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 | ||
065e3595 KH |
321 | Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source; |
322 | Lisp_Object Qinterrupted, Qinsufficient_memory; | |
323 | ||
5d5bf4d8 KH |
324 | int coding_system_require_warning; |
325 | ||
d46c5b12 KH |
326 | Lisp_Object Vselect_safe_coding_system_function; |
327 | ||
7722baf9 EZ |
328 | /* Mnemonic string for each format of end-of-line. */ |
329 | Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; | |
330 | /* Mnemonic string to indicate format of end-of-line is not yet | |
4ed46869 | 331 | decided. */ |
7722baf9 | 332 | Lisp_Object eol_mnemonic_undecided; |
4ed46869 KH |
333 | |
334 | #ifdef emacs | |
335 | ||
4608c386 KH |
336 | Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
337 | ||
338 | Lisp_Object Qcoding_system_p, Qcoding_system_error; | |
4ed46869 | 339 | |
d46c5b12 KH |
340 | /* Coding system emacs-mule and raw-text are for converting only |
341 | end-of-line format. */ | |
342 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 343 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 344 | |
4ed46869 KH |
345 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
346 | routines by the following three variables. */ | |
347 | /* Coding-system for reading files and receiving data from process. */ | |
348 | Lisp_Object Vcoding_system_for_read; | |
349 | /* Coding-system for writing files and sending data to process. */ | |
350 | Lisp_Object Vcoding_system_for_write; | |
351 | /* Coding-system actually used in the latest I/O. */ | |
352 | Lisp_Object Vlast_coding_system_used; | |
065e3595 KH |
353 | /* Set to non-nil when an error is detected while code conversion. */ |
354 | Lisp_Object Vlast_code_conversion_error; | |
c4825358 | 355 | /* A vector of length 256 which contains information about special |
94487c4e | 356 | Latin codes (especially for dealing with Microsoft codes). */ |
3f003981 | 357 | Lisp_Object Vlatin_extra_code_table; |
c4825358 | 358 | |
9ce27fde KH |
359 | /* Flag to inhibit code conversion of end-of-line format. */ |
360 | int inhibit_eol_conversion; | |
361 | ||
74383408 KH |
362 | /* Flag to inhibit ISO2022 escape sequence detection. */ |
363 | int inhibit_iso_escape_detection; | |
364 | ||
ed29121d EZ |
365 | /* Flag to make buffer-file-coding-system inherit from process-coding. */ |
366 | int inherit_process_coding_system; | |
367 | ||
c4825358 | 368 | /* Coding system to be used to encode text for terminal display. */ |
4ed46869 KH |
369 | struct coding_system terminal_coding; |
370 | ||
c4825358 KH |
371 | /* Coding system to be used to encode text for terminal display when |
372 | terminal coding system is nil. */ | |
373 | struct coding_system safe_terminal_coding; | |
374 | ||
375 | /* Coding system of what is sent from terminal keyboard. */ | |
4ed46869 KH |
376 | struct coding_system keyboard_coding; |
377 | ||
02ba4723 KH |
378 | Lisp_Object Vfile_coding_system_alist; |
379 | Lisp_Object Vprocess_coding_system_alist; | |
380 | Lisp_Object Vnetwork_coding_system_alist; | |
4ed46869 | 381 | |
68c45bf0 PE |
382 | Lisp_Object Vlocale_coding_system; |
383 | ||
4ed46869 KH |
384 | #endif /* emacs */ |
385 | ||
f967223b KH |
386 | /* Flag to tell if we look up translation table on character code |
387 | conversion. */ | |
84fbb8a0 | 388 | Lisp_Object Venable_character_translation; |
f967223b KH |
389 | /* Standard translation table to look up on decoding (reading). */ |
390 | Lisp_Object Vstandard_translation_table_for_decode; | |
391 | /* Standard translation table to look up on encoding (writing). */ | |
392 | Lisp_Object Vstandard_translation_table_for_encode; | |
84fbb8a0 | 393 | |
f967223b KH |
394 | Lisp_Object Qtranslation_table; |
395 | Lisp_Object Qtranslation_table_id; | |
396 | Lisp_Object Qtranslation_table_for_decode; | |
397 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 KH |
398 | |
399 | /* Alist of charsets vs revision number. */ | |
df7492f9 | 400 | static Lisp_Object Vcharset_revision_table; |
4ed46869 | 401 | |
02ba4723 KH |
402 | /* Default coding systems used for process I/O. */ |
403 | Lisp_Object Vdefault_process_coding_system; | |
404 | ||
002fdb44 DL |
405 | /* Char table for translating Quail and self-inserting input. */ |
406 | Lisp_Object Vtranslation_table_for_input; | |
407 | ||
df7492f9 KH |
408 | /* Two special coding systems. */ |
409 | Lisp_Object Vsjis_coding_system; | |
410 | Lisp_Object Vbig5_coding_system; | |
411 | ||
412 | ||
065e3595 KH |
413 | static void record_conversion_result (struct coding_system *coding, |
414 | enum coding_result_code result); | |
ff0dacd7 KH |
415 | static int detect_coding_utf_8 P_ ((struct coding_system *, |
416 | struct coding_detection_info *info)); | |
df7492f9 KH |
417 | static void decode_coding_utf_8 P_ ((struct coding_system *)); |
418 | static int encode_coding_utf_8 P_ ((struct coding_system *)); | |
419 | ||
ff0dacd7 KH |
420 | static int detect_coding_utf_16 P_ ((struct coding_system *, |
421 | struct coding_detection_info *info)); | |
df7492f9 KH |
422 | static void decode_coding_utf_16 P_ ((struct coding_system *)); |
423 | static int encode_coding_utf_16 P_ ((struct coding_system *)); | |
424 | ||
ff0dacd7 KH |
425 | static int detect_coding_iso_2022 P_ ((struct coding_system *, |
426 | struct coding_detection_info *info)); | |
df7492f9 KH |
427 | static void decode_coding_iso_2022 P_ ((struct coding_system *)); |
428 | static int encode_coding_iso_2022 P_ ((struct coding_system *)); | |
429 | ||
ff0dacd7 KH |
430 | static int detect_coding_emacs_mule P_ ((struct coding_system *, |
431 | struct coding_detection_info *info)); | |
df7492f9 KH |
432 | static void decode_coding_emacs_mule P_ ((struct coding_system *)); |
433 | static int encode_coding_emacs_mule P_ ((struct coding_system *)); | |
434 | ||
ff0dacd7 KH |
435 | static int detect_coding_sjis P_ ((struct coding_system *, |
436 | struct coding_detection_info *info)); | |
df7492f9 KH |
437 | static void decode_coding_sjis P_ ((struct coding_system *)); |
438 | static int encode_coding_sjis P_ ((struct coding_system *)); | |
439 | ||
ff0dacd7 KH |
440 | static int detect_coding_big5 P_ ((struct coding_system *, |
441 | struct coding_detection_info *info)); | |
df7492f9 KH |
442 | static void decode_coding_big5 P_ ((struct coding_system *)); |
443 | static int encode_coding_big5 P_ ((struct coding_system *)); | |
444 | ||
ff0dacd7 KH |
445 | static int detect_coding_ccl P_ ((struct coding_system *, |
446 | struct coding_detection_info *info)); | |
df7492f9 KH |
447 | static void decode_coding_ccl P_ ((struct coding_system *)); |
448 | static int encode_coding_ccl P_ ((struct coding_system *)); | |
449 | ||
450 | static void decode_coding_raw_text P_ ((struct coding_system *)); | |
451 | static int encode_coding_raw_text P_ ((struct coding_system *)); | |
452 | ||
453 | ||
454 | /* ISO2022 section */ | |
455 | ||
456 | #define CODING_ISO_INITIAL(coding, reg) \ | |
457 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
458 | coding_attr_iso_initial), \ | |
459 | reg))) | |
460 | ||
461 | ||
462 | #define CODING_ISO_REQUEST(coding, charset_id) \ | |
