | |
1488 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1489 | else | |
1490 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1491 | } | |
1492 | else | |
1493 | { | |
1494 | int c1, c2; | |
1495 | ||
1496 | c -= 0x10000; | |
1497 | c1 = (c >> 10) + 0xD800; | |
1498 | c2 = (c & 0x3FF) + 0xDC00; | |
1499 | if (big_endian) | |
1500 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1501 | else | |
1502 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1503 | } | |
1504 | } | |
1505 | coding->result = CODING_RESULT_SUCCESS; | |
1506 | coding->produced = dst - coding->destination; | |
1507 | coding->produced_char += produced_chars; | |
1508 | return 0; | |
1509 | } | |
1510 | ||
1511 | \f | |
1512 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1513 | ||
1514 | /* Emacs' internal format for representation of multiple character | |
1515 | sets is a kind of multi-byte encoding, i.e. characters are | |
1516 | represented by variable-length sequences of one-byte codes. | |
1517 | ||
1518 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1519 | represented by one-byte sequences which are their ASCII codes, in | |
1520 | the range 0x00 through 0x7F. | |
1521 | ||
1522 | 8-bit characters of the range 0x80..0x9F are represented by | |
1523 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1524 | code + 0x20). | |
1525 | ||
1526 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1527 | one-byte sequences which are their 8-bit code. | |
1528 | ||
1529 | The other characters are represented by a sequence of `base | |
1530 | leading-code', optional `extended leading-code', and one or two | |
1531 | `position-code's. The length of the sequence is determined by the | |
1532 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1533 | whereas extended leading-code and position-code take the range 0xA0 | |
1534 | through 0xFF. See `charset.h' for more details about leading-code | |
1535 | and position-code. | |
1536 | ||
1537 | --- CODE RANGE of Emacs' internal format --- | |
1538 | character set range | |
1539 | ------------- ----- | |
1540 | ascii 0x00..0x7F | |
1541 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1542 | eight-bit-graphic 0xA0..0xBF | |
1543 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1544 | --------------------------------------------- | |
1545 | ||
1546 | As this is the internal character representation, the format is | |
1547 | usually not used externally (i.e. in a file or in a data sent to a | |
1548 | process). But, it is possible to have a text externally in this | |
1549 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1550 | ||
1551 | In that case, a sequence of one-byte codes has a slightly different | |
1552 | form. | |
1553 | ||
1554 | At first, all characters in eight-bit-control are represented by | |
1555 | one-byte sequences which are their 8-bit code. | |
1556 | ||
1557 | Next, character composition data are represented by the byte | |
1558 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1559 | where, | |
1560 | METHOD is 0xF0 plus one of composition method (enum | |
1561 | composition_method), | |
1562 | ||
1563 | BYTES is 0xA0 plus a byte length of this composition data, | |
1564 | ||
1565 | CHARS is 0x20 plus a number of characters composed by this | |
1566 | data, | |
1567 | ||
1568 | COMPONENTs are characters of multibye form or composition | |
1569 | rules encoded by two-byte of ASCII codes. | |
1570 | ||
1571 | In addition, for backward compatibility, the following formats are | |
1572 | also recognized as composition data on decoding. | |
1573 | ||
1574 | 0x80 MSEQ ... | |
1575 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1576 | ||
1577 | Here, | |
1578 | MSEQ is a multibyte form but in these special format: | |
1579 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1580 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1581 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1582 | represents a composition rule. | |
1583 | */ | |
1584 | ||
1585 | char emacs_mule_bytes[256]; | |
1586 | ||
df7492f9 | 1587 | int |
ff0dacd7 | 1588 | emacs_mule_char (coding, src, nbytes, nchars, id) |
df7492f9 | 1589 | struct coding_system *coding; |
781d7a48 | 1590 | unsigned char *src; |
ff0dacd7 | 1591 | int *nbytes, *nchars, *id; |
df7492f9 | 1592 | { |
8f924df7 KH |
1593 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1594 | const unsigned char *src_base = src; | |
df7492f9 | 1595 | int multibytep = coding->src_multibyte; |
df7492f9 KH |
1596 | struct charset *charset; |
1597 | unsigned code; | |
1598 | int c; | |
1599 | int consumed_chars = 0; | |
1600 | ||
1601 | ONE_MORE_BYTE (c); | |
df7492f9 KH |
1602 | switch (emacs_mule_bytes[c]) |
1603 | { | |
1604 | case 2: | |
1605 | if (! (charset = emacs_mule_charset[c])) | |
1606 | goto invalid_code; | |
1607 | ONE_MORE_BYTE (c); | |
1608 | code = c & 0x7F; | |
1609 | break; | |
1610 | ||
1611 | case 3: | |
7c78e542 KH |
1612 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 |
1613 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
b73bfc1c | 1614 | { |
df7492f9 KH |
1615 | ONE_MORE_BYTE (c); |
1616 | if (! (charset = emacs_mule_charset[c])) | |
1617 | goto invalid_code; | |
1618 | ONE_MORE_BYTE (c); | |
1619 | code = c & 0x7F; | |
b73bfc1c KH |
1620 | } |
1621 | else | |
1622 | { | |
df7492f9 KH |
1623 | if (! (charset = emacs_mule_charset[c])) |
1624 | goto invalid_code; | |
1625 | ONE_MORE_BYTE (c); | |
781d7a48 | 1626 | code = (c & 0x7F) << 8; |
df7492f9 KH |
1627 | ONE_MORE_BYTE (c); |
1628 | code |= c & 0x7F; | |
1629 | } | |
1630 | break; | |
1631 | ||
1632 | case 4: | |
781d7a48 | 1633 | ONE_MORE_BYTE (c); |
df7492f9 KH |
1634 | if (! (charset = emacs_mule_charset[c])) |
1635 | goto invalid_code; | |
1636 | ONE_MORE_BYTE (c); | |
781d7a48 | 1637 | code = (c & 0x7F) << 8; |
df7492f9 KH |
1638 | ONE_MORE_BYTE (c); |
1639 | code |= c & 0x7F; | |
1640 | break; | |
1641 | ||
1642 | case 1: | |
1643 | code = c; | |
9d123124 KH |
1644 | charset = CHARSET_FROM_ID (ASCII_BYTE_P (code) |
1645 | ? charset_ascii : charset_eight_bit); | |
df7492f9 KH |
1646 | break; |
1647 | ||
1648 | default: | |
1649 | abort (); | |
1650 | } | |
1651 | c = DECODE_CHAR (charset, code); | |
1652 | if (c < 0) | |
1653 | goto invalid_code; | |
1654 | *nbytes = src - src_base; | |
1655 | *nchars = consumed_chars; | |
ff0dacd7 KH |
1656 | if (id) |
1657 | *id = charset->id; | |
df7492f9 KH |
1658 | return c; |
1659 | ||
1660 | no_more_source: | |
1661 | return -2; | |
1662 | ||
1663 | invalid_code: | |
1664 | return -1; | |
1665 | } | |
1666 | ||
1667 | ||
1668 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1669 | Check if a text is encoded in `emacs-mule'. If it is, return 1, |
1670 | else return 0. */ | |
df7492f9 KH |
1671 | |
1672 | static int | |
ff0dacd7 | 1673 | detect_coding_emacs_mule (coding, detect_info) |
df7492f9 | 1674 | struct coding_system *coding; |
ff0dacd7 | 1675 | struct coding_detection_info *detect_info; |
df7492f9 | 1676 | { |
8f924df7 KH |
1677 | const unsigned char *src = coding->source, *src_base = src; |
1678 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
1679 | int multibytep = coding->src_multibyte; |
1680 | int consumed_chars = 0; | |
1681 | int c; | |
1682 | int found = 0; | |
89528eb3 | 1683 | int incomplete; |
df7492f9 | 1684 | |
ff0dacd7 | 1685 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1686 | /* A coding system of this category is always ASCII compatible. */ |
1687 | src += coding->head_ascii; | |
1688 | ||
1689 | while (1) | |
1690 | { | |
89528eb3 | 1691 | incomplete = 0; |
df7492f9 | 1692 | ONE_MORE_BYTE (c); |
89528eb3 | 1693 | incomplete = 1; |
df7492f9 KH |
1694 | |
1695 | if (c == 0x80) | |
1696 | { | |
1697 | /* Perhaps the start of composite character. We simple skip | |
1698 | it because analyzing it is too heavy for detecting. But, | |
1699 | at least, we check that the composite character | |
1700 | constitues of more than 4 bytes. */ | |
8f924df7 | 1701 | const unsigned char *src_base; |
df7492f9 KH |
1702 | |
1703 | repeat: | |
1704 | src_base = src; | |
1705 | do | |
1706 | { | |
1707 | ONE_MORE_BYTE (c); | |
1708 | } | |
1709 | while (c >= 0xA0); | |
1710 | ||
1711 | if (src - src_base <= 4) | |
1712 | break; | |
ff0dacd7 | 1713 | found = CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1714 | if (c == 0x80) |
1715 | goto repeat; | |
b73bfc1c | 1716 | } |
df7492f9 KH |
1717 | |
1718 | if (c < 0x80) | |
b73bfc1c | 1719 | { |
df7492f9 KH |
1720 | if (c < 0x20 |
1721 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1722 | break; | |
1723 | } | |
1724 | else | |
1725 | { | |
8f924df7 | 1726 | const unsigned char *src_base = src - 1; |
df7492f9 KH |
1727 | |
1728 | do | |
1729 | { | |
1730 | ONE_MORE_BYTE (c); | |
1731 | } | |
1732 | while (c >= 0xA0); | |
1733 | if (src - src_base != emacs_mule_bytes[*src_base]) | |
1734 | break; | |
ff0dacd7 | 1735 | found = CATEGORY_MASK_EMACS_MULE; |
4ed46869 KH |
1736 | } |
1737 | } | |
ff0dacd7 | 1738 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1739 | return 0; |
1740 | ||
1741 | no_more_source: | |
89528eb3 KH |
1742 | if (incomplete && coding->mode & CODING_MODE_LAST_BLOCK) |
1743 | { | |
ff0dacd7 | 1744 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
89528eb3 KH |
1745 | return 0; |
1746 | } | |
ff0dacd7 KH |
1747 | detect_info->found |= found; |
1748 | return 1; | |
4ed46869 KH |
1749 | } |
1750 | ||
b73bfc1c | 1751 | |
df7492f9 KH |
1752 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
1753 | ||
1754 | /* Decode a character represented as a component of composition | |
1755 | sequence of Emacs 20/21 style at SRC. Set C to that character and | |
1756 | update SRC to the head of next character (or an encoded composition | |
1757 | rule). If SRC doesn't points a composition component, set C to -1. | |
1758 | If SRC points an invalid byte sequence, global exit by a return | |
1759 | value 0. */ | |
1760 | ||
1761 | #define DECODE_EMACS_MULE_COMPOSITION_CHAR(buf) \ | |
1762 | if (1) \ | |
1763 | { \ | |
1764 | int c; \ | |
1765 | int nbytes, nchars; \ | |
1766 | \ | |
1767 | if (src == src_end) \ | |
1768 | break; \ | |
ff0dacd7 | 1769 | c = emacs_mule_char (coding, src, &nbytes, &nchars, NULL);\ |
df7492f9 KH |
1770 | if (c < 0) \ |
1771 | { \ | |
1772 | if (c == -2) \ | |
1773 | break; \ | |
1774 | goto invalid_code; \ | |
1775 | } \ | |
1776 | *buf++ = c; \ | |
1777 | src += nbytes; \ | |
1778 | consumed_chars += nchars; \ | |
1779 | } \ | |
1780 | else | |
1781 | ||
1782 | ||
1783 | /* Decode a composition rule represented as a component of composition | |
781d7a48 KH |
1784 | sequence of Emacs 20 style at SRC. Store the decoded rule in *BUF, |
1785 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1786 | to -1. */ | |
df7492f9 | 1787 | |
781d7a48 | 1788 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(buf) \ |
df7492f9 KH |
1789 | do { \ |
1790 | int c, gref, nref; \ | |
1791 | \ | |
781d7a48 | 1792 | if (src >= src_end) \ |
df7492f9 KH |
1793 | goto invalid_code; \ |
1794 | ONE_MORE_BYTE_NO_CHECK (c); \ | |
781d7a48 | 1795 | c -= 0x20; \ |
df7492f9 KH |
1796 | if (c < 0 || c >= 81) \ |
1797 | goto invalid_code; \ | |
1798 | \ | |
1799 | gref = c / 9, nref = c % 9; \ | |
1800 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1801 | } while (0) | |
1802 | ||
1803 | ||
781d7a48 KH |
1804 | /* Decode a composition rule represented as a component of composition |
1805 | sequence of Emacs 21 style at SRC. Store the decoded rule in *BUF, | |
1806 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1807 | to -1. */ | |
1808 | ||
1809 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(buf) \ | |
1810 | do { \ | |
1811 | int gref, nref; \ | |
1812 | \ | |
1813 | if (src + 1>= src_end) \ | |
1814 | goto invalid_code; \ | |
1815 | ONE_MORE_BYTE_NO_CHECK (gref); \ | |
1816 | gref -= 0x20; \ | |
1817 | ONE_MORE_BYTE_NO_CHECK (nref); \ | |
1818 | nref -= 0x20; \ | |
1819 | if (gref < 0 || gref >= 81 \ | |
1820 | || nref < 0 || nref >= 81) \ | |
1821 | goto invalid_code; \ | |
1822 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1823 | } while (0) | |
1824 | ||
1825 | ||
df7492f9 | 1826 | #define DECODE_EMACS_MULE_21_COMPOSITION(c) \ |
aa72b389 | 1827 | do { \ |
df7492f9 | 1828 | /* Emacs 21 style format. The first three bytes at SRC are \ |
781d7a48 | 1829 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is \ |
df7492f9 KH |
1830 | the byte length of this composition information, CHARS is the \ |
1831 | number of characters composed by this composition. */ \ | |
781d7a48 KH |
1832 | enum composition_method method = c - 0xF2; \ |
1833 | int *charbuf_base = charbuf; \ | |
ff0dacd7 | 1834 | int from, to; \ |
df7492f9 KH |
1835 | int consumed_chars_limit; \ |
1836 | int nbytes, nchars; \ | |
1837 | \ | |
1838 | ONE_MORE_BYTE (c); \ | |
1839 | nbytes = c - 0xA0; \ | |
1840 | if (nbytes < 3) \ | |
1841 | goto invalid_code; \ | |
1842 | ONE_MORE_BYTE (c); \ | |
1843 | nchars = c - 0xA0; \ | |
ff0dacd7 KH |
1844 | from = coding->produced + char_offset; \ |
1845 | to = from + nchars; \ | |
1846 | ADD_COMPOSITION_DATA (charbuf, from, to, method); \ | |
df7492f9 KH |
1847 | consumed_chars_limit = consumed_chars_base + nbytes; \ |
1848 | if (method != COMPOSITION_RELATIVE) \ | |
aa72b389 | 1849 | { \ |
df7492f9 KH |
1850 | int i = 0; \ |
1851 | while (consumed_chars < consumed_chars_limit) \ | |
aa72b389 | 1852 | { \ |
df7492f9 | 1853 | if (i % 2 && method != COMPOSITION_WITH_ALTCHARS) \ |
781d7a48 | 1854 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (charbuf); \ |
df7492f9 KH |
1855 | else \ |
1856 | DECODE_EMACS_MULE_COMPOSITION_CHAR (charbuf); \ | |
781d7a48 | 1857 | i++; \ |
aa72b389 | 1858 | } \ |
df7492f9 KH |
1859 | if (consumed_chars < consumed_chars_limit) \ |
1860 | goto invalid_code; \ | |
781d7a48 | 1861 | charbuf_base[0] -= i; \ |
aa72b389 KH |
1862 | } \ |
1863 | } while (0) | |
93dec019 | 1864 | |
aa72b389 | 1865 | |
df7492f9 KH |
1866 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION(c) \ |
1867 | do { \ | |
1868 | /* Emacs 20 style format for relative composition. */ \ | |
1869 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 1870 | enum composition_method method = COMPOSITION_RELATIVE; \ |
df7492f9 KH |
1871 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
1872 | int *buf = components; \ | |
1873 | int i, j; \ | |
ff0dacd7 | 1874 | int from, to; \ |
df7492f9 KH |
1875 | \ |
1876 | src = src_base; \ | |
1877 | ONE_MORE_BYTE (c); /* skip 0x80 */ \ | |
1878 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
1879 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
1880 | if (i < 2) \ | |
1881 | goto invalid_code; \ | |
ff0dacd7 KH |
1882 | from = coding->produced_char + char_offset; \ |
1883 | to = from + i; \ | |
1884 | ADD_COMPOSITION_DATA (charbuf, from, to, method); \ | |
df7492f9 KH |
1885 | for (j = 0; j < i; j++) \ |
1886 | *charbuf++ = components[j]; \ | |
1887 | } while (0) | |
1888 | ||
1889 | ||
1890 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION(c) \ | |
1891 | do { \ | |
1892 | /* Emacs 20 style format for rule-base composition. */ \ | |
1893 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 1894 | enum composition_method method = COMPOSITION_WITH_RULE; \ |
df7492f9 KH |
1895 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
1896 | int *buf = components; \ | |
1897 | int i, j; \ | |
ff0dacd7 | 1898 | int from, to; \ |
df7492f9 KH |
1899 | \ |
1900 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
1901 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
1902 | { \ | |
781d7a48 | 1903 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (buf); \ |
df7492f9 KH |
1904 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ |
1905 | } \ | |
1906 | if (i < 1 || (buf - components) % 2 == 0) \ | |
1907 | goto invalid_code; \ | |
1908 | if (charbuf + i + (i / 2) + 1 < charbuf_end) \ | |
1909 | goto no_more_source; \ | |
ff0dacd7 KH |
1910 | from = coding->produced_char + char_offset; \ |
1911 | to = from + i; \ | |
1912 | ADD_COMPOSITION_DATA (buf, from, to, method); \ | |
df7492f9 KH |
1913 | for (j = 0; j < i; j++) \ |
1914 | *charbuf++ = components[j]; \ | |
1915 | for (j = 0; j < i; j += 2) \ | |
1916 | *charbuf++ = components[j]; \ | |
1917 | } while (0) | |
1918 | ||
aa72b389 KH |
1919 | |
1920 | static void | |
df7492f9 | 1921 | decode_coding_emacs_mule (coding) |
aa72b389 | 1922 | struct coding_system *coding; |
aa72b389 | 1923 | { |
8f924df7 KH |
1924 | const unsigned char *src = coding->source + coding->consumed; |
1925 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1926 | const unsigned char *src_base; | |
df7492f9 | 1927 | int *charbuf = coding->charbuf; |
ff0dacd7 | 1928 | int *charbuf_end = charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; |
df7492f9 | 1929 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 KH |
1930 | int multibytep = coding->src_multibyte; |
1931 | Lisp_Object attrs, eol_type, charset_list; | |
ff0dacd7 KH |
1932 | int char_offset = coding->produced_char; |
1933 | int last_offset = char_offset; | |
1934 | int last_id = charset_ascii; | |
aa72b389 | 1935 | |
df7492f9 | 1936 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
aa72b389 | 1937 | |
aa72b389 KH |
1938 | while (1) |
1939 | { | |
df7492f9 KH |
1940 | int c; |
1941 | ||
aa72b389 | 1942 | src_base = src; |
df7492f9 KH |
1943 | consumed_chars_base = consumed_chars; |
1944 | ||
1945 | if (charbuf >= charbuf_end) | |
1946 | break; | |
aa72b389 | 1947 | |
df7492f9 KH |
1948 | ONE_MORE_BYTE (c); |
1949 | ||
1950 | if (c < 0x80) | |
aa72b389 | 1951 | { |
df7492f9 KH |
1952 | if (c == '\r') |
1953 | { | |
1954 | if (EQ (eol_type, Qdos)) | |
1955 | { | |
1956 | if (src == src_end) | |
98725083 KH |
1957 | { |
1958 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; | |
1959 | goto no_more_source; | |
1960 | } | |
df7492f9 KH |
1961 | if (*src == '\n') |
1962 | ONE_MORE_BYTE (c); | |
1963 | } | |
1964 | else if (EQ (eol_type, Qmac)) | |
1965 | c = '\n'; | |
1966 | } | |
1967 | *charbuf++ = c; | |
1968 | char_offset++; | |
aa72b389 | 1969 | } |
df7492f9 KH |
1970 | else if (c == 0x80) |
1971 | { | |
df7492f9 | 1972 | ONE_MORE_BYTE (c); |
781d7a48 KH |
1973 | if (c - 0xF2 >= COMPOSITION_RELATIVE |
1974 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) | |
df7492f9 KH |
1975 | DECODE_EMACS_MULE_21_COMPOSITION (c); |
1976 | else if (c < 0xC0) | |
1977 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (c); | |
1978 | else if (c == 0xFF) | |
1979 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (c); | |
1980 | else | |
1981 | goto invalid_code; | |
1982 | } | |
1983 | else if (c < 0xA0 && emacs_mule_bytes[c] > 1) | |
1984 | { | |
1985 | int nbytes, nchars; | |
ff0dacd7 KH |
1986 | int id; |
1987 | ||
781d7a48 KH |
1988 | src = src_base; |
1989 | consumed_chars = consumed_chars_base; | |
ff0dacd7 | 1990 | c = emacs_mule_char (coding, src, &nbytes, &nchars, &id); |
df7492f9 KH |
1991 | if (c < 0) |
1992 | { | |
1993 | if (c == -2) | |
1994 | break; | |
1995 | goto invalid_code; | |
1996 | } | |
ff0dacd7 KH |
1997 | if (last_id != id) |
1998 | { | |
1999 | if (last_id != charset_ascii) | |
2000 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
2001 | last_id = id; | |
2002 | last_offset = char_offset; | |
2003 | } | |
df7492f9 | 2004 | *charbuf++ = c; |
781d7a48 KH |
2005 | src += nbytes; |
2006 | consumed_chars += nchars; | |
df7492f9 KH |
2007 | char_offset++; |
2008 | } | |
2009 | continue; | |
2010 | ||
2011 | invalid_code: | |
2012 | src = src_base; | |
2013 | consumed_chars = consumed_chars_base; | |
2014 | ONE_MORE_BYTE (c); | |
2015 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2016 | char_offset++; |
df7492f9 KH |
2017 | coding->errors++; |
2018 | } | |
2019 | ||
2020 | no_more_source: | |
ff0dacd7 KH |
2021 | if (last_id != charset_ascii) |
2022 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
df7492f9 KH |
2023 | coding->consumed_char += consumed_chars_base; |
2024 | coding->consumed = src_base - coding->source; | |
2025 | coding->charbuf_used = charbuf - coding->charbuf; | |
2026 | } | |
2027 | ||
2028 | ||
2029 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2030 | do { \ | |
2031 | if (id < 0xA0) \ | |
2032 | codes[0] = id, codes[1] = 0; \ | |
2033 | else if (id < 0xE0) \ | |
2034 | codes[0] = 0x9A, codes[1] = id; \ | |
2035 | else if (id < 0xF0) \ | |
2036 | codes[0] = 0x9B, codes[1] = id; \ | |
2037 | else if (id < 0xF5) \ | |
2038 | codes[0] = 0x9C, codes[1] = id; \ | |
2039 | else \ | |
2040 | codes[0] = 0x9D, codes[1] = id; \ | |
2041 | } while (0); | |
2042 | ||
aa72b389 | 2043 | |
df7492f9 KH |
2044 | static int |
2045 | encode_coding_emacs_mule (coding) | |
2046 | struct coding_system *coding; | |
2047 | { | |
2048 | int multibytep = coding->dst_multibyte; | |
2049 | int *charbuf = coding->charbuf; | |
2050 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2051 | unsigned char *dst = coding->destination + coding->produced; | |
2052 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2053 | int safe_room = 8; | |
df7492f9 KH |
2054 | int produced_chars = 0; |
2055 | Lisp_Object attrs, eol_type, charset_list; | |
2056 | int c; | |
ff0dacd7 | 2057 | int preferred_charset_id = -1; |
df7492f9 KH |
2058 | |
2059 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
eccb6815 KH |
2060 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2061 | { | |
2062 | CODING_ATTR_CHARSET_LIST (attrs) | |
2063 | = charset_list = Vemacs_mule_charset_list; | |
2064 | } | |
df7492f9 KH |
2065 | |
2066 | while (charbuf < charbuf_end) | |
2067 | { | |
2068 | ASSURE_DESTINATION (safe_room); | |
2069 | c = *charbuf++; | |
ff0dacd7 KH |
2070 | |
2071 | if (c < 0) | |
2072 | { | |
2073 | /* Handle an annotation. */ | |
2074 | switch (*charbuf) | |
2075 | { | |
2076 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2077 | /* Not yet implemented. */ | |
2078 | break; | |
2079 | case CODING_ANNOTATE_CHARSET_MASK: | |
2080 | preferred_charset_id = charbuf[3]; | |
2081 | if (preferred_charset_id >= 0 | |
2082 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2083 | charset_list))) | |
2084 | preferred_charset_id = -1; | |
2085 | break; | |
2086 | default: | |
2087 | abort (); | |
2088 | } | |
2089 | charbuf += -c - 1; | |
2090 | continue; | |
2091 | } | |
2092 | ||
df7492f9 KH |
2093 | if (ASCII_CHAR_P (c)) |
2094 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2095 | else if (CHAR_BYTE8_P (c)) |
2096 | { | |
2097 | c = CHAR_TO_BYTE8 (c); | |
2098 | EMIT_ONE_BYTE (c); | |
2099 | } | |
df7492f9 | 2100 | else |
aa72b389 | 2101 | { |
df7492f9 KH |
2102 | struct charset *charset; |
2103 | unsigned code; | |
2104 | int dimension; | |
2105 | int emacs_mule_id; | |
2106 | unsigned char leading_codes[2]; | |
2107 | ||
ff0dacd7 KH |
2108 | if (preferred_charset_id >= 0) |
2109 | { | |
2110 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
2111 | if (! CHAR_CHARSET_P (c, charset)) | |
2112 | charset = char_charset (c, charset_list, NULL); | |
2113 | } | |
2114 | else | |
2115 | charset = char_charset (c, charset_list, &code); | |
df7492f9 KH |
2116 | if (! charset) |
2117 | { | |
2118 | c = coding->default_char; | |
2119 | if (ASCII_CHAR_P (c)) | |
2120 | { | |
2121 | EMIT_ONE_ASCII_BYTE (c); | |
2122 | continue; | |
2123 | } | |
2124 | charset = char_charset (c, charset_list, &code); | |
2125 | } | |
2126 | dimension = CHARSET_DIMENSION (charset); | |
2127 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2128 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2129 | EMIT_ONE_BYTE (leading_codes[0]); | |
2130 | if (leading_codes[1]) | |
2131 | EMIT_ONE_BYTE (leading_codes[1]); | |
2132 | if (dimension == 1) | |
1fa663f9 | 2133 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2134 | else |
df7492f9 | 2135 | { |
1fa663f9 | 2136 | code |= 0x8080; |
df7492f9 KH |
2137 | EMIT_ONE_BYTE (code >> 8); |
2138 | EMIT_ONE_BYTE (code & 0xFF); | |
2139 | } | |
aa72b389 | 2140 | } |
aa72b389 | 2141 | } |
df7492f9 KH |
2142 | coding->result = CODING_RESULT_SUCCESS; |
2143 | coding->produced_char += produced_chars; | |
2144 | coding->produced = dst - coding->destination; | |
2145 | return 0; | |
aa72b389 | 2146 | } |
b73bfc1c | 2147 | |
4ed46869 | 2148 | \f |
df7492f9 | 2149 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2150 | |
2151 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2152 | Since the intention of this note is to help understand the |
5a936b46 | 2153 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2154 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2155 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2156 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2157 | |
2158 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2159 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2160 | is encoded using bytes less than 128. This may make the encoded |
2161 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2162 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2163 | Significant Bit). |
b73bfc1c | 2164 | |
cfb43547 DL |
2165 | There are two kinds of character sets: control character sets and |
2166 | graphic character sets. The former contain control characters such | |
4ed46869 | 2167 | as `newline' and `escape' to provide control functions (control |
39787efd | 2168 | functions are also provided by escape sequences). The latter |
cfb43547 | 2169 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2170 | two control character sets and many graphic character sets. |
2171 | ||
2172 | Graphic character sets are classified into one of the following | |
39787efd KH |
2173 | four classes, according to the number of bytes (DIMENSION) and |
2174 | number of characters in one dimension (CHARS) of the set: | |
2175 | - DIMENSION1_CHARS94 | |
2176 | - DIMENSION1_CHARS96 | |
2177 | - DIMENSION2_CHARS94 | |
2178 | - DIMENSION2_CHARS96 | |
2179 | ||
2180 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2181 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2182 | hereafter). The <F> of each character set is decided by ECMA(*) |
2183 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2184 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2185 | |
2186 | Note (*): ECMA = European Computer Manufacturers Association | |
2187 | ||
cfb43547 | 2188 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2189 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2190 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2191 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2192 | o DIMENSION2_CHARS96 -- none for the moment | |
2193 | ||
39787efd | 2194 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2195 | C0 [0x00..0x1F] -- control character plane 0 |
2196 | GL [0x20..0x7F] -- graphic character plane 0 | |
2197 | C1 [0x80..0x9F] -- control character plane 1 | |
2198 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2199 | ||
2200 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2201 | C1 by an escape sequence. The most common case is that: |
2202 | - ISO646's control character set is designated/invoked to C0, and | |
2203 | - ISO6429's control character set is designated/invoked to C1, | |
2204 | and usually these designations/invocations are omitted in encoded | |
2205 | text. In a 7-bit environment, only C0 can be used, and a control | |
2206 | character for C1 is encoded by an appropriate escape sequence to | |
2207 | fit into the environment. All control characters for C1 are | |
2208 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2209 | |
2210 | A graphic character set is at first designated to one of four | |
2211 | graphic registers (G0 through G3), then these graphic registers are | |
2212 | invoked to GL or GR. These designations and invocations can be | |
2213 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2214 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2215 | these invocations and designations are omitted in encoded text. | |
2216 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2217 | |
39787efd KH |
2218 | When a graphic character set of CHARS94 is invoked to GL, codes |
2219 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2220 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2221 | be used. | |
4ed46869 KH |
2222 | |
2223 | There are two ways of invocation: locking-shift and single-shift. | |
2224 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2225 | invocation, whereas with single-shift, the invocation affects the |
2226 | following character only and doesn't affect the locking-shift | |
2227 | state. Invocations are done by the following control characters or | |
2228 | escape sequences: | |
4ed46869 KH |
2229 | |
2230 | ---------------------------------------------------------------------- | |
39787efd | 2231 | abbrev function cntrl escape seq description |
4ed46869 | 2232 | ---------------------------------------------------------------------- |
39787efd KH |
2233 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2234 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2235 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2236 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2237 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2238 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2239 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2240 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2241 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2242 | ---------------------------------------------------------------------- |
39787efd KH |
2243 | (*) These are not used by any known coding system. |
2244 | ||
2245 | Control characters for these functions are defined by macros | |
2246 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2247 | |
39787efd | 2248 | Designations are done by the following escape sequences: |
4ed46869 KH |
2249 | ---------------------------------------------------------------------- |
2250 | escape sequence description | |
2251 | ---------------------------------------------------------------------- | |
2252 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2253 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2254 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2255 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2256 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2257 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2258 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2259 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2260 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2261 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2262 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2263 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2264 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2265 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2266 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2267 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2268 | ---------------------------------------------------------------------- | |
2269 | ||
2270 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2271 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2272 | |
2273 | Note (*): Although these designations are not allowed in ISO2022, | |
2274 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2275 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2276 | 7-bit environment, non-locking-shift, and non-single-shift. |
2277 | ||
2278 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2279 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2280 | |
cfb43547 | 2281 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2282 | same multilingual text in ISO2022. Actually, there exist many |
2283 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2284 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2285 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2286 | localized platforms), and all of these are variants of ISO2022. |
2287 | ||
2288 | In addition to the above, Emacs handles two more kinds of escape | |
2289 | sequences: ISO6429's direction specification and Emacs' private | |
2290 | sequence for specifying character composition. | |
2291 | ||
39787efd | 2292 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2293 | o CSI ']' -- end of the current direction |
2294 | o CSI '0' ']' -- end of the current direction | |
2295 | o CSI '1' ']' -- start of left-to-right text | |
2296 | o CSI '2' ']' -- start of right-to-left text | |
2297 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2298 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2299 | ||
2300 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2301 | o ESC '0' -- start relative composition |
2302 | o ESC '1' -- end composition | |
2303 | o ESC '2' -- start rule-base composition (*) | |
2304 | o ESC '3' -- start relative composition with alternate chars (**) | |
2305 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2306 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2307 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2308 | |
5a936b46 DL |
2309 | (*) This form is used only in Emacs 20.7 and older versions, |
2310 | but newer versions can safely decode it. | |
cfb43547 | 2311 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2312 | and older versions can't decode it. |
ec6d2bb8 | 2313 | |
cfb43547 | 2314 | Here's a list of example usages of these composition escape |
b73bfc1c | 2315 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2316 | |
b73bfc1c | 2317 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2318 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2319 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2320 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2321 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2322 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2323 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2324 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2325 | |
2326 | enum iso_code_class_type iso_code_class[256]; | |
2327 | ||
df7492f9 KH |
2328 | #define SAFE_CHARSET_P(coding, id) \ |
2329 | ((id) <= (coding)->max_charset_id \ | |
2330 | && (coding)->safe_charsets[id] >= 0) | |
2331 | ||
2332 | ||
2333 | #define SHIFT_OUT_OK(category) \ | |
2334 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
2335 | ||
2336 | static void | |
f0064e1f DL |
2337 | setup_iso_safe_charsets (attrs) |
2338 | Lisp_Object attrs; | |
df7492f9 KH |
2339 | { |
2340 | Lisp_Object charset_list, safe_charsets; | |
2341 | Lisp_Object request; | |
2342 | Lisp_Object reg_usage; | |
2343 | Lisp_Object tail; | |
2344 | int reg94, reg96; | |
2345 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
2346 | int max_charset_id; | |
2347 | ||
2348 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2349 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2350 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2351 | { | |
2352 | CODING_ATTR_CHARSET_LIST (attrs) | |
2353 | = charset_list = Viso_2022_charset_list; | |
2354 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
2355 | } | |
2356 | ||
2357 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2358 | return; | |
2359 | ||
2360 | max_charset_id = 0; | |
2361 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2362 | { | |
2363 | int id = XINT (XCAR (tail)); | |
2364 | if (max_charset_id < id) | |
2365 | max_charset_id = id; | |
2366 | } | |
d46c5b12 | 2367 | |
df7492f9 KH |
2368 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
2369 | make_number (255)); | |
2370 | request = AREF (attrs, coding_attr_iso_request); | |
2371 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2372 | reg94 = XINT (XCAR (reg_usage)); | |
2373 | reg96 = XINT (XCDR (reg_usage)); | |
2374 | ||
2375 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2376 | { | |
2377 | Lisp_Object id; | |
2378 | Lisp_Object reg; | |
2379 | struct charset *charset; | |
2380 | ||
2381 | id = XCAR (tail); | |
2382 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2383 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2384 | if (! NILP (reg)) |
8f924df7 | 2385 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2386 | else if (charset->iso_chars_96) |
2387 | { | |
2388 | if (reg96 < 4) | |
8f924df7 | 2389 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2390 | } |
2391 | else | |
2392 | { | |
2393 | if (reg94 < 4) | |
8f924df7 | 2394 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2395 | } |
2396 | } | |
2397 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2398 | } | |
d46c5b12 | 2399 | |
b6871cc7 | 2400 | |
4ed46869 | 2401 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
2402 | Check if a text is encoded in one of ISO-2022 based codig systems. |
2403 | If it is, return 1, else return 0. */ | |
4ed46869 | 2404 | |
0a28aafb | 2405 | static int |
ff0dacd7 | 2406 | detect_coding_iso_2022 (coding, detect_info) |
df7492f9 | 2407 | struct coding_system *coding; |
ff0dacd7 | 2408 | struct coding_detection_info *detect_info; |
4ed46869 | 2409 | { |
8f924df7 KH |
2410 | const unsigned char *src = coding->source, *src_base = src; |
2411 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 2412 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 2413 | int single_shifting = 0; |
df7492f9 KH |
2414 | int id; |
2415 | int c, c1; | |
2416 | int consumed_chars = 0; | |
2417 | int i; | |
ff0dacd7 KH |
2418 | int rejected = 0; |
2419 | int found = 0; | |
2420 | ||
2421 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2422 | |
2423 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2424 | { | |
2425 | struct coding_system *this = &(coding_categories[i]); | |
2426 | Lisp_Object attrs, val; | |
2427 | ||
2428 | attrs = CODING_ID_ATTRS (this->id); | |
2429 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
2430 | && ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs), Viso_2022_charset_list)) | |
2431 | setup_iso_safe_charsets (attrs); | |
2432 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
2433 | this->max_charset_id = SCHARS (val) - 1; |
2434 | this->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
2435 | } |
2436 | ||
2437 | /* A coding system of this category is always ASCII compatible. */ | |
2438 | src += coding->head_ascii; | |
3f003981 | 2439 | |
ff0dacd7 | 2440 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 2441 | { |
df7492f9 | 2442 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2443 | switch (c) |
2444 | { | |
2445 | case ISO_CODE_ESC: | |
74383408 KH |
2446 | if (inhibit_iso_escape_detection) |
2447 | break; | |