463 | ((charset_id <= (coding)->max_charset_id \ | |
464 | ? (coding)->safe_charsets[charset_id] \ | |
465 | : -1)) | |
466 | ||
467 | ||
468 | #define CODING_ISO_FLAGS(coding) \ | |
469 | ((coding)->spec.iso_2022.flags) | |
470 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
471 | ((coding)->spec.iso_2022.current_designation[reg]) | |
472 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
473 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
474 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
475 | ((coding)->spec.iso_2022.single_shifting) | |
476 | #define CODING_ISO_BOL(coding) \ | |
477 | ((coding)->spec.iso_2022.bol) | |
478 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
479 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
480 | ||
481 | /* Control characters of ISO2022. */ | |
482 | /* code */ /* function */ | |
483 | #define ISO_CODE_LF 0x0A /* line-feed */ | |
484 | #define ISO_CODE_CR 0x0D /* carriage-return */ | |
485 | #define ISO_CODE_SO 0x0E /* shift-out */ | |
486 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
487 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
488 | #define ISO_CODE_ESC 0x1B /* escape */ | |
489 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
490 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
491 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
492 | ||
493 | /* All code (1-byte) of ISO2022 is classified into one of the | |
494 | followings. */ | |
495 | enum iso_code_class_type | |
496 | { | |
497 | ISO_control_0, /* Control codes in the range | |
498 | 0x00..0x1F and 0x7F, except for the | |
499 | following 5 codes. */ | |
df7492f9 KH |
500 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
501 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
502 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
503 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
504 | ISO_control_1, /* Control codes in the range | |
505 | 0x80..0x9F, except for the | |
506 | following 3 codes. */ | |
507 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
508 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
509 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
510 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
511 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
512 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
513 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
514 | }; | |
05e6f5dc | 515 | |
df7492f9 KH |
516 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
517 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 518 | |
df7492f9 KH |
519 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
520 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
521 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 522 | |
df7492f9 KH |
523 | /* If set, reset graphic planes and registers at end-of-line to the |
524 | initial state. */ | |
525 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 526 | |
df7492f9 KH |
527 | /* If set, reset graphic planes and registers before any control |
528 | characters to the initial state. */ | |
529 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 530 | |
df7492f9 KH |
531 | /* If set, encode by 7-bit environment. */ |
532 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 533 | |
df7492f9 KH |
534 | /* If set, use locking-shift function. */ |
535 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 536 | |
df7492f9 KH |
537 | /* If set, use single-shift function. Overwrite |
538 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
539 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 540 | |
df7492f9 KH |
541 | /* If set, use designation escape sequence. */ |
542 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 543 | |
df7492f9 KH |
544 | /* If set, produce revision number sequence. */ |
545 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 546 | |
df7492f9 KH |
547 | /* If set, produce ISO6429's direction specifying sequence. */ |
548 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 549 | |
df7492f9 KH |
550 | /* If set, assume designation states are reset at beginning of line on |
551 | output. */ | |
552 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 553 | |
df7492f9 KH |
554 | /* If set, designation sequence should be placed at beginning of line |
555 | on output. */ | |
556 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 557 | |
df7492f9 KH |
558 | /* If set, do not encode unsafe charactes on output. */ |
559 | #define CODING_ISO_FLAG_SAFE 0x0800 | |
aa72b389 | 560 | |
df7492f9 KH |
561 | /* If set, extra latin codes (128..159) are accepted as a valid code |
562 | on input. */ | |
563 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 564 | |
df7492f9 | 565 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 566 | |
df7492f9 | 567 | #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 |
aa72b389 | 568 | |
bf16eb23 | 569 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 570 | |
bf16eb23 | 571 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 572 | |
bf16eb23 | 573 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 574 | |
df7492f9 KH |
575 | /* A character to be produced on output if encoding of the original |
576 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
577 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 578 | |
4ed46869 | 579 | |
df7492f9 KH |
580 | /* UTF-16 section */ |
581 | #define CODING_UTF_16_BOM(coding) \ | |
582 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 583 | |
df7492f9 KH |
584 | #define CODING_UTF_16_ENDIAN(coding) \ |
585 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 586 | |
df7492f9 KH |
587 | #define CODING_UTF_16_SURROGATE(coding) \ |
588 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 589 | |
4ed46869 | 590 | |
df7492f9 KH |
591 | /* CCL section */ |
592 | #define CODING_CCL_DECODER(coding) \ | |
593 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
594 | #define CODING_CCL_ENCODER(coding) \ | |
595 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
596 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 597 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 598 | |
5a936b46 | 599 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 600 | |
df7492f9 KH |
601 | enum coding_category |
602 | { | |
603 | coding_category_iso_7, | |
604 | coding_category_iso_7_tight, | |
605 | coding_category_iso_8_1, | |
606 | coding_category_iso_8_2, | |
607 | coding_category_iso_7_else, | |
608 | coding_category_iso_8_else, | |
609 | coding_category_utf_8, | |
610 | coding_category_utf_16_auto, | |
611 | coding_category_utf_16_be, | |
612 | coding_category_utf_16_le, | |
613 | coding_category_utf_16_be_nosig, | |
614 | coding_category_utf_16_le_nosig, | |
615 | coding_category_charset, | |
616 | coding_category_sjis, | |
617 | coding_category_big5, | |
618 | coding_category_ccl, | |
619 | coding_category_emacs_mule, | |
620 | /* All above are targets of code detection. */ | |
621 | coding_category_raw_text, | |
622 | coding_category_undecided, | |
623 | coding_category_max | |
624 | }; | |
625 | ||
626 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
627 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
628 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
629 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
630 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
631 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
632 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
633 | #define CATEGORY_MASK_UTF_8 (1 << coding_category_utf_8) | |
b49a1807 | 634 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
635 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
636 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
637 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
638 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
639 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
640 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
641 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
642 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
643 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 644 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
645 | |
646 | /* This value is returned if detect_coding_mask () find nothing other | |
647 | than ASCII characters. */ | |
648 | #define CATEGORY_MASK_ANY \ | |
649 | (CATEGORY_MASK_ISO_7 \ | |
650 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
651 | | CATEGORY_MASK_ISO_8_1 \ | |
652 | | CATEGORY_MASK_ISO_8_2 \ | |
653 | | CATEGORY_MASK_ISO_7_ELSE \ | |
654 | | CATEGORY_MASK_ISO_8_ELSE \ | |
655 | | CATEGORY_MASK_UTF_8 \ | |
656 | | CATEGORY_MASK_UTF_16_BE \ | |
657 | | CATEGORY_MASK_UTF_16_LE \ | |
658 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
659 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
660 | | CATEGORY_MASK_CHARSET \ | |
661 | | CATEGORY_MASK_SJIS \ | |
662 | | CATEGORY_MASK_BIG5 \ | |
663 | | CATEGORY_MASK_CCL \ | |
664 | | CATEGORY_MASK_EMACS_MULE) | |
665 | ||
666 | ||
667 | #define CATEGORY_MASK_ISO_7BIT \ | |
668 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
669 | ||
670 | #define CATEGORY_MASK_ISO_8BIT \ | |
671 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
672 | ||
673 | #define CATEGORY_MASK_ISO_ELSE \ | |
674 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
675 | ||
676 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
677 | (CATEGORY_MASK_ISO_7 \ | |
678 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
679 | | CATEGORY_MASK_ISO_7_ELSE \ | |
680 | | CATEGORY_MASK_ISO_8_ELSE) | |
681 | ||
682 | #define CATEGORY_MASK_ISO \ | |
683 | ( CATEGORY_MASK_ISO_7BIT \ | |
684 | | CATEGORY_MASK_ISO_8BIT \ | |
685 | | CATEGORY_MASK_ISO_ELSE) | |
686 | ||
687 | #define CATEGORY_MASK_UTF_16 \ | |
688 | (CATEGORY_MASK_UTF_16_BE \ | |
689 | | CATEGORY_MASK_UTF_16_LE \ | |
690 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
691 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
692 | ||
693 | ||
694 | /* List of symbols `coding-category-xxx' ordered by priority. This | |
695 | variable is exposed to Emacs Lisp. */ | |
696 | static Lisp_Object Vcoding_category_list; | |
697 | ||
698 | /* Table of coding categories (Lisp symbols). This variable is for | |
699 | internal use oly. */ | |
700 | static Lisp_Object Vcoding_category_table; | |
701 | ||
702 | /* Table of coding-categories ordered by priority. */ | |
703 | static enum coding_category coding_priorities[coding_category_max]; | |
704 | ||
705 | /* Nth element is a coding context for the coding system bound to the | |
706 | Nth coding category. */ | |
707 | static struct coding_system coding_categories[coding_category_max]; | |
708 | ||
df7492f9 KH |
709 | /*** Commonly used macros and functions ***/ |
710 | ||
711 | #ifndef min | |
712 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
713 | #endif | |
714 | #ifndef max | |
715 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
716 | #endif | |
4ed46869 | 717 | |
24a73b0a KH |
718 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
719 | do { \ | |
720 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
721 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 722 | } while (0) |
4ed46869 | 723 | |
4ed46869 | 724 | |
df7492f9 KH |
725 | /* Safely get one byte from the source text pointed by SRC which ends |
726 | at SRC_END, and set C to that byte. If there are not enough bytes | |
065e3595 KH |
727 | in the source, it jumps to `no_more_source'. If multibytep is |
728 | nonzero, and a multibyte character is found at SRC, set C to the | |
729 | negative value of the character code. The caller should declare | |
730 | and set these variables appropriately in advance: | |
731 | src, src_end, multibytep */ | |
aa72b389 | 732 | |
065e3595 KH |
733 | #define ONE_MORE_BYTE(c) \ |
734 | do { \ | |
735 | if (src == src_end) \ | |
736 | { \ | |
737 | if (src_base < src) \ | |
738 | record_conversion_result \ | |
739 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
740 | goto no_more_source; \ | |
741 | } \ | |
742 | c = *src++; \ | |
743 | if (multibytep && (c & 0x80)) \ | |
744 | { \ | |
745 | if ((c & 0xFE) == 0xC0) \ | |
746 | c = ((c & 1) << 6) | *src++; \ | |
747 | else \ | |
748 | { \ | |
749 | c = - string_char (--src, &src, NULL); \ | |
750 | record_conversion_result \ | |
751 | (coding, CODING_RESULT_INVALID_SRC); \ | |
752 | } \ | |
753 | } \ | |
754 | consumed_chars++; \ | |
aa72b389 KH |
755 | } while (0) |
756 | ||
aa72b389 | 757 | |
065e3595 KH |
758 | #define ONE_MORE_BYTE_NO_CHECK(c) \ |
759 | do { \ | |
760 | c = *src++; \ | |
761 | if (multibytep && (c & 0x80)) \ | |
762 | { \ | |
763 | if ((c & 0xFE) == 0xC0) \ | |
764 | c = ((c & 1) << 6) | *src++; \ | |
765 | else \ | |
766 | { \ | |
767 | c = - string_char (--src, &src, NULL); \ | |
768 | record_conversion_result \ | |
769 | (coding, CODING_RESULT_INVALID_SRC); \ | |
770 | } \ | |
771 | } \ | |
772 | consumed_chars++; \ | |
aa72b389 KH |
773 | } while (0) |
774 | ||
aa72b389 | 775 | |
df7492f9 KH |
776 | /* Store a byte C in the place pointed by DST and increment DST to the |
777 | next free point, and increment PRODUCED_CHARS. The caller should | |
778 | assure that C is 0..127, and declare and set the variable `dst' | |
779 | appropriately in advance. | |
780 | */ | |
aa72b389 KH |
781 | |
782 | ||
df7492f9 KH |
783 | #define EMIT_ONE_ASCII_BYTE(c) \ |
784 | do { \ | |
785 | produced_chars++; \ | |
786 | *dst++ = (c); \ | |
b6871cc7 | 787 | } while (0) |
aa72b389 KH |
788 | |
789 | ||
df7492f9 | 790 | /* Like EMIT_ONE_ASCII_BYTE byt store two bytes; C1 and C2. */ |
aa72b389 | 791 | |
df7492f9 KH |
792 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
793 | do { \ | |
794 | produced_chars += 2; \ | |
795 | *dst++ = (c1), *dst++ = (c2); \ | |
796 | } while (0) | |
aa72b389 KH |
797 | |
798 | ||
df7492f9 KH |
799 | /* Store a byte C in the place pointed by DST and increment DST to the |
800 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is | |
801 | nonzero, store in an appropriate multibyte from. The caller should | |
802 | declare and set the variables `dst' and `multibytep' appropriately | |
803 | in advance. */ | |
804 | ||
805 | #define EMIT_ONE_BYTE(c) \ | |
806 | do { \ | |
807 | produced_chars++; \ | |
808 | if (multibytep) \ | |
809 | { \ | |
810 | int ch = (c); \ | |