f46869e4 | 2448 | single_shifting = 0; |
df7492f9 | 2449 | ONE_MORE_BYTE (c); |
d46c5b12 | 2450 | if (c >= '(' && c <= '/') |
4ed46869 | 2451 | { |
bf9cdd4e | 2452 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 2453 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2454 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2455 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
2456 | /* Invalid designation sequence. Just ignore. */ |
2457 | break; | |
bf9cdd4e KH |
2458 | } |
2459 | else if (c == '$') | |
2460 | { | |
2461 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 2462 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
2463 | if (c >= '@' && c <= 'B') |
2464 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
ff0dacd7 | 2465 | id = iso_charset_table[1][0][c]; |
bf9cdd4e | 2466 | else if (c >= '(' && c <= '/') |
bcf26d6a | 2467 | { |
df7492f9 | 2468 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2469 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2470 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
2471 | /* Invalid designation sequence. Just ignore. */ |
2472 | break; | |
bcf26d6a | 2473 | } |
bf9cdd4e | 2474 | else |
ff0dacd7 | 2475 | /* Invalid designation sequence. Just ignore it. */ |
d46c5b12 KH |
2476 | break; |
2477 | } | |
ae9ff118 | 2478 | else if (c == 'N' || c == 'O') |
d46c5b12 | 2479 | { |
ae9ff118 | 2480 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
2481 | single_shifting = 1; |
2482 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
d46c5b12 | 2483 | break; |
4ed46869 | 2484 | } |
ec6d2bb8 KH |
2485 | else if (c >= '0' && c <= '4') |
2486 | { | |
2487 | /* ESC <Fp> for start/end composition. */ | |
ff0dacd7 | 2488 | found |= CATEGORY_MASK_ISO; |
ec6d2bb8 KH |
2489 | break; |
2490 | } | |
bf9cdd4e | 2491 | else |
df7492f9 | 2492 | { |
ff0dacd7 | 2493 | /* Invalid escape sequence. Just ignore it. */ |
df7492f9 KH |
2494 | break; |
2495 | } | |
d46c5b12 KH |
2496 | |
2497 | /* We found a valid designation sequence for CHARSET. */ | |
ff0dacd7 | 2498 | rejected |= CATEGORY_MASK_ISO_8BIT; |
df7492f9 KH |
2499 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], |
2500 | id)) | |
ff0dacd7 | 2501 | found |= CATEGORY_MASK_ISO_7; |
d46c5b12 | 2502 | else |
ff0dacd7 | 2503 | rejected |= CATEGORY_MASK_ISO_7; |
df7492f9 KH |
2504 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], |
2505 | id)) | |
ff0dacd7 | 2506 | found |= CATEGORY_MASK_ISO_7_TIGHT; |
d46c5b12 | 2507 | else |
ff0dacd7 | 2508 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; |
df7492f9 KH |
2509 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], |
2510 | id)) | |
ff0dacd7 | 2511 | found |= CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 | 2512 | else |
ff0dacd7 | 2513 | rejected |= CATEGORY_MASK_ISO_7_ELSE; |
df7492f9 KH |
2514 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], |
2515 | id)) | |
ff0dacd7 | 2516 | found |= CATEGORY_MASK_ISO_8_ELSE; |
ae9ff118 | 2517 | else |
ff0dacd7 | 2518 | rejected |= CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
2519 | break; |
2520 | ||
4ed46869 | 2521 | case ISO_CODE_SO: |
d46c5b12 | 2522 | case ISO_CODE_SI: |
ff0dacd7 | 2523 | /* Locking shift out/in. */ |
74383408 KH |
2524 | if (inhibit_iso_escape_detection) |
2525 | break; | |
f46869e4 | 2526 | single_shifting = 0; |
ff0dacd7 KH |
2527 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
2528 | found |= CATEGORY_MASK_ISO_ELSE; | |
d46c5b12 KH |
2529 | break; |
2530 | ||
4ed46869 | 2531 | case ISO_CODE_CSI: |
ff0dacd7 | 2532 | /* Control sequence introducer. */ |
f46869e4 | 2533 | single_shifting = 0; |
ff0dacd7 KH |
2534 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2535 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
2536 | goto check_extra_latin; | |
2537 | ||
2538 | ||
4ed46869 KH |
2539 | case ISO_CODE_SS2: |
2540 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
2541 | /* Single shift. */ |
2542 | if (inhibit_iso_escape_detection) | |
2543 | break; | |
2544 | single_shifting = 1; | |
2545 | rejected |= CATEGORY_MASK_ISO_7BIT; | |
2546 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2547 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
2548 | found |= CATEGORY_MASK_ISO_8_1; | |
2549 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) | |
2550 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
2551 | found |= CATEGORY_MASK_ISO_8_2; | |
2552 | goto check_extra_latin; | |
4ed46869 KH |
2553 | |
2554 | default: | |
2555 | if (c < 0x80) | |
f46869e4 KH |
2556 | { |
2557 | single_shifting = 0; | |
2558 | break; | |
2559 | } | |
ff0dacd7 | 2560 | if (c >= 0xA0) |
c4825358 | 2561 | { |
ff0dacd7 KH |
2562 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2563 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 2564 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
2565 | 0xA0..0FF. If the byte length is even, we include |
2566 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
2567 | only when we are not single shifting. */ | |
2568 | if (! single_shifting | |
2569 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 2570 | { |
e17de821 | 2571 | int i = 1; |
b73bfc1c KH |
2572 | while (src < src_end) |
2573 | { | |
df7492f9 | 2574 | ONE_MORE_BYTE (c); |
b73bfc1c KH |
2575 | if (c < 0xA0) |
2576 | break; | |
2577 | i++; | |
2578 | } | |
2579 | ||
2580 | if (i & 1 && src < src_end) | |
ff0dacd7 | 2581 | rejected |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2582 | else |
ff0dacd7 | 2583 | found |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2584 | } |
ff0dacd7 | 2585 | break; |
4ed46869 | 2586 | } |
ff0dacd7 KH |
2587 | check_extra_latin: |
2588 | single_shifting = 0; | |
2589 | if (! VECTORP (Vlatin_extra_code_table) | |
2590 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
2591 | { | |
2592 | rejected = CATEGORY_MASK_ISO; | |
2593 | break; | |
2594 | } | |
2595 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2596 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2597 | found |= CATEGORY_MASK_ISO_8_1; | |
2598 | else | |
2599 | rejected |= CATEGORY_MASK_ISO_8_1; | |
2600 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) | |
2601 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2602 | found |= CATEGORY_MASK_ISO_8_2; | |
2603 | else | |
2604 | rejected |= CATEGORY_MASK_ISO_8_2; | |
4ed46869 KH |
2605 | } |
2606 | } | |
ff0dacd7 KH |
2607 | detect_info->rejected |= CATEGORY_MASK_ISO; |
2608 | return 0; | |
4ed46869 | 2609 | |
df7492f9 | 2610 | no_more_source: |
ff0dacd7 KH |
2611 | detect_info->rejected |= rejected; |
2612 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 2613 | return 1; |
4ed46869 | 2614 | } |
ec6d2bb8 | 2615 | |
4ed46869 KH |
2616 | |
2617 | /* Set designation state into CODING. */ | |
df7492f9 KH |
2618 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
2619 | do { \ | |
2620 | int id, prev; \ | |
2621 | \ | |
2622 | if (final < '0' || final >= 128 \ | |
2623 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
2624 | || !SAFE_CHARSET_P (coding, id)) \ | |
2625 | { \ | |
2626 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
2627 | goto invalid_code; \ | |
2628 | } \ | |
2629 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
2630 | if (id == charset_jisx0201_roman) \ |
2631 | { \ | |
2632 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
2633 | id = charset_ascii; \ | |
2634 | } \ | |
2635 | else if (id == charset_jisx0208_1978) \ | |
2636 | { \ | |
2637 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
2638 | id = charset_jisx0208; \ | |
2639 | } \ | |
df7492f9 KH |
2640 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
2641 | /* If there was an invalid designation to REG previously, and this \ | |
2642 | designation is ASCII to REG, we should keep this designation \ | |
2643 | sequence. */ \ | |
2644 | if (prev == -2 && id == charset_ascii) \ | |
2645 | goto invalid_code; \ | |
4ed46869 KH |
2646 | } while (0) |
2647 | ||
d46c5b12 | 2648 | |
df7492f9 KH |
2649 | #define MAYBE_FINISH_COMPOSITION() \ |
2650 | do { \ | |
2651 | int i; \ | |
2652 | if (composition_state == COMPOSING_NO) \ | |
2653 | break; \ | |
2654 | /* It is assured that we have enough room for producing \ | |
2655 | characters stored in the table `components'. */ \ | |
2656 | if (charbuf + component_idx > charbuf_end) \ | |
2657 | goto no_more_source; \ | |
2658 | composition_state = COMPOSING_NO; \ | |
2659 | if (method == COMPOSITION_RELATIVE \ | |
2660 | || method == COMPOSITION_WITH_ALTCHARS) \ | |
2661 | { \ | |
2662 | for (i = 0; i < component_idx; i++) \ | |
2663 | *charbuf++ = components[i]; \ | |
2664 | char_offset += component_idx; \ | |
2665 | } \ | |
2666 | else \ | |
2667 | { \ | |
2668 | for (i = 0; i < component_idx; i += 2) \ | |
2669 | *charbuf++ = components[i]; \ | |
2670 | char_offset += (component_idx / 2) + 1; \ | |
2671 | } \ | |
2672 | } while (0) | |
2673 | ||
d46c5b12 | 2674 | |
aa72b389 KH |
2675 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
2676 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 | |
2677 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
2678 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
2679 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
aa72b389 | 2680 | */ |
ec6d2bb8 | 2681 | |
df7492f9 KH |
2682 | #define DECODE_COMPOSITION_START(c1) \ |
2683 | do { \ | |
2684 | if (c1 == '0' \ | |
781d7a48 | 2685 | && composition_state == COMPOSING_COMPONENT_RULE) \ |
df7492f9 KH |
2686 | { \ |
2687 | component_len = component_idx; \ | |
2688 | composition_state = COMPOSING_CHAR; \ | |
2689 | } \ | |
2690 | else \ | |
2691 | { \ | |
8f924df7 | 2692 | const unsigned char *p; \ |
df7492f9 KH |
2693 | \ |
2694 | MAYBE_FINISH_COMPOSITION (); \ | |
2695 | if (charbuf + MAX_COMPOSITION_COMPONENTS > charbuf_end) \ | |
2696 | goto no_more_source; \ | |
2697 | for (p = src; p < src_end - 1; p++) \ | |
2698 | if (*p == ISO_CODE_ESC && p[1] == '1') \ | |
2699 | break; \ | |
2700 | if (p == src_end - 1) \ | |
2701 | { \ | |
2702 | if (coding->mode & CODING_MODE_LAST_BLOCK) \ | |
2703 | goto invalid_code; \ | |
2704 | goto no_more_source; \ | |
2705 | } \ | |
2706 | \ | |
2707 | /* This is surely the start of a composition. */ \ | |
2708 | method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
2709 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
2710 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
2711 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
2712 | composition_state = (c1 <= '2' ? COMPOSING_CHAR \ | |
2713 | : COMPOSING_COMPONENT_CHAR); \ | |
2714 | component_idx = component_len = 0; \ | |
2715 | } \ | |
ec6d2bb8 KH |
2716 | } while (0) |
2717 | ||
ec6d2bb8 | 2718 | |
df7492f9 KH |
2719 | /* Handle compositoin end sequence ESC 1. */ |
2720 | ||
2721 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 2722 | do { \ |
df7492f9 KH |
2723 | int nchars = (component_len > 0 ? component_idx - component_len \ |
2724 | : method == COMPOSITION_RELATIVE ? component_idx \ | |
2725 | : (component_idx + 1) / 2); \ | |
2726 | int i; \ | |
2727 | int *saved_charbuf = charbuf; \ | |
8f924df7 | 2728 | int from = char_offset; \ |
ff0dacd7 | 2729 | int to = from + nchars; \ |
df7492f9 | 2730 | \ |
ff0dacd7 | 2731 | ADD_COMPOSITION_DATA (charbuf, from, to, method); \ |
df7492f9 | 2732 | if (method != COMPOSITION_RELATIVE) \ |
ec6d2bb8 | 2733 | { \ |
df7492f9 KH |
2734 | if (component_len == 0) \ |
2735 | for (i = 0; i < component_idx; i++) \ | |
2736 | *charbuf++ = components[i]; \ | |
2737 | else \ | |
2738 | for (i = 0; i < component_len; i++) \ | |
2739 | *charbuf++ = components[i]; \ | |
2740 | *saved_charbuf = saved_charbuf - charbuf; \ | |
ec6d2bb8 | 2741 | } \ |
df7492f9 KH |
2742 | if (method == COMPOSITION_WITH_RULE) \ |
2743 | for (i = 0; i < component_idx; i += 2, char_offset++) \ | |
2744 | *charbuf++ = components[i]; \ | |
ec6d2bb8 | 2745 | else \ |
df7492f9 KH |
2746 | for (i = component_len; i < component_idx; i++, char_offset++) \ |
2747 | *charbuf++ = components[i]; \ | |
2748 | coding->annotated = 1; \ | |
2749 | composition_state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
2750 | } while (0) |
2751 | ||
df7492f9 | 2752 | |
ec6d2bb8 KH |
2753 | /* Decode a composition rule from the byte C1 (and maybe one more byte |
2754 | from SRC) and store one encoded composition rule in | |
2755 | coding->cmp_data. */ | |
2756 | ||
2757 | #define DECODE_COMPOSITION_RULE(c1) \ | |
2758 | do { \ | |
ec6d2bb8 KH |
2759 | (c1) -= 32; \ |
2760 | if (c1 < 81) /* old format (before ver.21) */ \ | |
2761 | { \ | |
2762 | int gref = (c1) / 9; \ | |
2763 | int nref = (c1) % 9; \ | |
2764 | if (gref == 4) gref = 10; \ | |
2765 | if (nref == 4) nref = 10; \ | |
df7492f9 | 2766 | c1 = COMPOSITION_ENCODE_RULE (gref, nref); \ |
ec6d2bb8 | 2767 | } \ |
b73bfc1c | 2768 | else if (c1 < 93) /* new format (after ver.21) */ \ |
ec6d2bb8 KH |
2769 | { \ |
2770 | ONE_MORE_BYTE (c2); \ | |
df7492f9 | 2771 | c1 = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \ |
ec6d2bb8 | 2772 | } \ |
df7492f9 KH |
2773 | else \ |
2774 | c1 = 0; \ | |
ec6d2bb8 | 2775 | } while (0) |
88993dfd | 2776 | |
d46c5b12 | 2777 | |
4ed46869 KH |
2778 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
2779 | ||
b73bfc1c | 2780 | static void |
df7492f9 | 2781 | decode_coding_iso_2022 (coding) |
4ed46869 | 2782 | struct coding_system *coding; |
4ed46869 | 2783 | { |
8f924df7 KH |
2784 | const unsigned char *src = coding->source + coding->consumed; |
2785 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2786 | const unsigned char *src_base; | |
df7492f9 | 2787 | int *charbuf = coding->charbuf; |
ff0dacd7 KH |
2788 | int *charbuf_end |
2789 | = charbuf + coding->charbuf_size - 4 - MAX_ANNOTATION_LENGTH; | |
df7492f9 | 2790 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2791 | int multibytep = coding->src_multibyte; |
4ed46869 | 2792 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
2793 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
2794 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
2795 | struct charset *charset; | |
2796 | int c; | |
2797 | /* For handling composition sequence. */ | |
2798 | #define COMPOSING_NO 0 | |
2799 | #define COMPOSING_CHAR 1 | |
2800 | #define COMPOSING_RULE 2 | |
2801 | #define COMPOSING_COMPONENT_CHAR 3 | |
2802 | #define COMPOSING_COMPONENT_RULE 4 | |
2803 | ||
2804 | int composition_state = COMPOSING_NO; | |
2805 | enum composition_method method; | |
2806 | int components[MAX_COMPOSITION_COMPONENTS * 2 + 1]; | |
2807 | int component_idx; | |
2808 | int component_len; | |
2809 | Lisp_Object attrs, eol_type, charset_list; | |
ff0dacd7 KH |
2810 | int char_offset = coding->produced_char; |
2811 | int last_offset = char_offset; | |
2812 | int last_id = charset_ascii; | |
df7492f9 KH |
2813 | |
2814 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
2815 | setup_iso_safe_charsets (attrs); | |
b73bfc1c KH |
2816 | |
2817 | while (1) | |
4ed46869 | 2818 | { |
463f5630 | 2819 | int c1, c2; |
b73bfc1c KH |
2820 | |
2821 | src_base = src; | |
df7492f9 KH |
2822 | consumed_chars_base = consumed_chars; |
2823 | ||
2824 | if (charbuf >= charbuf_end) | |
2825 | break; | |
2826 | ||
b73bfc1c | 2827 | ONE_MORE_BYTE (c1); |
4ed46869 | 2828 | |
98725083 | 2829 | /* We produce at most one character. */ |
4ed46869 KH |
2830 | switch (iso_code_class [c1]) |
2831 | { | |
2832 | case ISO_0x20_or_0x7F: | |
df7492f9 | 2833 | if (composition_state != COMPOSING_NO) |
ec6d2bb8 | 2834 | { |
df7492f9 KH |
2835 | if (composition_state == COMPOSING_RULE |
2836 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2837 | { | |
2838 | DECODE_COMPOSITION_RULE (c1); | |
2839 | components[component_idx++] = c1; | |
2840 | composition_state--; | |
2841 | continue; | |
2842 | } | |
4ed46869 | 2843 | } |
df7492f9 KH |
2844 | if (charset_id_0 < 0 |
2845 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
2846 | /* This is SPACE or DEL. */ |
2847 | charset = CHARSET_FROM_ID (charset_ascii); | |
2848 | else | |
2849 | charset = CHARSET_FROM_ID (charset_id_0); | |
2850 | break; | |
4ed46869 KH |
2851 | |
2852 | case ISO_graphic_plane_0: | |
781d7a48 | 2853 | if (composition_state != COMPOSING_NO) |
b73bfc1c | 2854 | { |
781d7a48 KH |
2855 | if (composition_state == COMPOSING_RULE |
2856 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2857 | { | |
2858 | DECODE_COMPOSITION_RULE (c1); | |
2859 | components[component_idx++] = c1; | |
2860 | composition_state--; | |
2861 | continue; | |
2862 | } | |
b73bfc1c | 2863 | } |
df7492f9 | 2864 | charset = CHARSET_FROM_ID (charset_id_0); |
4ed46869 KH |
2865 | break; |
2866 | ||
2867 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
2868 | if (charset_id_1 < 0 |
2869 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
2870 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
2871 | goto invalid_code; | |
4ed46869 KH |
2872 | /* This is a graphic character, we fall down ... */ |
2873 | ||
2874 | case ISO_graphic_plane_1: | |
df7492f9 KH |
2875 | if (charset_id_1 < 0) |
2876 | goto invalid_code; | |
2877 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
2878 | break; |
2879 | ||
2880 | case ISO_carriage_return: | |
df7492f9 | 2881 | if (c1 == '\r') |
4ed46869 | 2882 | { |
df7492f9 | 2883 | if (EQ (eol_type, Qdos)) |
4ed46869 | 2884 | { |
df7492f9 | 2885 | if (src == src_end) |
98725083 KH |
2886 | { |
2887 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; | |
2888 | goto no_more_source; | |
8f924df7 | 2889 | } |
df7492f9 KH |
2890 | if (*src == '\n') |
2891 | ONE_MORE_BYTE (c1); | |
4ed46869 | 2892 | } |
df7492f9 KH |
2893 | else if (EQ (eol_type, Qmac)) |
2894 | c1 = '\n'; | |
4ed46869 | 2895 | } |
df7492f9 KH |
2896 | /* fall through */ |
2897 | ||
2898 | case ISO_control_0: | |
2899 | MAYBE_FINISH_COMPOSITION (); | |
2900 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
2901 | break; |
2902 | ||
df7492f9 KH |
2903 | case ISO_control_1: |
2904 | MAYBE_FINISH_COMPOSITION (); | |
2905 | goto invalid_code; | |
2906 | ||
4ed46869 | 2907 | case ISO_shift_out: |
df7492f9 KH |
2908 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
2909 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
2910 | goto invalid_code; | |
2911 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
2912 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 2913 | continue; |
4ed46869 KH |
2914 | |
2915 | case ISO_shift_in: | |
df7492f9 KH |
2916 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
2917 | goto invalid_code; | |
2918 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
2919 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 2920 | continue; |
4ed46869 KH |
2921 | |
2922 | case ISO_single_shift_2_7: | |
2923 | case ISO_single_shift_2: | |
df7492f9 KH |
2924 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
2925 | goto invalid_code; | |
4ed46869 KH |
2926 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
2927 | c1 = 'N'; | |
2928 | goto label_escape_sequence; | |
2929 | ||
2930 | case ISO_single_shift_3: | |
df7492f9 KH |
2931 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
2932 | goto invalid_code; | |
4ed46869 KH |
2933 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
2934 | c1 = 'O'; | |
2935 | goto label_escape_sequence; | |
2936 | ||
2937 | case ISO_control_sequence_introducer: | |
2938 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
2939 | c1 = '['; | |
2940 | goto label_escape_sequence; | |
2941 | ||
2942 | case ISO_escape: | |
2943 | ONE_MORE_BYTE (c1); | |
2944 | label_escape_sequence: | |
df7492f9 | 2945 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
2946 | designation, direction specification, and character |
2947 | composition specification. */ | |
2948 | switch (c1) | |
2949 | { | |
2950 | case '&': /* revision of following character set */ | |
2951 | ONE_MORE_BYTE (c1); | |
2952 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 2953 | goto invalid_code; |
4ed46869 KH |
2954 | ONE_MORE_BYTE (c1); |
2955 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 2956 | goto invalid_code; |
4ed46869 KH |
2957 | ONE_MORE_BYTE (c1); |
2958 | goto label_escape_sequence; | |
2959 | ||
2960 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
2961 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
2962 | goto invalid_code; | |
4ed46869 KH |
2963 | ONE_MORE_BYTE (c1); |
2964 | if (c1 >= '@' && c1 <= 'B') | |
2965 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 2966 | or JISX0208.1980 */ |
df7492f9 | 2967 | DECODE_DESIGNATION (0, 2, 0, c1); |
4ed46869 KH |
2968 | } |
2969 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
2970 | { /* designation of DIMENSION2_CHARS94 character set */ | |
2971 | ONE_MORE_BYTE (c2); | |
df7492f9 | 2972 | DECODE_DESIGNATION (c1 - 0x28, 2, 0, c2); |
4ed46869 KH |
2973 | } |
2974 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
2975 | { /* designation of DIMENSION2_CHARS96 character set */ | |
2976 | ONE_MORE_BYTE (c2); | |
df7492f9 | 2977 | DECODE_DESIGNATION (c1 - 0x2C, 2, 1, c2); |
4ed46869 KH |
2978 | } |
2979 | else | |
df7492f9 | 2980 | goto invalid_code; |
b73bfc1c | 2981 | /* We must update these variables now. */ |
df7492f9 KH |
2982 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
2983 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
b73bfc1c | 2984 | continue; |
4ed46869 KH |
2985 | |
2986 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
2987 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
2988 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
2989 | goto invalid_code; | |
2990 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
2991 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 2992 | continue; |
4ed46869 KH |
2993 | |
2994 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
2995 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
2996 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
2997 | goto invalid_code; | |
2998 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
2999 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3000 | continue; |
4ed46869 KH |
3001 | |
3002 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3003 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3004 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3005 | goto invalid_code; | |
3006 | charset = CHARSET_FROM_ID (CODING_ISO_DESIGNATION (coding, 2)); | |
b73bfc1c | 3007 | ONE_MORE_BYTE (c1); |
e7046a18 | 3008 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3009 | goto invalid_code; |
4ed46869 KH |
3010 | break; |
3011 | ||
3012 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3013 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3014 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3015 | goto invalid_code; | |
3016 | charset = CHARSET_FROM_ID (CODING_ISO_DESIGNATION (coding, 3)); | |
b73bfc1c | 3017 | ONE_MORE_BYTE (c1); |
e7046a18 | 3018 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3019 | goto invalid_code; |
4ed46869 KH |
3020 | break; |
3021 | ||
ec6d2bb8 | 3022 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3023 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3024 | goto invalid_code; | |
ec6d2bb8 | 3025 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3026 | continue; |
4ed46869 | 3027 | |
ec6d2bb8 | 3028 | case '1': /* end composition */ |
df7492f9 KH |
3029 | if (composition_state == COMPOSING_NO) |
3030 | goto invalid_code; | |
3031 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3032 | continue; |
4ed46869 KH |
3033 | |
3034 | case '[': /* specification of direction */ | |
df7492f9 KH |
3035 | if (! CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION) |
3036 | goto invalid_code; | |
4ed46869 | 3037 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3038 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
df7492f9 | 3039 | left-to-right, and nozero means right-to-left. */ |
4ed46869 KH |
3040 | ONE_MORE_BYTE (c1); |
3041 | switch (c1) | |
3042 | { | |
3043 | case ']': /* end of the current direction */ | |
d46c5b12 | 3044 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3045 | |
3046 | case '0': /* end of the current direction */ | |
3047 | case '1': /* start of left-to-right direction */ | |
3048 | ONE_MORE_BYTE (c1); | |
3049 | if (c1 == ']') | |
d46c5b12 | 3050 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3051 | else |
df7492f9 | 3052 | goto invalid_code; |
4ed46869 KH |
3053 | break; |
3054 | ||
3055 | case '2': /* start of right-to-left direction */ | |
3056 | ONE_MORE_BYTE (c1); | |
3057 | if (c1 == ']') | |
d46c5b12 | 3058 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3059 | else |
df7492f9 | 3060 | goto invalid_code; |
4ed46869 KH |
3061 | break; |
3062 | ||
3063 | default: | |
df7492f9 | 3064 | goto invalid_code; |
4ed46869 | 3065 | } |
b73bfc1c | 3066 | continue; |
4ed46869 | 3067 | |
103e0180 | 3068 | case '%': |
103e0180 KH |
3069 | ONE_MORE_BYTE (c1); |
3070 | if (c1 == '/') | |
3071 | { | |
3072 | /* CTEXT extended segment: | |
3073 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3074 | We keep these bytes as is for the moment. | |
3075 | They may be decoded by post-read-conversion. */ | |
3076 | int dim, M, L; | |
4776e638 | 3077 | int size; |
8f924df7 | 3078 | |
103e0180 KH |
3079 | ONE_MORE_BYTE (dim); |
3080 | ONE_MORE_BYTE (M); | |
3081 | ONE_MORE_BYTE (L); | |
3082 | size = ((M - 128) * 128) + (L - 128); | |
4776e638 KH |
3083 | if (charbuf + 8 + size > charbuf_end) |
3084 | goto break_loop; | |
3085 | *charbuf++ = ISO_CODE_ESC; | |
3086 | *charbuf++ = '%'; | |
3087 | *charbuf++ = '/'; | |
3088 | *charbuf++ = dim; | |
3089 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3090 | *charbuf++ = BYTE8_TO_CHAR (L); | |
103e0180 KH |
3091 | while (size-- > 0) |
3092 | { | |
3093 | ONE_MORE_BYTE (c1); | |
4776e638 | 3094 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3095 | } |
103e0180 KH |
3096 | } |
3097 | else if (c1 == 'G') | |
3098 | { | |
103e0180 KH |
3099 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3100 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3101 | We keep these bytes as is for the moment. | |
3102 | They may be decoded by post-read-conversion. */ | |
4776e638 KH |
3103 | int *p = charbuf; |
3104 | ||
3105 | if (p + 6 > charbuf_end) | |
3106 | goto break_loop; | |
3107 | *p++ = ISO_CODE_ESC; | |
3108 | *p++ = '%'; | |
3109 | *p++ = 'G'; | |
3110 | while (p < charbuf_end) | |
103e0180 KH |
3111 | { |
3112 | ONE_MORE_BYTE (c1); | |
3113 | if (c1 == ISO_CODE_ESC | |
3114 | && src + 1 < src_end | |
3115 | && src[0] == '%' | |
3116 | && src[1] == '@') | |
3117 | break; | |
4776e638 | 3118 | *p++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3119 | } |
4776e638 KH |
3120 | if (p + 3 > charbuf_end) |
3121 | goto break_loop; | |
3122 | *p++ = ISO_CODE_ESC; | |
3123 | *p++ = '%'; | |
3124 | *p++ = '@'; | |
3125 | charbuf = p; | |
103e0180 KH |
3126 | } |
3127 | else | |
4776e638 | 3128 | goto invalid_code; |
103e0180 | 3129 | continue; |
4776e638 | 3130 | break; |
103e0180 | 3131 | |
4ed46869 | 3132 | default: |
df7492f9 KH |
3133 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3134 | goto invalid_code; | |
4ed46869 KH |
3135 | if (c1 >= 0x28 && c1 <= 0x2B) |
3136 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3137 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3138 | DECODE_DESIGNATION (c1 - 0x28, 1, 0, c2); |
4ed46869 KH |
3139 | } |
3140 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3141 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3142 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3143 | DECODE_DESIGNATION (c1 - 0x2C, 1, 1, c2); |
4ed46869 KH |
3144 | } |
3145 | else | |
df7492f9 | 3146 | goto invalid_code; |
b73bfc1c | 3147 | /* We must update these variables now. */ |
df7492f9 KH |
3148 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3149 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
b73bfc1c | 3150 | continue; |
4ed46869 | 3151 | } |
b73bfc1c | 3152 | } |
4ed46869 | 3153 | |
ff0dacd7 KH |
3154 | if (charset->id != charset_ascii |
3155 | && last_id != charset->id) | |
3156 | { | |
3157 | if (last_id != charset_ascii) | |
3158 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
3159 | last_id = charset->id; | |
3160 | last_offset = char_offset; | |
3161 | } | |
3162 | ||
b73bfc1c | 3163 | /* Now we know CHARSET and 1st position code C1 of a character. |
df7492f9 KH |
3164 | Produce a decoded character while getting 2nd position code |
3165 | C2 if necessary. */ | |
3166 | c1 &= 0x7F; | |
3167 | if (CHARSET_DIMENSION (charset) > 1) | |
b73bfc1c KH |
3168 | { |
3169 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3170 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) |
b73bfc1c | 3171 | /* C2 is not in a valid range. */ |
df7492f9 KH |
3172 | goto invalid_code; |
3173 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3174 | if (CHARSET_DIMENSION (charset) > 2) | |
3175 | { | |
3176 | ONE_MORE_BYTE (c2); | |
3177 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) | |
3178 | /* C2 is not in a valid range. */ | |
3179 | goto invalid_code; | |
3180 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3181 | } | |
3182 | } | |
3183 | ||
3184 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); | |
3185 | if (c < 0) | |
3186 | { | |
3187 | MAYBE_FINISH_COMPOSITION (); | |
3188 | for (; src_base < src; src_base++, char_offset++) | |
3189 | { | |
3190 | if (ASCII_BYTE_P (*src_base)) | |
3191 | *charbuf++ = *src_base; | |
3192 | else | |
3193 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3194 | } | |
3195 | } | |
3196 | else if (composition_state == COMPOSING_NO) | |
3197 | { | |
3198 | *charbuf++ = c; | |
3199 | char_offset++; | |
4ed46869 | 3200 | } |
df7492f9 | 3201 | else |
781d7a48 KH |
3202 | { |
3203 | components[component_idx++] = c; | |
3204 | if (method == COMPOSITION_WITH_RULE | |
3205 | || (method == COMPOSITION_WITH_RULE_ALTCHARS | |
3206 | && composition_state == COMPOSING_COMPONENT_CHAR)) | |
3207 | composition_state++; | |
4ed46869 KH |
3208 | } |
3209 | continue; | |
3210 | ||
df7492f9 KH |
3211 | invalid_code: |
3212 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3213 | src = src_base; |
df7492f9 KH |
3214 | consumed_chars = consumed_chars_base; |
3215 | ONE_MORE_BYTE (c); | |
3216 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 3217 | char_offset++; |
df7492f9 | 3218 | coding->errors++; |
4776e638 KH |
3219 | continue; |
3220 | ||
3221 | break_loop: | |
3222 | break; | |
4ed46869 | 3223 | } |
fb88bf2d | 3224 | |
df7492f9 | 3225 | no_more_source: |
ff0dacd7 KH |
3226 | if (last_id != charset_ascii) |
3227 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
df7492f9 KH |
3228 | coding->consumed_char += consumed_chars_base; |
3229 | coding->consumed = src_base - coding->source; | |
3230 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3231 | } |
3232 | ||
b73bfc1c | 3233 | |
f4dee582 | 3234 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3235 | |
3236 | /* | |
f4dee582 | 3237 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 3238 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 3239 | variant has the following specifications: |
df7492f9 | 3240 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
3241 | 2. Allows short-form designation? |
3242 | 3. ASCII should be designated to G0 before control characters? | |
3243 | 4. ASCII should be designated to G0 at end of line? | |
3244 | 5. 7-bit environment or 8-bit environment? | |
3245 | 6. Use locking-shift? | |
3246 | 7. Use Single-shift? | |
3247 | And the following two are only for Japanese: | |
3248 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
3249 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
3250 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
3251 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 3252 | details. |
4ed46869 KH |
3253 | */ |
3254 | ||
3255 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
3256 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
3257 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
3258 | designation sequence of short-form. */ | |
4ed46869 KH |
3259 | |
3260 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
3261 | do { \ | |
df7492f9 | 3262 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
4ed46869 KH |
3263 | char *intermediate_char_94 = "()*+"; \ |
3264 | char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
3265 | int revision = -1; \ |
3266 | int c; \ | |
3267 | \ | |
3268 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 3269 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
3270 | \ |
3271 | if (revision >= 0) \ | |
70c22245 | 3272 | { \ |
df7492f9 KH |
3273 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
3274 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 3275 | } \ |
df7492f9 | 3276 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
3277 | if (CHARSET_DIMENSION (charset) == 1) \ |
3278 | { \ | |
df7492f9 KH |
3279 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
3280 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 3281 | else \ |
df7492f9 KH |
3282 | c = intermediate_char_96[reg]; \ |
3283 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
3284 | } \ |
3285 | else \ | |
3286 | { \ | |
df7492f9 KH |
3287 | EMIT_ONE_ASCII_BYTE ('$'); \ |
3288 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 3289 | { \ |
df7492f9 | 3290 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
3291 | || reg != 0 \ |
3292 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 3293 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
3294 | } \ |
3295 | else \ | |
df7492f9 | 3296 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 3297 | } \ |
df7492f9 KH |
3298 | EMIT_ONE_ASCII_BYTE (final_char); \ |
3299 | \ | |
3300 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
3301 | } while (0) |
3302 | ||
df7492f9 | 3303 | |
4ed46869 KH |
3304 | /* The following two macros produce codes (control character or escape |
3305 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
3306 | single-shift-3). */ | |
3307 | ||
df7492f9 KH |
3308 | #define ENCODE_SINGLE_SHIFT_2 \ |
3309 | do { \ | |
3310 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3311 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
3312 | else \ | |
3313 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
3314 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3315 | } while (0) |
3316 | ||
df7492f9 KH |
3317 | |
3318 | #define ENCODE_SINGLE_SHIFT_3 \ | |
3319 | do { \ | |
3320 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3321 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
3322 | else \ | |
3323 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
3324 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3325 | } while (0) |
3326 | ||
df7492f9 | 3327 | |
4ed46869 KH |
3328 | /* The following four macros produce codes (control character or |
3329 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
3330 | shift-out, locking-shift-2, and locking-shift-3). */ | |
3331 | ||
df7492f9 KH |
3332 | #define ENCODE_SHIFT_IN \ |
3333 | do { \ | |
3334 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
3335 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
3336 | } while (0) |
3337 | ||
df7492f9 KH |
3338 | |
3339 | #define ENCODE_SHIFT_OUT \ | |
3340 | do { \ | |
3341 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
3342 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
3343 | } while (0) |
3344 | ||
df7492f9 KH |
3345 | |
3346 | #define ENCODE_LOCKING_SHIFT_2 \ | |
3347 | do { \ | |
3348 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3349 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
3350 | } while (0) |
3351 | ||
df7492f9 KH |
3352 | |
3353 | #define ENCODE_LOCKING_SHIFT_3 \ | |
3354 | do { \ | |
3355 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3356 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
3357 | } while (0) |
3358 | ||
df7492f9 | 3359 | |
f4dee582 RS |
3360 | /* Produce codes for a DIMENSION1 character whose character set is |
3361 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
3362 | sequences are also produced in advance if necessary. */ |
3363 | ||
6e85d753 KH |
3364 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
3365 | do { \ | |
df7492f9 | 3366 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3367 | \ |
3368 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3369 | && id == charset_ascii) \ | |
3370 | { \ | |
3371 | id = charset_jisx0201_roman; \ | |
3372 | charset = CHARSET_FROM_ID (id); \ | |
3373 | } \ | |
3374 | \ | |
df7492f9 | 3375 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3376 | { \ |
df7492f9 KH |
3377 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3378 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 3379 | else \ |
df7492f9 KH |
3380 | EMIT_ONE_BYTE (c1 | 0x80); \ |
3381 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3382 | break; \ |
3383 | } \ | |
df7492f9 | 3384 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3385 | { \ |
df7492f9 | 3386 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
3387 | break; \ |
3388 | } \ | |
df7492f9 | 3389 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3390 | { \ |
df7492f9 | 3391 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
3392 | break; \ |
3393 | } \ | |
6e85d753 KH |
3394 | else \ |
3395 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3396 | must invoke it, or, at first, designate it to some graphic \ | |
3397 | register. Then repeat the loop to actually produce the \ | |
3398 | character. */ \ | |
df7492f9 KH |
3399 | dst = encode_invocation_designation (charset, coding, dst, \ |
3400 | &produced_chars); \ | |
4ed46869 KH |
3401 | } while (1) |
3402 | ||
df7492f9 | 3403 | |
f4dee582 RS |
3404 | /* Produce codes for a DIMENSION2 character whose character set is |
3405 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
3406 | invocation codes are also produced in advance if necessary. */ |
3407 | ||
6e85d753 KH |
3408 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
3409 | do { \ | |
df7492f9 | 3410 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3411 | \ |
3412 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3413 | && id == charset_jisx0208) \ | |
3414 | { \ | |
3415 | id = charset_jisx0208_1978; \ | |
3416 | charset = CHARSET_FROM_ID (id); \ | |
3417 | } \ | |
3418 | \ | |
df7492f9 | 3419 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3420 | { \ |
df7492f9 KH |
3421 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3422 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 3423 | else \ |
df7492f9 KH |