811 | if (ch >= 0x80) \ | |
812 | ch = BYTE8_TO_CHAR (ch); \ | |
813 | CHAR_STRING_ADVANCE (ch, dst); \ | |
814 | } \ | |
815 | else \ | |
816 | *dst++ = (c); \ | |
aa72b389 | 817 | } while (0) |
aa72b389 | 818 | |
aa72b389 | 819 | |
df7492f9 | 820 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 821 | |
e19c3639 KH |
822 | #define EMIT_TWO_BYTES(c1, c2) \ |
823 | do { \ | |
824 | produced_chars += 2; \ | |
825 | if (multibytep) \ | |
826 | { \ | |
827 | int ch; \ | |
828 | \ | |
829 | ch = (c1); \ | |
830 | if (ch >= 0x80) \ | |
831 | ch = BYTE8_TO_CHAR (ch); \ | |
832 | CHAR_STRING_ADVANCE (ch, dst); \ | |
833 | ch = (c2); \ | |
834 | if (ch >= 0x80) \ | |
835 | ch = BYTE8_TO_CHAR (ch); \ | |
836 | CHAR_STRING_ADVANCE (ch, dst); \ | |
837 | } \ | |
838 | else \ | |
839 | { \ | |
840 | *dst++ = (c1); \ | |
841 | *dst++ = (c2); \ | |
842 | } \ | |
aa72b389 KH |
843 | } while (0) |
844 | ||
845 | ||
df7492f9 KH |
846 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
847 | do { \ | |
848 | EMIT_ONE_BYTE (c1); \ | |
849 | EMIT_TWO_BYTES (c2, c3); \ | |
850 | } while (0) | |
aa72b389 | 851 | |
aa72b389 | 852 | |
df7492f9 KH |
853 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
854 | do { \ | |
855 | EMIT_TWO_BYTES (c1, c2); \ | |
856 | EMIT_TWO_BYTES (c3, c4); \ | |
857 | } while (0) | |
aa72b389 | 858 | |
aa72b389 | 859 | |
065e3595 KH |
860 | static void |
861 | record_conversion_result (struct coding_system *coding, | |
862 | enum coding_result_code result) | |
863 | { | |
864 | coding->result = result; | |
865 | switch (result) | |
866 | { | |
867 | case CODING_RESULT_INSUFFICIENT_SRC: | |
868 | Vlast_code_conversion_error = Qinsufficient_source; | |
869 | break; | |
870 | case CODING_RESULT_INCONSISTENT_EOL: | |
871 | Vlast_code_conversion_error = Qinconsistent_eol; | |
872 | break; | |
873 | case CODING_RESULT_INVALID_SRC: | |
874 | Vlast_code_conversion_error = Qinvalid_source; | |
875 | break; | |
876 | case CODING_RESULT_INTERRUPT: | |
877 | Vlast_code_conversion_error = Qinterrupted; | |
878 | break; | |
879 | case CODING_RESULT_INSUFFICIENT_MEM: | |
880 | Vlast_code_conversion_error = Qinsufficient_memory; | |
881 | break; | |
882 | } | |
883 | } | |
884 | ||
df7492f9 KH |
885 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
886 | do { \ | |
887 | charset_map_loaded = 0; \ | |
888 | c = DECODE_CHAR (charset, code); \ | |
889 | if (charset_map_loaded) \ | |
890 | { \ | |
8f924df7 | 891 | const unsigned char *orig = coding->source; \ |
df7492f9 KH |
892 | EMACS_INT offset; \ |
893 | \ | |
894 | coding_set_source (coding); \ | |
895 | offset = coding->source - orig; \ | |
896 | src += offset; \ | |
897 | src_base += offset; \ | |
898 | src_end += offset; \ | |
899 | } \ | |
aa72b389 KH |
900 | } while (0) |
901 | ||
902 | ||
df7492f9 KH |
903 | #define ASSURE_DESTINATION(bytes) \ |
904 | do { \ | |
905 | if (dst + (bytes) >= dst_end) \ | |
906 | { \ | |
907 | int more_bytes = charbuf_end - charbuf + (bytes); \ | |
908 | \ | |
909 | dst = alloc_destination (coding, more_bytes, dst); \ | |
910 | dst_end = coding->destination + coding->dst_bytes; \ | |
911 | } \ | |
912 | } while (0) | |
aa72b389 | 913 | |
aa72b389 | 914 | |
aa72b389 | 915 | |
df7492f9 KH |
916 | static void |
917 | coding_set_source (coding) | |
aa72b389 | 918 | struct coding_system *coding; |
aa72b389 | 919 | { |
df7492f9 KH |
920 | if (BUFFERP (coding->src_object)) |
921 | { | |
2cb26057 | 922 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 923 | |
df7492f9 | 924 | if (coding->src_pos < 0) |
2cb26057 | 925 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 926 | else |
2cb26057 | 927 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 928 | } |
df7492f9 | 929 | else if (STRINGP (coding->src_object)) |
aa72b389 | 930 | { |
8f924df7 | 931 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 932 | } |
df7492f9 KH |
933 | else |
934 | /* Otherwise, the source is C string and is never relocated | |
935 | automatically. Thus we don't have to update anything. */ | |
936 | ; | |
937 | } | |
aa72b389 | 938 | |
df7492f9 KH |
939 | static void |
940 | coding_set_destination (coding) | |
941 | struct coding_system *coding; | |
942 | { | |
943 | if (BUFFERP (coding->dst_object)) | |
aa72b389 | 944 | { |
df7492f9 | 945 | if (coding->src_pos < 0) |
aa72b389 | 946 | { |
28f67a95 KH |
947 | coding->destination = BEG_ADDR + coding->dst_pos_byte - 1; |
948 | coding->dst_bytes = (GAP_END_ADDR | |
949 | - (coding->src_bytes - coding->consumed) | |
950 | - coding->destination); | |
aa72b389 | 951 | } |
df7492f9 | 952 | else |
28f67a95 KH |
953 | { |
954 | /* We are sure that coding->dst_pos_byte is before the gap | |
955 | of the buffer. */ | |
956 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
957 | + coding->dst_pos_byte - 1); | |
958 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) | |
959 | - coding->destination); | |
960 | } | |
df7492f9 KH |
961 | } |
962 | else | |
963 | /* Otherwise, the destination is C string and is never relocated | |
964 | automatically. Thus we don't have to update anything. */ | |
965 | ; | |
966 | } | |
967 | ||
968 | ||
969 | static void | |
970 | coding_alloc_by_realloc (coding, bytes) | |
971 | struct coding_system *coding; | |
972 | EMACS_INT bytes; | |
973 | { | |
974 | coding->destination = (unsigned char *) xrealloc (coding->destination, | |
975 | coding->dst_bytes + bytes); | |
976 | coding->dst_bytes += bytes; | |
977 | } | |
978 | ||
979 | static void | |
980 | coding_alloc_by_making_gap (coding, bytes) | |
981 | struct coding_system *coding; | |
982 | EMACS_INT bytes; | |
983 | { | |
2c78b7e1 KH |
984 | if (BUFFERP (coding->dst_object) |
985 | && EQ (coding->src_object, coding->dst_object)) | |
df7492f9 KH |
986 | { |
987 | EMACS_INT add = coding->src_bytes - coding->consumed; | |
988 | ||
989 | GAP_SIZE -= add; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
990 | make_gap (bytes); | |
991 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
992 | } | |
993 | else | |
994 | { | |
2c78b7e1 KH |
995 | Lisp_Object this_buffer; |
996 | ||
997 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
998 | set_buffer_internal (XBUFFER (coding->dst_object)); |
999 | make_gap (bytes); | |
1000 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 1001 | } |
df7492f9 | 1002 | } |
8f924df7 | 1003 | |
df7492f9 KH |
1004 | |
1005 | static unsigned char * | |
1006 | alloc_destination (coding, nbytes, dst) | |
1007 | struct coding_system *coding; | |
3e139625 | 1008 | EMACS_INT nbytes; |
df7492f9 KH |
1009 | unsigned char *dst; |
1010 | { | |
1011 | EMACS_INT offset = dst - coding->destination; | |
1012 | ||
1013 | if (BUFFERP (coding->dst_object)) | |
1014 | coding_alloc_by_making_gap (coding, nbytes); | |
aa72b389 | 1015 | else |
df7492f9 | 1016 | coding_alloc_by_realloc (coding, nbytes); |
065e3595 | 1017 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1018 | coding_set_destination (coding); |
1019 | dst = coding->destination + offset; | |
1020 | return dst; | |
1021 | } | |
aa72b389 | 1022 | |
ff0dacd7 KH |
1023 | /** Macros for annotations. */ |
1024 | ||