3424 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
3425 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3426 | break; \ |
3427 | } \ | |
df7492f9 | 3428 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3429 | { \ |
df7492f9 | 3430 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
3431 | break; \ |
3432 | } \ | |
df7492f9 | 3433 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3434 | { \ |
df7492f9 | 3435 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
3436 | break; \ |
3437 | } \ | |
6e85d753 KH |
3438 | else \ |
3439 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3440 | must invoke it, or, at first, designate it to some graphic \ | |
3441 | register. Then repeat the loop to actually produce the \ | |
3442 | character. */ \ | |
df7492f9 KH |
3443 | dst = encode_invocation_designation (charset, coding, dst, \ |
3444 | &produced_chars); \ | |
4ed46869 KH |
3445 | } while (1) |
3446 | ||
05e6f5dc | 3447 | |
df7492f9 KH |
3448 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
3449 | do { \ | |
3450 | int code = ENCODE_CHAR ((charset),(c)); \ | |
3451 | \ | |
3452 | if (CHARSET_DIMENSION (charset) == 1) \ | |
3453 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
3454 | else \ | |
3455 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 3456 | } while (0) |
bdd9fb48 | 3457 | |
05e6f5dc | 3458 | |
4ed46869 | 3459 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 3460 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
3461 | Return new DST. */ |
3462 | ||
3463 | unsigned char * | |
df7492f9 KH |
3464 | encode_invocation_designation (charset, coding, dst, p_nchars) |
3465 | struct charset *charset; | |
4ed46869 KH |
3466 | struct coding_system *coding; |
3467 | unsigned char *dst; | |
df7492f9 | 3468 | int *p_nchars; |
4ed46869 | 3469 | { |
df7492f9 KH |
3470 | int multibytep = coding->dst_multibyte; |
3471 | int produced_chars = *p_nchars; | |
4ed46869 | 3472 | int reg; /* graphic register number */ |
df7492f9 | 3473 | int id = CHARSET_ID (charset); |
4ed46869 KH |
3474 | |
3475 | /* At first, check designations. */ | |
3476 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 3477 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
3478 | break; |
3479 | ||
3480 | if (reg >= 4) | |
3481 | { | |
3482 | /* CHARSET is not yet designated to any graphic registers. */ | |
3483 | /* At first check the requested designation. */ | |
df7492f9 KH |
3484 | reg = CODING_ISO_REQUEST (coding, id); |
3485 | if (reg < 0) | |
1ba9e4ab KH |
3486 | /* Since CHARSET requests no special designation, designate it |
3487 | to graphic register 0. */ | |
4ed46869 KH |
3488 | reg = 0; |
3489 | ||
3490 | ENCODE_DESIGNATION (charset, reg, coding); | |
3491 | } | |
3492 | ||
df7492f9 KH |
3493 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
3494 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
3495 | { |
3496 | /* Since the graphic register REG is not invoked to any graphic | |
3497 | planes, invoke it to graphic plane 0. */ | |
3498 | switch (reg) | |
3499 | { | |
3500 | case 0: /* graphic register 0 */ | |
3501 | ENCODE_SHIFT_IN; | |
3502 | break; | |
3503 | ||
3504 | case 1: /* graphic register 1 */ | |
3505 | ENCODE_SHIFT_OUT; | |
3506 | break; | |
3507 | ||
3508 | case 2: /* graphic register 2 */ | |
df7492f9 | 3509 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3510 | ENCODE_SINGLE_SHIFT_2; |
3511 | else | |
3512 | ENCODE_LOCKING_SHIFT_2; | |
3513 | break; | |
3514 | ||
3515 | case 3: /* graphic register 3 */ | |
df7492f9 | 3516 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3517 | ENCODE_SINGLE_SHIFT_3; |
3518 | else | |
3519 | ENCODE_LOCKING_SHIFT_3; | |
3520 | break; | |
3521 | } | |
3522 | } | |
b73bfc1c | 3523 | |
df7492f9 | 3524 | *p_nchars = produced_chars; |
4ed46869 KH |
3525 | return dst; |
3526 | } | |
3527 | ||
df7492f9 KH |
3528 | /* The following three macros produce codes for indicating direction |
3529 | of text. */ | |
3530 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 3531 | do { \ |
df7492f9 KH |
3532 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
3533 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 3534 | else \ |
df7492f9 | 3535 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
3536 | } while (0) |
3537 | ||
ec6d2bb8 | 3538 | |
df7492f9 KH |
3539 | #define ENCODE_DIRECTION_R2L() \ |
3540 | do { \ | |
3541 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
3542 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
3543 | } while (0) |
3544 | ||
ec6d2bb8 | 3545 | |
df7492f9 | 3546 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 3547 | do { \ |
df7492f9 KH |
3548 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
3549 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
ec6d2bb8 | 3550 | } while (0) |
4ed46869 | 3551 | |
4ed46869 KH |
3552 | |
3553 | /* Produce codes for designation and invocation to reset the graphic | |
3554 | planes and registers to initial state. */ | |
df7492f9 KH |
3555 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
3556 | do { \ | |
3557 | int reg; \ | |
3558 | struct charset *charset; \ | |
3559 | \ | |
3560 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
3561 | ENCODE_SHIFT_IN; \ | |
3562 | for (reg = 0; reg < 4; reg++) \ | |
3563 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
3564 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
3565 | != CODING_ISO_INITIAL (coding, reg))) \ | |
3566 | { \ | |
3567 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
3568 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
3569 | } \ | |
4ed46869 KH |
3570 | } while (0) |
3571 | ||
df7492f9 | 3572 | |
bdd9fb48 | 3573 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 3574 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
3575 | |
3576 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
3577 | find all the necessary designations. */ |
3578 | ||
b73bfc1c | 3579 | static unsigned char * |
df7492f9 | 3580 | encode_designation_at_bol (coding, charbuf, charbuf_end, dst) |
e0e989f6 | 3581 | struct coding_system *coding; |
df7492f9 KH |
3582 | int *charbuf, *charbuf_end; |
3583 | unsigned char *dst; | |
e0e989f6 | 3584 | { |
df7492f9 | 3585 | struct charset *charset; |
bdd9fb48 KH |
3586 | /* Table of charsets to be designated to each graphic register. */ |
3587 | int r[4]; | |
df7492f9 KH |
3588 | int c, found = 0, reg; |
3589 | int produced_chars = 0; | |
3590 | int multibytep = coding->dst_multibyte; | |
3591 | Lisp_Object attrs; | |
3592 | Lisp_Object charset_list; | |
3593 | ||
3594 | attrs = CODING_ID_ATTRS (coding->id); | |
3595 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
3596 | if (EQ (charset_list, Qiso_2022)) | |
3597 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
3598 | |
3599 | for (reg = 0; reg < 4; reg++) | |
3600 | r[reg] = -1; | |
3601 | ||
b73bfc1c | 3602 | while (found < 4) |
e0e989f6 | 3603 | { |
df7492f9 KH |
3604 | int id; |
3605 | ||
3606 | c = *charbuf++; | |
b73bfc1c KH |
3607 | if (c == '\n') |
3608 | break; | |
df7492f9 KH |
3609 | charset = char_charset (c, charset_list, NULL); |
3610 | id = CHARSET_ID (charset); | |
3611 | reg = CODING_ISO_REQUEST (coding, id); | |
3612 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
3613 | { |
3614 | found++; | |
df7492f9 | 3615 | r[reg] = id; |
bdd9fb48 | 3616 | } |
bdd9fb48 KH |
3617 | } |
3618 | ||
3619 | if (found) | |
3620 | { | |
3621 | for (reg = 0; reg < 4; reg++) | |
3622 | if (r[reg] >= 0 | |
df7492f9 KH |
3623 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
3624 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 3625 | } |
b73bfc1c KH |
3626 | |
3627 | return dst; | |
e0e989f6 KH |
3628 | } |
3629 | ||
4ed46869 KH |
3630 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
3631 | ||
df7492f9 KH |
3632 | static int |
3633 | encode_coding_iso_2022 (coding) | |
4ed46869 | 3634 | struct coding_system *coding; |
4ed46869 | 3635 | { |
df7492f9 KH |
3636 | int multibytep = coding->dst_multibyte; |
3637 | int *charbuf = coding->charbuf; | |
3638 | int *charbuf_end = charbuf + coding->charbuf_used; | |
3639 | unsigned char *dst = coding->destination + coding->produced; | |
3640 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
3641 | int safe_room = 16; | |
3642 | int bol_designation | |
3643 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
3644 | && CODING_ISO_BOL (coding)); | |
3645 | int produced_chars = 0; | |
3646 | Lisp_Object attrs, eol_type, charset_list; | |
3647 | int ascii_compatible; | |
b73bfc1c | 3648 | int c; |
ff0dacd7 | 3649 | int preferred_charset_id = -1; |
05e6f5dc | 3650 | |
df7492f9 | 3651 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
004068e4 | 3652 | setup_iso_safe_charsets (attrs); |
ff0dacd7 KH |
3653 | /* Charset list may have been changed. */ |
3654 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); \ | |
8f924df7 | 3655 | coding->safe_charsets = (char *) SDATA (CODING_ATTR_SAFE_CHARSETS(attrs)); |
0eecad43 | 3656 | |
df7492f9 | 3657 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
bdd9fb48 | 3658 | |
df7492f9 | 3659 | while (charbuf < charbuf_end) |
4ed46869 | 3660 | { |
df7492f9 | 3661 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 3662 | |
df7492f9 | 3663 | if (bol_designation) |
b73bfc1c | 3664 | { |
df7492f9 | 3665 | unsigned char *dst_prev = dst; |
4ed46869 | 3666 | |
bdd9fb48 | 3667 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
3668 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
3669 | bol_designation = 0; | |
3670 | /* We are sure that designation sequences are all ASCII bytes. */ | |
3671 | produced_chars += dst - dst_prev; | |
e0e989f6 KH |
3672 | } |
3673 | ||
df7492f9 | 3674 | c = *charbuf++; |
ec6d2bb8 | 3675 | |
ff0dacd7 KH |
3676 | if (c < 0) |
3677 | { | |
3678 | /* Handle an annotation. */ | |
3679 | switch (*charbuf) | |
ec6d2bb8 | 3680 | { |
ff0dacd7 KH |
3681 | case CODING_ANNOTATE_COMPOSITION_MASK: |
3682 | /* Not yet implemented. */ | |
3683 | break; | |
3684 | case CODING_ANNOTATE_CHARSET_MASK: | |
3685 | preferred_charset_id = charbuf[3]; | |
3686 | if (preferred_charset_id >= 0 | |
3687 | && NILP (Fmemq (make_number (preferred_charset_id), | |
3688 | charset_list))) | |
3689 | preferred_charset_id = -1; | |
3690 | break; | |
3691 | default: | |
3692 | abort (); | |
4ed46869 | 3693 | } |
ff0dacd7 KH |
3694 | charbuf += -c - 1; |
3695 | continue; | |
4ed46869 | 3696 | } |
ec6d2bb8 | 3697 | |
b73bfc1c KH |
3698 | /* Now encode the character C. */ |
3699 | if (c < 0x20 || c == 0x7F) | |
3700 | { | |
df7492f9 KH |
3701 | if (c == '\n' |
3702 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 3703 | { |
df7492f9 KH |
3704 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
3705 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3706 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 3707 | { |
df7492f9 KH |
3708 | int i; |
3709 | ||
3710 | for (i = 0; i < 4; i++) | |
3711 | CODING_ISO_DESIGNATION (coding, i) | |
3712 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 3713 | } |
df7492f9 KH |
3714 | bol_designation |
3715 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 3716 | } |
df7492f9 KH |
3717 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
3718 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3719 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 3720 | } |
df7492f9 | 3721 | else if (ASCII_CHAR_P (c)) |
88993dfd | 3722 | { |
df7492f9 KH |
3723 | if (ascii_compatible) |
3724 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 3725 | else |
19a8d9e0 | 3726 | { |
bf16eb23 KH |
3727 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
3728 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 3729 | } |
4ed46869 | 3730 | } |
16eafb5d | 3731 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 3732 | { |
16eafb5d KH |
3733 | c = CHAR_TO_BYTE8 (c); |
3734 | EMIT_ONE_BYTE (c); | |
88993dfd | 3735 | } |
b73bfc1c | 3736 | else |
df7492f9 | 3737 | { |
ff0dacd7 | 3738 | struct charset *charset; |
b73bfc1c | 3739 | |
ff0dacd7 KH |
3740 | if (preferred_charset_id >= 0) |
3741 | { | |
3742 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
3743 | if (! CHAR_CHARSET_P (c, charset)) | |
3744 | charset = char_charset (c, charset_list, NULL); | |
3745 | } | |
3746 | else | |
3747 | charset = char_charset (c, charset_list, NULL); | |
df7492f9 KH |
3748 | if (!charset) |
3749 | { | |
41cbe562 KH |
3750 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
3751 | { | |
3752 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
3753 | charset = CHARSET_FROM_ID (charset_ascii); | |
3754 | } | |
3755 | else | |
3756 | { | |
3757 | c = coding->default_char; | |
3758 | charset = char_charset (c, charset_list, NULL); | |
3759 | } | |
df7492f9 KH |
3760 | } |
3761 | ENCODE_ISO_CHARACTER (charset, c); | |
3762 | } | |
84fbb8a0 | 3763 | } |
b73bfc1c | 3764 | |
df7492f9 KH |
3765 | if (coding->mode & CODING_MODE_LAST_BLOCK |
3766 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
3767 | { | |
3768 | ASSURE_DESTINATION (safe_room); | |
3769 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3770 | } | |
3771 | coding->result = CODING_RESULT_SUCCESS; | |
3772 | CODING_ISO_BOL (coding) = bol_designation; | |
3773 | coding->produced_char += produced_chars; | |
3774 | coding->produced = dst - coding->destination; | |
3775 | return 0; | |
4ed46869 KH |
3776 | } |
3777 | ||
3778 | \f | |
df7492f9 | 3779 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 3780 | |
df7492f9 | 3781 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
3782 | quite widely. So, for the moment, Emacs supports them in the bare |
3783 | C code. But, in the future, they may be supported only by CCL. */ | |
3784 | ||
3785 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
3786 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
3787 | as is. A character of charset katakana-jisx0201 is encoded by | |
3788 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
3789 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 3790 | so that it fit in the range below. |
4ed46869 KH |
3791 | |
3792 | --- CODE RANGE of SJIS --- | |
3793 | (character set) (range) | |
3794 | ASCII 0x00 .. 0x7F | |
df7492f9 | 3795 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 3796 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 3797 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
3798 | ------------------------------- |
3799 | ||
3800 | */ | |
3801 | ||
3802 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
3803 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 3804 | character set and is encoded in two-byte. |
4ed46869 KH |
3805 | |
3806 | --- CODE RANGE of BIG5 --- | |
3807 | (character set) (range) | |
3808 | ASCII 0x00 .. 0x7F | |
3809 | Big5 (1st byte) 0xA1 .. 0xFE | |
3810 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
3811 | -------------------------- | |
3812 | ||
df7492f9 | 3813 | */ |
4ed46869 KH |
3814 | |
3815 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3816 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 3817 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 3818 | |
0a28aafb | 3819 | static int |
ff0dacd7 | 3820 | detect_coding_sjis (coding, detect_info) |
df7492f9 | 3821 | struct coding_system *coding; |
ff0dacd7 | 3822 | struct coding_detection_info *detect_info; |
4ed46869 | 3823 | { |
8f924df7 KH |
3824 | const unsigned char *src = coding->source, *src_base = src; |
3825 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
3826 | int multibytep = coding->src_multibyte; |
3827 | int consumed_chars = 0; | |
3828 | int found = 0; | |
b73bfc1c | 3829 | int c; |
89528eb3 | 3830 | int incomplete; |
df7492f9 | 3831 | |
ff0dacd7 | 3832 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3833 | /* A coding system of this category is always ASCII compatible. */ |
3834 | src += coding->head_ascii; | |
4ed46869 | 3835 | |
b73bfc1c | 3836 | while (1) |
4ed46869 | 3837 | { |
89528eb3 | 3838 | incomplete = 0; |
df7492f9 | 3839 | ONE_MORE_BYTE (c); |
89528eb3 | 3840 | incomplete = 1; |
682169fe KH |
3841 | if (c < 0x80) |
3842 | continue; | |
df7492f9 | 3843 | if ((c >= 0x81 && c <= 0x9F) || (c >= 0xE0 && c <= 0xEF)) |
4ed46869 | 3844 | { |
df7492f9 | 3845 | ONE_MORE_BYTE (c); |
682169fe | 3846 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 3847 | break; |
ff0dacd7 | 3848 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 3849 | } |
df7492f9 | 3850 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 3851 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
3852 | else |
3853 | break; | |
4ed46869 | 3854 | } |
ff0dacd7 | 3855 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3856 | return 0; |
3857 | ||
3858 | no_more_source: | |
89528eb3 KH |
3859 | if (incomplete && coding->mode & CODING_MODE_LAST_BLOCK) |
3860 | { | |
ff0dacd7 | 3861 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 3862 | return 0; |
4ed46869 | 3863 | } |
ff0dacd7 KH |
3864 | detect_info->found |= found; |
3865 | return 1; | |
4ed46869 KH |
3866 | } |
3867 | ||
3868 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3869 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 3870 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 3871 | |
0a28aafb | 3872 | static int |
ff0dacd7 | 3873 | detect_coding_big5 (coding, detect_info) |
df7492f9 | 3874 | struct coding_system *coding; |
ff0dacd7 | 3875 | struct coding_detection_info *detect_info; |
4ed46869 | 3876 | { |
8f924df7 KH |
3877 | const unsigned char *src = coding->source, *src_base = src; |
3878 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
3879 | int multibytep = coding->src_multibyte; |
3880 | int consumed_chars = 0; | |
3881 | int found = 0; | |
b73bfc1c | 3882 | int c; |
89528eb3 | 3883 | int incomplete; |
fa42c37f | 3884 | |
ff0dacd7 | 3885 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
3886 | /* A coding system of this category is always ASCII compatible. */ |
3887 | src += coding->head_ascii; | |
fa42c37f | 3888 | |
b73bfc1c | 3889 | while (1) |
fa42c37f | 3890 | { |
89528eb3 | 3891 | incomplete = 0; |
df7492f9 | 3892 | ONE_MORE_BYTE (c); |
89528eb3 | 3893 | incomplete = 1; |
df7492f9 | 3894 | if (c < 0x80) |
fa42c37f | 3895 | continue; |
df7492f9 | 3896 | if (c >= 0xA1) |
fa42c37f | 3897 | { |
df7492f9 KH |
3898 | ONE_MORE_BYTE (c); |
3899 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 3900 | return 0; |
ff0dacd7 | 3901 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 3902 | } |
df7492f9 KH |
3903 | else |
3904 | break; | |
fa42c37f | 3905 | } |
ff0dacd7 | 3906 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 3907 | return 0; |
fa42c37f | 3908 | |
df7492f9 | 3909 | no_more_source: |
89528eb3 KH |
3910 | if (incomplete && coding->mode & CODING_MODE_LAST_BLOCK) |
3911 | { | |
ff0dacd7 | 3912 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
3913 | return 0; |
3914 | } | |
ff0dacd7 KH |
3915 | detect_info->found |= found; |
3916 | return 1; | |
fa42c37f KH |
3917 | } |
3918 | ||
4ed46869 KH |
3919 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
3920 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
fa42c37f | 3921 | |
b73bfc1c | 3922 | static void |
df7492f9 | 3923 | decode_coding_sjis (coding) |
4ed46869 | 3924 | struct coding_system *coding; |
4ed46869 | 3925 | { |
8f924df7 KH |
3926 | const unsigned char *src = coding->source + coding->consumed; |
3927 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
3928 | const unsigned char *src_base; | |
df7492f9 | 3929 | int *charbuf = coding->charbuf; |
ff0dacd7 | 3930 | int *charbuf_end = charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; |
df7492f9 KH |
3931 | int consumed_chars = 0, consumed_chars_base; |
3932 | int multibytep = coding->src_multibyte; | |
3933 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
3934 | Lisp_Object attrs, eol_type, charset_list, val; | |
ff0dacd7 KH |
3935 | int char_offset = coding->produced_char; |
3936 | int last_offset = char_offset; | |
3937 | int last_id = charset_ascii; | |
a5d301df | 3938 | |
df7492f9 KH |
3939 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
3940 | ||
3941 | val = charset_list; | |
3942 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 KH |
3943 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
3944 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 3945 | |
b73bfc1c | 3946 | while (1) |
4ed46869 | 3947 | { |
df7492f9 | 3948 | int c, c1; |
fa42c37f | 3949 | |
b73bfc1c | 3950 | src_base = src; |
df7492f9 | 3951 | consumed_chars_base = consumed_chars; |
fa42c37f | 3952 | |
df7492f9 KH |
3953 | if (charbuf >= charbuf_end) |
3954 | break; | |
3955 | ||
3956 | ONE_MORE_BYTE (c); | |
b73bfc1c | 3957 | |
df7492f9 | 3958 | if (c == '\r') |
4ed46869 | 3959 | { |
df7492f9 | 3960 | if (EQ (eol_type, Qdos)) |
4ed46869 | 3961 | { |
df7492f9 | 3962 | if (src == src_end) |
98725083 KH |
3963 | { |
3964 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; | |
3965 | goto no_more_source; | |
3966 | } | |
df7492f9 KH |
3967 | if (*src == '\n') |
3968 | ONE_MORE_BYTE (c); | |
4ed46869 | 3969 | } |
df7492f9 KH |
3970 | else if (EQ (eol_type, Qmac)) |
3971 | c = '\n'; | |
4ed46869 | 3972 | } |
54f78171 | 3973 | else |
df7492f9 KH |
3974 | { |
3975 | struct charset *charset; | |
fa42c37f | 3976 | |
df7492f9 KH |
3977 | if (c < 0x80) |
3978 | charset = charset_roman; | |
3979 | else | |
4ed46869 | 3980 | { |
df7492f9 KH |
3981 | if (c >= 0xF0) |
3982 | goto invalid_code; | |
3983 | if (c < 0xA0 || c >= 0xE0) | |
fb88bf2d | 3984 | { |
54f78171 | 3985 | /* SJIS -> JISX0208 */ |
df7492f9 KH |
3986 | ONE_MORE_BYTE (c1); |
3987 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
3988 | goto invalid_code; | |
3989 | c = (c << 8) | c1; | |
3990 | SJIS_TO_JIS (c); | |
3991 | charset = charset_kanji; | |
5e34de15 | 3992 | } |
7487494c | 3993 | else if (c > 0xA0) |
89528eb3 KH |
3994 | { |
3995 | /* SJIS -> JISX0201-Kana */ | |
3996 | c &= 0x7F; | |
3997 | charset = charset_kana; | |
3998 | } | |
7487494c KH |
3999 | else |
4000 | goto invalid_code; | |
df7492f9 | 4001 | } |
ff0dacd7 KH |
4002 | if (charset->id != charset_ascii |
4003 | && last_id != charset->id) | |
4004 | { | |
4005 | if (last_id != charset_ascii) | |
4006 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
4007 | last_id = charset->id; | |
4008 | last_offset = char_offset; | |
4009 | } | |
df7492f9 KH |
4010 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
4011 | } | |
4012 | *charbuf++ = c; | |
ff0dacd7 | 4013 | char_offset++; |
df7492f9 | 4014 | continue; |
b73bfc1c | 4015 | |
df7492f9 KH |
4016 | invalid_code: |
4017 | src = src_base; | |
4018 | consumed_chars = consumed_chars_base; | |
4019 | ONE_MORE_BYTE (c); | |
4020 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 4021 | char_offset++; |
df7492f9 KH |
4022 | coding->errors++; |
4023 | } | |
fa42c37f | 4024 | |
df7492f9 | 4025 | no_more_source: |
ff0dacd7 KH |
4026 | if (last_id != charset_ascii) |
4027 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
df7492f9 KH |
4028 | coding->consumed_char += consumed_chars_base; |
4029 | coding->consumed = src_base - coding->source; | |
4030 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4031 | } |
4032 | ||
b73bfc1c | 4033 | static void |
df7492f9 | 4034 | decode_coding_big5 (coding) |
4ed46869 | 4035 | struct coding_system *coding; |
4ed46869 | 4036 | { |
8f924df7 KH |
4037 | const unsigned char *src = coding->source + coding->consumed; |
4038 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4039 | const unsigned char *src_base; | |
df7492f9 | 4040 | int *charbuf = coding->charbuf; |
ff0dacd7 | 4041 | int *charbuf_end = charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; |
df7492f9 KH |
4042 | int consumed_chars = 0, consumed_chars_base; |
4043 | int multibytep = coding->src_multibyte; | |
4044 | struct charset *charset_roman, *charset_big5; | |
4045 | Lisp_Object attrs, eol_type, charset_list, val; | |
ff0dacd7 KH |
4046 | int char_offset = coding->produced_char; |
4047 | int last_offset = char_offset; | |
4048 | int last_id = charset_ascii; | |
df7492f9 KH |
4049 | |
4050 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
4051 | val = charset_list; | |
4052 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4053 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4054 | |
b73bfc1c | 4055 | while (1) |
4ed46869 | 4056 | { |
df7492f9 | 4057 | int c, c1; |
b73bfc1c KH |
4058 | |
4059 | src_base = src; | |
df7492f9 KH |
4060 | consumed_chars_base = consumed_chars; |
4061 | ||
4062 | if (charbuf >= charbuf_end) | |
4063 | break; | |
4064 | ||
4065 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4066 | |
df7492f9 | 4067 | if (c == '\r') |
4ed46869 | 4068 | { |
df7492f9 | 4069 | if (EQ (eol_type, Qdos)) |
4ed46869 | 4070 | { |
df7492f9 | 4071 | if (src == src_end) |
b73bfc1c | 4072 | { |
98725083 KH |
4073 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; |
4074 | goto no_more_source; | |
d46c5b12 | 4075 | } |
df7492f9 KH |
4076 | if (*src == '\n') |
4077 | ONE_MORE_BYTE (c); | |
4ed46869 | 4078 | } |
df7492f9 KH |
4079 | else if (EQ (eol_type, Qmac)) |
4080 | c = '\n'; | |
4ed46869 | 4081 | } |
54f78171 | 4082 | else |
df7492f9 KH |
4083 | { |
4084 | struct charset *charset; | |
4085 | if (c < 0x80) | |
4086 | charset = charset_roman; | |
fb88bf2d | 4087 | else |
fb88bf2d | 4088 | { |
54f78171 | 4089 | /* BIG5 -> Big5 */ |
df7492f9 KH |
4090 | if (c < 0xA1 || c > 0xFE) |
4091 | goto invalid_code; | |
4092 | ONE_MORE_BYTE (c1); | |
4093 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4094 | goto invalid_code; | |
4095 | c = c << 8 | c1; | |
4096 | charset = charset_big5; | |
4ed46869 | 4097 | } |
ff0dacd7 KH |
4098 | if (charset->id != charset_ascii |
4099 | && last_id != charset->id) | |
4100 | { | |
4101 | if (last_id != charset_ascii) | |
4102 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
4103 | last_id = charset->id; | |
4104 | last_offset = char_offset; | |
4ed46869 | 4105 | } |
df7492f9 | 4106 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
4ed46869 | 4107 | } |
4ed46869 | 4108 | |
df7492f9 | 4109 | *charbuf++ = c; |
ff0dacd7 | 4110 | char_offset++; |
fb88bf2d KH |
4111 | continue; |
4112 | ||
df7492f9 | 4113 | invalid_code: |
4ed46869 | 4114 | src = src_base; |
df7492f9 KH |
4115 | consumed_chars = consumed_chars_base; |
4116 | ONE_MORE_BYTE (c); | |
4117 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 4118 | char_offset++; |
df7492f9 | 4119 | coding->errors++; |
fb88bf2d | 4120 | } |
d46c5b12 | 4121 | |
df7492f9 | 4122 | no_more_source: |
ff0dacd7 KH |
4123 | if (last_id != charset_ascii) |
4124 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
df7492f9 KH |
4125 | coding->consumed_char += consumed_chars_base; |
4126 | coding->consumed = src_base - coding->source; | |
4127 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4128 | } |
4129 | ||
4130 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4131 | This function can encode charsets `ascii', `katakana-jisx0201', |
4132 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4133 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
4134 | (i.e. do not have extended leading-codes). Characters of other |
4135 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
4136 | SJIS text, else encode BIG5 text. */ | |
4137 | ||
df7492f9 KH |
4138 | static int |
4139 | encode_coding_sjis (coding) | |
4ed46869 | 4140 | struct coding_system *coding; |
4ed46869 | 4141 | { |
df7492f9 KH |
4142 | int multibytep = coding->dst_multibyte; |
4143 | int *charbuf = coding->charbuf; | |
4144 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4145 | unsigned char *dst = coding->destination + coding->produced; | |
4146 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4147 | int safe_room = 4; | |
4148 | int produced_chars = 0; | |
4149 | Lisp_Object attrs, eol_type, charset_list, val; | |
4150 | int ascii_compatible; | |
4151 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
4152 | int c; | |
a5d301df | 4153 | |
df7492f9 KH |
4154 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
4155 | val = charset_list; | |
4156 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4157 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4158 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4159 | |
df7492f9 | 4160 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4161 | |
df7492f9 KH |
4162 | while (charbuf < charbuf_end) |
4163 | { | |
4164 | ASSURE_DESTINATION (safe_room); | |
4165 | c = *charbuf++; | |
b73bfc1c | 4166 | /* Now encode the character C. */ |
df7492f9 KH |
4167 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4168 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4169 | else if (CHAR_BYTE8_P (c)) |
4170 | { | |
4171 | c = CHAR_TO_BYTE8 (c); | |
4172 | EMIT_ONE_BYTE (c); | |
4173 | } | |
df7492f9 | 4174 | else |
b73bfc1c | 4175 | { |
df7492f9 KH |
4176 | unsigned code; |
4177 | struct charset *charset = char_charset (c, charset_list, &code); | |
4178 | ||
4179 | if (!charset) | |
4ed46869 | 4180 | { |
41cbe562 | 4181 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4182 | { |
41cbe562 KH |
4183 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4184 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4185 | } |
41cbe562 | 4186 | else |
b73bfc1c | 4187 | { |
41cbe562 KH |
4188 | c = coding->default_char; |
4189 | charset = char_charset (c, charset_list, &code); | |
b73bfc1c | 4190 | } |
b73bfc1c | 4191 | } |
df7492f9 KH |
4192 | if (code == CHARSET_INVALID_CODE (charset)) |
4193 | abort (); | |
4194 | if (charset == charset_kanji) | |
4195 | { | |
4196 | int c1, c2; | |
4197 | JIS_TO_SJIS (code); | |
4198 | c1 = code >> 8, c2 = code & 0xFF; | |
4199 | EMIT_TWO_BYTES (c1, c2); | |
4200 | } | |
4201 | else if (charset == charset_kana) | |
4202 | EMIT_ONE_BYTE (code | 0x80); | |
4203 | else | |
4204 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4205 | } | |
4206 | } | |
4207 | coding->result = CODING_RESULT_SUCCESS; | |
4208 | coding->produced_char += produced_chars; | |
4209 | coding->produced = dst - coding->destination; | |
4210 | return 0; | |
4211 | } | |
4212 | ||
4213 | static int | |
4214 | encode_coding_big5 (coding) | |
4215 | struct coding_system *coding; | |
4216 | { | |
4217 | int multibytep = coding->dst_multibyte; | |
4218 | int *charbuf = coding->charbuf; | |
4219 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4220 | unsigned char *dst = coding->destination + coding->produced; | |
4221 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4222 | int safe_room = 4; | |
4223 | int produced_chars = 0; | |
4224 | Lisp_Object attrs, eol_type, charset_list, val; | |
4225 | int ascii_compatible; | |
4226 | struct charset *charset_roman, *charset_big5; | |
4227 | int c; | |
4228 | ||
4229 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
4230 | val = charset_list; | |
4231 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4232 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4233 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
4234 | ||
4235 | while (charbuf < charbuf_end) | |
4236 | { | |
4237 | ASSURE_DESTINATION (safe_room); | |
4238 | c = *charbuf++; | |
4239 | /* Now encode the character C. */ | |
4240 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
4241 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4242 | else if (CHAR_BYTE8_P (c)) |
4243 | { | |
4244 | c = CHAR_TO_BYTE8 (c); | |
4245 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
4246 | } |
4247 | else | |
4248 | { | |
df7492f9 KH |
4249 | unsigned code; |
4250 | struct charset *charset = char_charset (c, charset_list, &code); | |
4251 | ||
4252 | if (! charset) | |
b73bfc1c | 4253 | { |
41cbe562 | 4254 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4255 | { |
41cbe562 KH |
4256 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4257 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4258 | } |
41cbe562 | 4259 | else |
0eecad43 | 4260 | { |
41cbe562 KH |
4261 | c = coding->default_char; |
4262 | charset = char_charset (c, charset_list, &code); | |
0eecad43 | 4263 | } |
4ed46869 | 4264 | } |
df7492f9 KH |
4265 | if (code == CHARSET_INVALID_CODE (charset)) |
4266 | abort (); | |
4267 | if (charset == charset_big5) | |
b73bfc1c | 4268 | { |
df7492f9 KH |
4269 | int c1, c2; |
4270 | ||
4271 | c1 = code >> 8, c2 = code & 0xFF; | |
4272 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 4273 | } |
df7492f9 KH |
4274 | else |
4275 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 4276 | } |
4ed46869 | 4277 | } |
df7492f9 KH |
4278 | coding->result = CODING_RESULT_SUCCESS; |
4279 | coding->produced_char += produced_chars; | |
4280 | coding->produced = dst - coding->destination; | |
4281 | return 0; | |
4ed46869 KH |
4282 | } |
4283 | ||
4284 | \f | |
df7492f9 | 4285 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
4286 | |
4287 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4288 | Check if a text is encoded in a coding system of which | |
4289 | encoder/decoder are written in CCL program. If it is, return | |
df7492f9 | 4290 | CATEGORY_MASK_CCL, else return 0. */ |
1397dc18 | 4291 | |
0a28aafb | 4292 | static int |
ff0dacd7 | 4293 | detect_coding_ccl (coding, detect_info) |
df7492f9 | 4294 | struct coding_system *coding; |
ff0dacd7 | 4295 | struct coding_detection_info *detect_info; |
1397dc18 | 4296 | { |
8f924df7 KH |
4297 | const unsigned char *src = coding->source, *src_base = src; |
4298 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
4299 | int multibytep = coding->src_multibyte; |
4300 | int consumed_chars = 0; | |
4301 | int found = 0; | |
4302 | unsigned char *valids = CODING_CCL_VALIDS (coding); | |
4303 | int head_ascii = coding->head_ascii; | |
4304 | Lisp_Object attrs; | |
4305 | ||
ff0dacd7 KH |
4306 | detect_info->checked |= CATEGORY_MASK_CCL; |
4307 | ||
df7492f9 KH |
4308 | coding = &coding_categories[coding_category_ccl]; |
4309 | attrs = CODING_ID_ATTRS (coding->id); | |
4310 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4311 | src += head_ascii; | |
1397dc18 | 4312 | |
b73bfc1c | 4313 | while (1) |
1397dc18 | 4314 | { |
df7492f9 KH |
4315 | int c; |
4316 | ONE_MORE_BYTE (c); | |
4317 | if (! valids[c]) | |
4318 | break; | |
ff0dacd7 KH |
4319 | if ((valids[c] > 1)) |
4320 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 4321 | } |
ff0dacd7 | 4322 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
4323 | return 0; |
4324 | ||
4325 | no_more_source: | |
ff0dacd7 KH |
4326 | detect_info->found |= found; |
4327 | return 1; | |
df7492f9 KH |
4328 | } |
4329 | ||
4330 | static void | |
4331 | decode_coding_ccl (coding) | |
4332 | struct coding_system *coding; | |
4333 | { | |
7c78e542 | 4334 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 4335 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4336 | int *charbuf = coding->charbuf; |
4337 | int *charbuf_end = charbuf + coding->charbuf_size; | |
4338 | int consumed_chars = 0; | |
4339 | int multibytep = coding->src_multibyte; | |
4340 | struct ccl_program ccl; | |
4341 | int source_charbuf[1024]; | |
4342 | int source_byteidx[1024]; | |
4776e638 | 4343 | Lisp_Object attrs, eol_type, charset_list; |
df7492f9 | 4344 | |
8dcbea82 | 4345 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
df7492f9 KH |
4346 | setup_ccl_program (&ccl, CODING_CCL_DECODER (coding)); |
4347 | ||
4348 | while (src < src_end) | |
4349 | { | |
7c78e542 | 4350 | const unsigned char *p = src; |
df7492f9 KH |
4351 | int *source, *source_end; |
4352 | int i = 0; | |
4353 | ||
4354 | if (multibytep) | |
4355 | while (i < 1024 && p < src_end) | |
4356 | { | |
4357 | source_byteidx[i] = p - src; | |
4358 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
4359 | } | |
4360 | else | |
4361 | while (i < 1024 && p < src_end) | |
4362 | source_charbuf[i++] = *p++; | |
8f924df7 | 4363 | |
df7492f9 KH |
4364 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
4365 | ccl.last_block = 1; | |
4366 | ||
4367 | source = source_charbuf; | |
4368 | source_end = source + i; | |
4369 | while (source < source_end) | |
4370 | { | |
4371 | ccl_driver (&ccl, source, charbuf, | |
8dcbea82 KH |
4372 | source_end - source, charbuf_end - charbuf, |
4373 | charset_list); | |
df7492f9 KH |
4374 | source += ccl.consumed; |
4375 | charbuf += ccl.produced; | |
4376 | if (ccl.status != CCL_STAT_SUSPEND_BY_DST) | |
4377 | break; | |
4378 | } | |
4379 | if (source < source_end) | |
4380 | src += source_byteidx[source - source_charbuf]; | |
4381 | else | |
4382 | src = p; | |
4383 | consumed_chars += source - source_charbuf; | |
4384 | ||
4385 | if (ccl.status != CCL_STAT_SUSPEND_BY_SRC | |
4386 | && ccl.status != CODING_RESULT_INSUFFICIENT_SRC) | |
4387 | break; | |
4388 | } | |
4389 | ||
4390 | switch (ccl.status) | |
4391 | { | |
4392 | case CCL_STAT_SUSPEND_BY_SRC: | |
4393 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; | |
4394 | break; | |
4395 | case CCL_STAT_SUSPEND_BY_DST: | |
4396 | break; | |
4397 | case CCL_STAT_QUIT: | |
4398 | case CCL_STAT_INVALID_CMD: | |
4399 | coding->result = CODING_RESULT_INTERRUPT; | |
4400 | break; | |
4401 | default: | |
4402 | coding->result = CODING_RESULT_SUCCESS; | |
4403 | break; | |
4404 | } | |
4405 | coding->consumed_char += consumed_chars; | |
4406 | coding->consumed = src - coding->source; | |
4407 | coding->charbuf_used = charbuf - coding->charbuf; | |
4408 | } | |
4409 | ||
4410 | static int | |
4411 | encode_coding_ccl (coding) | |
4412 | struct coding_system *coding; | |
4413 | { | |
4414 | struct ccl_program ccl; | |
4415 | int multibytep = coding->dst_multibyte; | |
4416 | int *charbuf = coding->charbuf; | |
4417 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4418 | unsigned char *dst = coding->destination + coding->produced; | |
4419 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4420 | unsigned char *adjusted_dst_end = dst_end - 1; | |
4421 | int destination_charbuf[1024]; | |
4422 | int i, produced_chars = 0; | |
8dcbea82 | 4423 | Lisp_Object attrs, eol_type, charset_list; |
df7492f9 | 4424 | |
8dcbea82 | 4425 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
df7492f9 KH |
4426 | setup_ccl_program (&ccl, CODING_CCL_ENCODER (coding)); |
4427 | ||
4428 | ccl.last_block = coding->mode & CODING_MODE_LAST_BLOCK; | |
4429 | ccl.dst_multibyte = coding->dst_multibyte; | |
4430 | ||
4431 | while (charbuf < charbuf_end && dst < adjusted_dst_end) | |
4432 | { | |
4433 | int dst_bytes = dst_end - dst; | |
4434 | if (dst_bytes > 1024) | |
4435 | dst_bytes = 1024; | |
4436 | ||
4437 | ccl_driver (&ccl, charbuf, destination_charbuf, | |
8dcbea82 | 4438 | charbuf_end - charbuf, dst_bytes, charset_list); |