1025 | /* Maximum length of annotation data (sum of annotations for | |
1026 | composition and charset). */ | |
1027 | #define MAX_ANNOTATION_LENGTH (5 + (MAX_COMPOSITION_COMPONENTS * 2) - 1 + 5) | |
1028 | ||
1029 | /* An annotation data is stored in the array coding->charbuf in this | |
1030 | format: | |
1031 | [ -LENGTH ANNOTATION_MASK FROM TO ... ] | |
1032 | LENGTH is the number of elements in the annotation. | |
1033 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
1034 | FROM and TO specify the range of text annotated. They are relative | |
1035 | to coding->src_pos (on encoding) or coding->dst_pos (on decoding). | |
1036 | ||
1037 | The format of the following elements depend on ANNOTATION_MASK. | |
1038 | ||
1039 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1040 | follows: | |
1041 | ... METHOD [ COMPOSITION-COMPONENTS ... ] | |
1042 | METHOD is one of enum composition_method. | |
1043 | Optionnal COMPOSITION-COMPONENTS are characters and composition | |
1044 | rules. | |
1045 | ||
1046 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
1047 | follows. */ | |
1048 | ||
1049 | #define ADD_ANNOTATION_DATA(buf, len, mask, from, to) \ | |
1050 | do { \ | |
1051 | *(buf)++ = -(len); \ | |
1052 | *(buf)++ = (mask); \ | |
1053 | *(buf)++ = (from); \ | |
1054 | *(buf)++ = (to); \ | |
1055 | coding->annotated = 1; \ | |
1056 | } while (0); | |
1057 | ||
1058 | #define ADD_COMPOSITION_DATA(buf, from, to, method) \ | |
1059 | do { \ | |
1060 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, from, to); \ | |
1061 | *buf++ = method; \ | |
1062 | } while (0) | |
1063 | ||
1064 | ||
1065 | #define ADD_CHARSET_DATA(buf, from, to, id) \ | |
1066 | do { \ | |
1067 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_CHARSET_MASK, from, to); \ | |
1068 | *buf++ = id; \ | |
1069 | } while (0) | |
1070 | ||
df7492f9 KH |
1071 | \f |
1072 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1073 | ||
1074 | ||
1075 | ||
1076 | \f | |
1077 | /*** 3. UTF-8 ***/ | |
1078 | ||
1079 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1080 | Check if a text is encoded in UTF-8. If it is, return 1, else |
1081 | return 0. */ | |
df7492f9 KH |
1082 | |
1083 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1084 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1085 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1086 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1087 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1088 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1089 | ||
1090 | static int | |
ff0dacd7 | 1091 | detect_coding_utf_8 (coding, detect_info) |
df7492f9 | 1092 | struct coding_system *coding; |
ff0dacd7 | 1093 | struct coding_detection_info *detect_info; |
df7492f9 | 1094 | { |
065e3595 | 1095 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1096 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1097 | int multibytep = coding->src_multibyte; |
1098 | int consumed_chars = 0; | |
1099 | int found = 0; | |
1100 | ||
ff0dacd7 | 1101 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1102 | /* A coding system of this category is always ASCII compatible. */ |
1103 | src += coding->head_ascii; | |
1104 | ||
1105 | while (1) | |
aa72b389 | 1106 | { |
df7492f9 | 1107 | int c, c1, c2, c3, c4; |
aa72b389 | 1108 | |
065e3595 | 1109 | src_base = src; |
df7492f9 | 1110 | ONE_MORE_BYTE (c); |
065e3595 | 1111 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1112 | continue; |
1113 | ONE_MORE_BYTE (c1); | |
065e3595 | 1114 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1115 | break; |
1116 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1117 | { |
ff0dacd7 | 1118 | found = CATEGORY_MASK_UTF_8; |
df7492f9 | 1119 | continue; |
aa72b389 | 1120 | } |
df7492f9 | 1121 | ONE_MORE_BYTE (c2); |
065e3595 | 1122 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1123 | break; |
1124 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1125 | { |
ff0dacd7 | 1126 | found = CATEGORY_MASK_UTF_8; |
df7492f9 | 1127 | continue; |
aa72b389 | 1128 | } |
df7492f9 | 1129 | ONE_MORE_BYTE (c3); |
065e3595 | 1130 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1131 | break; |
1132 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1133 | { |
ff0dacd7 | 1134 | found = CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1135 | continue; |
1136 | } | |
1137 | ONE_MORE_BYTE (c4); | |
065e3595 | 1138 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1139 | break; |
1140 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1141 | { | |
ff0dacd7 | 1142 | found = CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1143 | continue; |
1144 | } | |
1145 | break; | |
aa72b389 | 1146 | } |
ff0dacd7 | 1147 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1148 | return 0; |
aa72b389 | 1149 | |
df7492f9 | 1150 | no_more_source: |
065e3595 | 1151 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1152 | { |
ff0dacd7 | 1153 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1154 | return 0; |
aa72b389 | 1155 | } |
ff0dacd7 KH |
1156 | detect_info->found |= found; |
1157 | return 1; | |
aa72b389 KH |
1158 | } |
1159 | ||
4ed46869 | 1160 | |
b73bfc1c | 1161 | static void |
df7492f9 | 1162 | decode_coding_utf_8 (coding) |
b73bfc1c | 1163 | struct coding_system *coding; |
b73bfc1c | 1164 | { |
8f924df7 KH |
1165 | const unsigned char *src = coding->source + coding->consumed; |
1166 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1167 | const unsigned char *src_base; | |
df7492f9 KH |
1168 | int *charbuf = coding->charbuf; |
1169 | int *charbuf_end = charbuf + coding->charbuf_size; | |
1170 | int consumed_chars = 0, consumed_chars_base; | |
1171 | int multibytep = coding->src_multibyte; | |
24a73b0a | 1172 | Lisp_Object attr, charset_list; |
4ed46869 | 1173 | |
24a73b0a | 1174 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 KH |
1175 | |
1176 | while (1) | |
b73bfc1c | 1177 | { |
df7492f9 | 1178 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1179 | |
df7492f9 KH |
1180 | src_base = src; |
1181 | consumed_chars_base = consumed_chars; | |
4af310db | 1182 | |
df7492f9 KH |
1183 | if (charbuf >= charbuf_end) |
1184 | break; | |
1185 | ||
1186 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1187 | if (c1 < 0) |
1188 | { | |
1189 | c = - c1; | |
1190 | } | |
1191 | else if (UTF_8_1_OCTET_P(c1)) | |
df7492f9 KH |
1192 | { |
1193 | c = c1; | |
4af310db | 1194 | } |
df7492f9 | 1195 | else |
4af310db | 1196 | { |
df7492f9 | 1197 | ONE_MORE_BYTE (c2); |
065e3595 | 1198 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1199 | goto invalid_code; |
1200 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1201 | { |
b0edb2c5 DL |
1202 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1203 | /* Reject overlong sequences here and below. Encoders | |
1204 | producing them are incorrect, they can be misleading, | |
1205 | and they mess up read/write invariance. */ | |
1206 | if (c < 128) | |
1207 | goto invalid_code; | |
4af310db | 1208 | } |
df7492f9 | 1209 | else |
aa72b389 | 1210 | { |
df7492f9 | 1211 | ONE_MORE_BYTE (c3); |
065e3595 | 1212 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1213 | goto invalid_code; |