df7492f9 KH |
4439 | charbuf += ccl.consumed; |
4440 | if (multibytep) | |
4441 | for (i = 0; i < ccl.produced; i++) | |
4442 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); | |
4443 | else | |
4444 | { | |
4445 | for (i = 0; i < ccl.produced; i++) | |
4446 | *dst++ = destination_charbuf[i] & 0xFF; | |
4447 | produced_chars += ccl.produced; | |
4448 | } | |
4449 | } | |
4450 | ||
4451 | switch (ccl.status) | |
4452 | { | |
4453 | case CCL_STAT_SUSPEND_BY_SRC: | |
4454 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; | |
4455 | break; | |
4456 | case CCL_STAT_SUSPEND_BY_DST: | |
4457 | coding->result = CODING_RESULT_INSUFFICIENT_DST; | |
4458 | break; | |
4459 | case CCL_STAT_QUIT: | |
4460 | case CCL_STAT_INVALID_CMD: | |
4461 | coding->result = CODING_RESULT_INTERRUPT; | |
4462 | break; | |
4463 | default: | |
4464 | coding->result = CODING_RESULT_SUCCESS; | |
4465 | break; | |
1397dc18 | 4466 | } |
df7492f9 KH |
4467 | |
4468 | coding->produced_char += produced_chars; | |
4469 | coding->produced = dst - coding->destination; | |
4470 | return 0; | |
1397dc18 KH |
4471 | } |
4472 | ||
df7492f9 | 4473 | |
1397dc18 | 4474 | \f |
df7492f9 | 4475 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 4476 | |
b73bfc1c | 4477 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 4478 | |
b73bfc1c | 4479 | static void |
df7492f9 | 4480 | decode_coding_raw_text (coding) |
4ed46869 | 4481 | struct coding_system *coding; |
4ed46869 | 4482 | { |
df7492f9 | 4483 | coding->chars_at_source = 1; |
2c78b7e1 KH |
4484 | coding->consumed_char = 0; |
4485 | coding->consumed = 0; | |
df7492f9 KH |
4486 | coding->result = CODING_RESULT_SUCCESS; |
4487 | } | |
4ed46869 | 4488 | |
df7492f9 KH |
4489 | static int |
4490 | encode_coding_raw_text (coding) | |
4491 | struct coding_system *coding; | |
4492 | { | |
4493 | int multibytep = coding->dst_multibyte; | |
4494 | int *charbuf = coding->charbuf; | |
4495 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
4496 | unsigned char *dst = coding->destination + coding->produced; | |
4497 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4498 | int produced_chars = 0; | |
b73bfc1c KH |
4499 | int c; |
4500 | ||
df7492f9 | 4501 | if (multibytep) |
b73bfc1c | 4502 | { |
df7492f9 | 4503 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 4504 | |
df7492f9 KH |
4505 | if (coding->src_multibyte) |
4506 | while (charbuf < charbuf_end) | |
4507 | { | |
4508 | ASSURE_DESTINATION (safe_room); | |
4509 | c = *charbuf++; | |
4510 | if (ASCII_CHAR_P (c)) | |
4511 | EMIT_ONE_ASCII_BYTE (c); | |
4512 | else if (CHAR_BYTE8_P (c)) | |
4513 | { | |
4514 | c = CHAR_TO_BYTE8 (c); | |
4515 | EMIT_ONE_BYTE (c); | |
4516 | } | |
4517 | else | |
4518 | { | |
4519 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 4520 | |
df7492f9 KH |
4521 | CHAR_STRING_ADVANCE (c, p1); |
4522 | while (p0 < p1) | |
9d123124 KH |
4523 | { |
4524 | EMIT_ONE_BYTE (*p0); | |
4525 | p0++; | |
4526 | } | |
df7492f9 KH |
4527 | } |
4528 | } | |
b73bfc1c | 4529 | else |
df7492f9 KH |
4530 | while (charbuf < charbuf_end) |
4531 | { | |
4532 | ASSURE_DESTINATION (safe_room); | |
4533 | c = *charbuf++; | |
4534 | EMIT_ONE_BYTE (c); | |
4535 | } | |
4536 | } | |
4537 | else | |
4ed46869 | 4538 | { |
df7492f9 | 4539 | if (coding->src_multibyte) |
d46c5b12 | 4540 | { |
df7492f9 KH |
4541 | int safe_room = MAX_MULTIBYTE_LENGTH; |
4542 | ||
4543 | while (charbuf < charbuf_end) | |
d46c5b12 | 4544 | { |
df7492f9 KH |
4545 | ASSURE_DESTINATION (safe_room); |
4546 | c = *charbuf++; | |
4547 | if (ASCII_CHAR_P (c)) | |
4548 | *dst++ = c; | |
4549 | else if (CHAR_BYTE8_P (c)) | |
4550 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 4551 | else |
df7492f9 KH |
4552 | CHAR_STRING_ADVANCE (c, dst); |
4553 | produced_chars++; | |
d46c5b12 KH |
4554 | } |
4555 | } | |
df7492f9 KH |
4556 | else |
4557 | { | |
4558 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
4559 | while (charbuf < charbuf_end && dst < dst_end) | |
4560 | *dst++ = *charbuf++; | |
4561 | produced_chars = dst - (coding->destination + coding->dst_bytes); | |
8f924df7 | 4562 | } |
4ed46869 | 4563 | } |
df7492f9 KH |
4564 | coding->result = CODING_RESULT_SUCCESS; |
4565 | coding->produced_char += produced_chars; | |
4566 | coding->produced = dst - coding->destination; | |
4567 | return 0; | |
4ed46869 KH |
4568 | } |
4569 | ||
ff0dacd7 KH |
4570 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
4571 | Check if a text is encoded in a charset-based coding system. If it | |
4572 | is, return 1, else return 0. */ | |
4573 | ||
0a28aafb | 4574 | static int |
ff0dacd7 | 4575 | detect_coding_charset (coding, detect_info) |
df7492f9 | 4576 | struct coding_system *coding; |
ff0dacd7 | 4577 | struct coding_detection_info *detect_info; |
1397dc18 | 4578 | { |
8f924df7 KH |
4579 | const unsigned char *src = coding->source, *src_base = src; |
4580 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
4581 | int multibytep = coding->src_multibyte; |
4582 | int consumed_chars = 0; | |
4583 | Lisp_Object attrs, valids; | |
584948ac | 4584 | int found = 0; |
1397dc18 | 4585 | |
ff0dacd7 KH |
4586 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
4587 | ||
df7492f9 KH |
4588 | coding = &coding_categories[coding_category_charset]; |
4589 | attrs = CODING_ID_ATTRS (coding->id); | |
4590 | valids = AREF (attrs, coding_attr_charset_valids); | |
4591 | ||
4592 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4593 | src += coding->head_ascii; | |
1397dc18 | 4594 | |
b73bfc1c | 4595 | while (1) |
1397dc18 | 4596 | { |
df7492f9 | 4597 | int c; |
1397dc18 | 4598 | |
df7492f9 KH |
4599 | ONE_MORE_BYTE (c); |
4600 | if (NILP (AREF (valids, c))) | |
4601 | break; | |
584948ac | 4602 | if (c >= 0x80) |
ff0dacd7 | 4603 | found = CATEGORY_MASK_CHARSET; |
df7492f9 | 4604 | } |
ff0dacd7 | 4605 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 4606 | return 0; |
4ed46869 | 4607 | |
df7492f9 | 4608 | no_more_source: |
ff0dacd7 KH |
4609 | detect_info->found |= found; |
4610 | return 1; | |
df7492f9 | 4611 | } |
b73bfc1c | 4612 | |
b73bfc1c | 4613 | static void |
df7492f9 | 4614 | decode_coding_charset (coding) |
4ed46869 | 4615 | struct coding_system *coding; |
4ed46869 | 4616 | { |
8f924df7 KH |
4617 | const unsigned char *src = coding->source + coding->consumed; |
4618 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4619 | const unsigned char *src_base; | |
df7492f9 | 4620 | int *charbuf = coding->charbuf; |
ff0dacd7 | 4621 | int *charbuf_end = charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; |
df7492f9 KH |
4622 | int consumed_chars = 0, consumed_chars_base; |
4623 | int multibytep = coding->src_multibyte; | |
4eb6d3f1 | 4624 | Lisp_Object attrs, eol_type, charset_list, valids; |
ff0dacd7 KH |
4625 | int char_offset = coding->produced_char; |
4626 | int last_offset = char_offset; | |
4627 | int last_id = charset_ascii; | |
df7492f9 KH |
4628 | |
4629 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
4eb6d3f1 | 4630 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 4631 | |
df7492f9 | 4632 | while (1) |
4ed46869 | 4633 | { |
4eb6d3f1 | 4634 | int c; |
df7492f9 KH |
4635 | |
4636 | src_base = src; | |
4637 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 4638 | |
df7492f9 KH |
4639 | if (charbuf >= charbuf_end) |
4640 | break; | |
4641 | ||
4eb6d3f1 | 4642 | ONE_MORE_BYTE (c); |
df7492f9 | 4643 | if (c == '\r') |
d46c5b12 | 4644 | { |
c7c66a95 KH |
4645 | /* Here we assume that no charset maps '\r' to something |
4646 | else. */ | |
df7492f9 | 4647 | if (EQ (eol_type, Qdos)) |
b73bfc1c | 4648 | { |
98725083 | 4649 | if (src == src_end) |
b73bfc1c | 4650 | { |
98725083 KH |
4651 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; |
4652 | goto no_more_source; | |
b73bfc1c | 4653 | } |
98725083 | 4654 | if (*src == '\n') |
df7492f9 | 4655 | ONE_MORE_BYTE (c); |
b73bfc1c | 4656 | } |
df7492f9 | 4657 | else if (EQ (eol_type, Qmac)) |
b73bfc1c | 4658 | c = '\n'; |
d46c5b12 | 4659 | } |
df7492f9 | 4660 | else |
d46c5b12 | 4661 | { |
4eb6d3f1 KH |
4662 | Lisp_Object val; |
4663 | struct charset *charset; | |
c7c66a95 | 4664 | int dim; |
acb2a965 KH |
4665 | int len = 1; |
4666 | unsigned code = c; | |
4eb6d3f1 KH |
4667 | |
4668 | val = AREF (valids, c); | |
4669 | if (NILP (val)) | |
4670 | goto invalid_code; | |
c7c66a95 | 4671 | if (INTEGERP (val)) |
4eb6d3f1 | 4672 | { |
c7c66a95 KH |
4673 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
4674 | dim = CHARSET_DIMENSION (charset); | |
f9d71dcd | 4675 | while (len < dim) |
4eb6d3f1 | 4676 | { |
acb2a965 KH |
4677 | ONE_MORE_BYTE (c); |
4678 | code = (code << 8) | c; | |
f9d71dcd | 4679 | len++; |
4eb6d3f1 | 4680 | } |
c7c66a95 KH |
4681 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
4682 | charset, code, c); | |
4683 | } | |
4684 | else | |
4685 | { | |
4686 | /* VAL is a list of charset IDs. It is assured that the | |
4687 | list is sorted by charset dimensions (smaller one | |
4688 | comes first). */ | |
c7c66a95 KH |
4689 | while (CONSP (val)) |
4690 | { | |
4691 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); | |
4692 | dim = CHARSET_DIMENSION (charset); | |
f9d71dcd | 4693 | while (len < dim) |
c7c66a95 | 4694 | { |
acb2a965 KH |
4695 | ONE_MORE_BYTE (c); |
4696 | code = (code << 8) | c; | |
f9d71dcd | 4697 | len++; |
c7c66a95 | 4698 | } |
c7c66a95 KH |
4699 | CODING_DECODE_CHAR (coding, src, src_base, |
4700 | src_end, charset, code, c); | |
4701 | if (c >= 0) | |
4702 | break; | |
4703 | val = XCDR (val); | |
4704 | } | |
4eb6d3f1 | 4705 | } |
df7492f9 KH |
4706 | if (c < 0) |
4707 | goto invalid_code; | |
ff0dacd7 KH |
4708 | if (charset->id != charset_ascii |
4709 | && last_id != charset->id) | |
4710 | { | |
4711 | if (last_id != charset_ascii) | |
4712 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
4713 | last_id = charset->id; | |
4714 | last_offset = char_offset; | |
4715 | } | |
d46c5b12 | 4716 | } |
df7492f9 | 4717 | *charbuf++ = c; |
ff0dacd7 | 4718 | char_offset++; |
df7492f9 KH |
4719 | continue; |
4720 | ||
4721 | invalid_code: | |
4722 | src = src_base; | |
4723 | consumed_chars = consumed_chars_base; | |
4724 | ONE_MORE_BYTE (c); | |
4725 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 4726 | char_offset++; |
df7492f9 | 4727 | coding->errors++; |
4ed46869 KH |
4728 | } |
4729 | ||
df7492f9 | 4730 | no_more_source: |
ff0dacd7 KH |
4731 | if (last_id != charset_ascii) |
4732 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
df7492f9 KH |
4733 | coding->consumed_char += consumed_chars_base; |
4734 | coding->consumed = src_base - coding->source; | |
4735 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4736 | } |
4737 | ||
df7492f9 KH |
4738 | static int |
4739 | encode_coding_charset (coding) | |
4ed46869 | 4740 | struct coding_system *coding; |
4ed46869 | 4741 | { |
df7492f9 KH |
4742 | int multibytep = coding->dst_multibyte; |
4743 | int *charbuf = coding->charbuf; | |
4744 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4745 | unsigned char *dst = coding->destination + coding->produced; | |
4746 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4747 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
4748 | int produced_chars = 0; | |
df7492f9 KH |
4749 | Lisp_Object attrs, eol_type, charset_list; |
4750 | int ascii_compatible; | |
b73bfc1c | 4751 | int c; |
b73bfc1c | 4752 | |
df7492f9 | 4753 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
df7492f9 | 4754 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 4755 | |
df7492f9 | 4756 | while (charbuf < charbuf_end) |
4ed46869 | 4757 | { |
4eb6d3f1 | 4758 | struct charset *charset; |
df7492f9 | 4759 | unsigned code; |
8f924df7 | 4760 | |
df7492f9 KH |
4761 | ASSURE_DESTINATION (safe_room); |
4762 | c = *charbuf++; | |
4763 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
4764 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 4765 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 4766 | { |
16eafb5d KH |
4767 | c = CHAR_TO_BYTE8 (c); |
4768 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 4769 | } |
d46c5b12 | 4770 | else |
b73bfc1c | 4771 | { |
4eb6d3f1 KH |
4772 | charset = char_charset (c, charset_list, &code); |
4773 | if (charset) | |
4774 | { | |
4775 | if (CHARSET_DIMENSION (charset) == 1) | |
4776 | EMIT_ONE_BYTE (code); | |
4777 | else if (CHARSET_DIMENSION (charset) == 2) | |
4778 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
4779 | else if (CHARSET_DIMENSION (charset) == 3) | |
4780 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
4781 | else | |
4782 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
4783 | (code >> 8) & 0xFF, code & 0xFF); | |
4784 | } | |
4785 | else | |
41cbe562 KH |
4786 | { |
4787 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
4788 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4789 | else | |
4790 | c = coding->default_char; | |
4791 | EMIT_ONE_BYTE (c); | |
4792 | } | |
4ed46869 | 4793 | } |
4ed46869 KH |
4794 | } |
4795 | ||
df7492f9 KH |
4796 | coding->result = CODING_RESULT_SUCCESS; |
4797 | coding->produced_char += produced_chars; | |
4798 | coding->produced = dst - coding->destination; | |
4799 | return 0; | |
4ed46869 KH |
4800 | } |
4801 | ||
4802 | \f | |
1397dc18 | 4803 | /*** 7. C library functions ***/ |
4ed46869 | 4804 | |
df7492f9 KH |
4805 | /* Setup coding context CODING from information about CODING_SYSTEM. |
4806 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
4807 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 4808 | |
ec6d2bb8 | 4809 | void |
e0e989f6 KH |
4810 | setup_coding_system (coding_system, coding) |
4811 | Lisp_Object coding_system; | |
4ed46869 KH |
4812 | struct coding_system *coding; |
4813 | { | |
df7492f9 KH |
4814 | Lisp_Object attrs; |
4815 | Lisp_Object eol_type; | |
4816 | Lisp_Object coding_type; | |
4608c386 | 4817 | Lisp_Object val; |
4ed46869 | 4818 | |
df7492f9 KH |
4819 | if (NILP (coding_system)) |
4820 | coding_system = Qno_conversion; | |
c07c8e12 | 4821 | |
df7492f9 | 4822 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 4823 | |
df7492f9 KH |
4824 | attrs = CODING_ID_ATTRS (coding->id); |
4825 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
1f5dbf34 | 4826 | |
df7492f9 KH |
4827 | coding->mode = 0; |
4828 | coding->head_ascii = -1; | |
4829 | coding->common_flags | |
4830 | = (VECTORP (eol_type) ? CODING_REQUIRE_DETECTION_MASK : 0); | |
5e5c78be KH |
4831 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
4832 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
4833 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
4834 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
4835 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
4836 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 4837 | |
df7492f9 | 4838 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 KH |
4839 | coding->max_charset_id = SCHARS (val) - 1; |
4840 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 | 4841 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
4608c386 | 4842 | |
df7492f9 KH |
4843 | coding_type = CODING_ATTR_TYPE (attrs); |
4844 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 4845 | { |
df7492f9 KH |
4846 | coding->detector = NULL; |
4847 | coding->decoder = decode_coding_raw_text; | |
4848 | coding->encoder = encode_coding_raw_text; | |
4849 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 4850 | } |
df7492f9 | 4851 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 4852 | { |
df7492f9 KH |
4853 | int i; |
4854 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
4855 | ||
4856 | /* Invoke graphic register 0 to plane 0. */ | |
4857 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
4858 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
4859 | CODING_ISO_INVOCATION (coding, 1) | |
4860 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
4861 | /* Setup the initial status of designation. */ | |
4862 | for (i = 0; i < 4; i++) | |
4863 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
4864 | /* Not single shifting initially. */ | |
4865 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
4866 | /* Beginning of buffer should also be regarded as bol. */ | |
4867 | CODING_ISO_BOL (coding) = 1; | |
4868 | coding->detector = detect_coding_iso_2022; | |
4869 | coding->decoder = decode_coding_iso_2022; | |
4870 | coding->encoder = encode_coding_iso_2022; | |
4871 | if (flags & CODING_ISO_FLAG_SAFE) | |
4872 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 4873 | coding->common_flags |
df7492f9 KH |
4874 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
4875 | | CODING_REQUIRE_FLUSHING_MASK); | |
4876 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
4877 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
4878 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
4879 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
4880 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
4881 | { | |
4882 | setup_iso_safe_charsets (attrs); | |
4883 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
4884 | coding->max_charset_id = SCHARS (val) - 1; |
4885 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
4886 | } |
4887 | CODING_ISO_FLAGS (coding) = flags; | |
d46c5b12 | 4888 | } |
df7492f9 | 4889 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 4890 | { |
df7492f9 KH |
4891 | coding->detector = detect_coding_charset; |
4892 | coding->decoder = decode_coding_charset; | |
4893 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 4894 | coding->common_flags |
df7492f9 | 4895 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 4896 | } |
df7492f9 | 4897 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 4898 | { |
df7492f9 KH |
4899 | coding->detector = detect_coding_utf_8; |
4900 | coding->decoder = decode_coding_utf_8; | |
4901 | coding->encoder = encode_coding_utf_8; | |
4902 | coding->common_flags | |
4903 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
4904 | } | |
4905 | else if (EQ (coding_type, Qutf_16)) | |
4906 | { | |
4907 | val = AREF (attrs, coding_attr_utf_16_bom); | |
4908 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_16_detect_bom | |
4909 | : EQ (val, Qt) ? utf_16_with_bom | |
4910 | : utf_16_without_bom); | |
4911 | val = AREF (attrs, coding_attr_utf_16_endian); | |
b49a1807 | 4912 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 4913 | : utf_16_little_endian); |
e19c3639 | 4914 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
4915 | coding->detector = detect_coding_utf_16; |
4916 | coding->decoder = decode_coding_utf_16; | |
4917 | coding->encoder = encode_coding_utf_16; | |
4918 | coding->common_flags | |
4919 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
b49a1807 KH |
4920 | if (CODING_UTF_16_BOM (coding) == utf_16_detect_bom) |
4921 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 4922 | } |
df7492f9 | 4923 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 4924 | { |
df7492f9 KH |
4925 | coding->detector = detect_coding_ccl; |
4926 | coding->decoder = decode_coding_ccl; | |
4927 | coding->encoder = encode_coding_ccl; | |
c952af22 | 4928 | coding->common_flags |
df7492f9 KH |
4929 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
4930 | | CODING_REQUIRE_FLUSHING_MASK); | |
4931 | } | |
4932 | else if (EQ (coding_type, Qemacs_mule)) | |
4933 | { | |
4934 | coding->detector = detect_coding_emacs_mule; | |
4935 | coding->decoder = decode_coding_emacs_mule; | |
4936 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 4937 | coding->common_flags |
df7492f9 KH |
4938 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
4939 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
4940 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
4941 | { | |
4942 | Lisp_Object tail, safe_charsets; | |
4943 | int max_charset_id = 0; | |
4944 | ||
4945 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
4946 | tail = XCDR (tail)) | |
4947 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
4948 | max_charset_id = XFASTINT (XCAR (tail)); | |
4949 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), | |
4950 | make_number (255)); | |
4951 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
4952 | tail = XCDR (tail)) | |
8f924df7 | 4953 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 4954 | coding->max_charset_id = max_charset_id; |
8f924df7 | 4955 | coding->safe_charsets = (char *) SDATA (safe_charsets); |
df7492f9 KH |
4956 | } |
4957 | } | |
4958 | else if (EQ (coding_type, Qshift_jis)) | |
4959 | { | |
4960 | coding->detector = detect_coding_sjis; | |
4961 | coding->decoder = decode_coding_sjis; | |
4962 | coding->encoder = encode_coding_sjis; | |
c952af22 | 4963 | coding->common_flags |
df7492f9 KH |
4964 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
4965 | } | |
4966 | else if (EQ (coding_type, Qbig5)) | |
4967 | { | |
4968 | coding->detector = detect_coding_big5; | |
4969 | coding->decoder = decode_coding_big5; | |
4970 | coding->encoder = encode_coding_big5; | |
c952af22 | 4971 | coding->common_flags |
df7492f9 KH |
4972 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
4973 | } | |
4974 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 4975 | { |
df7492f9 KH |
4976 | coding->detector = NULL; |
4977 | coding->decoder = decode_coding_raw_text; | |
4978 | coding->encoder = encode_coding_raw_text; | |
4ed46869 | 4979 | } |
4ed46869 | 4980 | |
df7492f9 | 4981 | return; |
4ed46869 KH |
4982 | } |
4983 | ||
df7492f9 KH |
4984 | /* Return raw-text or one of its subsidiaries that has the same |
4985 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 4986 | |
df7492f9 KH |
4987 | Lisp_Object |
4988 | raw_text_coding_system (coding_system) | |
4989 | Lisp_Object coding_system; | |
ec6d2bb8 | 4990 | { |
0be8721c | 4991 | Lisp_Object spec, attrs; |
df7492f9 | 4992 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 4993 | |
d3e4cb56 KH |
4994 | if (NILP (coding_system)) |
4995 | return Qraw_text; | |
df7492f9 KH |
4996 | spec = CODING_SYSTEM_SPEC (coding_system); |
4997 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 4998 | |
df7492f9 KH |
4999 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5000 | return coding_system; | |
ec6d2bb8 | 5001 | |
df7492f9 KH |
5002 | eol_type = AREF (spec, 2); |
5003 | if (VECTORP (eol_type)) | |
5004 | return Qraw_text; | |
5005 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5006 | raw_text_eol_type = AREF (spec, 2); | |
5007 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5008 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5009 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5010 | } |
5011 | ||
54f78171 | 5012 | |
df7492f9 KH |
5013 | /* If CODING_SYSTEM doesn't specify end-of-line format but PARENT |
5014 | does, return one of the subsidiary that has the same eol-spec as | |
5015 | PARENT. Otherwise, return CODING_SYSTEM. */ | |
5016 | ||
5017 | Lisp_Object | |
5018 | coding_inherit_eol_type (coding_system, parent) | |
b74e4686 | 5019 | Lisp_Object coding_system, parent; |
54f78171 | 5020 | { |
3e139625 | 5021 | Lisp_Object spec, eol_type; |
54f78171 | 5022 | |
d3e4cb56 KH |
5023 | if (NILP (coding_system)) |
5024 | coding_system = Qraw_text; | |
df7492f9 | 5025 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5026 | eol_type = AREF (spec, 2); |
d3e4cb56 KH |
5027 | if (VECTORP (eol_type) |
5028 | && ! NILP (parent)) | |
df7492f9 KH |
5029 | { |
5030 | Lisp_Object parent_spec; | |
df7492f9 KH |
5031 | Lisp_Object parent_eol_type; |
5032 | ||
5033 | parent_spec | |
5034 | = CODING_SYSTEM_SPEC (buffer_defaults.buffer_file_coding_system); | |
5035 | parent_eol_type = AREF (parent_spec, 2); | |
5036 | if (EQ (parent_eol_type, Qunix)) | |
5037 | coding_system = AREF (eol_type, 0); | |
5038 | else if (EQ (parent_eol_type, Qdos)) | |
5039 | coding_system = AREF (eol_type, 1); | |
5040 | else if (EQ (parent_eol_type, Qmac)) | |
5041 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5042 | } |
df7492f9 | 5043 | return coding_system; |
54f78171 KH |
5044 | } |
5045 | ||
4ed46869 KH |
5046 | /* Emacs has a mechanism to automatically detect a coding system if it |
5047 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
5048 | it's impossible to distinguish some coding systems accurately | |
5049 | because they use the same range of codes. So, at first, coding | |
5050 | systems are categorized into 7, those are: | |
5051 | ||
0ef69138 | 5052 | o coding-category-emacs-mule |
4ed46869 KH |
5053 | |
5054 | The category for a coding system which has the same code range | |
5055 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 5056 | symbol) `emacs-mule' by default. |
4ed46869 KH |
5057 | |
5058 | o coding-category-sjis | |
5059 | ||
5060 | The category for a coding system which has the same code range | |
5061 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 5062 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
5063 | |
5064 | o coding-category-iso-7 | |
5065 | ||
5066 | The category for a coding system which has the same code range | |
7717c392 | 5067 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
5068 | shift and single shift functions. This can encode/decode all |
5069 | charsets. Assigned the coding-system (Lisp symbol) | |
5070 | `iso-2022-7bit' by default. | |
5071 | ||
5072 | o coding-category-iso-7-tight | |
5073 | ||
5074 | Same as coding-category-iso-7 except that this can | |
5075 | encode/decode only the specified charsets. | |
4ed46869 KH |
5076 | |
5077 | o coding-category-iso-8-1 | |
5078 | ||
5079 | The category for a coding system which has the same code range | |
5080 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5081 | for DIMENSION1 charset. This doesn't use any locking shift |
5082 | and single shift functions. Assigned the coding-system (Lisp | |
5083 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
5084 | |
5085 | o coding-category-iso-8-2 | |
5086 | ||
5087 | The category for a coding system which has the same code range | |
5088 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5089 | for DIMENSION2 charset. This doesn't use any locking shift |
5090 | and single shift functions. Assigned the coding-system (Lisp | |
5091 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 5092 | |
7717c392 | 5093 | o coding-category-iso-7-else |
4ed46869 KH |
5094 | |
5095 | The category for a coding system which has the same code range | |
df7492f9 | 5096 | as ISO2022 of 7-bit environemnt but uses locking shift or |
7717c392 KH |
5097 | single shift functions. Assigned the coding-system (Lisp |
5098 | symbol) `iso-2022-7bit-lock' by default. | |
5099 | ||
5100 | o coding-category-iso-8-else | |
5101 | ||
5102 | The category for a coding system which has the same code range | |
df7492f9 | 5103 | as ISO2022 of 8-bit environemnt but uses locking shift or |
7717c392 KH |
5104 | single shift functions. Assigned the coding-system (Lisp |
5105 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
5106 | |
5107 | o coding-category-big5 | |
5108 | ||
5109 | The category for a coding system which has the same code range | |
5110 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5111 | `cn-big5' by default. |
4ed46869 | 5112 | |
fa42c37f KH |
5113 | o coding-category-utf-8 |
5114 | ||
5115 | The category for a coding system which has the same code range | |
5116 | as UTF-8 (cf. RFC2279). Assigned the coding-system (Lisp | |
5117 | symbol) `utf-8' by default. | |
5118 | ||
5119 | o coding-category-utf-16-be | |
5120 | ||
5121 | The category for a coding system in which a text has an | |
5122 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
5123 | endian at the head. Assigned the coding-system (Lisp symbol) | |
5124 | `utf-16-be' by default. | |
5125 | ||
5126 | o coding-category-utf-16-le | |
5127 | ||
5128 | The category for a coding system in which a text has an | |
5129 | Unicode signature (cf. Unicode Standard) in the order of | |
5130 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
5131 | symbol) `utf-16-le' by default. | |
5132 | ||
1397dc18 KH |
5133 | o coding-category-ccl |
5134 | ||
5135 | The category for a coding system of which encoder/decoder is | |
5136 | written in CCL programs. The default value is nil, i.e., no | |
5137 | coding system is assigned. | |
5138 | ||
4ed46869 KH |
5139 | o coding-category-binary |
5140 | ||
5141 | The category for a coding system not categorized in any of the | |
5142 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5143 | `no-conversion' by default. |
4ed46869 KH |
5144 | |
5145 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 5146 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
5147 | What Emacs does actually is to detect a category of coding system. |
5148 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 5149 | decide only one possible category, it selects a category of the |
4ed46869 KH |
5150 | highest priority. Priorities of categories are also specified by a |
5151 | user in a Lisp variable `coding-category-list'. | |
5152 | ||
5153 | */ | |
5154 | ||
df7492f9 KH |
5155 | #define EOL_SEEN_NONE 0 |
5156 | #define EOL_SEEN_LF 1 | |
5157 | #define EOL_SEEN_CR 2 | |
5158 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 5159 | |
ff0dacd7 KH |
5160 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
5161 | SOURCE is encoded. If CATEGORY is one of | |
5162 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
5163 | two-byte, else they are encoded by one-byte. | |
5164 | ||
5165 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 5166 | |
bc4bc72a | 5167 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
5168 | |
5169 | static int | |
89528eb3 | 5170 | detect_eol (source, src_bytes, category) |
d46c5b12 | 5171 | unsigned char *source; |
df7492f9 | 5172 | EMACS_INT src_bytes; |
89528eb3 | 5173 | enum coding_category category; |
4ed46869 | 5174 | { |
d46c5b12 | 5175 | unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 5176 | unsigned char c; |
df7492f9 KH |
5177 | int total = 0; |
5178 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 5179 | |
89528eb3 | 5180 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 5181 | { |
df7492f9 | 5182 | int msb, lsb; |
fa42c37f | 5183 | |
89528eb3 KH |
5184 | msb = category == (coding_category_utf_16_le |
5185 | | coding_category_utf_16_le_nosig); | |
df7492f9 | 5186 | lsb = 1 - msb; |
fa42c37f | 5187 | |
df7492f9 | 5188 | while (src + 1 < src_end) |
fa42c37f | 5189 | { |
df7492f9 KH |
5190 | c = src[lsb]; |
5191 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 5192 | { |
df7492f9 KH |
5193 | int this_eol; |
5194 | ||
5195 | if (c == '\n') | |
5196 | this_eol = EOL_SEEN_LF; | |
5197 | else if (src + 3 >= src_end | |
5198 | || src[msb + 2] != 0 | |
5199 | || src[lsb + 2] != '\n') | |
5200 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 5201 | else |
8f924df7 | 5202 | this_eol = EOL_SEEN_CRLF; |
df7492f9 KH |
5203 | |
5204 | if (eol_seen == EOL_SEEN_NONE) | |
5205 | /* This is the first end-of-line. */ | |
5206 | eol_seen = this_eol; | |
5207 | else if (eol_seen != this_eol) | |
fa42c37f | 5208 | { |
df7492f9 KH |
5209 | /* The found type is different from what found before. */ |
5210 | eol_seen = EOL_SEEN_LF; | |
5211 | break; | |
fa42c37f | 5212 | } |
df7492f9 KH |
5213 | if (++total == MAX_EOL_CHECK_COUNT) |
5214 | break; | |
fa42c37f | 5215 | } |
df7492f9 | 5216 | src += 2; |
fa42c37f | 5217 | } |
bcf26d6a | 5218 | } |
d46c5b12 | 5219 | else |
c4825358 | 5220 | { |
df7492f9 | 5221 | while (src < src_end) |
27901516 | 5222 | { |
df7492f9 KH |
5223 | c = *src++; |
5224 | if (c == '\n' || c == '\r') | |
5225 | { | |
5226 | int this_eol; | |
d46c5b12 | 5227 | |
df7492f9 KH |
5228 | if (c == '\n') |
5229 | this_eol = EOL_SEEN_LF; | |
5230 | else if (src >= src_end || *src != '\n') | |
5231 | this_eol = EOL_SEEN_CR; | |
5232 | else | |
5233 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 5234 | |
df7492f9 KH |
5235 | if (eol_seen == EOL_SEEN_NONE) |
5236 | /* This is the first end-of-line. */ | |
5237 | eol_seen = this_eol; | |
5238 | else if (eol_seen != this_eol) | |
5239 | { | |
5240 | /* The found type is different from what found before. */ | |
5241 | eol_seen = EOL_SEEN_LF; | |
5242 | break; | |
5243 | } | |
5244 | if (++total == MAX_EOL_CHECK_COUNT) | |
5245 | break; | |
5246 | } | |
5247 | } | |
73be902c | 5248 | } |
df7492f9 | 5249 | return eol_seen; |
73be902c KH |
5250 | } |
5251 | ||
df7492f9 | 5252 | |
73be902c | 5253 | static void |
df7492f9 KH |
5254 | adjust_coding_eol_type (coding, eol_seen) |
5255 | struct coding_system *coding; | |
5256 | int eol_seen; | |
73be902c | 5257 | { |
0be8721c | 5258 | Lisp_Object eol_type; |
8f924df7 | 5259 | |
df7492f9 KH |
5260 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
5261 | if (eol_seen & EOL_SEEN_LF) | |
5262 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
6f197c07 | 5263 | else if (eol_seen & EOL_SEEN_CRLF) |
df7492f9 | 5264 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); |
6f197c07 | 5265 | else if (eol_seen & EOL_SEEN_CR) |
df7492f9 | 5266 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); |
d46c5b12 | 5267 | } |
4ed46869 | 5268 | |
df7492f9 KH |
5269 | /* Detect how a text specified in CODING is encoded. If a coding |
5270 | system is detected, update fields of CODING by the detected coding | |
5271 | system. */ | |
0a28aafb | 5272 | |
df7492f9 KH |
5273 | void |
5274 | detect_coding (coding) | |
d46c5b12 | 5275 | struct coding_system *coding; |
d46c5b12 | 5276 | { |
8f924df7 | 5277 | const unsigned char *src, *src_end; |
df7492f9 | 5278 | Lisp_Object attrs, coding_type; |
d46c5b12 | 5279 | |
df7492f9 KH |
5280 | coding->consumed = coding->consumed_char = 0; |
5281 | coding->produced = coding->produced_char = 0; | |
5282 | coding_set_source (coding); | |
1c3478b0 | 5283 | |
df7492f9 | 5284 | src_end = coding->source + coding->src_bytes; |
1c3478b0 | 5285 | |
df7492f9 KH |
5286 | /* If we have not yet decided the text encoding type, detect it |
5287 | now. */ | |
5288 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 5289 | { |
df7492f9 KH |
5290 | int c, i; |
5291 | ||
5292 | for (src = coding->source; src < src_end; src++) | |
d46c5b12 | 5293 | { |
df7492f9 KH |
5294 | c = *src; |
5295 | if (c & 0x80 || (c < 0x20 && (c == ISO_CODE_ESC | |
5296 | || c == ISO_CODE_SI | |
5297 | || c == ISO_CODE_SO))) | |
5298 | break; | |
d46c5b12 | 5299 | } |
df7492f9 KH |
5300 | coding->head_ascii = src - (coding->source + coding->consumed); |
5301 | ||
5302 | if (coding->head_ascii < coding->src_bytes) | |
d46c5b12 | 5303 | { |
ff0dacd7 KH |
5304 | struct coding_detection_info detect_info; |
5305 | enum coding_category category; | |
5306 | struct coding_system *this; | |
df7492f9 | 5307 | |
ff0dacd7 | 5308 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
df7492f9 | 5309 | for (i = 0; i < coding_category_raw_text; i++) |
d46c5b12 | 5310 | { |
ff0dacd7 KH |
5311 | category = coding_priorities[i]; |
5312 | this = coding_categories + category; | |
df7492f9 | 5313 | if (this->id < 0) |
fa42c37f | 5314 | { |
df7492f9 | 5315 | /* No coding system of this category is defined. */ |
ff0dacd7 | 5316 | detect_info.rejected |= (1 << category); |
fa42c37f | 5317 | } |
ff0dacd7 | 5318 | else if (category >= coding_category_raw_text) |
89528eb3 | 5319 | continue; |
ff0dacd7 | 5320 | else if (detect_info.checked & (1 << category)) |
fa42c37f | 5321 | { |
ff0dacd7 KH |
5322 | if (detect_info.found & (1 << category)) |
5323 | break; | |
fa42c37f | 5324 | } |
ff0dacd7 KH |
5325 | else if ((*(this->detector)) (coding, &detect_info) |
5326 | && detect_info.found & (1 << category)) | |
5327 | break; | |
d46c5b12 | 5328 | } |
ff0dacd7 KH |
5329 | if (i < coding_category_raw_text) |
5330 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5331 | else if (detect_info.rejected == CATEGORY_MASK_ANY) | |
df7492f9 | 5332 | setup_coding_system (Qraw_text, coding); |
ff0dacd7 | 5333 | else if (detect_info.rejected) |
df7492f9 | 5334 | for (i = 0; i < coding_category_raw_text; i++) |
ff0dacd7 KH |
5335 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) |
5336 | { | |
5337 | this = coding_categories + coding_priorities[i]; | |
5338 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5339 | break; | |
5340 | } | |
d46c5b12 | 5341 | } |
b73bfc1c | 5342 | } |
b49a1807 KH |
5343 | else if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qutf_16)) |
5344 | { | |
5345 | Lisp_Object coding_systems; | |
5346 | struct coding_detection_info detect_info; | |
5347 | ||
5348 | coding_systems | |
5349 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_16_bom); | |
5350 | detect_info.found = detect_info.rejected = 0; | |
5351 | if (CONSP (coding_systems) | |
5352 | && detect_coding_utf_16 (coding, &detect_info) | |
5353 | && (detect_info.found & (CATEGORY_MASK_UTF_16_LE | |
5354 | | CATEGORY_MASK_UTF_16_BE))) | |
5355 | { | |
5356 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
5357 | setup_coding_system (XCAR (coding_systems), coding); | |
5358 | else | |
5359 | setup_coding_system (XCDR (coding_systems), coding); | |
5360 | } | |
5361 | } | |
4ed46869 | 5362 | |
df7492f9 KH |
5363 | attrs = CODING_ID_ATTRS (coding->id); |
5364 | coding_type = CODING_ATTR_TYPE (attrs); | |
4ed46869 | 5365 | |
df7492f9 KH |
5366 | /* If we have not yet decided the EOL type, detect it now. But, the |
5367 | detection is impossible for a CCL based coding system, in which | |
5368 | case, we detct the EOL type after decoding. */ | |
5369 | if (VECTORP (CODING_ID_EOL_TYPE (coding->id)) | |
5370 | && ! EQ (coding_type, Qccl)) | |
d46c5b12 | 5371 | { |
89528eb3 | 5372 | int eol_seen = detect_eol (coding->source, coding->src_bytes, |
3e139625 | 5373 | (enum coding_category) XINT (CODING_ATTR_CATEGORY (attrs))); |
4ed46869 | 5374 | |
df7492f9 KH |
5375 | if (eol_seen != EOL_SEEN_NONE) |
5376 | adjust_coding_eol_type (coding, eol_seen); | |
d46c5b12 | 5377 | } |
4ed46869 | 5378 | } |
4ed46869 | 5379 | |
d46c5b12 | 5380 | |
aaaf0b1e | 5381 | static void |
df7492f9 | 5382 | decode_eol (coding) |
aaaf0b1e | 5383 | struct coding_system *coding; |
aaaf0b1e | 5384 | { |
df7492f9 | 5385 | if (VECTORP (CODING_ID_EOL_TYPE (coding->id))) |
aaaf0b1e | 5386 | { |
df7492f9 KH |
5387 | unsigned char *p = CHAR_POS_ADDR (coding->dst_pos); |
5388 | unsigned char *pend = p + coding->produced; | |
5389 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 5390 | |
df7492f9 | 5391 | for (; p < pend; p++) |
aaaf0b1e | 5392 | { |
df7492f9 KH |
5393 | if (*p == '\n') |
5394 | eol_seen |= EOL_SEEN_LF; | |
5395 | else if (*p == '\r') | |
aaaf0b1e | 5396 | { |
df7492f9 | 5397 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 5398 | { |
df7492f9 KH |
5399 | eol_seen |= EOL_SEEN_CRLF; |
5400 | p++; | |
aaaf0b1e | 5401 | } |
aaaf0b1e | 5402 | else |
df7492f9 | 5403 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 5404 | } |
aaaf0b1e | 5405 | } |
df7492f9 KH |
5406 | if (eol_seen != EOL_SEEN_NONE) |
5407 | adjust_coding_eol_type (coding, eol_seen); | |
aaaf0b1e | 5408 | } |
d46c5b12 | 5409 | |
df7492f9 | 5410 | if (EQ (CODING_ID_EOL_TYPE (coding->id), Qmac)) |
27901516 | 5411 | { |
df7492f9 KH |
5412 | unsigned char *p = CHAR_POS_ADDR (coding->dst_pos); |
5413 | unsigned char *pend = p + coding->produced; | |
d46c5b12 | 5414 | |
df7492f9 KH |
5415 | for (; p < pend; p++) |
5416 | if (*p == '\r') | |
5417 | *p = '\n'; | |
4ed46869 | 5418 | } |
df7492f9 KH |
5419 | else if (EQ (CODING_ID_EOL_TYPE (coding->id), Qdos)) |
5420 | { | |
5421 | unsigned char *p, *pbeg, *pend; | |
5422 | Lisp_Object undo_list; | |
b73bfc1c | 5423 | |
df7492f9 KH |
5424 | move_gap_both (coding->dst_pos + coding->produced_char, |
5425 | coding->dst_pos_byte + coding->produced); | |
5426 | undo_list = current_buffer->undo_list; | |
5427 | current_buffer->undo_list = Qt; | |
c197f191 | 5428 | del_range_2 (coding->dst_pos, coding->dst_pos_byte, GPT, GPT_BYTE, 0); |
df7492f9 KH |
5429 | current_buffer->undo_list = undo_list; |
5430 | pbeg = GPT_ADDR; | |
5431 | pend = pbeg + coding->produced; | |
b73bfc1c | 5432 | |
df7492f9 KH |
5433 | for (p = pend - 1; p >= pbeg; p--) |
5434 | if (*p == '\r') | |
5435 | { | |
5436 | safe_bcopy ((char *) (p + 1), (char *) p, pend - p - 1); | |
5437 | pend--; | |
5438 | } | |
5439 | coding->produced_char -= coding->produced - (pend - pbeg); | |
5440 | coding->produced = pend - pbeg; | |
5441 | insert_from_gap (coding->produced_char, coding->produced); | |
aaaf0b1e | 5442 | } |
4ed46869 KH |
5443 | } |
5444 | ||
df7492f9 KH |
5445 | static void |
5446 | translate_chars (coding, table) | |
4ed46869 | 5447 | struct coding_system *coding; |
df7492f9 | 5448 | Lisp_Object table; |
4ed46869 | 5449 | { |
df7492f9 KH |
5450 | int *charbuf = coding->charbuf; |
5451 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5452 | int c; | |
d46c5b12 | 5453 | |
df7492f9 KH |
5454 | if (coding->chars_at_source) |
5455 | return; | |
4ed46869 | 5456 | |
df7492f9 | 5457 | while (charbuf < charbuf_end) |
8844fa83 | 5458 | { |
df7492f9 KH |
5459 | c = *charbuf; |
5460 | if (c < 0) | |
5461 | charbuf += c; | |
5462 | else | |
5463 | *charbuf++ = translate_char (table, c); | |
8844fa83 | 5464 | } |
df7492f9 | 5465 | } |
bc4bc72a | 5466 | |
d46c5b12 | 5467 | static int |
df7492f9 KH |
5468 | produce_chars (coding) |
5469 | struct coding_system *coding; | |
4ed46869 | 5470 | { |
df7492f9 KH |
5471 | unsigned char *dst = coding->destination + coding->produced; |
5472 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5473 | int produced; | |
5474 | int produced_chars = 0; | |
4ed46869 | 5475 | |
df7492f9 | 5476 | if (! coding->chars_at_source) |
4ed46869 | 5477 | { |
df7492f9 | 5478 | /* Characters are in coding->charbuf. */ |
fba4576f AS |
5479 | int *buf = coding->charbuf; |
5480 | int *buf_end = buf + coding->charbuf_used; | |
df7492f9 | 5481 | unsigned char *adjusted_dst_end; |
4ed46869 | 5482 | |
df7492f9 KH |
5483 | if (BUFFERP (coding->src_object) |
5484 | && EQ (coding->src_object, coding->dst_object)) | |
8f924df7 | 5485 | dst_end = ((unsigned char *) coding->source) + coding->consumed; |
df7492f9 | 5486 | adjusted_dst_end = dst_end - MAX_MULTIBYTE_LENGTH; |
4ed46869 | 5487 | |
df7492f9 | 5488 | while (buf < buf_end) |
4ed46869 | 5489 | { |
df7492f9 | 5490 | int c = *buf++; |
bc4bc72a | 5491 | |
df7492f9 | 5492 | if (dst >= adjusted_dst_end) |
d46c5b12 | 5493 | { |
df7492f9 KH |
5494 | dst = alloc_destination (coding, |
5495 | buf_end - buf + MAX_MULTIBYTE_LENGTH, | |
5496 | dst); | |
5497 | dst_end = coding->destination + coding->dst_bytes; | |
5498 | adjusted_dst_end = dst_end - MAX_MULTIBYTE_LENGTH; | |
5499 | } | |
5500 | if (c >= 0) | |
5501 | { | |
5502 | if (coding->dst_multibyte | |
5503 | || ! CHAR_BYTE8_P (c)) | |
5504 | CHAR_STRING_ADVANCE (c, dst); | |
5505 | else | |
5506 | *dst++ = CHAR_TO_BYTE8 (c); | |
5507 | produced_chars++; | |
d46c5b12 | 5508 | } |
df7492f9 | 5509 | else |
d3e4cb56 KH |
5510 | /* This is an annotation datum. (-C) is the length of |
5511 | it. */ | |
5512 | buf += -c - 1; | |
4ed46869 KH |
5513 | } |
5514 | } | |
fa42c37f | 5515 | else |
fa42c37f | 5516 | { |
8f924df7 KH |
5517 | const unsigned char *src = coding->source; |
5518 | const unsigned char *src_end = src + coding->src_bytes; | |
df7492f9 | 5519 | Lisp_Object eol_type; |
fa42c37f | 5520 | |
df7492f9 | 5521 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
4ed46869 | 5522 | |
df7492f9 | 5523 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 5524 | { |
df7492f9 | 5525 | if (coding->src_multibyte) |
fa42c37f | 5526 | { |
71c81426 | 5527 | int multibytep = 1; |
df7492f9 | 5528 | int consumed_chars; |
d46c5b12 | 5529 | |
df7492f9 KH |
5530 | while (1) |
5531 | { | |
8f924df7 | 5532 | const unsigned char *src_base = src; |
df7492f9 | 5533 | int c; |
b73bfc1c | 5534 | |
df7492f9 KH |
5535 | ONE_MORE_BYTE (c); |
5536 | if (c == '\r') | |
5537 | { | |
5538 | if (EQ (eol_type, Qdos)) | |
5539 | { | |
98725083 KH |
5540 | if (src == src_end) |
5541 | { | |
5542 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; | |
5543 | goto no_more_source; | |
5544 | } | |
5545 | if (*src == '\n') | |
df7492f9 KH |
5546 | c = *src++; |
5547 | } | |
5548 | else if (EQ (eol_type, Qmac)) | |
5549 | c = '\n'; | |
5550 | } | |
5551 | if (dst == dst_end) | |
5552 | { | |
2c78b7e1 | 5553 | coding->consumed = src - coding->source; |
b73bfc1c | 5554 | |
2c78b7e1 | 5555 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5556 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5557 | if (dst == dst_end) |
5558 | { | |
5559 | dst = alloc_destination (coding, src_end - src + 1, | |
5560 | dst); | |
5561 | dst_end = coding->destination + coding->dst_bytes; | |
5562 | coding_set_source (coding); | |
5563 | src = coding->source + coding->consumed; | |
5564 | src_end = coding->source + coding->src_bytes; | |
5565 | } | |
df7492f9 KH |
5566 | } |
5567 | *dst++ = c; | |
5568 | produced_chars++; | |
5569 | } | |
5570 | no_more_source: | |
5571 | ; | |
fa42c37f KH |
5572 | } |
5573 | else | |
df7492f9 KH |
5574 | while (src < src_end) |
5575 | { | |
71c81426 | 5576 | int multibytep = 1; |
df7492f9 | 5577 | int c = *src++; |
b73bfc1c | 5578 | |
df7492f9 KH |
5579 | if (c == '\r') |
5580 | { | |
5581 | if (EQ (eol_type, Qdos)) | |
5582 | { | |
5583 | if (src < src_end | |
5584 | && *src == '\n') | |
5585 | c = *src++; | |
5586 | } | |
5587 | else if (EQ (eol_type, Qmac)) | |
5588 | c = '\n'; | |
5589 | } | |
5590 | if (dst >= dst_end - 1) | |
5591 | { | |
2c78b7e1 | 5592 | coding->consumed = src - coding->source; |
df7492f9 | 5593 | |
2c78b7e1 | 5594 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5595 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5596 | if (dst >= dst_end - 1) |
5597 | { | |
5598 | dst = alloc_destination (coding, src_end - src + 2, | |
5599 | dst); | |
5600 | dst_end = coding->destination + coding->dst_bytes; | |
5601 | coding_set_source (coding); | |
5602 | src = coding->source + coding->consumed; | |
5603 | src_end = coding->source + coding->src_bytes; | |
5604 | } | |
df7492f9 KH |
5605 | } |
5606 | EMIT_ONE_BYTE (c); | |
5607 | } | |
d46c5b12 | 5608 | } |
df7492f9 KH |
5609 | else |
5610 | { | |
5611 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 5612 | { |
df7492f9 | 5613 | int require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 5614 | |
df7492f9 | 5615 | if (require > 0) |
fa42c37f | 5616 | { |
df7492f9 KH |
5617 | EMACS_INT offset = src - coding->source; |
5618 | ||
5619 | dst = alloc_destination (coding, require, dst); | |
5620 | coding_set_source (coding); | |
5621 | src = coding->source + offset; | |
5622 | src_end = coding->source + coding->src_bytes; | |
fa42c37f KH |
5623 | } |
5624 | } | |
df7492f9 KH |
5625 | produced_chars = coding->src_chars; |
5626 | while (src < src_end) | |
fa42c37f | 5627 | { |
df7492f9 KH |
5628 | int c = *src++; |
5629 | ||
5630 | if (c == '\r') | |
5631 | { | |
5632 | if (EQ (eol_type, Qdos)) | |
5633 | { | |
5634 | if (src < src_end | |
5635 | && *src == '\n') | |
5636 | c = *src++; | |
5637 | produced_chars--; | |
5638 | } | |
5639 | else if (EQ (eol_type, Qmac)) | |
5640 | c = '\n'; | |
5641 | } | |
5642 | *dst++ = c; | |
fa42c37f KH |
5643 | } |
5644 | } | |
2c78b7e1 KH |
5645 | coding->consumed = coding->src_bytes; |
5646 | coding->consumed_char = coding->src_chars; | |
fa42c37f KH |
5647 | } |
5648 | ||
df7492f9 KH |
5649 | produced = dst - (coding->destination + coding->produced); |
5650 | if (BUFFERP (coding->dst_object)) | |
5651 | insert_from_gap (produced_chars, produced); | |
5652 | coding->produced += produced; | |
5653 | coding->produced_char += produced_chars; | |
5654 | return produced_chars; | |
fa42c37f KH |
5655 | } |
5656 | ||
ff0dacd7 KH |
5657 | /* Compose text in CODING->object according to the annotation data at |
5658 | CHARBUF. CHARBUF is an array: | |
5659 | [ -LENGTH ANNOTATION_MASK FROM TO METHOD COMP_LEN [ COMPONENTS... ] ] | |
df7492f9 | 5660 | */ |
4ed46869 | 5661 | |
df7492f9 KH |
5662 | static INLINE void |
5663 | produce_composition (coding, charbuf) | |
4ed46869 | 5664 | struct coding_system *coding; |
df7492f9 | 5665 | int *charbuf; |
4ed46869 | 5666 | { |
df7492f9 | 5667 | int len; |
ff0dacd7 | 5668 | EMACS_INT from, to; |
df7492f9 | 5669 | enum composition_method method; |
df7492f9 | 5670 | Lisp_Object components; |
fa42c37f | 5671 | |
df7492f9 | 5672 | len = -charbuf[0]; |
ff0dacd7 KH |
5673 | from = coding->dst_pos + charbuf[2]; |
5674 | to = coding->dst_pos + charbuf[3]; | |
5675 | method = (enum composition_method) (charbuf[4]); | |
d46c5b12 | 5676 | |
df7492f9 KH |
5677 | if (method == COMPOSITION_RELATIVE) |
5678 | components = Qnil; | |
d46c5b12 | 5679 | else |
d46c5b12 | 5680 | { |
df7492f9 KH |
5681 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
5682 | int i; | |
b73bfc1c | 5683 | |
df7492f9 KH |
5684 | len -= 5; |
5685 | charbuf += 5; | |
5686 | for (i = 0; i < len; i++) | |
5687 | args[i] = make_number (charbuf[i]); | |
5688 | components = (method == COMPOSITION_WITH_ALTCHARS | |
5689 | ? Fstring (len, args) : Fvector (len, args)); | |
d46c5b12 | 5690 | } |
ff0dacd7 | 5691 | compose_text (from, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
5692 | } |
5693 | ||
d46c5b12 | 5694 | |
ff0dacd7 KH |
5695 | /* Put `charset' property on text in CODING->object according to |
5696 | the annotation data at CHARBUF. CHARBUF is an array: | |
5697 | [ -LENGTH ANNOTATION_MASK FROM TO CHARSET-ID ] | |
5698 | */ | |
d46c5b12 | 5699 | |
ff0dacd7 KH |
5700 | static INLINE void |
5701 | produce_charset (coding, charbuf) | |
d46c5b12 | 5702 | struct coding_system *coding; |
ff0dacd7 | 5703 | int *charbuf; |
d46c5b12 | 5704 | { |
ff0dacd7 KH |
5705 | EMACS_INT from = coding->dst_pos + charbuf[2]; |
5706 | EMACS_INT to = coding->dst_pos + charbuf[3]; | |
5707 | struct charset *charset = CHARSET_FROM_ID (charbuf[4]); | |
b73bfc1c | 5708 | |
ff0dacd7 KH |
5709 | Fput_text_property (make_number (from), make_number (to), |
5710 | Qcharset, CHARSET_NAME (charset), | |
5711 | coding->dst_object); | |
d46c5b12 KH |
5712 | } |
5713 | ||
d46c5b12 | 5714 | |
df7492f9 KH |
5715 | #define CHARBUF_SIZE 0x4000 |
5716 | ||
5717 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
5718 | do { \ | |
5719 | int size = CHARBUF_SIZE;; \ | |
5720 | \ | |
5721 | coding->charbuf = NULL; \ | |
5722 | while (size > 1024) \ | |
5723 | { \ | |
5724 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
5725 | if (coding->charbuf) \ | |
5726 | break; \ | |
5727 | size >>= 1; \ | |
5728 | } \ | |
5729 | if (! coding->charbuf) \ | |
5730 | { \ | |
5731 | coding->result = CODING_RESULT_INSUFFICIENT_MEM; \ | |
5732 | return coding->result; \ | |
5733 | } \ | |
5734 | coding->charbuf_size = size; \ | |
5735 | } while (0) | |
4ed46869 | 5736 | |
d46c5b12 KH |
5737 | |
5738 | static void | |
df7492f9 | 5739 | produce_annotation (coding) |
d46c5b12 | 5740 | struct coding_system *coding; |
d46c5b12 | 5741 | { |
df7492f9 KH |
5742 | int *charbuf = coding->charbuf; |
5743 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 5744 | |
ff0dacd7 KH |
5745 | if (NILP (coding->dst_object)) |
5746 | return; | |
d46c5b12 | 5747 | |
df7492f9 | 5748 | while (charbuf < charbuf_end) |
a84f1519 | 5749 | { |
df7492f9 KH |
5750 | if (*charbuf >= 0) |
5751 | charbuf++; | |
d46c5b12 | 5752 | else |
d46c5b12 | 5753 | { |
df7492f9 | 5754 | int len = -*charbuf; |
ff0dacd7 | 5755 | switch (charbuf[1]) |
df7492f9 KH |
5756 | { |
5757 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
5758 | produce_composition (coding, charbuf); | |
5759 | break; | |
ff0dacd7 KH |
5760 | case CODING_ANNOTATE_CHARSET_MASK: |
5761 | produce_charset (coding, charbuf); | |
5762 | break; | |
df7492f9 KH |
5763 | default: |
5764 | abort (); | |
5765 | } | |
5766 | charbuf += len; | |
d46c5b12 | 5767 | } |
a84f1519 | 5768 | } |
d46c5b12 KH |
5769 | } |
5770 | ||
df7492f9 KH |
5771 | /* Decode the data at CODING->src_object into CODING->dst_object. |
5772 | CODING->src_object is a buffer, a string, or nil. | |
5773 | CODING->dst_object is a buffer. | |
d46c5b12 | 5774 | |
df7492f9 KH |
5775 | If CODING->src_object is a buffer, it must be the current buffer. |
5776 | In this case, if CODING->src_pos is positive, it is a position of | |
5777 | the source text in the buffer, otherwise, the source text is in the | |
5778 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
5779 | the text from GPT (which must be the same as PT). If this is the | |
5780 | same buffer as CODING->dst_object, CODING->src_pos must be | |
5781 | negative. | |
d46c5b12 | 5782 | |
df7492f9 KH |
5783 | If CODING->src_object is a string, CODING->src_pos in an index to |
5784 | that string. | |
d46c5b12 | 5785 | |
df7492f9 KH |
5786 | If CODING->src_object is nil, CODING->source must already point to |
5787 | the non-relocatable memory area. In this case, CODING->src_pos is | |
5788 | an offset from CODING->source. | |
73be902c | 5789 | |
df7492f9 KH |
5790 | The decoded data is inserted at the current point of the buffer |
5791 | CODING->dst_object. | |
5792 | */ | |
d46c5b12 | 5793 | |
df7492f9 KH |
5794 | static int |
5795 | decode_coding (coding) | |
d46c5b12 | 5796 | struct coding_system *coding; |
d46c5b12 | 5797 | { |
df7492f9 | 5798 | Lisp_Object attrs; |
d46c5b12 | 5799 | |
df7492f9 KH |
5800 | if (BUFFERP (coding->src_object) |
5801 | && coding->src_pos > 0 | |
5802 | && coding->src_pos < GPT | |
5803 | && coding->src_pos + coding->src_chars > GPT) | |
5804 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 5805 | |
df7492f9 | 5806 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 5807 | { |
df7492f9 KH |
5808 | if (current_buffer != XBUFFER (coding->dst_object)) |
5809 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
5810 | if (GPT != PT) | |
5811 | move_gap_both (PT, PT_BYTE); | |
1c3478b0 KH |
5812 | } |
5813 | ||
df7492f9 KH |
5814 | coding->consumed = coding->consumed_char = 0; |
5815 | coding->produced = coding->produced_char = 0; | |
5816 | coding->chars_at_source = 0; | |
5817 | coding->result = CODING_RESULT_SUCCESS; | |
5818 | coding->errors = 0; | |
1c3478b0 | 5819 | |
df7492f9 KH |
5820 | ALLOC_CONVERSION_WORK_AREA (coding); |
5821 | ||
5822 | attrs = CODING_ID_ATTRS (coding->id); | |
5823 | ||
5824 | do | |
b73bfc1c | 5825 | { |
df7492f9 KH |
5826 | coding_set_source (coding); |
5827 | coding->annotated = 0; | |
5828 | (*(coding->decoder)) (coding); | |
5829 | if (!NILP (CODING_ATTR_DECODE_TBL (attrs))) | |
da4109a9 KH |
5830 | translate_chars (coding, CODING_ATTR_DECODE_TBL (attrs)); |
5831 | else if (!NILP (Vstandard_translation_table_for_decode)) | |
5832 | translate_chars (coding, Vstandard_translation_table_for_decode); | |
df7492f9 KH |
5833 | coding_set_destination (coding); |
5834 | produce_chars (coding); | |
5835 | if (coding->annotated) | |
5836 | produce_annotation (coding); | |
d46c5b12 | 5837 | } |
df7492f9 KH |
5838 | while (coding->consumed < coding->src_bytes |
5839 | && ! coding->result); | |
d46c5b12 | 5840 | |
df7492f9 KH |
5841 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qccl) |
5842 | && SYMBOLP (CODING_ID_EOL_TYPE (coding->id)) | |
5843 | && ! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix)) | |
5844 | decode_eol (coding); | |
d46c5b12 | 5845 | |
df7492f9 KH |
5846 | coding->carryover_bytes = 0; |
5847 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 5848 | { |
df7492f9 | 5849 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 5850 | const unsigned char *src; |
df7492f9 KH |
5851 | |
5852 | coding_set_source (coding); | |
5853 | coding_set_destination (coding); | |
5854 | src = coding->source + coding->consumed; | |
5855 | ||
5856 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 5857 | { |
df7492f9 KH |
5858 | /* Flush out unprocessed data as binary chars. We are sure |
5859 | that the number of data is less than the size of | |
5860 | coding->charbuf. */ | |
df7492f9 | 5861 | while (nbytes-- > 0) |
1c3478b0 | 5862 | { |
df7492f9 | 5863 | int c = *src++; |
98725083 KH |
5864 | |
5865 | coding->charbuf[coding->charbuf_used++] = (c & 0x80 ? - c : c); | |
1c3478b0 | 5866 | } |
df7492f9 | 5867 | produce_chars (coding); |
d46c5b12 | 5868 | } |
d46c5b12 | 5869 | else |
df7492f9 KH |
5870 | { |
5871 | /* Record unprocessed bytes in coding->carryover. We are | |
5872 | sure that the number of data is less than the size of | |
5873 | coding->carryover. */ | |
5874 | unsigned char *p = coding->carryover; | |
5875 | ||
5876 | coding->carryover_bytes = nbytes; | |
5877 | while (nbytes-- > 0) | |
5878 | *p++ = *src++; | |
1c3478b0 | 5879 | } |
df7492f9 | 5880 | coding->consumed = coding->src_bytes; |
b73bfc1c | 5881 | } |
69f76525 | 5882 | |
73be902c | 5883 | return coding->result; |
4ed46869 KH |
5884 | } |
5885 | ||
aaaf0b1e | 5886 | |
e1c23804 | 5887 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
5888 | ending before LIMIT of CODING->src_object (buffer or string), store |
5889 | the data in BUF, set *STOP to a starting position of the next | |
5890 | composition (if any) or to LIMIT, and return the address of the | |
5891 | next element of BUF. | |
5892 | ||
5893 | If such an annotation is not found, set *STOP to a starting | |
5894 | position of a composition after POS (if any) or to LIMIT, and | |
5895 | return BUF. */ | |
5896 | ||
5897 | static INLINE int * | |
5898 | handle_composition_annotation (pos, limit, coding, buf, stop) | |
5899 | EMACS_INT pos, limit; | |
aaaf0b1e | 5900 | struct coding_system *coding; |
ff0dacd7 KH |
5901 | int *buf; |
5902 | EMACS_INT *stop; | |
aaaf0b1e | 5903 | { |
ff0dacd7 KH |
5904 | EMACS_INT start, end; |
5905 | Lisp_Object prop; | |
aaaf0b1e | 5906 | |
ff0dacd7 KH |
5907 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
5908 | || end > limit) | |
5909 | *stop = limit; | |
5910 | else if (start > pos) | |
5911 | *stop = start; | |
5912 | else | |
aaaf0b1e | 5913 | { |
ff0dacd7 | 5914 | if (start == pos) |
aaaf0b1e | 5915 | { |
ff0dacd7 KH |
5916 | /* We found a composition. Store the corresponding |
5917 | annotation data in BUF. */ | |
5918 | int *head = buf; | |
5919 | enum composition_method method = COMPOSITION_METHOD (prop); | |
5920 | int nchars = COMPOSITION_LENGTH (prop); | |
5921 | ||
5922 | ADD_COMPOSITION_DATA (buf, 0, nchars, method); | |
5923 | if (method != COMPOSITION_RELATIVE) | |
aaaf0b1e | 5924 | { |
ff0dacd7 KH |
5925 | Lisp_Object components; |
5926 | int len, i, i_byte; | |
5927 | ||
5928 | components = COMPOSITION_COMPONENTS (prop); | |
5929 | if (VECTORP (components)) | |
aaaf0b1e | 5930 | { |
ff0dacd7 KH |
5931 | len = XVECTOR (components)->size; |
5932 | for (i = 0; i < len; i++) | |
5933 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 5934 | } |
ff0dacd7 | 5935 | else if (STRINGP (components)) |
aaaf0b1e | 5936 | { |
8f924df7 | 5937 | len = SCHARS (components); |
ff0dacd7 KH |
5938 | i = i_byte = 0; |
5939 | while (i < len) | |
5940 | { | |
5941 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
5942 | buf++; | |
5943 | } | |
5944 | } | |
5945 | else if (INTEGERP (components)) | |
5946 | { | |
5947 | len = 1; | |
5948 | *buf++ = XINT (components); | |
5949 | } | |
5950 | else if (CONSP (components)) | |
5951 | { | |
5952 | for (len = 0; CONSP (components); | |
5953 | len++, components = XCDR (components)) | |
5954 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 5955 | } |
aaaf0b1e | 5956 | else |
ff0dacd7 KH |
5957 | abort (); |
5958 | *head -= len; | |
aaaf0b1e | 5959 | } |
aaaf0b1e | 5960 | } |
ff0dacd7 KH |
5961 | |
5962 | if (find_composition (end, limit, &start, &end, &prop, | |
5963 | coding->src_object) | |
5964 | && end <= limit) | |
5965 | *stop = start; | |
5966 | else | |
5967 | *stop = limit; | |
aaaf0b1e | 5968 | } |
ff0dacd7 KH |
5969 | return buf; |
5970 | } | |
5971 | ||
5972 | ||
e1c23804 | 5973 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
5974 | CODING->src_object (buffer of string), store the data in BUF, set |
5975 | *STOP to the position where the value of `charset' property changes | |
5976 | (limiting by LIMIT), and return the address of the next element of | |
5977 | BUF. | |
5978 | ||
5979 | If the property value is nil, set *STOP to the position where the | |
5980 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
5981 | ||
5982 | static INLINE int * | |
5983 | handle_charset_annotation (pos, limit, coding, buf, stop) | |
5984 | EMACS_INT pos, limit; | |
5985 | struct coding_system *coding; | |
5986 | int *buf; | |
5987 | EMACS_INT *stop; | |
5988 | { | |
5989 | Lisp_Object val, next; | |
5990 | int id; | |
5991 | ||
5992 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
5993 | if (! NILP (val) && CHARSETP (val)) | |
5994 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
5995 | else | |
5996 | id = -1; | |
5997 | ADD_CHARSET_DATA (buf, 0, 0, id); | |
5998 | next = Fnext_single_property_change (make_number (pos), Qcharset, | |
5999 | coding->src_object, | |
6000 | make_number (limit)); | |
6001 | *stop = XINT (next); | |
6002 | return buf; | |
6003 | } | |
6004 | ||
6005 | ||
df7492f9 KH |
6006 | static void |
6007 | consume_chars (coding) | |
6008 | struct coding_system *coding; | |
6009 | { | |
6010 | int *buf = coding->charbuf; | |
ff0dacd7 | 6011 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 6012 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 6013 | const unsigned char *src_end = coding->source + coding->src_bytes; |
ff0dacd7 KH |
6014 | EMACS_INT pos = coding->src_pos + coding->consumed_char; |
6015 | EMACS_INT end_pos = coding->src_pos + coding->src_chars; | |
df7492f9 KH |
6016 | int multibytep = coding->src_multibyte; |
6017 | Lisp_Object eol_type; | |
6018 | int c; | |
ff0dacd7 | 6019 | EMACS_INT stop, stop_composition, stop_charset; |
88993dfd | 6020 | |
df7492f9 KH |
6021 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6022 | if (VECTORP (eol_type)) | |
6023 | eol_type = Qunix; | |
88993dfd | 6024 | |
df7492f9 KH |
6025 | /* Note: composition handling is not yet implemented. */ |
6026 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 6027 | |
0b5670c9 KH |
6028 | if (NILP (coding->src_object)) |
6029 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 6030 | else |
0b5670c9 KH |
6031 | { |
6032 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
6033 | stop = stop_composition = pos; | |
6034 | else | |
6035 | stop = stop_composition = end_pos; | |
6036 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
6037 | stop = stop_charset = pos; | |
6038 | else | |
6039 | stop_charset = end_pos; | |
6040 | } | |
ec6d2bb8 | 6041 | |
ff0dacd7 KH |
6042 | /* Compensate for CRLF and annotation. */ |
6043 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; | |
df7492f9 | 6044 | while (buf < buf_end) |
aaaf0b1e | 6045 | { |
df7492f9 | 6046 | if (pos == stop) |
ec6d2bb8 | 6047 | { |
df7492f9 KH |
6048 | if (pos == end_pos) |
6049 | break; | |
ff0dacd7 KH |
6050 | if (pos == stop_composition) |
6051 | buf = handle_composition_annotation (pos, end_pos, coding, | |
6052 | buf, &stop_composition); | |
6053 | if (pos == stop_charset) | |
6054 | buf = handle_charset_annotation (pos, end_pos, coding, | |
6055 | buf, &stop_charset); | |
6056 | stop = (stop_composition < stop_charset | |
6057 | ? stop_composition : stop_charset); | |
df7492f9 KH |
6058 | } |
6059 | ||
6060 | if (! multibytep) | |
4776e638 | 6061 | { |
d3e4cb56 | 6062 | EMACS_INT bytes; |
aaaf0b1e | 6063 | |
d3e4cb56 KH |
6064 | if (! CODING_FOR_UNIBYTE (coding) |
6065 | && (bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
4776e638 KH |
6066 | c = STRING_CHAR_ADVANCE (src), pos += bytes; |
6067 | else | |
6068 | c = *src++, pos++; | |
6069 | } | |
df7492f9 | 6070 | else |
4776e638 | 6071 | c = STRING_CHAR_ADVANCE (src), pos++; |
df7492f9 KH |
6072 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
6073 | c = '\n'; | |
6074 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 6075 | { |
df7492f9 | 6076 | if (c == '\n') |
aaaf0b1e | 6077 | { |
df7492f9 KH |
6078 | if (EQ (eol_type, Qdos)) |
6079 | *buf++ = '\r'; | |
6080 | else | |
6081 | c = '\r'; | |
aaaf0b1e KH |
6082 | } |
6083 | } | |
df7492f9 | 6084 | *buf++ = c; |
aaaf0b1e | 6085 | } |
ec6d2bb8 | 6086 | |
df7492f9 KH |
6087 | coding->consumed = src - coding->source; |
6088 | coding->consumed_char = pos - coding->src_pos; | |
6089 | coding->charbuf_used = buf - coding->charbuf; | |
6090 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
6091 | } |
6092 | ||
4ed46869 | 6093 | |
df7492f9 KH |
6094 | /* Encode the text at CODING->src_object into CODING->dst_object. |
6095 | CODING->src_object is a buffer or a string. | |
6096 | CODING->dst_object is a buffer or nil. | |
6097 | ||
6098 | If CODING->src_object is a buffer, it must be the current buffer. | |
6099 | In this case, if CODING->src_pos is positive, it is a position of | |
6100 | the source text in the buffer, otherwise. the source text is in the | |
6101 | gap area of the buffer, and coding->src_pos specifies the offset of | |
6102 | the text from GPT (which must be the same as PT). If this is the | |
6103 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6104 | negative and CODING should not have `pre-write-conversion'. | |
6105 | ||
6106 | If CODING->src_object is a string, CODING should not have | |
6107 | `pre-write-conversion'. | |
6108 | ||
6109 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
6110 | the current point of that buffer. | |
6111 | ||
6112 | If CODING->dst_object is nil, the encoded data is placed at the | |
6113 | memory area specified by CODING->destination. */ | |
6114 | ||
6115 | static int | |
6116 | encode_coding (coding) | |
4ed46869 | 6117 | struct coding_system *coding; |
4ed46869 | 6118 | { |
df7492f9 | 6119 | Lisp_Object attrs; |
9861e777 | 6120 | |
df7492f9 | 6121 | attrs = CODING_ID_ATTRS (coding->id); |
4ed46869 | 6122 | |
df7492f9 | 6123 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 6124 | { |
df7492f9 KH |
6125 | set_buffer_internal (XBUFFER (coding->dst_object)); |
6126 | coding->dst_multibyte | |
6127 | = ! NILP (current_buffer->enable_multibyte_characters); | |
8844fa83 | 6128 | } |
4ed46869 | 6129 | |
b73bfc1c | 6130 | coding->consumed = coding->consumed_char = 0; |
df7492f9 KH |
6131 | coding->produced = coding->produced_char = 0; |
6132 | coding->result = CODING_RESULT_SUCCESS; | |
b73bfc1c | 6133 | coding->errors = 0; |
b73bfc1c | 6134 | |
df7492f9 | 6135 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 6136 | |
df7492f9 KH |
6137 | do { |
6138 | coding_set_source (coding); | |
6139 | consume_chars (coding); | |
4ed46869 | 6140 | |
df7492f9 | 6141 | if (!NILP (CODING_ATTR_ENCODE_TBL (attrs))) |
da4109a9 KH |
6142 | translate_chars (coding, CODING_ATTR_ENCODE_TBL (attrs)); |
6143 | else if (!NILP (Vstandard_translation_table_for_encode)) | |
6144 | translate_chars (coding, Vstandard_translation_table_for_encode); | |
b73bfc1c | 6145 | |
df7492f9 KH |
6146 | coding_set_destination (coding); |
6147 | (*(coding->encoder)) (coding); | |
6148 | } while (coding->consumed_char < coding->src_chars); | |
6149 | ||
6150 | if (BUFFERP (coding->dst_object)) | |
6151 | insert_from_gap (coding->produced_char, coding->produced); | |
6152 | ||
6153 | return (coding->result); | |
ec6d2bb8 KH |
6154 | } |
6155 | ||
fb88bf2d | 6156 | |
4776e638 KH |
6157 | /* Stack of working buffers used in code conversion. An nil element |
6158 | means that the code conversion of that level is not using a working | |
6159 | buffer. */ | |
df7492f9 | 6160 | Lisp_Object Vcode_conversion_work_buf_list; |
d46c5b12 | 6161 | |
df7492f9 KH |
6162 | /* A working buffer used by the top level conversion. */ |
6163 | Lisp_Object Vcode_conversion_reused_work_buf; | |
b73bfc1c | 6164 | |
4ed46869 | 6165 | |
df7492f9 KH |
6166 | /* Return a working buffer that can be freely used by the following |
6167 | code conversion. MULTIBYTEP specifies the multibyteness of the | |
6168 | buffer. */ | |
b73bfc1c | 6169 | |
df7492f9 | 6170 | Lisp_Object |
4776e638 KH |
6171 | make_conversion_work_buffer (multibytep, depth) |
6172 | int multibytep, depth; | |
df7492f9 KH |
6173 | { |
6174 | struct buffer *current = current_buffer; | |
4776e638 | 6175 | Lisp_Object buf, name; |
4ed46869 | 6176 | |
4776e638 | 6177 | if (depth == 0) |
e133c8fa | 6178 | { |
df7492f9 KH |
6179 | if (NILP (Vcode_conversion_reused_work_buf)) |
6180 | Vcode_conversion_reused_work_buf | |
857dccb0 | 6181 | = Fget_buffer_create (build_string (" *code-converting-work<0>*")); |
4776e638 | 6182 | buf = Vcode_conversion_reused_work_buf; |
e133c8fa | 6183 | } |
df7492f9 | 6184 | else |
d46c5b12 | 6185 | { |
4776e638 | 6186 | if (depth < 0) |
aaaf0b1e | 6187 | { |
857dccb0 | 6188 | name = build_string (" *code-converting-work*"); |
4776e638 | 6189 | name = Fgenerate_new_buffer_name (name, Qnil); |
aaaf0b1e | 6190 | } |
4776e638 | 6191 | else |
9861e777 | 6192 | { |
4776e638 | 6193 | char str[128]; |
d46c5b12 | 6194 | |
857dccb0 | 6195 | sprintf (str, " *code-converting-work*<%d>", depth); |
4776e638 KH |
6196 | name = build_string (str); |
6197 | } | |
6198 | buf = Fget_buffer_create (name); | |
b73bfc1c | 6199 | } |
df7492f9 KH |
6200 | set_buffer_internal (XBUFFER (buf)); |
6201 | current_buffer->undo_list = Qt; | |
6202 | Ferase_buffer (); | |
8f924df7 | 6203 | Fset_buffer_multibyte (multibytep ? Qt : Qnil); |
df7492f9 KH |
6204 | set_buffer_internal (current); |
6205 | return buf; | |
6206 | } | |
d46c5b12 | 6207 | |
4776e638 KH |
6208 | static Lisp_Object |
6209 | code_conversion_restore (buffer) | |
6210 | Lisp_Object buffer; | |
6211 | { | |
6212 | Lisp_Object workbuf; | |
6213 | ||
6214 | workbuf = XCAR (Vcode_conversion_work_buf_list); | |
6215 | if (! NILP (workbuf) | |
6216 | && ! EQ (workbuf, Vcode_conversion_reused_work_buf) | |
6217 | && ! NILP (Fbuffer_live_p (workbuf))) | |
6218 | Fkill_buffer (workbuf); | |
6219 | Vcode_conversion_work_buf_list = XCDR (Vcode_conversion_work_buf_list); | |
6220 | set_buffer_internal (XBUFFER (buffer)); | |
6221 | return Qnil; | |
6222 | } | |
b73bfc1c | 6223 | |
4776e638 KH |
6224 | static Lisp_Object |
6225 | code_conversion_save (buffer, with_work_buf, multibyte) | |
6226 | Lisp_Object buffer; | |
6227 | int with_work_buf, multibyte; | |
df7492f9 | 6228 | { |
4776e638 | 6229 | Lisp_Object workbuf; |
b73bfc1c | 6230 | |
4776e638 | 6231 | if (with_work_buf) |
b73bfc1c | 6232 | { |
4776e638 | 6233 | int depth = XINT (Flength (Vcode_conversion_work_buf_list)); |
b73bfc1c | 6234 | |
4776e638 | 6235 | workbuf = make_conversion_work_buffer (multibyte, depth); |
4ed46869 | 6236 | } |
4776e638 KH |
6237 | else |
6238 | workbuf = Qnil; | |
6239 | Vcode_conversion_work_buf_list | |
6240 | = Fcons (workbuf, Vcode_conversion_work_buf_list); | |
6241 | record_unwind_protect (code_conversion_restore, buffer); | |
6242 | return workbuf; | |
df7492f9 | 6243 | } |
d46c5b12 | 6244 | |
df7492f9 KH |
6245 | int |
6246 | decode_coding_gap (coding, chars, bytes) | |
6247 | struct coding_system *coding; | |
6248 | EMACS_INT chars, bytes; | |
6249 | { | |
6250 | int count = specpdl_ptr - specpdl; | |
5e5c78be | 6251 | Lisp_Object attrs; |
4776e638 | 6252 | Lisp_Object buffer; |
fb88bf2d | 6253 | |
4776e638 KH |
6254 | buffer = Fcurrent_buffer (); |
6255 | code_conversion_save (buffer, 0, 0); | |
ec6d2bb8 | 6256 | |
4776e638 | 6257 | coding->src_object = buffer; |
df7492f9 KH |
6258 | coding->src_chars = chars; |
6259 | coding->src_bytes = bytes; | |
6260 | coding->src_pos = -chars; | |
6261 | coding->src_pos_byte = -bytes; | |
6262 | coding->src_multibyte = chars < bytes; | |
5e5c78be | 6263 | coding->dst_object = buffer; |
df7492f9 KH |
6264 | coding->dst_pos = PT; |
6265 | coding->dst_pos_byte = PT_BYTE; | |
71c81426 | 6266 | coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters); |
98725083 | 6267 | coding->mode |= CODING_MODE_LAST_BLOCK; |
4ed46869 | 6268 | |
df7492f9 KH |
6269 | if (CODING_REQUIRE_DETECTION (coding)) |
6270 | detect_coding (coding); | |
8f924df7 | 6271 | |
df7492f9 | 6272 | decode_coding (coding); |
d46c5b12 | 6273 | |
5e5c78be KH |
6274 | attrs = CODING_ID_ATTRS (coding->id); |
6275 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 6276 | { |
5e5c78be KH |
6277 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
6278 | Lisp_Object val; | |
6279 | ||
6280 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
6281 | val = call1 (CODING_ATTR_POST_READ (attrs), |
6282 | make_number (coding->produced_char)); | |
5e5c78be KH |
6283 | CHECK_NATNUM (val); |
6284 | coding->produced_char += Z - prev_Z; | |
6285 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 6286 | } |
4ed46869 | 6287 | |
df7492f9 | 6288 | unbind_to (count, Qnil); |
b73bfc1c KH |
6289 | return coding->result; |
6290 | } | |
52d41803 | 6291 | |
4ed46869 | 6292 | int |
df7492f9 | 6293 | encode_coding_gap (coding, chars, bytes) |
4ed46869 | 6294 | struct coding_system *coding; |
df7492f9 | 6295 | EMACS_INT chars, bytes; |
4ed46869 | 6296 | { |
df7492f9 KH |
6297 | int count = specpdl_ptr - specpdl; |
6298 | Lisp_Object buffer; | |
4ed46869 | 6299 | |
df7492f9 | 6300 | buffer = Fcurrent_buffer (); |
4776e638 | 6301 | code_conversion_save (buffer, 0, 0); |
4ed46869 | 6302 | |
df7492f9 KH |
6303 | coding->src_object = buffer; |
6304 | coding->src_chars = chars; | |
6305 | coding->src_bytes = bytes; | |
6306 | coding->src_pos = -chars; | |
6307 | coding->src_pos_byte = -bytes; | |
6308 | coding->src_multibyte = chars < bytes; | |
6309 | coding->dst_object = coding->src_object; | |
6310 | coding->dst_pos = PT; | |
6311 | coding->dst_pos_byte = PT_BYTE; | |
4ed46869 | 6312 | |
df7492f9 | 6313 | encode_coding (coding); |
b73bfc1c | 6314 | |
df7492f9 KH |
6315 | unbind_to (count, Qnil); |
6316 | return coding->result; | |
6317 | } | |
4ed46869 | 6318 | |
d46c5b12 | 6319 | |
df7492f9 KH |
6320 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
6321 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 6322 | |
df7492f9 | 6323 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 6324 | |
df7492f9 KH |
6325 | If it is a buffer, the text is at point of the buffer. FROM and TO |
6326 | are positions in the buffer. | |
b73bfc1c | 6327 | |
df7492f9 KH |
6328 | If it is a string, the text is at the beginning of the string. |
6329 | FROM and TO are indices to the string. | |
4ed46869 | 6330 | |
df7492f9 KH |
6331 | If it is nil, the text is at coding->source. FROM and TO are |
6332 | indices to coding->source. | |
bb10be8b | 6333 | |
df7492f9 | 6334 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 6335 | |
df7492f9 KH |
6336 | If it is a buffer, the decoded text is inserted at point of the |
6337 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
6338 | is deleted. | |
4ed46869 | 6339 | |
df7492f9 KH |
6340 | If it is Qt, a string is made from the decoded text, and |
6341 | set in CODING->dst_object. | |
d46c5b12 | 6342 | |
df7492f9 | 6343 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 6344 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
6345 | CODING->destination by xmalloc. If the decoded text is longer than |
6346 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
6347 | */ | |
d46c5b12 | 6348 | |
df7492f9 KH |
6349 | void |
6350 | decode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6351 | dst_object) | |
d46c5b12 | 6352 | struct coding_system *coding; |
df7492f9 KH |
6353 | Lisp_Object src_object; |
6354 | EMACS_INT from, from_byte, to, to_byte; | |
6355 | Lisp_Object dst_object; | |
d46c5b12 | 6356 | { |
df7492f9 KH |
6357 | int count = specpdl_ptr - specpdl; |
6358 | unsigned char *destination; | |
6359 | EMACS_INT dst_bytes; | |
6360 | EMACS_INT chars = to - from; | |
6361 | EMACS_INT bytes = to_byte - from_byte; | |
6362 | Lisp_Object attrs; | |
4776e638 KH |
6363 | Lisp_Object buffer; |
6364 | int saved_pt = -1, saved_pt_byte; | |
d46c5b12 | 6365 | |
4776e638 | 6366 | buffer = Fcurrent_buffer (); |
93dec019 | 6367 | |
df7492f9 | 6368 | if (NILP (dst_object)) |
d46c5b12 | 6369 | { |
df7492f9 KH |
6370 | destination = coding->destination; |
6371 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 6372 | } |
93dec019 | 6373 | |
df7492f9 KH |
6374 | coding->src_object = src_object; |
6375 | coding->src_chars = chars; | |
6376 | coding->src_bytes = bytes; | |
6377 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 6378 | |
df7492f9 | 6379 | if (STRINGP (src_object)) |
d46c5b12 | 6380 | { |
df7492f9 KH |
6381 | coding->src_pos = from; |
6382 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6383 | } |
df7492f9 | 6384 | else if (BUFFERP (src_object)) |
88993dfd | 6385 | { |
df7492f9 KH |
6386 | set_buffer_internal (XBUFFER (src_object)); |
6387 | if (from != GPT) | |
6388 | move_gap_both (from, from_byte); | |
6389 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 6390 | { |
4776e638 | 6391 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6392 | TEMP_SET_PT_BOTH (from, from_byte); |
6393 | del_range_both (from, from_byte, to, to_byte, 1); | |
6394 | coding->src_pos = -chars; | |
6395 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 6396 | } |
df7492f9 | 6397 | else |
fb88bf2d | 6398 | { |
df7492f9 KH |
6399 | coding->src_pos = from; |
6400 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 6401 | } |
88993dfd KH |
6402 | } |
6403 | ||
df7492f9 KH |