1214 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1215 | { |
1216 | c = (((c1 & 0xF) << 12) | |
1217 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1218 | if (c < 0x800 |
1219 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1220 | goto invalid_code; |
1221 | } | |
df7492f9 KH |
1222 | else |
1223 | { | |
1224 | ONE_MORE_BYTE (c4); | |
065e3595 | 1225 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1226 | goto invalid_code; |
1227 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1228 | { |
df7492f9 KH |
1229 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1230 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1231 | if (c < 0x10000) |
1232 | goto invalid_code; | |
1233 | } | |
df7492f9 KH |
1234 | else |
1235 | { | |
1236 | ONE_MORE_BYTE (c5); | |
065e3595 | 1237 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1238 | goto invalid_code; |
1239 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1240 | { | |
1241 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1242 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1243 | | (c5 & 0x3F)); | |
b0edb2c5 | 1244 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1245 | goto invalid_code; |
1246 | } | |
1247 | else | |
1248 | goto invalid_code; | |
1249 | } | |
1250 | } | |
aa72b389 | 1251 | } |
b73bfc1c | 1252 | } |
df7492f9 KH |
1253 | |
1254 | *charbuf++ = c; | |
1255 | continue; | |
1256 | ||
1257 | invalid_code: | |
1258 | src = src_base; | |
1259 | consumed_chars = consumed_chars_base; | |
1260 | ONE_MORE_BYTE (c); | |
1261 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1262 | coding->errors++; | |
aa72b389 KH |
1263 | } |
1264 | ||
df7492f9 KH |
1265 | no_more_source: |
1266 | coding->consumed_char += consumed_chars_base; | |
1267 | coding->consumed = src_base - coding->source; | |
1268 | coding->charbuf_used = charbuf - coding->charbuf; | |
1269 | } | |
1270 | ||
1271 | ||
1272 | static int | |
1273 | encode_coding_utf_8 (coding) | |
1274 | struct coding_system *coding; | |
1275 | { | |
1276 | int multibytep = coding->dst_multibyte; | |
1277 | int *charbuf = coding->charbuf; | |
1278 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1279 | unsigned char *dst = coding->destination + coding->produced; | |
1280 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
e19c3639 | 1281 | int produced_chars = 0; |
df7492f9 KH |
1282 | int c; |
1283 | ||
1284 | if (multibytep) | |
aa72b389 | 1285 | { |
df7492f9 KH |
1286 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1287 | ||
1288 | while (charbuf < charbuf_end) | |
b73bfc1c | 1289 | { |
df7492f9 | 1290 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1291 | |
df7492f9 KH |
1292 | ASSURE_DESTINATION (safe_room); |
1293 | c = *charbuf++; | |
28f67a95 KH |
1294 | if (CHAR_BYTE8_P (c)) |
1295 | { | |
1296 | c = CHAR_TO_BYTE8 (c); | |
1297 | EMIT_ONE_BYTE (c); | |
1298 | } | |
1299 | else | |
1300 | { | |
1301 | CHAR_STRING_ADVANCE (c, pend); | |
1302 | for (p = str; p < pend; p++) | |
1303 | EMIT_ONE_BYTE (*p); | |
1304 | } | |
b73bfc1c | 1305 | } |
aa72b389 | 1306 | } |
df7492f9 KH |
1307 | else |
1308 | { | |
1309 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1310 | ||
1311 | while (charbuf < charbuf_end) | |
b73bfc1c | 1312 | { |
df7492f9 KH |
1313 | ASSURE_DESTINATION (safe_room); |
1314 | c = *charbuf++; | |
1315 | dst += CHAR_STRING (c, dst); | |
1316 | produced_chars++; | |
4ed46869 KH |
1317 | } |
1318 | } | |
065e3595 | 1319 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1320 | coding->produced_char += produced_chars; |
1321 | coding->produced = dst - coding->destination; | |
1322 | return 0; | |
4ed46869 KH |
1323 | } |
1324 | ||
b73bfc1c | 1325 | |
df7492f9 | 1326 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
1327 | Check if a text is encoded in one of UTF-16 based coding systems. |
1328 | If it is, return 1, else return 0. */ | |
aa72b389 | 1329 | |
df7492f9 KH |
1330 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1331 | (((val) & 0xFC00) == 0xD800) | |
1332 | ||
1333 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1334 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1335 | |
df7492f9 KH |
1336 | #define UTF_16_INVALID_P(val) \ |
1337 | (((val) == 0xFFFE) \ | |
1338 | || ((val) == 0xFFFF) \ | |
1339 | || UTF_16_LOW_SURROGATE_P (val)) | |
aa72b389 | 1340 | |
aa72b389 | 1341 | |
df7492f9 | 1342 | static int |
ff0dacd7 | 1343 | detect_coding_utf_16 (coding, detect_info) |
aa72b389 | 1344 | struct coding_system *coding; |
ff0dacd7 | 1345 | struct coding_detection_info *detect_info; |
aa72b389 | 1346 | { |
8f924df7 KH |
1347 | const unsigned char *src = coding->source, *src_base = src; |
1348 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
1349 | int multibytep = coding->src_multibyte; |
1350 | int consumed_chars = 0; | |
1351 | int c1, c2; | |
aa72b389 | 1352 | |
ff0dacd7 | 1353 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1354 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1355 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1356 | { |
1357 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1358 | return 0; | |
1359 | } | |
24a73b0a | 1360 | |
df7492f9 KH |
1361 | ONE_MORE_BYTE (c1); |
1362 | ONE_MORE_BYTE (c2); | |
df7492f9 | 1363 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1364 | { |
b49a1807 KH |
1365 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1366 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1367 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1368 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1369 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1370 | } |
df7492f9 | 1371 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1372 | { |
b49a1807 KH |
1373 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1374 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1375 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1376 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1377 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1378 | } | |
065e3595 | 1379 | else if (c1 >= 0 && c2 >= 0) |
24a73b0a KH |
1380 | { |
1381 | unsigned char b1[256], b2[256]; | |
1382 | int b1_variants = 1, b2_variants = 1; | |
1383 | int n; | |
1384 | ||
1385 | bzero (b1, 256), bzero (b2, 256); | |
1386 | b1[c1]++, b2[c2]++; | |
1387 | for (n = 0; n < 256 && src < src_end; n++) | |
1388 | { | |
065e3595 | 1389 | src_base = src; |
24a73b0a KH |
1390 | ONE_MORE_BYTE (c1); |
1391 | ONE_MORE_BYTE (c2); | |
065e3595 KH |
1392 | if (c1 < 0 || c2 < 0) |
1393 | break; | |
24a73b0a KH |
1394 | if (! b1[c1++]) b1_variants++; |
1395 | if (! b2[c2++]) b2_variants++; | |
1396 | } | |
1397 | if (b1_variants < b2_variants) | |
1398 | detect_info->found |= CATEGORY_MASK_UTF_16_BE_NOSIG; | |
1399 | else | |
1400 | detect_info->found |= CATEGORY_MASK_UTF_16_LE_NOSIG; | |
1401 | detect_info->rejected | |
1402 | |= (CATEGORY_MASK_UTF_16_BE | CATEGORY_MASK_UTF_16_LE); | |
ff0dacd7 | 1403 | } |
df7492f9 | 1404 | no_more_source: |
ff0dacd7 | 1405 | return 1; |
df7492f9 | 1406 | } |
aa72b389 | 1407 | |
df7492f9 KH |
1408 | static void |
1409 | decode_coding_utf_16 (coding) | |
1410 | struct coding_system *coding; | |