6404 | if (CODING_REQUIRE_DETECTION (coding)) |
6405 | detect_coding (coding); | |
6406 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 6407 | |
2cb26057 KH |
6408 | if (EQ (dst_object, Qt) |
6409 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
6410 | && NILP (dst_object))) | |
b73bfc1c | 6411 | { |
4776e638 | 6412 | coding->dst_object = code_conversion_save (buffer, 1, 1); |
df7492f9 KH |
6413 | coding->dst_pos = BEG; |
6414 | coding->dst_pos_byte = BEG_BYTE; | |
6415 | coding->dst_multibyte = 1; | |
b73bfc1c | 6416 | } |
df7492f9 | 6417 | else if (BUFFERP (dst_object)) |
d46c5b12 | 6418 | { |
4776e638 | 6419 | code_conversion_save (buffer, 0, 0); |
df7492f9 KH |
6420 | coding->dst_object = dst_object; |
6421 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6422 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6423 | coding->dst_multibyte | |
6424 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
d46c5b12 KH |
6425 | } |
6426 | else | |
6427 | { | |
4776e638 | 6428 | code_conversion_save (buffer, 0, 0); |
df7492f9 KH |
6429 | coding->dst_object = Qnil; |
6430 | coding->dst_multibyte = 1; | |
d46c5b12 KH |
6431 | } |
6432 | ||
df7492f9 | 6433 | decode_coding (coding); |
fa46990e | 6434 | |
df7492f9 KH |
6435 | if (BUFFERP (coding->dst_object)) |
6436 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 6437 | |
df7492f9 | 6438 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 6439 | { |
df7492f9 KH |
6440 | struct gcpro gcpro1, gcpro2; |
6441 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; | |
2b4f9037 | 6442 | Lisp_Object val; |
d46c5b12 | 6443 | |
c0cc7f7f | 6444 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
df7492f9 KH |
6445 | GCPRO2 (coding->src_object, coding->dst_object); |
6446 | val = call1 (CODING_ATTR_POST_READ (attrs), | |
6447 | make_number (coding->produced_char)); | |
6448 | UNGCPRO; | |
6449 | CHECK_NATNUM (val); | |
6450 | coding->produced_char += Z - prev_Z; | |
6451 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 6452 | } |
de79a6a5 | 6453 | |
df7492f9 | 6454 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 6455 | { |
df7492f9 KH |
6456 | coding->dst_object = Fbuffer_string (); |
6457 | } | |
6458 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
6459 | { | |
6460 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6461 | if (dst_bytes < coding->produced) | |
6462 | { | |
6463 | destination | |
6464 | = (unsigned char *) xrealloc (destination, coding->produced); | |
6465 | if (! destination) | |
6466 | { | |
6467 | coding->result = CODING_RESULT_INSUFFICIENT_DST; | |
6468 | unbind_to (count, Qnil); | |
6469 | return; | |
6470 | } | |
6471 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
6472 | move_gap_both (BEGV, BEGV_BYTE); | |
6473 | bcopy (BEGV_ADDR, destination, coding->produced); | |
6474 | coding->destination = destination; | |
d46c5b12 | 6475 | } |
ec6d2bb8 | 6476 | } |
b73bfc1c | 6477 | |
4776e638 KH |
6478 | if (saved_pt >= 0) |
6479 | { | |
6480 | /* This is the case of: | |
6481 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
6482 | As we have moved PT while replacing the original buffer | |
6483 | contents, we must recover it now. */ | |
6484 | set_buffer_internal (XBUFFER (src_object)); | |
6485 | if (saved_pt < from) | |
6486 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
6487 | else if (saved_pt < from + chars) | |
6488 | TEMP_SET_PT_BOTH (from, from_byte); | |
6489 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
6490 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
6491 | saved_pt_byte + (coding->produced - bytes)); | |
6492 | else | |
6493 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
6494 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 6495 | } |
4776e638 | 6496 | |
df7492f9 | 6497 | unbind_to (count, Qnil); |
d46c5b12 KH |
6498 | } |
6499 | ||
d46c5b12 | 6500 | |
df7492f9 KH |
6501 | void |
6502 | encode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6503 | dst_object) | |
d46c5b12 | 6504 | struct coding_system *coding; |
df7492f9 KH |
6505 | Lisp_Object src_object; |
6506 | EMACS_INT from, from_byte, to, to_byte; | |
6507 | Lisp_Object dst_object; | |
d46c5b12 | 6508 | { |
b73bfc1c | 6509 | int count = specpdl_ptr - specpdl; |
df7492f9 KH |
6510 | EMACS_INT chars = to - from; |
6511 | EMACS_INT bytes = to_byte - from_byte; | |
6512 | Lisp_Object attrs; | |
4776e638 KH |
6513 | Lisp_Object buffer; |
6514 | int saved_pt = -1, saved_pt_byte; | |
df7492f9 | 6515 | |
4776e638 | 6516 | buffer = Fcurrent_buffer (); |
df7492f9 KH |
6517 | |
6518 | coding->src_object = src_object; | |
6519 | coding->src_chars = chars; | |
6520 | coding->src_bytes = bytes; | |
6521 | coding->src_multibyte = chars < bytes; | |
6522 | ||
6523 | attrs = CODING_ID_ATTRS (coding->id); | |
6524 | ||
6525 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
6bac5b12 | 6526 | { |
4776e638 KH |
6527 | coding->src_object = code_conversion_save (buffer, 1, |
6528 | coding->src_multibyte); | |
df7492f9 KH |
6529 | set_buffer_internal (XBUFFER (coding->src_object)); |
6530 | if (STRINGP (src_object)) | |
6531 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
6532 | else if (BUFFERP (src_object)) | |
6533 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
6534 | else | |
6535 | insert_1_both (coding->source + from, chars, bytes, 0, 0, 0); | |
d46c5b12 | 6536 | |
df7492f9 KH |
6537 | if (EQ (src_object, dst_object)) |
6538 | { | |
6539 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 6540 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6541 | del_range_both (from, from_byte, to, to_byte, 1); |
6542 | set_buffer_internal (XBUFFER (coding->src_object)); | |
6543 | } | |
6544 | ||
ac87bbef KH |
6545 | call2 (CODING_ATTR_PRE_WRITE (attrs), |
6546 | make_number (BEG), make_number (Z)); | |
6547 | coding->src_object = Fcurrent_buffer (); | |
df7492f9 KH |
6548 | if (BEG != GPT) |
6549 | move_gap_both (BEG, BEG_BYTE); | |
6550 | coding->src_chars = Z - BEG; | |
6551 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
6552 | coding->src_pos = BEG; | |
6553 | coding->src_pos_byte = BEG_BYTE; | |
6554 | coding->src_multibyte = Z < Z_BYTE; | |
6555 | } | |
6556 | else if (STRINGP (src_object)) | |
d46c5b12 | 6557 | { |
4776e638 | 6558 | code_conversion_save (buffer, 0, 0); |
df7492f9 KH |
6559 | coding->src_pos = from; |
6560 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 6561 | } |
df7492f9 | 6562 | else if (BUFFERP (src_object)) |
b73bfc1c | 6563 | { |
4776e638 | 6564 | code_conversion_save (buffer, 0, 0); |
df7492f9 | 6565 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 6566 | if (EQ (src_object, dst_object)) |
d46c5b12 | 6567 | { |
4776e638 | 6568 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
6569 | coding->src_object = del_range_1 (from, to, 1, 1); |
6570 | coding->src_pos = 0; | |
6571 | coding->src_pos_byte = 0; | |
d46c5b12 | 6572 | } |
df7492f9 | 6573 | else |
d46c5b12 | 6574 | { |
ff0dacd7 KH |
6575 | if (from < GPT && to >= GPT) |
6576 | move_gap_both (from, from_byte); | |
df7492f9 KH |
6577 | coding->src_pos = from; |
6578 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6579 | } |
d46c5b12 | 6580 | } |
4776e638 KH |
6581 | else |
6582 | code_conversion_save (buffer, 0, 0); | |
d46c5b12 | 6583 | |
df7492f9 | 6584 | if (BUFFERP (dst_object)) |
88993dfd | 6585 | { |
df7492f9 | 6586 | coding->dst_object = dst_object; |
28f67a95 KH |
6587 | if (EQ (src_object, dst_object)) |
6588 | { | |
6589 | coding->dst_pos = from; | |
6590 | coding->dst_pos_byte = from_byte; | |
6591 | } | |
6592 | else | |
6593 | { | |
6594 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6595 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6596 | } | |
df7492f9 KH |
6597 | coding->dst_multibyte |
6598 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
88993dfd | 6599 | } |
df7492f9 | 6600 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 6601 | { |
df7492f9 | 6602 | coding->dst_object = Qnil; |
df7492f9 | 6603 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
6604 | if (coding->dst_bytes == 0) |
6605 | coding->dst_bytes = 1; | |
6606 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 6607 | coding->dst_multibyte = 0; |
d46c5b12 KH |
6608 | } |
6609 | else | |
6610 | { | |
df7492f9 KH |
6611 | coding->dst_object = Qnil; |
6612 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
6613 | } |
6614 | ||
df7492f9 | 6615 | encode_coding (coding); |
d46c5b12 | 6616 | |
df7492f9 | 6617 | if (EQ (dst_object, Qt)) |
d46c5b12 | 6618 | { |
df7492f9 KH |
6619 | if (BUFFERP (coding->dst_object)) |
6620 | coding->dst_object = Fbuffer_string (); | |
6621 | else | |
d46c5b12 | 6622 | { |
df7492f9 KH |
6623 | coding->dst_object |
6624 | = make_unibyte_string ((char *) coding->destination, | |
6625 | coding->produced); | |
6626 | xfree (coding->destination); | |
d46c5b12 | 6627 | } |
4ed46869 | 6628 | } |
d46c5b12 | 6629 | |
4776e638 KH |
6630 | if (saved_pt >= 0) |
6631 | { | |
6632 | /* This is the case of: | |
6633 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
6634 | As we have moved PT while replacing the original buffer | |
6635 | contents, we must recover it now. */ | |
6636 | set_buffer_internal (XBUFFER (src_object)); | |
6637 | if (saved_pt < from) | |
6638 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
6639 | else if (saved_pt < from + chars) | |
6640 | TEMP_SET_PT_BOTH (from, from_byte); | |
6641 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
6642 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
6643 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 6644 | else |
4776e638 KH |
6645 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
6646 | saved_pt_byte + (coding->produced - bytes)); | |
6647 | } | |
6648 | ||
df7492f9 | 6649 | unbind_to (count, Qnil); |
b73bfc1c KH |
6650 | } |
6651 | ||
df7492f9 | 6652 | |
b73bfc1c | 6653 | Lisp_Object |
df7492f9 | 6654 | preferred_coding_system () |
b73bfc1c | 6655 | { |
df7492f9 | 6656 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 6657 | |
df7492f9 | 6658 | return CODING_ID_NAME (id); |
4ed46869 KH |
6659 | } |
6660 | ||
6661 | \f | |
6662 | #ifdef emacs | |
1397dc18 | 6663 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 6664 | |
4ed46869 | 6665 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 6666 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 6667 | See the documentation of `define-coding-system' for information |
48b0f3ae PJ |
6668 | about coding-system objects. */) |
6669 | (obj) | |
4ed46869 KH |
6670 | Lisp_Object obj; |
6671 | { | |
df7492f9 | 6672 | return ((NILP (obj) || CODING_SYSTEM_P (obj)) ? Qt : Qnil); |
4ed46869 KH |
6673 | } |
6674 | ||
9d991de8 RS |
6675 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
6676 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae PJ |
6677 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
6678 | (prompt) | |
4ed46869 KH |
6679 | Lisp_Object prompt; |
6680 | { | |
e0e989f6 | 6681 | Lisp_Object val; |
9d991de8 RS |
6682 | do |
6683 | { | |
4608c386 KH |
6684 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
6685 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 6686 | } |
8f924df7 | 6687 | while (SCHARS (val) == 0); |
e0e989f6 | 6688 | return (Fintern (val, Qnil)); |
4ed46869 KH |
6689 | } |
6690 | ||
9b787f3e | 6691 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae PJ |
6692 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
6693 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. */) | |
6694 | (prompt, default_coding_system) | |
9b787f3e | 6695 | Lisp_Object prompt, default_coding_system; |
4ed46869 | 6696 | { |
f44d27ce | 6697 | Lisp_Object val; |
9b787f3e | 6698 | if (SYMBOLP (default_coding_system)) |
a3181084 | 6699 | XSETSTRING (default_coding_system, XPNTR (SYMBOL_NAME (default_coding_system))); |
4608c386 | 6700 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
6701 | Qt, Qnil, Qcoding_system_history, |
6702 | default_coding_system, Qnil); | |
8f924df7 | 6703 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
6704 | } |
6705 | ||
6706 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
6707 | 1, 1, 0, | |
48b0f3ae | 6708 | doc: /* Check validity of CODING-SYSTEM. |
b054002f | 6709 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. */) |
df7492f9 | 6710 | (coding_system) |
4ed46869 KH |
6711 | Lisp_Object coding_system; |
6712 | { | |
b7826503 | 6713 | CHECK_SYMBOL (coding_system); |
4ed46869 KH |
6714 | if (!NILP (Fcoding_system_p (coding_system))) |
6715 | return coding_system; | |
6716 | while (1) | |
02ba4723 | 6717 | Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil)); |
4ed46869 | 6718 | } |
df7492f9 | 6719 | |
3a73fa5d | 6720 | \f |
89528eb3 KH |
6721 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
6722 | HIGHEST is nonzero, return the coding system of the highest | |
6723 | priority among the detected coding systems. Otherwize return a | |
6724 | list of detected coding systems sorted by their priorities. If | |
6725 | MULTIBYTEP is nonzero, it is assumed that the bytes are in correct | |
6726 | multibyte form but contains only ASCII and eight-bit chars. | |
6727 | Otherwise, the bytes are raw bytes. | |
6728 | ||
6729 | CODING-SYSTEM controls the detection as below: | |
6730 | ||
6731 | If it is nil, detect both text-format and eol-format. If the | |
6732 | text-format part of CODING-SYSTEM is already specified | |
6733 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
6734 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
6735 | detect only text-format. */ | |
6736 | ||
d46c5b12 | 6737 | Lisp_Object |
df7492f9 | 6738 | detect_coding_system (src, src_bytes, highest, multibytep, coding_system) |
8f924df7 | 6739 | const unsigned char *src; |
d46c5b12 | 6740 | int src_bytes, highest; |
0a28aafb | 6741 | int multibytep; |
df7492f9 | 6742 | Lisp_Object coding_system; |
4ed46869 | 6743 | { |
8f924df7 | 6744 | const unsigned char *src_end = src + src_bytes; |
df7492f9 KH |
6745 | Lisp_Object attrs, eol_type; |
6746 | Lisp_Object val; | |
6747 | struct coding_system coding; | |
89528eb3 | 6748 | int id; |
ff0dacd7 | 6749 | struct coding_detection_info detect_info; |
b73bfc1c | 6750 | |
df7492f9 KH |
6751 | if (NILP (coding_system)) |
6752 | coding_system = Qundecided; | |
6753 | setup_coding_system (coding_system, &coding); | |
6754 | attrs = CODING_ID_ATTRS (coding.id); | |
6755 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 6756 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 6757 | |
df7492f9 KH |
6758 | coding.source = src; |
6759 | coding.src_bytes = src_bytes; | |
6760 | coding.src_multibyte = multibytep; | |
6761 | coding.consumed = 0; | |
89528eb3 | 6762 | coding.mode |= CODING_MODE_LAST_BLOCK; |
d46c5b12 | 6763 | |
ff0dacd7 | 6764 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 6765 | |
89528eb3 KH |
6766 | /* At first, detect text-format if necessary. */ |
6767 | if (XINT (CODING_ATTR_CATEGORY (attrs)) == coding_category_undecided) | |
4ed46869 | 6768 | { |
ff0dacd7 KH |
6769 | enum coding_category category; |
6770 | struct coding_system *this; | |
6771 | int c, i; | |
88993dfd | 6772 | |
df7492f9 | 6773 | for (; src < src_end; src++) |
4ed46869 | 6774 | { |
df7492f9 | 6775 | c = *src; |
89528eb3 KH |
6776 | if (c & 0x80 |
6777 | || (c < 0x20 && (c == ISO_CODE_ESC | |
6778 | || c == ISO_CODE_SI | |
584948ac | 6779 | || c == ISO_CODE_SO))) |
d46c5b12 | 6780 | break; |
4ed46869 | 6781 | } |
df7492f9 | 6782 | coding.head_ascii = src - coding.source; |
88993dfd | 6783 | |
df7492f9 KH |
6784 | if (src < src_end) |
6785 | for (i = 0; i < coding_category_raw_text; i++) | |
6786 | { | |
ff0dacd7 KH |
6787 | category = coding_priorities[i]; |
6788 | this = coding_categories + category; | |
b843d1ae | 6789 | |
df7492f9 KH |
6790 | if (this->id < 0) |
6791 | { | |
6792 | /* No coding system of this category is defined. */ | |
ff0dacd7 | 6793 | detect_info.rejected |= (1 << category); |
df7492f9 | 6794 | } |
ff0dacd7 | 6795 | else if (category >= coding_category_raw_text) |
89528eb3 | 6796 | continue; |
ff0dacd7 KH |
6797 | else if (detect_info.checked & (1 << category)) |
6798 | { | |
6799 | if (highest | |
6800 | && (detect_info.found & (1 << category))) | |
6801 | break; | |
6802 | } | |
df7492f9 KH |
6803 | else |
6804 | { | |
ff0dacd7 | 6805 | if ((*(this->detector)) (&coding, &detect_info) |
89528eb3 | 6806 | && highest |
ff0dacd7 KH |
6807 | && (detect_info.found & (1 << category))) |
6808 | break; | |
df7492f9 KH |
6809 | } |
6810 | } | |
ec6d2bb8 | 6811 | |
ec6d2bb8 | 6812 | |
ff0dacd7 | 6813 | if (detect_info.rejected == CATEGORY_MASK_ANY) |
ec6d2bb8 | 6814 | { |
ff0dacd7 | 6815 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
89528eb3 KH |
6816 | id = coding_categories[coding_category_raw_text].id; |
6817 | val = Fcons (make_number (id), Qnil); | |
6818 | } | |
ff0dacd7 | 6819 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 6820 | { |
ff0dacd7 | 6821 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
6822 | id = coding_categories[coding_category_undecided].id; |
6823 | val = Fcons (make_number (id), Qnil); | |
6824 | } | |
6825 | else if (highest) | |
6826 | { | |
ff0dacd7 | 6827 | if (detect_info.found) |
ec6d2bb8 | 6828 | { |
ff0dacd7 KH |
6829 | detect_info.found = 1 << category; |
6830 | val = Fcons (make_number (this->id), Qnil); | |
6831 | } | |
6832 | else | |
6833 | for (i = 0; i < coding_category_raw_text; i++) | |
6834 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
6835 | { | |
6836 | detect_info.found = 1 << coding_priorities[i]; | |
6837 | id = coding_categories[coding_priorities[i]].id; | |
6838 | val = Fcons (make_number (id), Qnil); | |
6839 | break; | |
6840 | } | |
6841 | } | |
89528eb3 KH |
6842 | else |
6843 | { | |
ff0dacd7 KH |
6844 | int mask = detect_info.rejected | detect_info.found; |
6845 | int found = 0; | |
89528eb3 | 6846 | val = Qnil; |
ec6d2bb8 | 6847 | |
89528eb3 | 6848 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
6849 | { |
6850 | category = coding_priorities[i]; | |
6851 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 6852 | { |
ff0dacd7 KH |
6853 | found |= 1 << category; |
6854 | id = coding_categories[category].id; | |
6855 | val = Fcons (make_number (id), val); | |
6856 | } | |
6857 | } | |
6858 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
6859 | { | |
6860 | category = coding_priorities[i]; | |
6861 | if (detect_info.found & (1 << category)) | |
6862 | { | |
6863 | id = coding_categories[category].id; | |
6864 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 6865 | } |
ec6d2bb8 | 6866 | } |
ff0dacd7 | 6867 | detect_info.found |= found; |
ec6d2bb8 | 6868 | } |
ec6d2bb8 | 6869 | } |
df7492f9 KH |
6870 | else |
6871 | { | |
ff0dacd7 | 6872 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 6873 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 6874 | } |
df7492f9 | 6875 | |
89528eb3 | 6876 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 6877 | { |
89528eb3 | 6878 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol; |
df7492f9 KH |
6879 | Lisp_Object tail; |
6880 | ||
89528eb3 KH |
6881 | if (VECTORP (eol_type)) |
6882 | { | |
ff0dacd7 | 6883 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
89528eb3 KH |
6884 | normal_eol = detect_eol (coding.source, src_bytes, |
6885 | coding_category_raw_text); | |
ff0dacd7 KH |
6886 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
6887 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
6888 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
6889 | coding_category_utf_16_be); | |
ff0dacd7 KH |
6890 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
6891 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
6892 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
6893 | coding_category_utf_16_le); | |
6894 | } | |
6895 | else | |
6896 | { | |
6897 | if (EQ (eol_type, Qunix)) | |
6898 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
6899 | else if (EQ (eol_type, Qdos)) | |
6900 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
6901 | else | |
6902 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
6903 | } | |
6904 | ||
df7492f9 KH |
6905 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
6906 | { | |
89528eb3 | 6907 | enum coding_category category; |
df7492f9 | 6908 | int this_eol; |
89528eb3 KH |
6909 | |
6910 | id = XINT (XCAR (tail)); | |
6911 | attrs = CODING_ID_ATTRS (id); | |
6912 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
6913 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
6914 | if (VECTORP (eol_type)) |
6915 | { | |
89528eb3 KH |
6916 | if (category == coding_category_utf_16_be |
6917 | || category == coding_category_utf_16_be_nosig) | |
6918 | this_eol = utf_16_be_eol; | |
6919 | else if (category == coding_category_utf_16_le | |
6920 | || category == coding_category_utf_16_le_nosig) | |
6921 | this_eol = utf_16_le_eol; | |
df7492f9 | 6922 | else |
89528eb3 KH |
6923 | this_eol = normal_eol; |
6924 | ||
df7492f9 KH |
6925 | if (this_eol == EOL_SEEN_LF) |
6926 | XSETCAR (tail, AREF (eol_type, 0)); | |
6927 | else if (this_eol == EOL_SEEN_CRLF) | |
6928 | XSETCAR (tail, AREF (eol_type, 1)); | |
6929 | else if (this_eol == EOL_SEEN_CR) | |
6930 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
6931 | else |
6932 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 6933 | } |
89528eb3 KH |
6934 | else |
6935 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
6936 | } |
6937 | } | |
ec6d2bb8 | 6938 | |
03699b14 | 6939 | return (highest ? XCAR (val) : val); |
ec6d2bb8 KH |
6940 | } |
6941 | ||
ec6d2bb8 | 6942 | |
d46c5b12 KH |
6943 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
6944 | 2, 3, 0, | |
48b0f3ae PJ |
6945 | doc: /* Detect coding system of the text in the region between START and END. |
6946 | Return a list of possible coding systems ordered by priority. | |
ec6d2bb8 | 6947 | |
48b0f3ae PJ |
6948 | If only ASCII characters are found, it returns a list of single element |
6949 | `undecided' or its subsidiary coding system according to a detected | |
6950 | end-of-line format. | |
ec6d2bb8 | 6951 | |
48b0f3ae PJ |
6952 | If optional argument HIGHEST is non-nil, return the coding system of |
6953 | highest priority. */) | |
6954 | (start, end, highest) | |
d46c5b12 KH |
6955 | Lisp_Object start, end, highest; |
6956 | { | |
6957 | int from, to; | |
6958 | int from_byte, to_byte; | |
ec6d2bb8 | 6959 | |
b7826503 PJ |
6960 | CHECK_NUMBER_COERCE_MARKER (start); |
6961 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 6962 | |
d46c5b12 KH |
6963 | validate_region (&start, &end); |
6964 | from = XINT (start), to = XINT (end); | |
6965 | from_byte = CHAR_TO_BYTE (from); | |
6966 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 6967 | |
d46c5b12 KH |
6968 | if (from < GPT && to >= GPT) |
6969 | move_gap_both (to, to_byte); | |
c210f766 | 6970 | |
d46c5b12 | 6971 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
df7492f9 | 6972 | to_byte - from_byte, |
0a28aafb KH |
6973 | !NILP (highest), |
6974 | !NILP (current_buffer | |
df7492f9 KH |
6975 | ->enable_multibyte_characters), |
6976 | Qnil); | |
ec6d2bb8 KH |
6977 | } |
6978 | ||
d46c5b12 KH |
6979 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
6980 | 1, 2, 0, | |
48b0f3ae PJ |
6981 | doc: /* Detect coding system of the text in STRING. |
6982 | Return a list of possible coding systems ordered by priority. | |
fb88bf2d | 6983 | |
48b0f3ae PJ |
6984 | If only ASCII characters are found, it returns a list of single element |
6985 | `undecided' or its subsidiary coding system according to a detected | |
6986 | end-of-line format. | |
d46c5b12 | 6987 | |
48b0f3ae PJ |
6988 | If optional argument HIGHEST is non-nil, return the coding system of |
6989 | highest priority. */) | |
6990 | (string, highest) | |
d46c5b12 KH |
6991 | Lisp_Object string, highest; |
6992 | { | |
b7826503 | 6993 | CHECK_STRING (string); |
b73bfc1c | 6994 | |
8f924df7 KH |
6995 | return detect_coding_system (SDATA (string), SBYTES (string), |
6996 | !NILP (highest), STRING_MULTIBYTE (string), | |
df7492f9 | 6997 | Qnil); |
4ed46869 | 6998 | } |
4ed46869 | 6999 | |
b73bfc1c | 7000 | |
df7492f9 KH |
7001 | static INLINE int |
7002 | char_encodable_p (c, attrs) | |
7003 | int c; | |
7004 | Lisp_Object attrs; | |
05e6f5dc | 7005 | { |
df7492f9 | 7006 | Lisp_Object tail; |
df7492f9 | 7007 | struct charset *charset; |
d46c5b12 | 7008 | |
df7492f9 KH |
7009 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
7010 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 7011 | { |
df7492f9 KH |
7012 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
7013 | if (CHAR_CHARSET_P (c, charset)) | |
7014 | break; | |
e133c8fa | 7015 | } |
df7492f9 | 7016 | return (! NILP (tail)); |
05e6f5dc | 7017 | } |
83fa074f | 7018 | |
fb88bf2d | 7019 | |
df7492f9 KH |
7020 | /* Return a list of coding systems that safely encode the text between |
7021 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
7022 | systems not to check. The returned list doesn't contain any such | |
48468dac | 7023 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 7024 | unibyte, return t. */ |
e077cc80 | 7025 | |
df7492f9 KH |
7026 | DEFUN ("find-coding-systems-region-internal", |
7027 | Ffind_coding_systems_region_internal, | |
7028 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
7029 | doc: /* Internal use only. */) | |
7030 | (start, end, exclude) | |
7031 | Lisp_Object start, end, exclude; | |
7032 | { | |
7033 | Lisp_Object coding_attrs_list, safe_codings; | |
7034 | EMACS_INT start_byte, end_byte; | |
7c78e542 | 7035 | const unsigned char *p, *pbeg, *pend; |
df7492f9 KH |
7036 | int c; |
7037 | Lisp_Object tail, elt; | |
d46c5b12 | 7038 | |
df7492f9 KH |
7039 | if (STRINGP (start)) |
7040 | { | |
7041 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 7042 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
7043 | return Qt; |
7044 | start_byte = 0; | |
8f924df7 | 7045 | end_byte = SBYTES (start); |
df7492f9 KH |
7046 | } |
7047 | else | |
d46c5b12 | 7048 | { |
df7492f9 KH |
7049 | CHECK_NUMBER_COERCE_MARKER (start); |
7050 | CHECK_NUMBER_COERCE_MARKER (end); | |
7051 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
7052 | args_out_of_range (start, end); | |
7053 | if (NILP (current_buffer->enable_multibyte_characters)) | |
7054 | return Qt; | |
7055 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7056 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7057 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
7058 | return Qt; | |
d46c5b12 | 7059 | |
e1c23804 | 7060 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 7061 | { |
e1c23804 DL |
7062 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7063 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7064 | else |
e1c23804 | 7065 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
7066 | } |
7067 | } | |
7068 | ||
df7492f9 KH |
7069 | coding_attrs_list = Qnil; |
7070 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
7071 | if (NILP (exclude) | |
7072 | || NILP (Fmemq (XCAR (tail), exclude))) | |
7073 | { | |
7074 | Lisp_Object attrs; | |
d46c5b12 | 7075 | |
df7492f9 KH |
7076 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
7077 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
7078 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7079 | coding_attrs_list = Fcons (attrs, coding_attrs_list); | |
7080 | } | |
d46c5b12 | 7081 | |
df7492f9 | 7082 | if (STRINGP (start)) |
8f924df7 | 7083 | p = pbeg = SDATA (start); |
df7492f9 KH |
7084 | else |
7085 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
7086 | pend = p + (end_byte - start_byte); | |
b843d1ae | 7087 | |
df7492f9 KH |
7088 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
7089 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 7090 | |
05e6f5dc | 7091 | while (p < pend) |
72d1a715 | 7092 | { |
df7492f9 KH |
7093 | if (ASCII_BYTE_P (*p)) |
7094 | p++; | |
72d1a715 RS |
7095 | else |
7096 | { | |
df7492f9 | 7097 | c = STRING_CHAR_ADVANCE (p); |
12410ef1 | 7098 | |
df7492f9 KH |
7099 | charset_map_loaded = 0; |
7100 | for (tail = coding_attrs_list; CONSP (tail);) | |
7101 | { | |
7102 | elt = XCAR (tail); | |
7103 | if (NILP (elt)) | |
7104 | tail = XCDR (tail); | |
7105 | else if (char_encodable_p (c, elt)) | |
7106 | tail = XCDR (tail); | |
7107 | else if (CONSP (XCDR (tail))) | |
7108 | { | |
7109 | XSETCAR (tail, XCAR (XCDR (tail))); | |
7110 | XSETCDR (tail, XCDR (XCDR (tail))); | |
7111 | } | |
7112 | else | |
7113 | { | |
7114 | XSETCAR (tail, Qnil); | |
7115 | tail = XCDR (tail); | |
7116 | } | |
7117 | } | |
7118 | if (charset_map_loaded) | |
7119 | { | |
7120 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 7121 | |
df7492f9 | 7122 | if (STRINGP (start)) |
8f924df7 | 7123 | pbeg = SDATA (start); |
df7492f9 KH |
7124 | else |
7125 | pbeg = BYTE_POS_ADDR (start_byte); | |
7126 | p = pbeg + p_offset; | |
7127 | pend = pbeg + pend_offset; | |
7128 | } | |
7129 | } | |
ec6d2bb8 | 7130 | } |
fb88bf2d | 7131 | |
df7492f9 KH |
7132 | safe_codings = Qnil; |
7133 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) | |
7134 | if (! NILP (XCAR (tail))) | |
7135 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 7136 | |
05e6f5dc KH |
7137 | return safe_codings; |
7138 | } | |
4956c225 | 7139 | |
d46c5b12 | 7140 | |
8f924df7 KH |
7141 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
7142 | Sunencodable_char_position, 3, 5, 0, | |
7143 | doc: /* | |
7144 | Return position of first un-encodable character in a region. | |
7145 | START and END specfiy the region and CODING-SYSTEM specifies the | |
7146 | encoding to check. Return nil if CODING-SYSTEM does encode the region. | |
d46c5b12 | 7147 | |
8f924df7 KH |
7148 | If optional 4th argument COUNT is non-nil, it specifies at most how |
7149 | many un-encodable characters to search. In this case, the value is a | |
7150 | list of positions. | |
d46c5b12 | 7151 | |
8f924df7 KH |
7152 | If optional 5th argument STRING is non-nil, it is a string to search |
7153 | for un-encodable characters. In that case, START and END are indexes | |
7154 | to the string. */) | |
7155 | (start, end, coding_system, count, string) | |
7156 | Lisp_Object start, end, coding_system, count, string; | |
7157 | { | |
7158 | int n; | |
7159 | struct coding_system coding; | |
7160 | Lisp_Object attrs, charset_list; | |
7161 | Lisp_Object positions; | |
7162 | int from, to; | |
7163 | const unsigned char *p, *stop, *pend; | |
7164 | int ascii_compatible; | |
fb88bf2d | 7165 | |
8f924df7 KH |
7166 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
7167 | attrs = CODING_ID_ATTRS (coding.id); | |
7168 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
7169 | return Qnil; | |
7170 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
7171 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
fb88bf2d | 7172 | |
8f924df7 KH |
7173 | if (NILP (string)) |
7174 | { | |
7175 | validate_region (&start, &end); | |
7176 | from = XINT (start); | |
7177 | to = XINT (end); | |
7178 | if (NILP (current_buffer->enable_multibyte_characters) | |
7179 | || (ascii_compatible | |
7180 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
7181 | return Qnil; | |
7182 | p = CHAR_POS_ADDR (from); | |
7183 | pend = CHAR_POS_ADDR (to); | |
7184 | if (from < GPT && to >= GPT) | |
7185 | stop = GPT_ADDR; | |
7186 | else | |
7187 | stop = pend; | |
7188 | } | |
7189 | else | |
7190 | { | |
7191 | CHECK_STRING (string); | |
7192 | CHECK_NATNUM (start); | |
7193 | CHECK_NATNUM (end); | |
7194 | from = XINT (start); | |
7195 | to = XINT (end); | |
7196 | if (from > to | |
7197 | || to > SCHARS (string)) | |
7198 | args_out_of_range_3 (string, start, end); | |
7199 | if (! STRING_MULTIBYTE (string)) | |
7200 | return Qnil; | |
7201 | p = SDATA (string) + string_char_to_byte (string, from); | |
7202 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
7203 | if (ascii_compatible && (to - from) == (pend - p)) | |
7204 | return Qnil; | |
7205 | } | |
f2558efd | 7206 | |
8f924df7 KH |
7207 | if (NILP (count)) |
7208 | n = 1; | |
7209 | else | |
b73bfc1c | 7210 | { |
8f924df7 KH |
7211 | CHECK_NATNUM (count); |
7212 | n = XINT (count); | |
b73bfc1c KH |
7213 | } |
7214 | ||
8f924df7 KH |
7215 | positions = Qnil; |
7216 | while (1) | |
d46c5b12 | 7217 | { |
8f924df7 | 7218 | int c; |
ec6d2bb8 | 7219 | |
8f924df7 KH |
7220 | if (ascii_compatible) |
7221 | while (p < stop && ASCII_BYTE_P (*p)) | |
7222 | p++, from++; | |
7223 | if (p >= stop) | |
0e79d667 | 7224 | { |
8f924df7 KH |
7225 | if (p >= pend) |
7226 | break; | |
7227 | stop = pend; | |
7228 | p = GAP_END_ADDR; | |
0e79d667 | 7229 | } |
ec6d2bb8 | 7230 | |
8f924df7 KH |
7231 | c = STRING_CHAR_ADVANCE (p); |
7232 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7233 | && ! char_charset (c, charset_list, NULL)) | |
ec6d2bb8 | 7234 | { |
8f924df7 KH |
7235 | positions = Fcons (make_number (from), positions); |
7236 | n--; | |
7237 | if (n == 0) | |
7238 | break; | |
ec6d2bb8 KH |
7239 | } |
7240 | ||
8f924df7 KH |
7241 | from++; |
7242 | } | |
d46c5b12 | 7243 | |
8f924df7 KH |
7244 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
7245 | } | |
d46c5b12 | 7246 | |
d46c5b12 | 7247 | |
df7492f9 KH |
7248 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
7249 | Scheck_coding_systems_region, 3, 3, 0, | |
7250 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 7251 | |
df7492f9 KH |
7252 | START and END are buffer positions specifying the region. |
7253 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 7254 | |
df7492f9 KH |
7255 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
7256 | CODING-SYSTEM is a member of CODING-SYSTEM-LIst and can't encode the | |
7257 | whole region, POS0, POS1, ... are buffer positions where non-encodable | |
7258 | characters are found. | |
93dec019 | 7259 | |
df7492f9 KH |
7260 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
7261 | value is nil. | |
93dec019 | 7262 | |
df7492f9 KH |
7263 | START may be a string. In that case, check if the string is |
7264 | encodable, and the value contains indices to the string instead of | |
7265 | buffer positions. END is ignored. */) | |
7266 | (start, end, coding_system_list) | |
7267 | Lisp_Object start, end, coding_system_list; | |
05e6f5dc | 7268 | { |
df7492f9 KH |
7269 | Lisp_Object list; |
7270 | EMACS_INT start_byte, end_byte; | |
7271 | int pos; | |
7c78e542 | 7272 | const unsigned char *p, *pbeg, *pend; |
df7492f9 KH |
7273 | int c; |
7274 | Lisp_Object tail, elt; | |
70ad9fc4 | 7275 | |
05e6f5dc KH |
7276 | if (STRINGP (start)) |
7277 | { | |
df7492f9 | 7278 | if (!STRING_MULTIBYTE (start) |
8f924df7 | 7279 | && SCHARS (start) != SBYTES (start)) |
df7492f9 KH |
7280 | return Qnil; |
7281 | start_byte = 0; | |
8f924df7 | 7282 | end_byte = SBYTES (start); |
df7492f9 | 7283 | pos = 0; |
d46c5b12 | 7284 | } |
05e6f5dc | 7285 | else |
b73bfc1c | 7286 | { |
b7826503 PJ |
7287 | CHECK_NUMBER_COERCE_MARKER (start); |
7288 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
7289 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
7290 | args_out_of_range (start, end); | |
7291 | if (NILP (current_buffer->enable_multibyte_characters)) | |
df7492f9 KH |
7292 | return Qnil; |
7293 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7294 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7295 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
05e6f5dc | 7296 | return Qt; |
df7492f9 | 7297 | |
e1c23804 | 7298 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 7299 | { |
e1c23804 DL |
7300 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7301 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7302 | else |
e1c23804 | 7303 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 7304 | } |
e1c23804 | 7305 | pos = XINT (start); |
b73bfc1c | 7306 | } |
7553d0e1 | 7307 | |
df7492f9 KH |
7308 | list = Qnil; |
7309 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 7310 | { |
df7492f9 KH |
7311 | elt = XCAR (tail); |
7312 | list = Fcons (Fcons (elt, Fcons (AREF (CODING_SYSTEM_SPEC (elt), 0), | |
7313 | Qnil)), | |
7314 | list); | |
12410ef1 KH |
7315 | } |
7316 | ||
df7492f9 | 7317 | if (STRINGP (start)) |
8f924df7 | 7318 | p = pbeg = SDATA (start); |
72d1a715 | 7319 | else |
df7492f9 KH |
7320 | p = pbeg = BYTE_POS_ADDR (start_byte); |
7321 | pend = p + (end_byte - start_byte); | |
4ed46869 | 7322 | |
df7492f9 KH |
7323 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
7324 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 7325 | |
df7492f9 | 7326 | while (p < pend) |
d46c5b12 | 7327 | { |
df7492f9 KH |
7328 | if (ASCII_BYTE_P (*p)) |
7329 | p++; | |
e133c8fa | 7330 | else |
05e6f5dc | 7331 | { |
df7492f9 KH |
7332 | c = STRING_CHAR_ADVANCE (p); |
7333 | ||
7334 | charset_map_loaded = 0; | |
7335 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
7336 | { | |
7337 | elt = XCDR (XCAR (tail)); | |
7338 | if (! char_encodable_p (c, XCAR (elt))) | |
7339 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
7340 | } | |
7341 | if (charset_map_loaded) | |
7342 | { | |
7343 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
7344 | ||
7345 | if (STRINGP (start)) | |
8f924df7 | 7346 | pbeg = SDATA (start); |
df7492f9 KH |
7347 | else |
7348 | pbeg = BYTE_POS_ADDR (start_byte); | |
7349 | p = pbeg + p_offset; | |
7350 | pend = pbeg + pend_offset; | |
7351 | } | |
05e6f5dc | 7352 | } |
df7492f9 | 7353 | pos++; |
d46c5b12 | 7354 | } |
4ed46869 | 7355 | |
df7492f9 KH |
7356 | tail = list; |
7357 | list = Qnil; | |
7358 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 7359 | { |
df7492f9 KH |
7360 | elt = XCAR (tail); |
7361 | if (CONSP (XCDR (XCDR (elt)))) | |
7362 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
7363 | list); | |
ec6d2bb8 | 7364 | } |
2b4f9037 | 7365 | |
df7492f9 | 7366 | return list; |
d46c5b12 KH |
7367 | } |
7368 | ||
3fd9494b | 7369 | |
b73bfc1c KH |
7370 | |
7371 | Lisp_Object | |
df7492f9 KH |
7372 | code_convert_region (start, end, coding_system, dst_object, encodep, norecord) |
7373 | Lisp_Object start, end, coding_system, dst_object; | |
7374 | int encodep, norecord; | |
4ed46869 | 7375 | { |
3a73fa5d | 7376 | struct coding_system coding; |
df7492f9 KH |
7377 | EMACS_INT from, from_byte, to, to_byte; |
7378 | Lisp_Object src_object; | |
4ed46869 | 7379 | |
b7826503 PJ |
7380 | CHECK_NUMBER_COERCE_MARKER (start); |
7381 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
7382 | if (NILP (coding_system)) |
7383 | coding_system = Qno_conversion; | |
7384 | else | |
7385 | CHECK_CODING_SYSTEM (coding_system); | |
7386 | src_object = Fcurrent_buffer (); | |
7387 | if (NILP (dst_object)) | |
7388 | dst_object = src_object; | |
7389 | else if (! EQ (dst_object, Qt)) | |
7390 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 7391 | |
d46c5b12 KH |
7392 | validate_region (&start, &end); |
7393 | from = XFASTINT (start); | |
df7492f9 | 7394 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 7395 | to = XFASTINT (end); |
df7492f9 | 7396 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 7397 | |
df7492f9 KH |
7398 | setup_coding_system (coding_system, &coding); |
7399 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 7400 | |
df7492f9 KH |
7401 | if (encodep) |
7402 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7403 | dst_object); | |
7404 | else | |
7405 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7406 | dst_object); | |
7407 | if (! norecord) | |
7408 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 7409 | |
df7492f9 KH |
7410 | if (coding.result != CODING_RESULT_SUCCESS) |
7411 | error ("Code conversion error: %d", coding.result); | |
b73bfc1c | 7412 | |
df7492f9 KH |
7413 | return (BUFFERP (dst_object) |
7414 | ? make_number (coding.produced_char) | |
7415 | : coding.dst_object); | |
4031e2bf | 7416 | } |
78108bcd | 7417 | |
4ed46869 | 7418 | |
4031e2bf | 7419 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 7420 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 7421 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
7422 | When called from a program, takes four arguments: |
7423 | START, END, CODING-SYSTEM, and DESTINATION. | |
7424 | START and END are buffer positions. | |
8844fa83 | 7425 | |
df7492f9 KH |
7426 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
7427 | If nil, the region between START and END is replace by the decoded text. | |
7428 | If buffer, the decoded text is inserted in the buffer. | |
7429 | If t, the decoded text is returned. | |
8844fa83 | 7430 | |
48b0f3ae PJ |
7431 | This function sets `last-coding-system-used' to the precise coding system |
7432 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7433 | not fully specified.) | |
7434 | It returns the length of the decoded text. */) | |
df7492f9 KH |
7435 | (start, end, coding_system, destination) |
7436 | Lisp_Object start, end, coding_system, destination; | |
4031e2bf | 7437 | { |
df7492f9 | 7438 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 7439 | } |
8844fa83 | 7440 | |
3a73fa5d | 7441 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
7442 | 3, 4, "r\nzCoding system: ", |
7443 | doc: /* Encode the current region by specified coding system. | |
48b0f3ae PJ |
7444 | When called from a program, takes three arguments: |
7445 | START, END, and CODING-SYSTEM. START and END are buffer positions. | |
d46c5b12 | 7446 | |
df7492f9 KH |
7447 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
7448 | If nil, the region between START and END is replace by the encoded text. | |
7449 | If buffer, the encoded text is inserted in the buffer. | |
7450 | If t, the encoded text is returned. | |
2391eaa4 | 7451 | |
48b0f3ae PJ |
7452 | This function sets `last-coding-system-used' to the precise coding system |
7453 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7454 | not fully specified.) | |
7455 | It returns the length of the encoded text. */) | |
df7492f9 KH |
7456 | (start, end, coding_system, destination) |
7457 | Lisp_Object start, end, coding_system, destination; | |
3a73fa5d | 7458 | { |
df7492f9 | 7459 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
7460 | } |
7461 | ||
7462 | Lisp_Object | |
df7492f9 KH |
7463 | code_convert_string (string, coding_system, dst_object, |
7464 | encodep, nocopy, norecord) | |
7465 | Lisp_Object string, coding_system, dst_object; | |
7466 | int encodep, nocopy, norecord; | |
b73bfc1c | 7467 | { |
4031e2bf | 7468 | struct coding_system coding; |
df7492f9 | 7469 | EMACS_INT chars, bytes; |
ec6d2bb8 | 7470 | |
b7826503 | 7471 | CHECK_STRING (string); |
d46c5b12 | 7472 | if (NILP (coding_system)) |
4956c225 | 7473 | { |
df7492f9 KH |
7474 | if (! norecord) |
7475 | Vlast_coding_system_used = Qno_conversion; | |
7476 | if (NILP (dst_object)) | |
7477 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 7478 | } |
b73bfc1c | 7479 | |
df7492f9 KH |
7480 | if (NILP (coding_system)) |
7481 | coding_system = Qno_conversion; | |
7482 | else | |
7483 | CHECK_CODING_SYSTEM (coding_system); | |
7484 | if (NILP (dst_object)) | |
7485 | dst_object = Qt; | |
7486 | else if (! EQ (dst_object, Qt)) | |
7487 | CHECK_BUFFER (dst_object); | |
73be902c | 7488 | |
df7492f9 | 7489 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 7490 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
7491 | chars = SCHARS (string); |
7492 | bytes = SBYTES (string); | |
df7492f9 KH |
7493 | if (encodep) |
7494 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7495 | else | |
7496 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7497 | if (! norecord) | |
7498 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 7499 | |
df7492f9 KH |
7500 | if (coding.result != CODING_RESULT_SUCCESS) |
7501 | error ("Code conversion error: %d", coding.result); | |
2391eaa4 | 7502 | |
df7492f9 KH |
7503 | return (BUFFERP (dst_object) |
7504 | ? make_number (coding.produced_char) | |
7505 | : coding.dst_object); | |
4ed46869 | 7506 | } |
73be902c | 7507 | |
b73bfc1c | 7508 | |
ecec61c1 | 7509 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 7510 | Do not set Vlast_coding_system_used. |
4ed46869 | 7511 | |
ec6d2bb8 KH |
7512 | This function is called only from macros DECODE_FILE and |
7513 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 7514 | |
ecec61c1 KH |
7515 | Lisp_Object |
7516 | code_convert_string_norecord (string, coding_system, encodep) | |
7517 | Lisp_Object string, coding_system; | |
7518 | int encodep; | |
4ed46869 | 7519 | { |
0be8721c | 7520 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
7521 | } |
7522 | ||
4ed46869 | 7523 | |
df7492f9 KH |
7524 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
7525 | 2, 4, 0, | |
7526 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
7527 | ||
7528 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
7529 | if the decoding operation is trivial. | |
ecec61c1 | 7530 | |
df7492f9 | 7531 | Optional fourth arg BUFFER non-nil meant that the decoded text is |
a3f6ee6d | 7532 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 | 7533 | the return value is BUFFER. |
ecec61c1 | 7534 | |
df7492f9 KH |
7535 | This function sets `last-coding-system-used' to the precise coding system |
7536 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7537 | not fully specified. */) | |
7538 | (string, coding_system, nocopy, buffer) | |
7539 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 7540 | { |
df7492f9 KH |
7541 | return code_convert_string (string, coding_system, buffer, |
7542 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
7543 | } |
7544 | ||
df7492f9 KH |
7545 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
7546 | 2, 4, 0, | |
7547 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
7548 | ||
7549 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
7550 | itself if the encoding operation is trivial. | |
7551 | ||
7552 | Optional fourth arg BUFFER non-nil meant that the encoded text is | |
a3f6ee6d | 7553 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 KH |
7554 | the return value is BUFFER. |
7555 | ||
7556 | This function sets `last-coding-system-used' to the precise coding system | |
7557 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7558 | not fully specified.) */) | |
7559 | (string, coding_system, nocopy, buffer) | |
7560 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 7561 | { |
df7492f9 | 7562 | return code_convert_string (string, coding_system, buffer, |
c197f191 | 7563 | 1, ! NILP (nocopy), 1); |
4ed46869 | 7564 | } |
df7492f9 | 7565 | |
3a73fa5d | 7566 | \f |
4ed46869 | 7567 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
7568 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
7569 | Return the corresponding character. */) | |
7570 | (code) | |
4ed46869 | 7571 | Lisp_Object code; |
4ed46869 | 7572 | { |
df7492f9 KH |
7573 | Lisp_Object spec, attrs, val; |
7574 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
7575 | int c; | |
4ed46869 | 7576 | |
df7492f9 KH |
7577 | CHECK_NATNUM (code); |
7578 | c = XFASTINT (code); | |
7579 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
7580 | attrs = AREF (spec, 0); | |
4ed46869 | 7581 | |
df7492f9 KH |
7582 | if (ASCII_BYTE_P (c) |
7583 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7584 | return code; | |
4ed46869 | 7585 | |
df7492f9 KH |
7586 | val = CODING_ATTR_CHARSET_LIST (attrs); |
7587 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
7588 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
7589 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 7590 | |
df7492f9 KH |
7591 | if (c <= 0x7F) |
7592 | charset = charset_roman; | |
7593 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 7594 | { |
df7492f9 KH |
7595 | charset = charset_kana; |
7596 | c -= 0x80; | |
4ed46869 | 7597 | } |
55ab7be3 | 7598 | else |
4ed46869 | 7599 | { |
004068e4 | 7600 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
7601 | |
7602 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
7603 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
7604 | error ("Invalid code: %d", code); | |
7605 | SJIS_TO_JIS (c); | |
7606 | charset = charset_kanji; | |
4ed46869 | 7607 | } |
df7492f9 KH |
7608 | c = DECODE_CHAR (charset, c); |
7609 | if (c < 0) | |
7610 | error ("Invalid code: %d", code); | |
7611 | return make_number (c); | |
93dec019 | 7612 | } |
4ed46869 | 7613 | |
48b0f3ae | 7614 | |
4ed46869 | 7615 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
7616 | doc: /* Encode a Japanese character CHAR to shift_jis encoding. |
7617 | Return the corresponding code in SJIS. */) | |
7618 | (ch) | |
df7492f9 | 7619 | Lisp_Object ch; |
4ed46869 | 7620 | { |
df7492f9 KH |
7621 | Lisp_Object spec, attrs, charset_list; |
7622 | int c; | |
7623 | struct charset *charset; | |
7624 | unsigned code; | |
48b0f3ae | 7625 | |
df7492f9 KH |
7626 | CHECK_CHARACTER (ch); |
7627 | c = XFASTINT (ch); | |
7628 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
7629 | attrs = AREF (spec, 0); | |
7630 | ||
7631 | if (ASCII_CHAR_P (c) | |
7632 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7633 | return ch; | |
7634 | ||
7635 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
7636 | charset = char_charset (c, charset_list, &code); | |
7637 | if (code == CHARSET_INVALID_CODE (charset)) | |
7638 | error ("Can't encode by shift_jis encoding: %d", c); | |
7639 | JIS_TO_SJIS (code); | |
7640 | ||
7641 | return make_number (code); | |
4ed46869 KH |
7642 | } |
7643 | ||
7644 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
7645 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
7646 | Return the corresponding character. */) | |
7647 | (code) | |
4ed46869 | 7648 | Lisp_Object code; |
d46c5b12 | 7649 | { |
df7492f9 KH |
7650 | Lisp_Object spec, attrs, val; |
7651 | struct charset *charset_roman, *charset_big5, *charset; | |
7652 | int c; | |
6289dd10 | 7653 | |
df7492f9 KH |
7654 | CHECK_NATNUM (code); |
7655 | c = XFASTINT (code); | |
7656 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
7657 | attrs = AREF (spec, 0); | |
4ed46869 | 7658 | |
df7492f9 KH |
7659 | if (ASCII_BYTE_P (c) |
7660 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7661 | return code; | |
6289dd10 | 7662 | |
df7492f9 KH |
7663 | val = CODING_ATTR_CHARSET_LIST (attrs); |
7664 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
7665 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 7666 | |
df7492f9 KH |
7667 | if (c <= 0x7F) |
7668 | charset = charset_roman; | |
c28a9453 KH |
7669 | else |
7670 | { | |
df7492f9 KH |
7671 | int b1 = c >> 8, b2 = c & 0x7F; |
7672 | if (b1 < 0xA1 || b1 > 0xFE | |
7673 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
7674 | error ("Invalid code: %d", code); | |
7675 | charset = charset_big5; | |
c28a9453 | 7676 | } |
df7492f9 KH |
7677 | c = DECODE_CHAR (charset, (unsigned )c); |
7678 | if (c < 0) | |
7679 | error ("Invalid code: %d", code); | |
7680 | return make_number (c); | |
d46c5b12 | 7681 | } |
6289dd10 | 7682 | |
4ed46869 | 7683 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
48b0f3ae PJ |
7684 | doc: /* Encode the Big5 character CHAR to BIG5 coding system. |
7685 | Return the corresponding character code in Big5. */) | |
7686 | (ch) | |
4ed46869 KH |
7687 | Lisp_Object ch; |
7688 | { | |
df7492f9 KH |
7689 | Lisp_Object spec, attrs, charset_list; |
7690 | struct charset *charset; | |
7691 | int c; | |
7692 | unsigned code; | |
7693 | ||
7694 | CHECK_CHARACTER (ch); | |
7695 | c = XFASTINT (ch); | |
7696 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
7697 | attrs = AREF (spec, 0); | |
7698 | if (ASCII_CHAR_P (c) | |
7699 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7700 | return ch; | |
7701 | ||
7702 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
7703 | charset = char_charset (c, charset_list, &code); | |
7704 | if (code == CHARSET_INVALID_CODE (charset)) | |
7705 | error ("Can't encode by Big5 encoding: %d", c); | |
7706 | ||
7707 | return make_number (code); | |
4ed46869 | 7708 | } |
48b0f3ae | 7709 | |
3a73fa5d | 7710 | \f |
1ba9e4ab KH |
7711 | DEFUN ("set-terminal-coding-system-internal", |
7712 | Fset_terminal_coding_system_internal, | |
48b0f3ae PJ |
7713 | Sset_terminal_coding_system_internal, 1, 1, 0, |
7714 | doc: /* Internal use only. */) | |
7715 | (coding_system) | |
b74e4686 | 7716 | Lisp_Object coding_system; |
4ed46869 | 7717 | { |
b7826503 | 7718 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
7719 | setup_coding_system (Fcheck_coding_system (coding_system), |
7720 | &terminal_coding); | |
48b0f3ae | 7721 | |
70c22245 | 7722 | /* We had better not send unsafe characters to terminal. */ |
df7492f9 KH |
7723 | terminal_coding.mode |= CODING_MODE_SAFE_ENCODING; |
7724 | /* Characer composition should be disabled. */ | |
7725 | terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
7726 | terminal_coding.src_multibyte = 1; |
7727 | terminal_coding.dst_multibyte = 0; | |
4ed46869 KH |
7728 | return Qnil; |
7729 | } | |
7730 | ||
c4825358 KH |
7731 | DEFUN ("set-safe-terminal-coding-system-internal", |
7732 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 7733 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 7734 | doc: /* Internal use only. */) |
48b0f3ae | 7735 | (coding_system) |
b74e4686 | 7736 | Lisp_Object coding_system; |
d46c5b12 | 7737 | { |
b7826503 | 7738 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
7739 | setup_coding_system (Fcheck_coding_system (coding_system), |
7740 | &safe_terminal_coding); | |
df7492f9 KH |
7741 | /* Characer composition should be disabled. */ |
7742 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
7743 | safe_terminal_coding.src_multibyte = 1; |
7744 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
7745 | return Qnil; |
7746 | } | |
4ed46869 | 7747 | |
4ed46869 KH |
7748 | DEFUN ("terminal-coding-system", |
7749 | Fterminal_coding_system, Sterminal_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
7750 | doc: /* Return coding system specified for terminal output. */) |
7751 | () | |
4ed46869 | 7752 | { |
df7492f9 | 7753 | return CODING_ID_NAME (terminal_coding.id); |
4ed46869 KH |
7754 | } |
7755 | ||
1ba9e4ab KH |
7756 | DEFUN ("set-keyboard-coding-system-internal", |
7757 | Fset_keyboard_coding_system_internal, | |
48b0f3ae PJ |
7758 | Sset_keyboard_coding_system_internal, 1, 1, 0, |
7759 | doc: /* Internal use only. */) | |
7760 | (coding_system) | |
4ed46869 KH |
7761 | Lisp_Object coding_system; |
7762 | { | |
b7826503 | 7763 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
7764 | setup_coding_system (Fcheck_coding_system (coding_system), |
7765 | &keyboard_coding); | |
7766 | /* Characer composition should be disabled. */ | |
7767 | keyboard_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
7768 | return Qnil; |
7769 | } | |
7770 | ||
7771 | DEFUN ("keyboard-coding-system", | |
7772 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
7773 | doc: /* Return coding system specified for decoding keyboard input. */) |
7774 | () | |
4ed46869 | 7775 | { |
df7492f9 | 7776 | return CODING_ID_NAME (keyboard_coding.id); |
4ed46869 KH |
7777 | } |
7778 | ||
4ed46869 | 7779 | \f |
a5d301df KH |
7780 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
7781 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
7782 | doc: /* Choose a coding system for an operation based on the target name. |
7783 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
7784 | DECODING-SYSTEM is the coding system to use for decoding | |
7785 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
7786 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 7787 | |
48b0f3ae PJ |
7788 | The first argument OPERATION specifies an I/O primitive: |
7789 | For file I/O, `insert-file-contents' or `write-region'. | |
7790 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
7791 | For network I/O, `open-network-stream'. | |
05e6f5dc | 7792 | |
48b0f3ae PJ |
7793 | The remaining arguments should be the same arguments that were passed |
7794 | to the primitive. Depending on which primitive, one of those arguments | |
7795 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
7796 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 7797 | |
48b0f3ae PJ |
7798 | TARGET has a meaning which depends on OPERATION: |
7799 | For file I/O, TARGET is a file name. | |
7800 | For process I/O, TARGET is a process name. | |
7801 | For network I/O, TARGET is a service name or a port number | |
05e6f5dc | 7802 | |
48b0f3ae PJ |
7803 | This function looks up what specified for TARGET in, |
7804 | `file-coding-system-alist', `process-coding-system-alist', | |
7805 | or `network-coding-system-alist' depending on OPERATION. | |
7806 | They may specify a coding system, a cons of coding systems, | |
7807 | or a function symbol to call. | |
7808 | In the last case, we call the function with one argument, | |
7809 | which is a list of all the arguments given to this function. | |
7810 | ||
7811 | usage: (find-operation-coding-system OPERATION ARGUMENTS ...) */) | |
7812 | (nargs, args) | |
4ed46869 KH |
7813 | int nargs; |
7814 | Lisp_Object *args; | |
6b89e3aa | 7815 | { |
4ed46869 KH |
7816 | Lisp_Object operation, target_idx, target, val; |
7817 | register Lisp_Object chain; | |
177c0ea7 | 7818 | |
4ed46869 KH |
7819 | if (nargs < 2) |
7820 | error ("Too few arguments"); | |
7821 | operation = args[0]; | |
7822 | if (!SYMBOLP (operation) | |
7823 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
df7492f9 | 7824 | error ("Invalid first arguement"); |
4ed46869 KH |
7825 | if (nargs < 1 + XINT (target_idx)) |
7826 | error ("Too few arguments for operation: %s", | |
8f924df7 | 7827 | SDATA (SYMBOL_NAME (operation))); |
4ed46869 KH |
7828 | target = args[XINT (target_idx) + 1]; |
7829 | if (!(STRINGP (target) | |
7830 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) | |
df7492f9 | 7831 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
4ed46869 | 7832 | |
2e34157c RS |
7833 | chain = ((EQ (operation, Qinsert_file_contents) |
7834 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 7835 | ? Vfile_coding_system_alist |
2e34157c | 7836 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
7837 | ? Vnetwork_coding_system_alist |
7838 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
7839 | if (NILP (chain)) |
7840 | return Qnil; | |
7841 | ||
03699b14 | 7842 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 7843 | { |
f44d27ce | 7844 | Lisp_Object elt; |
6b89e3aa | 7845 | |
df7492f9 | 7846 | elt = XCAR (chain); |
4ed46869 KH |
7847 | if (CONSP (elt) |
7848 | && ((STRINGP (target) | |
03699b14 KR |
7849 | && STRINGP (XCAR (elt)) |
7850 | && fast_string_match (XCAR (elt), target) >= 0) | |
7851 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 7852 | { |
03699b14 | 7853 | val = XCDR (elt); |
b19fd4c5 KH |
7854 | /* Here, if VAL is both a valid coding system and a valid |
7855 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
7856 | if (CONSP (val)) |
7857 | return val; | |
7858 | if (! SYMBOLP (val)) | |
7859 | return Qnil; | |
7860 | if (! NILP (Fcoding_system_p (val))) | |
7861 | return Fcons (val, val); | |
b19fd4c5 | 7862 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 7863 | { |
b19fd4c5 KH |
7864 | val = call1 (val, Flist (nargs, args)); |
7865 | if (CONSP (val)) | |
7866 | return val; | |
7867 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
7868 | return Fcons (val, val); | |
6b89e3aa | 7869 | } |
02ba4723 | 7870 | return Qnil; |
6b89e3aa KH |
7871 | } |
7872 | } | |
4ed46869 | 7873 | return Qnil; |
6b89e3aa KH |
7874 | } |
7875 | ||
df7492f9 | 7876 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 7877 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 7878 | doc: /* Assign higher priority to the coding systems given as arguments. |
ff563fce | 7879 | If multiple coding systems belongs to the same category, |
a3181084 DL |
7880 | all but the first one are ignored. |
7881 | ||
7882 | usage: (set-coding-system-priority ...) */) | |
df7492f9 KH |
7883 | (nargs, args) |
7884 | int nargs; | |
7885 | Lisp_Object *args; | |
7886 | { | |
7887 | int i, j; | |
7888 | int changed[coding_category_max]; | |
7889 | enum coding_category priorities[coding_category_max]; | |
7890 | ||
7891 | bzero (changed, sizeof changed); | |
6b89e3aa | 7892 | |
df7492f9 | 7893 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 7894 | { |
df7492f9 KH |
7895 | enum coding_category category; |
7896 | Lisp_Object spec, attrs; | |
6b89e3aa | 7897 | |
df7492f9 KH |
7898 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
7899 | attrs = AREF (spec, 0); | |
7900 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
7901 | if (changed[category]) | |
7902 | /* Ignore this coding system because a coding system of the | |
7903 | same category already had a higher priority. */ | |
7904 | continue; | |
7905 | changed[category] = 1; | |
7906 | priorities[j++] = category; | |
7907 | if (coding_categories[category].id >= 0 | |
7908 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
7909 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 7910 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 7911 | } |
6b89e3aa | 7912 | |
df7492f9 KH |
7913 | /* Now we have decided top J priorities. Reflect the order of the |
7914 | original priorities to the remaining priorities. */ | |
6b89e3aa | 7915 | |
df7492f9 | 7916 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 7917 | { |
df7492f9 KH |
7918 | while (j < coding_category_max |
7919 | && changed[coding_priorities[j]]) | |
7920 | j++; | |
7921 | if (j == coding_category_max) | |
7922 | abort (); | |
7923 | priorities[i] = coding_priorities[j]; | |
7924 | } | |
6b89e3aa | 7925 | |
df7492f9 | 7926 | bcopy (priorities, coding_priorities, sizeof priorities); |
177c0ea7 | 7927 | |
ff563fce KH |
7928 | /* Update `coding-category-list'. */ |
7929 | Vcoding_category_list = Qnil; | |
7930 | for (i = coding_category_max - 1; i >= 0; i--) | |
7931 | Vcoding_category_list | |
7932 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
7933 | Vcoding_category_list); | |
6b89e3aa | 7934 | |
df7492f9 | 7935 | return Qnil; |
6b89e3aa KH |
7936 | } |
7937 | ||
df7492f9 KH |
7938 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
7939 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 DL |
7940 | doc: /* Return a list of coding systems ordered by their priorities. |
7941 | HIGHESTP non-nil means just return the highest priority one. */) | |
df7492f9 KH |
7942 | (highestp) |
7943 | Lisp_Object highestp; | |
d46c5b12 KH |
7944 | { |
7945 | int i; | |
df7492f9 | 7946 | Lisp_Object val; |
6b89e3aa | 7947 | |
df7492f9 | 7948 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 7949 | { |
df7492f9 KH |
7950 | enum coding_category category = coding_priorities[i]; |
7951 | int id = coding_categories[category].id; | |
7952 | Lisp_Object attrs; | |
068a9dbd | 7953 | |
df7492f9 KH |
7954 | if (id < 0) |
7955 | continue; | |
7956 | attrs = CODING_ID_ATTRS (id); | |
7957 | if (! NILP (highestp)) | |
7958 | return CODING_ATTR_BASE_NAME (attrs); | |
7959 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
7960 | } | |
7961 | return Fnreverse (val); | |
7962 | } | |
068a9dbd | 7963 | |
f0064e1f | 7964 | static char *suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
7965 | |
7966 | static Lisp_Object | |
df7492f9 KH |
7967 | make_subsidiaries (base) |
7968 | Lisp_Object base; | |
068a9dbd | 7969 | { |
df7492f9 | 7970 | Lisp_Object subsidiaries; |
8f924df7 | 7971 | int base_name_len = SBYTES (SYMBOL_NAME (base)); |
df7492f9 KH |
7972 | char *buf = (char *) alloca (base_name_len + 6); |
7973 | int i; | |
068a9dbd | 7974 | |
8f924df7 | 7975 | bcopy (SDATA (SYMBOL_NAME (base)), buf, base_name_len); |
df7492f9 KH |
7976 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
7977 | for (i = 0; i < 3; i++) | |
068a9dbd | 7978 | { |
df7492f9 KH |
7979 | bcopy (suffixes[i], buf + base_name_len, strlen (suffixes[i]) + 1); |
7980 | ASET (subsidiaries, i, intern (buf)); | |
068a9dbd | 7981 | } |
df7492f9 | 7982 | return subsidiaries; |
068a9dbd KH |
7983 | } |
7984 | ||
7985 | ||
df7492f9 KH |
7986 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
7987 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
7988 | doc: /* For internal use only. |
7989 | usage: (define-coding-system-internal ...) */) | |
df7492f9 KH |
7990 | (nargs, args) |
7991 | int nargs; | |
7992 | Lisp_Object *args; | |
068a9dbd | 7993 | { |
df7492f9 KH |
7994 | Lisp_Object name; |
7995 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
7996 | Lisp_Object attrs; /* Vector of attributes. */ | |
7997 | Lisp_Object eol_type; | |
7998 | Lisp_Object aliases; | |
7999 | Lisp_Object coding_type, charset_list, safe_charsets; | |
8000 | enum coding_category category; | |
8001 | Lisp_Object tail, val; | |
8002 | int max_charset_id = 0; | |
8003 | int i; | |
068a9dbd | 8004 | |
df7492f9 KH |
8005 | if (nargs < coding_arg_max) |
8006 | goto short_args; | |
068a9dbd | 8007 | |
df7492f9 | 8008 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 8009 | |
df7492f9 KH |
8010 | name = args[coding_arg_name]; |
8011 | CHECK_SYMBOL (name); | |
8012 | CODING_ATTR_BASE_NAME (attrs) = name; | |
068a9dbd | 8013 | |
df7492f9 KH |
8014 | val = args[coding_arg_mnemonic]; |
8015 | if (! STRINGP (val)) | |
8016 | CHECK_CHARACTER (val); | |
8017 | CODING_ATTR_MNEMONIC (attrs) = val; | |
068a9dbd | 8018 | |
df7492f9 KH |
8019 | coding_type = args[coding_arg_coding_type]; |
8020 | CHECK_SYMBOL (coding_type); | |
8021 | CODING_ATTR_TYPE (attrs) = coding_type; | |
068a9dbd | 8022 | |
df7492f9 KH |
8023 | charset_list = args[coding_arg_charset_list]; |
8024 | if (SYMBOLP (charset_list)) | |
8025 | { | |
8026 | if (EQ (charset_list, Qiso_2022)) | |
8027 | { | |
8028 | if (! EQ (coding_type, Qiso_2022)) | |
8029 | error ("Invalid charset-list"); | |
8030 | charset_list = Viso_2022_charset_list; | |
8031 | } | |
8032 | else if (EQ (charset_list, Qemacs_mule)) | |
8033 | { | |
8034 | if (! EQ (coding_type, Qemacs_mule)) | |
8035 | error ("Invalid charset-list"); | |
8036 | charset_list = Vemacs_mule_charset_list; | |
8037 | } | |
8038 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8039 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
8040 | max_charset_id = XFASTINT (XCAR (tail)); | |
8041 | } | |
068a9dbd KH |
8042 | else |
8043 | { | |
df7492f9 KH |
8044 | charset_list = Fcopy_sequence (charset_list); |
8045 | for (tail = charset_list; !NILP (tail); tail = Fcdr (tail)) | |
068a9dbd | 8046 | { |
df7492f9 KH |
8047 | struct charset *charset; |
8048 | ||
8049 | val = Fcar (tail); | |
8050 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8051 | if (EQ (coding_type, Qiso_2022) | |
8052 | ? CHARSET_ISO_FINAL (charset) < 0 | |
8053 | : EQ (coding_type, Qemacs_mule) | |
8054 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
8055 | : 0) | |
8056 | error ("Can't handle charset `%s'", | |
8f924df7 | 8057 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 8058 | |
8f924df7 | 8059 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
8060 | if (max_charset_id < charset->id) |
8061 | max_charset_id = charset->id; | |
068a9dbd KH |
8062 | } |
8063 | } | |
df7492f9 | 8064 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; |
068a9dbd | 8065 | |
df7492f9 KH |
8066 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
8067 | make_number (255)); | |
8068 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8f924df7 | 8069 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 8070 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; |
068a9dbd | 8071 | |
584948ac | 8072 | CODING_ATTR_ASCII_COMPAT (attrs) = args[coding_arg_ascii_compatible_p]; |
3a73fa5d | 8073 | |
df7492f9 KH |
8074 | val = args[coding_arg_decode_translation_table]; |
8075 | if (! NILP (val)) | |
8076 | CHECK_CHAR_TABLE (val); | |
8077 | CODING_ATTR_DECODE_TBL (attrs) = val; | |
3a73fa5d | 8078 | |
df7492f9 KH |
8079 | val = args[coding_arg_encode_translation_table]; |
8080 | if (! NILP (val)) | |
8081 | CHECK_CHAR_TABLE (val); | |
8082 | CODING_ATTR_ENCODE_TBL (attrs) = val; | |
d46c5b12 | 8083 | |
df7492f9 KH |
8084 | val = args[coding_arg_post_read_conversion]; |
8085 | CHECK_SYMBOL (val); | |
8086 | CODING_ATTR_POST_READ (attrs) = val; | |
d46c5b12 | 8087 | |
df7492f9 KH |
8088 | val = args[coding_arg_pre_write_conversion]; |
8089 | CHECK_SYMBOL (val); | |
8090 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
3a73fa5d | 8091 | |
df7492f9 KH |
8092 | val = args[coding_arg_default_char]; |
8093 | if (NILP (val)) | |
8094 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
8095 | else | |
8096 | { | |
8f924df7 | 8097 | CHECK_CHARACTER (val); |
df7492f9 KH |
8098 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; |
8099 | } | |
4031e2bf | 8100 | |
8f924df7 KH |
8101 | val = args[coding_arg_for_unibyte]; |
8102 | CODING_ATTR_FOR_UNIBYTE (attrs) = NILP (val) ? Qnil : Qt; | |
3a73fa5d | 8103 | |
df7492f9 KH |
8104 | val = args[coding_arg_plist]; |
8105 | CHECK_LIST (val); | |
8106 | CODING_ATTR_PLIST (attrs) = val; | |
3a73fa5d | 8107 | |
df7492f9 KH |
8108 | if (EQ (coding_type, Qcharset)) |
8109 | { | |
4187a77d | 8110 | Lisp_Object list; |
c7c66a95 KH |
8111 | /* Generate a lisp vector of 256 elements. Each element is nil, |
8112 | integer, or a list of charset IDs. | |
3a73fa5d | 8113 | |
c7c66a95 KH |
8114 | If Nth element is nil, the byte code N is invalid in this |
8115 | coding system. | |
4ed46869 | 8116 | |
c7c66a95 KH |
8117 | If Nth element is a number NUM, N is the first byte of a |
8118 | charset whose ID is NUM. | |
4ed46869 | 8119 | |
c7c66a95 KH |
8120 | If Nth element is a list of charset IDs, N is the first byte |
8121 | of one of them. The list is sorted by dimensions of the | |
8122 | charsets. A charset of smaller dimension comes firtst. | |
8123 | */ | |
4187a77d KH |
8124 | for (list = Qnil, tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
8125 | { | |
8126 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); | |
5f1cd180 | 8127 | |
4187a77d KH |
8128 | if (charset->method == CHARSET_METHOD_SUPERSET) |
8129 | { | |
8130 | val = CHARSET_SUPERSET (charset); | |
8131 | for (; CONSP (val); val = XCDR (val)) | |
8f924df7 | 8132 | list = Fcons (XCAR (XCAR (val)), list); |
4187a77d KH |
8133 | } |
8134 | else | |
8135 | list = Fcons (XCAR (tail), list); | |
8136 | } | |
ec6d2bb8 | 8137 | |
df7492f9 | 8138 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 8139 | |
4187a77d | 8140 | for (tail = Fnreverse (list); CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 8141 | { |
c7c66a95 KH |
8142 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
8143 | int dim = CHARSET_DIMENSION (charset); | |
8144 | int idx = (dim - 1) * 4; | |
4ed46869 | 8145 | |
584948ac KH |
8146 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8147 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
4031e2bf | 8148 | |
15d143f7 KH |
8149 | for (i = charset->code_space[idx]; |
8150 | i <= charset->code_space[idx + 1]; i++) | |
8151 | { | |
c7c66a95 KH |
8152 | Lisp_Object tmp, tmp2; |
8153 | int dim2; | |
ec6d2bb8 | 8154 | |
c7c66a95 KH |
8155 | tmp = AREF (val, i); |
8156 | if (NILP (tmp)) | |
8157 | tmp = XCAR (tail); | |
8158 | else if (NUMBERP (tmp)) | |
8159 | { | |
8160 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
8161 | if (dim < dim2) | |
c7c66a95 | 8162 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
8163 | else |
8164 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 8165 | } |
15d143f7 | 8166 | else |
c7c66a95 KH |
8167 | { |
8168 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
8169 | { | |
8170 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
8171 | if (dim < dim2) | |
8172 | break; | |
8173 | } | |
8174 | if (NILP (tmp2)) | |
8175 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
8176 | else | |
8177 | { | |
8178 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
8179 | XSETCAR (tmp2, XCAR (tail)); | |
8180 | } | |
8181 | } | |
8182 | ASET (val, i, tmp); | |
15d143f7 | 8183 | } |
df7492f9 KH |
8184 | } |
8185 | ASET (attrs, coding_attr_charset_valids, val); | |
8186 | category = coding_category_charset; | |
8187 | } | |
8188 | else if (EQ (coding_type, Qccl)) | |
8189 | { | |
8190 | Lisp_Object valids; | |
ecec61c1 | 8191 | |
df7492f9 KH |
8192 | if (nargs < coding_arg_ccl_max) |
8193 | goto short_args; | |
ecec61c1 | 8194 | |
df7492f9 KH |
8195 | val = args[coding_arg_ccl_decoder]; |
8196 | CHECK_CCL_PROGRAM (val); | |
8197 | if (VECTORP (val)) | |
8198 | val = Fcopy_sequence (val); | |
8199 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 8200 | |
df7492f9 KH |
8201 | val = args[coding_arg_ccl_encoder]; |
8202 | CHECK_CCL_PROGRAM (val); | |
8203 | if (VECTORP (val)) | |
8204 | val = Fcopy_sequence (val); | |
8205 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 8206 | |
df7492f9 KH |
8207 | val = args[coding_arg_ccl_valids]; |
8208 | valids = Fmake_string (make_number (256), make_number (0)); | |
8209 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
8210 | { | |
8dcbea82 | 8211 | int from, to; |
ecec61c1 | 8212 | |
df7492f9 KH |
8213 | val = Fcar (tail); |
8214 | if (INTEGERP (val)) | |
8dcbea82 KH |
8215 | { |
8216 | from = to = XINT (val); | |
8217 | if (from < 0 || from > 255) | |
8218 | args_out_of_range_3 (val, make_number (0), make_number (255)); | |
8219 | } | |
df7492f9 KH |
8220 | else |
8221 | { | |
df7492f9 | 8222 | CHECK_CONS (val); |
8f924df7 KH |
8223 | CHECK_NATNUM_CAR (val); |
8224 | CHECK_NATNUM_CDR (val); | |
df7492f9 | 8225 | from = XINT (XCAR (val)); |
8f924df7 | 8226 | if (from > 255) |
8dcbea82 KH |
8227 | args_out_of_range_3 (XCAR (val), |
8228 | make_number (0), make_number (255)); | |
df7492f9 | 8229 | to = XINT (XCDR (val)); |
8dcbea82 KH |
8230 | if (to < from || to > 255) |
8231 | args_out_of_range_3 (XCDR (val), | |
8232 | XCAR (val), make_number (255)); | |
df7492f9 | 8233 | } |
8dcbea82 | 8234 | for (i = from; i <= to; i++) |
8f924df7 | 8235 | SSET (valids, i, 1); |
df7492f9 KH |
8236 | } |
8237 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 8238 | |
df7492f9 | 8239 | category = coding_category_ccl; |
55ab7be3 | 8240 | } |
df7492f9 | 8241 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 8242 | { |
df7492f9 | 8243 | Lisp_Object bom, endian; |
4ed46869 | 8244 | |
584948ac | 8245 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; |
4ed46869 | 8246 | |
df7492f9 KH |
8247 | if (nargs < coding_arg_utf16_max) |
8248 | goto short_args; | |
4ed46869 | 8249 | |
df7492f9 KH |
8250 | bom = args[coding_arg_utf16_bom]; |
8251 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
8252 | { | |
8253 | CHECK_CONS (bom); | |
8f924df7 KH |
8254 | val = XCAR (bom); |
8255 | CHECK_CODING_SYSTEM (val); | |
8256 | val = XCDR (bom); | |
8257 | CHECK_CODING_SYSTEM (val); | |
df7492f9 KH |
8258 | } |
8259 | ASET (attrs, coding_attr_utf_16_bom, bom); | |
8260 | ||
8261 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
8262 | CHECK_SYMBOL (endian); |
8263 | if (NILP (endian)) | |
8264 | endian = Qbig; | |
8265 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 8266 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
8267 | ASET (attrs, coding_attr_utf_16_endian, endian); |
8268 | ||
8269 | category = (CONSP (bom) | |
8270 | ? coding_category_utf_16_auto | |
8271 | : NILP (bom) | |
b49a1807 | 8272 | ? (EQ (endian, Qbig) |
df7492f9 KH |
8273 | ? coding_category_utf_16_be_nosig |
8274 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 8275 | : (EQ (endian, Qbig) |
df7492f9 KH |
8276 | ? coding_category_utf_16_be |
8277 | : coding_category_utf_16_le)); | |
8278 | } | |
8279 | else if (EQ (coding_type, Qiso_2022)) | |
8280 | { | |
8281 | Lisp_Object initial, reg_usage, request, flags; | |
4776e638 | 8282 | int i; |
1397dc18 | 8283 | |
df7492f9 KH |
8284 | if (nargs < coding_arg_iso2022_max) |
8285 | goto short_args; | |
8286 | ||
8287 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
8288 | CHECK_VECTOR (initial); | |
8289 | for (i = 0; i < 4; i++) | |
8290 | { | |
8291 | val = Faref (initial, make_number (i)); | |
8292 | if (! NILP (val)) | |
8293 | { | |
584948ac KH |
8294 | struct charset *charset; |
8295 | ||
8296 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8297 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
8298 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
8299 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8300 | } |
8301 | else | |
8302 | ASET (initial, i, make_number (-1)); | |
8303 | } | |
8304 | ||
8305 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
8306 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
8307 | CHECK_NUMBER_CAR (reg_usage); |
8308 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
8309 | |
8310 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
8311 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 8312 | { |
df7492f9 | 8313 | int id; |
8f924df7 | 8314 | Lisp_Object tmp; |
df7492f9 KH |
8315 | |
8316 | val = Fcar (tail); | |
8317 | CHECK_CONS (val); | |
8f924df7 KH |
8318 | tmp = XCAR (val); |
8319 | CHECK_CHARSET_GET_ID (tmp, id); | |
8320 | CHECK_NATNUM_CDR (val); | |
df7492f9 KH |
8321 | if (XINT (XCDR (val)) >= 4) |
8322 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