1411 | { | |
8f924df7 KH |
1412 | const unsigned char *src = coding->source + coding->consumed; |
1413 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1414 | const unsigned char *src_base; | |
df7492f9 KH |
1415 | int *charbuf = coding->charbuf; |
1416 | int *charbuf_end = charbuf + coding->charbuf_size; | |
1417 | int consumed_chars = 0, consumed_chars_base; | |
1418 | int multibytep = coding->src_multibyte; | |
1419 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1420 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); | |
1421 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
24a73b0a | 1422 | Lisp_Object attr, charset_list; |
df7492f9 | 1423 | |
24a73b0a | 1424 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1425 | |
b49a1807 | 1426 | if (bom == utf_16_with_bom) |
aa72b389 | 1427 | { |
df7492f9 | 1428 | int c, c1, c2; |
4af310db | 1429 | |
aa72b389 | 1430 | src_base = src; |
df7492f9 KH |
1431 | ONE_MORE_BYTE (c1); |
1432 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1433 | c = (c1 << 8) | c2; |
aa72b389 | 1434 | |
b49a1807 KH |
1435 | if (endian == utf_16_big_endian |
1436 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1437 | { |
b49a1807 KH |
1438 | /* The first two bytes are not BOM. Treat them as bytes |
1439 | for a normal character. */ | |
1440 | src = src_base; | |
1441 | coding->errors++; | |
aa72b389 | 1442 | } |
b49a1807 KH |
1443 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1444 | } | |
1445 | else if (bom == utf_16_detect_bom) | |
1446 | { | |
1447 | /* We have already tried to detect BOM and failed in | |
1448 | detect_coding. */ | |
1449 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; | |
df7492f9 | 1450 | } |
aa72b389 | 1451 | |
df7492f9 KH |
1452 | while (1) |
1453 | { | |
1454 | int c, c1, c2; | |
1455 | ||
1456 | src_base = src; | |
1457 | consumed_chars_base = consumed_chars; | |
1458 | ||
1459 | if (charbuf + 2 >= charbuf_end) | |
1460 | break; | |
1461 | ||
1462 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1463 | if (c1 < 0) |
1464 | { | |
1465 | *charbuf++ = -c1; | |
1466 | continue; | |
1467 | } | |
df7492f9 | 1468 | ONE_MORE_BYTE (c2); |
065e3595 KH |
1469 | if (c2 < 0) |
1470 | { | |
1471 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1472 | *charbuf++ = -c2; | |
1473 | continue; | |
1474 | } | |
df7492f9 | 1475 | c = (endian == utf_16_big_endian |
e19c3639 | 1476 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
df7492f9 | 1477 | if (surrogate) |
fd3ae0b9 | 1478 | { |
df7492f9 | 1479 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1480 | { |
df7492f9 KH |
1481 | if (endian == utf_16_big_endian) |
1482 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1483 | else | |
1484 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1485 | *charbuf++ = c1; | |
1486 | *charbuf++ = c2; | |
1487 | coding->errors++; | |
1488 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1489 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1490 | else |
df7492f9 | 1491 | *charbuf++ = c; |
fd3ae0b9 KH |
1492 | } |
1493 | else | |
df7492f9 KH |
1494 | { |
1495 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1496 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
1497 | *charbuf++ = c; | |
1498 | } | |
fd3ae0b9 | 1499 | } |
aa72b389 | 1500 | else |
df7492f9 KH |
1501 | { |
1502 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1503 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1504 | else | |
1505 | *charbuf++ = c; | |
8f924df7 | 1506 | } |
aa72b389 | 1507 | } |
df7492f9 KH |
1508 | |
1509 | no_more_source: | |
1510 | coding->consumed_char += consumed_chars_base; | |
1511 | coding->consumed = src_base - coding->source; | |
1512 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1513 | } |
b73bfc1c | 1514 | |
df7492f9 KH |
1515 | static int |
1516 | encode_coding_utf_16 (coding) | |
1517 | struct coding_system *coding; | |
1518 | { | |
1519 | int multibytep = coding->dst_multibyte; | |
1520 | int *charbuf = coding->charbuf; | |
1521 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1522 | unsigned char *dst = coding->destination + coding->produced; | |
1523 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1524 | int safe_room = 8; | |
1525 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1526 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; | |
1527 | int produced_chars = 0; | |
24a73b0a | 1528 | Lisp_Object attrs, charset_list; |
df7492f9 | 1529 | int c; |
4ed46869 | 1530 | |
24a73b0a | 1531 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 1532 | |
b49a1807 | 1533 | if (bom != utf_16_without_bom) |
df7492f9 KH |
1534 | { |
1535 | ASSURE_DESTINATION (safe_room); | |
1536 | if (big_endian) | |
df7492f9 | 1537 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1538 | else |
1539 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
df7492f9 KH |
1540 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1541 | } | |
1542 | ||
1543 | while (charbuf < charbuf_end) | |
1544 | { | |
1545 | ASSURE_DESTINATION (safe_room); | |
1546 | c = *charbuf++; | |
e19c3639 KH |
1547 | if (c >= MAX_UNICODE_CHAR) |
1548 | c = coding->default_char; | |
df7492f9 KH |
1549 | |
1550 | if (c < 0x10000) | |
1551 | { | |
1552 | if (big_endian) | |
1553 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1554 | else | |
1555 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1556 | } | |
1557 | else | |
1558 | { | |
1559 | int c1, c2; | |
1560 | ||
1561 | c -= 0x10000; | |
1562 | c1 = (c >> 10) + 0xD800; | |
1563 | c2 = (c & 0x3FF) + 0xDC00; | |
1564 | if (big_endian) | |
1565 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1566 | else | |
1567 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1568 | } | |
1569 | } | |
065e3595 | 1570 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1571 | coding->produced = dst - coding->destination; |
1572 | coding->produced_char += produced_chars; | |
1573 | return 0; | |
1574 | } | |
1575 | ||
1576 | \f | |
1577 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1578 | ||
1579 | /* Emacs' internal format for representation of multiple character | |
1580 | sets is a kind of multi-byte encoding, i.e. characters are | |
1581 | represented by variable-length sequences of one-byte codes. | |
1582 | ||
1583 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1584 | represented by one-byte sequences which are their ASCII codes, in | |
1585 | the range 0x00 through 0x7F. | |
1586 | ||
1587 | 8-bit characters of the range 0x80..0x9F are represented by | |
1588 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1589 | code + 0x20). | |
1590 | ||
1591 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1592 | one-byte sequences which are their 8-bit code. | |
1593 | ||
1594 | The other characters are represented by a sequence of `base | |
1595 | leading-code', optional `extended leading-code', and one or two | |
1596 | `position-code's. The length of the sequence is determined by the | |
1597 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1598 | whereas extended leading-code and position-code take the range 0xA0 | |
1599 | through 0xFF. See `charset.h' for more details about leading-code | |