8f924df7 | 8323 | XSETCAR (val, make_number (id)); |
1397dc18 | 8324 | } |
4ed46869 | 8325 | |
df7492f9 KH |
8326 | flags = args[coding_arg_iso2022_flags]; |
8327 | CHECK_NATNUM (flags); | |
8328 | i = XINT (flags); | |
8329 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
8330 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
8331 | ||
8332 | ASET (attrs, coding_attr_iso_initial, initial); | |
8333 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
8334 | ASET (attrs, coding_attr_iso_request, request); | |
8335 | ASET (attrs, coding_attr_iso_flags, flags); | |
8336 | setup_iso_safe_charsets (attrs); | |
8337 | ||
8338 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
8339 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
8340 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
8341 | ? coding_category_iso_7_else | |
8342 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
8343 | ? coding_category_iso_7 | |
8344 | : coding_category_iso_7_tight); | |
8345 | else | |
8346 | { | |
8347 | int id = XINT (AREF (initial, 1)); | |
8348 | ||
c6fb6e98 | 8349 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
8350 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
8351 | || id < 0) | |
8352 | ? coding_category_iso_8_else | |
8353 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
8354 | ? coding_category_iso_8_1 | |
8355 | : coding_category_iso_8_2); | |
8356 | } | |
0ce7886f KH |
8357 | if (category != coding_category_iso_8_1 |
8358 | && category != coding_category_iso_8_2) | |
8359 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; | |
df7492f9 KH |
8360 | } |
8361 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 8362 | { |
df7492f9 KH |
8363 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
8364 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
584948ac | 8365 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
df7492f9 | 8366 | category = coding_category_emacs_mule; |
c28a9453 | 8367 | } |
df7492f9 | 8368 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 8369 | { |
df7492f9 KH |
8370 | |
8371 | struct charset *charset; | |
8372 | ||
8373 | if (XINT (Flength (charset_list)) != 3) | |
8374 | error ("There should be just three charsets"); | |
8375 | ||
8376 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8377 | if (CHARSET_DIMENSION (charset) != 1) | |
8378 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8379 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8380 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8381 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8382 | |
8383 | charset_list = XCDR (charset_list); | |
8384 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8385 | if (CHARSET_DIMENSION (charset) != 1) | |
8386 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8387 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
8388 | |
8389 | charset_list = XCDR (charset_list); | |
8390 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8391 | if (CHARSET_DIMENSION (charset) != 2) | |
8392 | error ("Dimension of charset %s is not two", | |
8f924df7 | 8393 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
8394 | |
8395 | category = coding_category_sjis; | |
8396 | Vsjis_coding_system = name; | |
c28a9453 | 8397 | } |
df7492f9 KH |
8398 | else if (EQ (coding_type, Qbig5)) |
8399 | { | |
8400 | struct charset *charset; | |
4ed46869 | 8401 | |
df7492f9 KH |
8402 | if (XINT (Flength (charset_list)) != 2) |
8403 | error ("There should be just two charsets"); | |
8404 | ||
8405 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8406 | if (CHARSET_DIMENSION (charset) != 1) | |
8407 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8408 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8409 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8410 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8411 | |
8412 | charset_list = XCDR (charset_list); | |
8413 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8414 | if (CHARSET_DIMENSION (charset) != 2) | |
8415 | error ("Dimension of charset %s is not two", | |
8f924df7 | 8416 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 8417 | |
df7492f9 KH |
8418 | category = coding_category_big5; |
8419 | Vbig5_coding_system = name; | |
8420 | } | |
8421 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 8422 | { |
584948ac KH |
8423 | category = coding_category_raw_text; |
8424 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
c28a9453 | 8425 | } |
df7492f9 | 8426 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 8427 | { |
584948ac KH |
8428 | category = coding_category_utf_8; |
8429 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
4ed46869 | 8430 | } |
df7492f9 KH |
8431 | else if (EQ (coding_type, Qundecided)) |
8432 | category = coding_category_undecided; | |
4ed46869 | 8433 | else |
df7492f9 | 8434 | error ("Invalid coding system type: %s", |
8f924df7 | 8435 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 8436 | |
df7492f9 | 8437 | CODING_ATTR_CATEGORY (attrs) = make_number (category); |
01378f49 KH |
8438 | CODING_ATTR_PLIST (attrs) |
8439 | = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category), | |
8440 | CODING_ATTR_PLIST (attrs))); | |
c4825358 | 8441 | |
df7492f9 KH |
8442 | eol_type = args[coding_arg_eol_type]; |
8443 | if (! NILP (eol_type) | |
8444 | && ! EQ (eol_type, Qunix) | |
8445 | && ! EQ (eol_type, Qdos) | |
8446 | && ! EQ (eol_type, Qmac)) | |
8447 | error ("Invalid eol-type"); | |
4ed46869 | 8448 | |
df7492f9 | 8449 | aliases = Fcons (name, Qnil); |
4ed46869 | 8450 | |
df7492f9 KH |
8451 | if (NILP (eol_type)) |
8452 | { | |
8453 | eol_type = make_subsidiaries (name); | |
8454 | for (i = 0; i < 3; i++) | |
1397dc18 | 8455 | { |
df7492f9 KH |
8456 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
8457 | ||
8458 | this_name = AREF (eol_type, i); | |
8459 | this_aliases = Fcons (this_name, Qnil); | |
8460 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
8461 | this_spec = Fmake_vector (make_number (3), attrs); | |
8462 | ASET (this_spec, 1, this_aliases); | |
8463 | ASET (this_spec, 2, this_eol_type); | |
8464 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
8465 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
8466 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
8467 | Vcoding_system_alist); | |
1397dc18 | 8468 | } |
d46c5b12 | 8469 | } |
4ed46869 | 8470 | |
df7492f9 KH |
8471 | spec_vec = Fmake_vector (make_number (3), attrs); |
8472 | ASET (spec_vec, 1, aliases); | |
8473 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 8474 | |
df7492f9 KH |
8475 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
8476 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
8477 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
8478 | Vcoding_system_alist); | |
48b0f3ae | 8479 | |
df7492f9 KH |
8480 | { |
8481 | int id = coding_categories[category].id; | |
48b0f3ae | 8482 | |
df7492f9 KH |
8483 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
8484 | setup_coding_system (name, &coding_categories[category]); | |
8485 | } | |
48b0f3ae | 8486 | |
d46c5b12 | 8487 | return Qnil; |
48b0f3ae | 8488 | |
df7492f9 KH |
8489 | short_args: |
8490 | return Fsignal (Qwrong_number_of_arguments, | |
8491 | Fcons (intern ("define-coding-system-internal"), | |
8492 | make_number (nargs))); | |
d46c5b12 | 8493 | } |
4ed46869 | 8494 | |
d6925f38 | 8495 | |
df7492f9 KH |
8496 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
8497 | Sdefine_coding_system_alias, 2, 2, 0, | |
8498 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
8499 | (alias, coding_system) | |
8500 | Lisp_Object alias, coding_system; | |
66cfb530 | 8501 | { |
df7492f9 | 8502 | Lisp_Object spec, aliases, eol_type; |
4ed46869 | 8503 | |
df7492f9 KH |
8504 | CHECK_SYMBOL (alias); |
8505 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8506 | aliases = AREF (spec, 1); | |
d6925f38 KH |
8507 | /* ALISES should be a list of length more than zero, and the first |
8508 | element is a base coding system. Append ALIAS at the tail of the | |
8509 | list. */ | |
df7492f9 KH |
8510 | while (!NILP (XCDR (aliases))) |
8511 | aliases = XCDR (aliases); | |
8f924df7 | 8512 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 8513 | |
df7492f9 KH |
8514 | eol_type = AREF (spec, 2); |
8515 | if (VECTORP (eol_type)) | |
4ed46869 | 8516 | { |
df7492f9 KH |
8517 | Lisp_Object subsidiaries; |
8518 | int i; | |
4ed46869 | 8519 | |
df7492f9 KH |
8520 | subsidiaries = make_subsidiaries (alias); |
8521 | for (i = 0; i < 3; i++) | |
8522 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
8523 | AREF (eol_type, i)); | |
4ed46869 | 8524 | } |
df7492f9 KH |
8525 | |
8526 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 8527 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
5bad0796 DL |
8528 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), |
8529 | Vcoding_system_alist); | |
66cfb530 | 8530 | |
4ed46869 KH |
8531 | return Qnil; |
8532 | } | |
8533 | ||
df7492f9 KH |
8534 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
8535 | 1, 1, 0, | |
8536 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 8537 | Any alias or subsidiary coding system is not a base coding system. */) |
df7492f9 KH |
8538 | (coding_system) |
8539 | Lisp_Object coding_system; | |
d46c5b12 | 8540 | { |
df7492f9 | 8541 | Lisp_Object spec, attrs; |
d46c5b12 | 8542 | |
df7492f9 KH |
8543 | if (NILP (coding_system)) |
8544 | return (Qno_conversion); | |
8545 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8546 | attrs = AREF (spec, 0); | |
8547 | return CODING_ATTR_BASE_NAME (attrs); | |
8548 | } | |
1397dc18 | 8549 | |
df7492f9 KH |
8550 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
8551 | 1, 1, 0, | |
8552 | doc: "Return the property list of CODING-SYSTEM.") | |
8553 | (coding_system) | |
8554 | Lisp_Object coding_system; | |
8555 | { | |
8556 | Lisp_Object spec, attrs; | |
1397dc18 | 8557 | |
df7492f9 KH |
8558 | if (NILP (coding_system)) |
8559 | coding_system = Qno_conversion; | |
8560 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8561 | attrs = AREF (spec, 0); | |
8562 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
8563 | } |
8564 | ||
df7492f9 KH |
8565 | |
8566 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
8567 | 1, 1, 0, | |
da7db224 | 8568 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
df7492f9 KH |
8569 | (coding_system) |
8570 | Lisp_Object coding_system; | |
66cfb530 | 8571 | { |
df7492f9 | 8572 | Lisp_Object spec; |
84d60297 | 8573 | |
df7492f9 KH |
8574 | if (NILP (coding_system)) |
8575 | coding_system = Qno_conversion; | |
8576 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 8577 | return AREF (spec, 1); |
df7492f9 | 8578 | } |
66cfb530 | 8579 | |
df7492f9 KH |
8580 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
8581 | Scoding_system_eol_type, 1, 1, 0, | |
8582 | doc: /* Return eol-type of CODING-SYSTEM. | |
8583 | An eol-type is integer 0, 1, 2, or a vector of coding systems. | |
66cfb530 | 8584 | |
df7492f9 KH |
8585 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
8586 | and CR respectively. | |
66cfb530 | 8587 | |
df7492f9 KH |
8588 | A vector value indicates that a format of end-of-line should be |
8589 | detected automatically. Nth element of the vector is the subsidiary | |
8590 | coding system whose eol-type is N. */) | |
6b89e3aa KH |
8591 | (coding_system) |
8592 | Lisp_Object coding_system; | |
8593 | { | |
df7492f9 KH |
8594 | Lisp_Object spec, eol_type; |
8595 | int n; | |
6b89e3aa | 8596 | |
df7492f9 KH |
8597 | if (NILP (coding_system)) |
8598 | coding_system = Qno_conversion; | |
8599 | if (! CODING_SYSTEM_P (coding_system)) | |
8600 | return Qnil; | |
8601 | spec = CODING_SYSTEM_SPEC (coding_system); | |
8602 | eol_type = AREF (spec, 2); | |
8603 | if (VECTORP (eol_type)) | |
8604 | return Fcopy_sequence (eol_type); | |
8605 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
8606 | return make_number (n); | |
6b89e3aa KH |
8607 | } |
8608 | ||
4ed46869 KH |
8609 | #endif /* emacs */ |
8610 | ||
8611 | \f | |
1397dc18 | 8612 | /*** 9. Post-amble ***/ |
4ed46869 | 8613 | |
dfcf069d | 8614 | void |
4ed46869 KH |
8615 | init_coding_once () |
8616 | { | |
8617 | int i; | |
8618 | ||
df7492f9 KH |
8619 | for (i = 0; i < coding_category_max; i++) |
8620 | { | |
8621 | coding_categories[i].id = -1; | |
8622 | coding_priorities[i] = i; | |
8623 | } | |
4ed46869 KH |
8624 | |
8625 | /* ISO2022 specific initialize routine. */ | |
8626 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 8627 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
8628 | for (i = 0x21; i < 0x7F; i++) |
8629 | iso_code_class[i] = ISO_graphic_plane_0; | |
8630 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 8631 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
8632 | for (i = 0xA1; i < 0xFF; i++) |
8633 | iso_code_class[i] = ISO_graphic_plane_1; | |
8634 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
8635 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
8636 | iso_code_class[ISO_CODE_CR] = ISO_carriage_return; | |
8637 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; | |
8638 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
8639 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
8640 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
8641 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
8642 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
8643 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
8644 | ||
df7492f9 KH |
8645 | for (i = 0; i < 256; i++) |
8646 | { | |
8647 | emacs_mule_bytes[i] = 1; | |
8648 | } | |
7c78e542 KH |
8649 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
8650 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
8651 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
8652 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
8653 | } |
8654 | ||
8655 | #ifdef emacs | |
8656 | ||
dfcf069d | 8657 | void |
e0e989f6 KH |
8658 | syms_of_coding () |
8659 | { | |
df7492f9 | 8660 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
8661 | { |
8662 | Lisp_Object args[2]; | |
8663 | args[0] = QCtest; | |
8664 | args[1] = Qeq; | |
8665 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
8666 | } | |
df7492f9 KH |
8667 | |
8668 | staticpro (&Vsjis_coding_system); | |
8669 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 8670 | |
df7492f9 KH |
8671 | staticpro (&Vbig5_coding_system); |
8672 | Vbig5_coding_system = Qnil; | |
8673 | ||
8674 | staticpro (&Vcode_conversion_work_buf_list); | |
8675 | Vcode_conversion_work_buf_list = Qnil; | |
e0e989f6 | 8676 | |
df7492f9 KH |
8677 | staticpro (&Vcode_conversion_reused_work_buf); |
8678 | Vcode_conversion_reused_work_buf = Qnil; | |
8679 | ||
8680 | DEFSYM (Qcharset, "charset"); | |
8681 | DEFSYM (Qtarget_idx, "target-idx"); | |
8682 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
8683 | Fset (Qcoding_system_history, Qnil); |
8684 | ||
9ce27fde | 8685 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 8686 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 8687 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
8688 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
8689 | ||
df7492f9 | 8690 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 8691 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
8692 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
8693 | ||
df7492f9 | 8694 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 8695 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
8696 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
8697 | ||
df7492f9 | 8698 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 8699 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
8700 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
8701 | ||
df7492f9 | 8702 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 8703 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
8704 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
8705 | ||
df7492f9 KH |
8706 | DEFSYM (Qcoding_system, "coding-system"); |
8707 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 8708 | |
df7492f9 KH |
8709 | DEFSYM (Qeol_type, "eol-type"); |
8710 | DEFSYM (Qunix, "unix"); | |
8711 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 8712 | |
df7492f9 KH |
8713 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
8714 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
8715 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
8716 | DEFSYM (Qdefault_char, "default-char"); | |
8717 | DEFSYM (Qundecided, "undecided"); | |
8718 | DEFSYM (Qno_conversion, "no-conversion"); | |
8719 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 8720 | |
df7492f9 | 8721 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 8722 | |
df7492f9 | 8723 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 8724 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 8725 | |
df7492f9 | 8726 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
8727 | DEFSYM (Qbig, "big"); |
8728 | DEFSYM (Qlittle, "little"); | |
27901516 | 8729 | |
df7492f9 KH |
8730 | DEFSYM (Qshift_jis, "shift-jis"); |
8731 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 8732 | |
df7492f9 | 8733 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 8734 | |
df7492f9 | 8735 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 KH |
8736 | Fput (Qcoding_system_error, Qerror_conditions, |
8737 | Fcons (Qcoding_system_error, Fcons (Qerror, Qnil))); | |
8738 | Fput (Qcoding_system_error, Qerror_message, | |
9ce27fde | 8739 | build_string ("Invalid coding system")); |
4ed46869 | 8740 | |
05e6f5dc KH |
8741 | /* Intern this now in case it isn't already done. |
8742 | Setting this variable twice is harmless. | |
8743 | But don't staticpro it here--that is done in alloc.c. */ | |
8744 | Qchar_table_extra_slots = intern ("char-table-extra-slots"); | |
70c22245 | 8745 | |
df7492f9 | 8746 | DEFSYM (Qtranslation_table, "translation-table"); |
1397dc18 | 8747 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (1)); |
df7492f9 KH |
8748 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
8749 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
8750 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 8751 | |
df7492f9 | 8752 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 8753 | |
df7492f9 | 8754 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 8755 | |
01378f49 KH |
8756 | DEFSYM (QCcategory, ":category"); |
8757 | ||
df7492f9 KH |
8758 | Vcoding_category_table |
8759 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
8760 | staticpro (&Vcoding_category_table); | |
8761 | /* Followings are target of code detection. */ | |
8762 | ASET (Vcoding_category_table, coding_category_iso_7, | |
8763 | intern ("coding-category-iso-7")); | |
8764 | ASET (Vcoding_category_table, coding_category_iso_7_tight, | |
8765 | intern ("coding-category-iso-7-tight")); | |
8766 | ASET (Vcoding_category_table, coding_category_iso_8_1, | |
8767 | intern ("coding-category-iso-8-1")); | |
8768 | ASET (Vcoding_category_table, coding_category_iso_8_2, | |
8769 | intern ("coding-category-iso-8-2")); | |
8770 | ASET (Vcoding_category_table, coding_category_iso_7_else, | |
8771 | intern ("coding-category-iso-7-else")); | |
8772 | ASET (Vcoding_category_table, coding_category_iso_8_else, | |
8773 | intern ("coding-category-iso-8-else")); | |
8774 | ASET (Vcoding_category_table, coding_category_utf_8, | |
8775 | intern ("coding-category-utf-8")); | |
8776 | ASET (Vcoding_category_table, coding_category_utf_16_be, | |
8777 | intern ("coding-category-utf-16-be")); | |
ff563fce KH |
8778 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
8779 | intern ("coding-category-utf-16-auto")); | |
df7492f9 KH |
8780 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
8781 | intern ("coding-category-utf-16-le")); | |
8782 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, | |
8783 | intern ("coding-category-utf-16-be-nosig")); | |
8784 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, | |
8785 | intern ("coding-category-utf-16-le-nosig")); | |
8786 | ASET (Vcoding_category_table, coding_category_charset, | |
8787 | intern ("coding-category-charset")); | |
8788 | ASET (Vcoding_category_table, coding_category_sjis, | |
8789 | intern ("coding-category-sjis")); | |
8790 | ASET (Vcoding_category_table, coding_category_big5, | |
8791 | intern ("coding-category-big5")); | |
8792 | ASET (Vcoding_category_table, coding_category_ccl, | |
8793 | intern ("coding-category-ccl")); | |
8794 | ASET (Vcoding_category_table, coding_category_emacs_mule, | |
8795 | intern ("coding-category-emacs-mule")); | |
8796 | /* Followings are NOT target of code detection. */ | |
8797 | ASET (Vcoding_category_table, coding_category_raw_text, | |
8798 | intern ("coding-category-raw-text")); | |
8799 | ASET (Vcoding_category_table, coding_category_undecided, | |
8800 | intern ("coding-category-undecided")); | |
ecf488bc | 8801 | |
4ed46869 KH |
8802 | defsubr (&Scoding_system_p); |
8803 | defsubr (&Sread_coding_system); | |
8804 | defsubr (&Sread_non_nil_coding_system); | |
8805 | defsubr (&Scheck_coding_system); | |
8806 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 8807 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 8808 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 8809 | defsubr (&Sunencodable_char_position); |
df7492f9 | 8810 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
8811 | defsubr (&Sdecode_coding_region); |
8812 | defsubr (&Sencode_coding_region); | |
8813 | defsubr (&Sdecode_coding_string); | |
8814 | defsubr (&Sencode_coding_string); | |
8815 | defsubr (&Sdecode_sjis_char); | |
8816 | defsubr (&Sencode_sjis_char); | |
8817 | defsubr (&Sdecode_big5_char); | |
8818 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 8819 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 8820 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 8821 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 8822 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 8823 | defsubr (&Skeyboard_coding_system); |
a5d301df | 8824 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 8825 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 8826 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 KH |
8827 | defsubr (&Sdefine_coding_system_alias); |
8828 | defsubr (&Scoding_system_base); | |
8829 | defsubr (&Scoding_system_plist); | |
8830 | defsubr (&Scoding_system_aliases); | |
8831 | defsubr (&Scoding_system_eol_type); | |
8832 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 8833 | |
4608c386 | 8834 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
48b0f3ae PJ |
8835 | doc: /* List of coding systems. |
8836 | ||
8837 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 8838 | updated by the functions `define-coding-system' and |
48b0f3ae | 8839 | `define-coding-system-alias'. */); |
4608c386 KH |
8840 | Vcoding_system_list = Qnil; |
8841 | ||
8842 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, | |
48b0f3ae PJ |
8843 | doc: /* Alist of coding system names. |
8844 | Each element is one element list of coding system name. | |
8845 | This variable is given to `completing-read' as TABLE argument. | |
8846 | ||
8847 | Do not alter the value of this variable manually. This variable should be | |
8848 | updated by the functions `make-coding-system' and | |
8849 | `define-coding-system-alias'. */); | |
4608c386 KH |
8850 | Vcoding_system_alist = Qnil; |
8851 | ||
4ed46869 | 8852 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
48b0f3ae PJ |
8853 | doc: /* List of coding-categories (symbols) ordered by priority. |
8854 | ||
8855 | On detecting a coding system, Emacs tries code detection algorithms | |
8856 | associated with each coding-category one by one in this order. When | |
8857 | one algorithm agrees with a byte sequence of source text, the coding | |
8858 | system bound to the corresponding coding-category is selected. */); | |
4ed46869 KH |
8859 | { |
8860 | int i; | |
8861 | ||
8862 | Vcoding_category_list = Qnil; | |
df7492f9 | 8863 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 8864 | Vcoding_category_list |
d46c5b12 KH |
8865 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
8866 | Vcoding_category_list); | |
4ed46869 KH |
8867 | } |
8868 | ||
8869 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, | |
48b0f3ae PJ |
8870 | doc: /* Specify the coding system for read operations. |
8871 | It is useful to bind this variable with `let', but do not set it globally. | |
8872 | If the value is a coding system, it is used for decoding on read operation. | |
8873 | If not, an appropriate element is used from one of the coding system alists: | |
8874 | There are three such tables, `file-coding-system-alist', | |
8875 | `process-coding-system-alist', and `network-coding-system-alist'. */); | |
4ed46869 KH |
8876 | Vcoding_system_for_read = Qnil; |
8877 | ||
8878 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, | |
48b0f3ae PJ |
8879 | doc: /* Specify the coding system for write operations. |
8880 | Programs bind this variable with `let', but you should not set it globally. | |
8881 | If the value is a coding system, it is used for encoding of output, | |
8882 | when writing it to a file and when sending it to a file or subprocess. | |
8883 | ||
8884 | If this does not specify a coding system, an appropriate element | |
8885 | is used from one of the coding system alists: | |
8886 | There are three such tables, `file-coding-system-alist', | |
8887 | `process-coding-system-alist', and `network-coding-system-alist'. | |
8888 | For output to files, if the above procedure does not specify a coding system, | |
8889 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
8890 | Vcoding_system_for_write = Qnil; |
8891 | ||
8892 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, | |
df7492f9 KH |
8893 | doc: /* |
8894 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
8895 | Vlast_coding_system_used = Qnil; |
8896 | ||
9ce27fde | 8897 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
df7492f9 KH |
8898 | doc: /* |
8899 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
8900 | See info node `Coding Systems' and info node `Text and Binary' concerning |
8901 | such conversion. */); | |
9ce27fde KH |
8902 | inhibit_eol_conversion = 0; |
8903 | ||
ed29121d | 8904 | DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
df7492f9 KH |
8905 | doc: /* |
8906 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
8907 | Bind it to t if the process output is to be treated as if it were a file |
8908 | read from some filesystem. */); | |
ed29121d EZ |
8909 | inherit_process_coding_system = 0; |
8910 | ||
02ba4723 | 8911 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
df7492f9 KH |
8912 | doc: /* |
8913 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
8914 | The format is ((PATTERN . VAL) ...), |
8915 | where PATTERN is a regular expression matching a file name, | |
8916 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
8917 | If VAL is a coding system, it is used for both decoding and encoding | |
8918 | the file contents. | |
8919 | If VAL is a cons of coding systems, the car part is used for decoding, | |
8920 | and the cdr part is used for encoding. | |
8921 | If VAL is a function symbol, the function must return a coding system | |
0192762c DL |
8922 | or a cons of coding systems which are used as above. The function gets |
8923 | the arguments with which `find-operation-coding-systems' was called. | |
48b0f3ae PJ |
8924 | |
8925 | See also the function `find-operation-coding-system' | |
8926 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
8927 | Vfile_coding_system_alist = Qnil; |
8928 | ||
8929 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, | |
df7492f9 KH |
8930 | doc: /* |
8931 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
8932 | The format is ((PATTERN . VAL) ...), |
8933 | where PATTERN is a regular expression matching a program name, | |
8934 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
8935 | If VAL is a coding system, it is used for both decoding what received | |
8936 | from the program and encoding what sent to the program. | |
8937 | If VAL is a cons of coding systems, the car part is used for decoding, | |
8938 | and the cdr part is used for encoding. | |
8939 | If VAL is a function symbol, the function must return a coding system | |
8940 | or a cons of coding systems which are used as above. | |
8941 | ||
8942 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
8943 | Vprocess_coding_system_alist = Qnil; |
8944 | ||
8945 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, | |
df7492f9 KH |
8946 | doc: /* |
8947 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
8948 | The format is ((PATTERN . VAL) ...), |
8949 | where PATTERN is a regular expression matching a network service name | |
8950 | or is a port number to connect to, | |
8951 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
8952 | If VAL is a coding system, it is used for both decoding what received | |
8953 | from the network stream and encoding what sent to the network stream. | |
8954 | If VAL is a cons of coding systems, the car part is used for decoding, | |
8955 | and the cdr part is used for encoding. | |
8956 | If VAL is a function symbol, the function must return a coding system | |
8957 | or a cons of coding systems which are used as above. | |
8958 | ||
8959 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 8960 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 8961 | |
68c45bf0 | 8962 | DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
75205970 RS |
8963 | doc: /* Coding system to use with system messages. |
8964 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
8965 | Vlocale_coding_system = Qnil; |
8966 | ||
005f0d35 | 8967 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
7722baf9 | 8968 | DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
df7492f9 KH |
8969 | doc: /* |
8970 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
7722baf9 | 8971 | eol_mnemonic_unix = build_string (":"); |
4ed46869 | 8972 | |
7722baf9 | 8973 | DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
df7492f9 KH |
8974 | doc: /* |
8975 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
7722baf9 | 8976 | eol_mnemonic_dos = build_string ("\\"); |
4ed46869 | 8977 | |
7722baf9 | 8978 | DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
df7492f9 KH |
8979 | doc: /* |
8980 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
7722baf9 | 8981 | eol_mnemonic_mac = build_string ("/"); |
4ed46869 | 8982 | |
7722baf9 | 8983 | DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
df7492f9 KH |
8984 | doc: /* |
8985 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
7722baf9 | 8986 | eol_mnemonic_undecided = build_string (":"); |
4ed46869 | 8987 | |
84fbb8a0 | 8988 | DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
df7492f9 KH |
8989 | doc: /* |
8990 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 8991 | Venable_character_translation = Qt; |
bdd9fb48 | 8992 | |
f967223b | 8993 | DEFVAR_LISP ("standard-translation-table-for-decode", |
48b0f3ae PJ |
8994 | &Vstandard_translation_table_for_decode, |
8995 | doc: /* Table for translating characters while decoding. */); | |
f967223b | 8996 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 8997 | |
f967223b | 8998 | DEFVAR_LISP ("standard-translation-table-for-encode", |
48b0f3ae PJ |
8999 | &Vstandard_translation_table_for_encode, |
9000 | doc: /* Table for translating characters while encoding. */); | |
f967223b | 9001 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 9002 | |
df7492f9 | 9003 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table, |
48b0f3ae PJ |
9004 | doc: /* Alist of charsets vs revision numbers. |
9005 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
9006 | designate it with the escape sequence identifying revision (cdr part |
9007 | of the element). */); | |
9008 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
9009 | |
9010 | DEFVAR_LISP ("default-process-coding-system", | |
9011 | &Vdefault_process_coding_system, | |
48b0f3ae PJ |
9012 | doc: /* Cons of coding systems used for process I/O by default. |
9013 | The car part is used for decoding a process output, | |
9014 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 9015 | Vdefault_process_coding_system = Qnil; |
c4825358 | 9016 | |
3f003981 | 9017 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
df7492f9 KH |
9018 | doc: /* |
9019 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
9020 | This is a vector of length 256. |
9021 | If Nth element is non-nil, the existence of code N in a file | |
9022 | \(or output of subprocess) doesn't prevent it to be detected as | |
9023 | a coding system of ISO 2022 variant which has a flag | |
9024 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
9025 | or reading output of a subprocess. | |
9026 | Only 128th through 159th elements has a meaning. */); | |
3f003981 | 9027 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
9028 | |
9029 | DEFVAR_LISP ("select-safe-coding-system-function", | |
9030 | &Vselect_safe_coding_system_function, | |
df7492f9 KH |
9031 | doc: /* |
9032 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
9033 | |
9034 | If set, this function is called to force a user to select a proper | |
9035 | coding system which can encode the text in the case that a default | |
9036 | coding system used in each operation can't encode the text. | |
9037 | ||
9038 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
9039 | Vselect_safe_coding_system_function = Qnil; |
9040 | ||
5d5bf4d8 KH |
9041 | DEFVAR_BOOL ("coding-system-require-warning", |
9042 | &coding_system_require_warning, | |
9043 | doc: /* Internal use only. | |
6b89e3aa KH |
9044 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
9045 | called even if `coding-system-for-write' is non-nil. The command | |
9046 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
9047 | coding_system_require_warning = 0; |
9048 | ||
9049 | ||
22ab2303 | 9050 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
74383408 | 9051 | &inhibit_iso_escape_detection, |
df7492f9 KH |
9052 | doc: /* |
9053 | If non-nil, Emacs ignores ISO2022's escape sequence on code detection. | |
48b0f3ae PJ |
9054 | |
9055 | By default, on reading a file, Emacs tries to detect how the text is | |
9056 | encoded. This code detection is sensitive to escape sequences. If | |
9057 | the sequence is valid as ISO2022, the code is determined as one of | |
9058 | the ISO2022 encodings, and the file is decoded by the corresponding | |
9059 | coding system (e.g. `iso-2022-7bit'). | |
9060 | ||
9061 | However, there may be a case that you want to read escape sequences in | |
9062 | a file as is. In such a case, you can set this variable to non-nil. | |
9063 | Then, as the code detection ignores any escape sequences, no file is | |
9064 | detected as encoded in some ISO2022 encoding. The result is that all | |
9065 | escape sequences become visible in a buffer. | |
9066 | ||
9067 | The default value is nil, and it is strongly recommended not to change | |
9068 | it. That is because many Emacs Lisp source files that contain | |
9069 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
9070 | in Emacs's distribution, and they won't be decoded correctly on | |
9071 | reading if you suppress escape sequence detection. | |
9072 | ||
9073 | The other way to read escape sequences in a file without decoding is | |
9074 | to explicitly specify some coding system that doesn't use ISO2022's | |
9075 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); | |
74383408 | 9076 | inhibit_iso_escape_detection = 0; |
002fdb44 DL |
9077 | |
9078 | DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input, | |
15c8f9d1 DL |
9079 | doc: /* Char table for translating self-inserting characters. |
9080 | This is applied to the result of input methods, not their input. See also | |
9081 | `keyboard-translate-table'. */); | |
002fdb44 | 9082 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 9083 | |
2c78b7e1 KH |
9084 | { |
9085 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 9086 | Lisp_Object plist[16]; |
2c78b7e1 KH |
9087 | int i; |
9088 | ||
9089 | for (i = 0; i < coding_arg_max; i++) | |
9090 | args[i] = Qnil; | |
9091 | ||
9092 | plist[0] = intern (":name"); | |
9093 | plist[1] = args[coding_arg_name] = Qno_conversion; | |
9094 | plist[2] = intern (":mnemonic"); | |
9095 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); | |
9096 | plist[4] = intern (":coding-type"); | |
9097 | plist[5] = args[coding_arg_coding_type] = Qraw_text; | |
9098 | plist[6] = intern (":ascii-compatible-p"); | |
9099 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; | |
9100 | plist[8] = intern (":default-char"); | |
9101 | plist[9] = args[coding_arg_default_char] = make_number (0); | |
8f924df7 KH |
9102 | plist[10] = intern (":for-unibyte"); |
9103 | plist[11] = args[coding_arg_for_unibyte] = Qt; | |
9104 | plist[12] = intern (":docstring"); | |
9105 | plist[13] = build_string ("Do no conversion.\n\ | |
2c78b7e1 KH |
9106 | \n\ |
9107 | When you visit a file with this coding, the file is read into a\n\ | |
9108 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
9109 | character."); | |
8f924df7 KH |
9110 | plist[14] = intern (":eol-type"); |
9111 | plist[15] = args[coding_arg_eol_type] = Qunix; | |
9112 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 KH |
9113 | Fdefine_coding_system_internal (coding_arg_max, args); |
9114 | } | |
9115 | ||
9116 | setup_coding_system (Qno_conversion, &keyboard_coding); | |
9117 | setup_coding_system (Qno_conversion, &terminal_coding); | |
9118 | setup_coding_system (Qno_conversion, &safe_terminal_coding); | |
ff563fce KH |
9119 | |
9120 | { | |
9121 | int i; | |
9122 | ||
9123 | for (i = 0; i < coding_category_max; i++) | |
9124 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
9125 | } | |
4ed46869 KH |
9126 | } |
9127 | ||
68c45bf0 PE |
9128 | char * |
9129 | emacs_strerror (error_number) | |
9130 | int error_number; | |
9131 | { | |
9132 | char *str; | |
9133 | ||
ca9c0567 | 9134 | synchronize_system_messages_locale (); |
68c45bf0 PE |
9135 | str = strerror (error_number); |
9136 | ||
9137 | if (! NILP (Vlocale_coding_system)) | |
9138 | { | |
9139 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
9140 | Vlocale_coding_system, | |
9141 | 0); | |
d5db4077 | 9142 | str = (char *) SDATA (dec); |
68c45bf0 PE |
9143 | } |
9144 | ||
9145 | return str; | |
9146 | } | |
9147 | ||
4ed46869 | 9148 | #endif /* emacs */ |