1600 | and position-code. | |
1601 | ||
1602 | --- CODE RANGE of Emacs' internal format --- | |
1603 | character set range | |
1604 | ------------- ----- | |
1605 | ascii 0x00..0x7F | |
1606 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1607 | eight-bit-graphic 0xA0..0xBF | |
1608 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1609 | --------------------------------------------- | |
1610 | ||
1611 | As this is the internal character representation, the format is | |
1612 | usually not used externally (i.e. in a file or in a data sent to a | |
1613 | process). But, it is possible to have a text externally in this | |
1614 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1615 | ||
1616 | In that case, a sequence of one-byte codes has a slightly different | |
1617 | form. | |
1618 | ||
1619 | At first, all characters in eight-bit-control are represented by | |
1620 | one-byte sequences which are their 8-bit code. | |
1621 | ||
1622 | Next, character composition data are represented by the byte | |
1623 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1624 | where, | |
1625 | METHOD is 0xF0 plus one of composition method (enum | |
1626 | composition_method), | |
1627 | ||
1628 | BYTES is 0xA0 plus a byte length of this composition data, | |
1629 | ||
1630 | CHARS is 0x20 plus a number of characters composed by this | |
1631 | data, | |
1632 | ||
1633 | COMPONENTs are characters of multibye form or composition | |
1634 | rules encoded by two-byte of ASCII codes. | |
1635 | ||
1636 | In addition, for backward compatibility, the following formats are | |
1637 | also recognized as composition data on decoding. | |
1638 | ||
1639 | 0x80 MSEQ ... | |
1640 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1641 | ||
1642 | Here, | |
1643 | MSEQ is a multibyte form but in these special format: | |
1644 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1645 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1646 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1647 | represents a composition rule. | |
1648 | */ | |
1649 | ||
1650 | char emacs_mule_bytes[256]; | |
1651 | ||
df7492f9 | 1652 | int |
ff0dacd7 | 1653 | emacs_mule_char (coding, src, nbytes, nchars, id) |
df7492f9 | 1654 | struct coding_system *coding; |
065e3595 | 1655 | const unsigned char *src; |
ff0dacd7 | 1656 | int *nbytes, *nchars, *id; |
df7492f9 | 1657 | { |
8f924df7 KH |
1658 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1659 | const unsigned char *src_base = src; | |
df7492f9 | 1660 | int multibytep = coding->src_multibyte; |
df7492f9 KH |
1661 | struct charset *charset; |
1662 | unsigned code; | |
1663 | int c; | |
1664 | int consumed_chars = 0; | |
1665 | ||
1666 | ONE_MORE_BYTE (c); | |
065e3595 | 1667 | if (c < 0) |
df7492f9 | 1668 | { |
065e3595 KH |
1669 | c = -c; |
1670 | charset = emacs_mule_charset[0]; | |
1671 | } | |
1672 | else | |
1673 | { | |
1674 | switch (emacs_mule_bytes[c]) | |
b73bfc1c | 1675 | { |
065e3595 | 1676 | case 2: |
df7492f9 KH |
1677 | if (! (charset = emacs_mule_charset[c])) |
1678 | goto invalid_code; | |
1679 | ONE_MORE_BYTE (c); | |
065e3595 KH |
1680 | if (c < 0) |
1681 | goto invalid_code; | |
df7492f9 | 1682 | code = c & 0x7F; |
065e3595 KH |
1683 | break; |
1684 | ||
1685 | case 3: | |
1686 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
1687 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
1688 | { | |
1689 | ONE_MORE_BYTE (c); | |
1690 | if (c < 0 || ! (charset = emacs_mule_charset[c])) | |
1691 | goto invalid_code; | |
1692 | ONE_MORE_BYTE (c); | |
1693 | if (c < 0) | |
1694 | goto invalid_code; | |
1695 | code = c & 0x7F; | |
1696 | } | |
1697 | else | |
1698 | { | |
1699 | if (! (charset = emacs_mule_charset[c])) | |
1700 | goto invalid_code; | |
1701 | ONE_MORE_BYTE (c); | |
1702 | if (c < 0) | |
1703 | goto invalid_code; | |
1704 | code = (c & 0x7F) << 8; | |
1705 | ONE_MORE_BYTE (c); | |
1706 | if (c < 0) | |
1707 | goto invalid_code; | |
1708 | code |= c & 0x7F; | |
1709 | } | |
1710 | break; | |
1711 | ||
1712 | case 4: | |
1713 | ONE_MORE_BYTE (c); | |
1714 | if (c < 0 || ! (charset = emacs_mule_charset[c])) | |
df7492f9 KH |
1715 | goto invalid_code; |
1716 | ONE_MORE_BYTE (c); | |
065e3595 KH |
1717 | if (c < 0) |
1718 | goto invalid_code; | |
781d7a48 | 1719 | code = (c & 0x7F) << 8; |
df7492f9 | 1720 | ONE_MORE_BYTE (c); |
065e3595 KH |
1721 | if (c < 0) |
1722 | goto invalid_code; | |
df7492f9 | 1723 | code |= c & 0x7F; |
065e3595 | 1724 | break; |
df7492f9 | 1725 | |
065e3595 KH |
1726 | case 1: |
1727 | code = c; | |
1728 | charset = CHARSET_FROM_ID (ASCII_BYTE_P (code) | |
1729 | ? charset_ascii : charset_eight_bit); | |
1730 | break; | |
df7492f9 | 1731 | |
065e3595 KH |
1732 | default: |
1733 | abort (); | |
1734 | } | |
1735 | c = DECODE_CHAR (charset, code); | |
1736 | if (c < 0) | |
1737 | goto invalid_code; | |
df7492f9 | 1738 | } |
df7492f9 KH |
1739 | *nbytes = src - src_base; |
1740 | *nchars = consumed_chars; | |
ff0dacd7 KH |
1741 | if (id) |
1742 | *id = charset->id; | |
df7492f9 KH |
1743 | return c; |
1744 | ||
1745 | no_more_source: | |
1746 | return -2; | |
1747 | ||
1748 | invalid_code: | |
1749 | return -1; | |
1750 | } | |
1751 | ||
1752 | ||
1753 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1754 | Check if a text is encoded in `emacs-mule'. If it is, return 1, |
1755 | else return 0. */ | |
df7492f9 KH |
1756 | |
1757 | static int | |
ff0dacd7 | 1758 | detect_coding_emacs_mule (coding, detect_info) |
df7492f9 | 1759 | struct coding_system *coding; |
ff0dacd7 | 1760 | struct coding_detection_info *detect_info; |
df7492f9 | 1761 | { |
065e3595 | 1762 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1763 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1764 | int multibytep = coding->src_multibyte; |
1765 | int consumed_chars = 0; | |
1766 | int c; | |
1767 | int found = 0; | |
1768 | ||
ff0dacd7 | 1769 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1770 | /* A coding system of this category is always ASCII compatible. */ |
1771 | src += coding->head_ascii; | |
1772 | ||
1773 | while (1) | |
1774 | { | |
065e3595 | 1775 | src_base = src; |
df7492f9 | 1776 | ONE_MORE_BYTE (c); |
065e3595 KH |
1777 | if (c < 0) |
1778 | continue; | |
df7492f9 KH |
1779 | if (c == 0x80) |
1780 | { | |
1781 | /* Perhaps the start of composite character. We simple skip | |
1782 | it because analyzing it is too heavy for detecting. But, | |
1783 | at least, we check that the composite character | |
1784 | constitues of more than 4 bytes. */ | |
8f924df7 | 1785 | const unsigned char *src_base; |
df7492f9 KH |
1786 | |
1787 | repeat: | |
1788 | src_base = src; | |
1789 | do | |
1790 | { | |
1791 | ONE_MORE_BYTE (c); | |
1792 | } | |
1793 | while (c >= 0xA0); | |
1794 | ||
1795 | if (src - src_base <= 4) | |
1796 | break; | |
ff0dacd7 | 1797 | found = CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1798 | if (c == 0x80) |
1799 | goto repeat; | |
b73bfc1c | 1800 | } |
df7492f9 KH |
1801 | |
1802 | if (c < 0x80) | |
b73bfc1c | 1803 | { |
df7492f9 KH |
1804 | if (c < 0x20 |
1805 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1806 | break; | |
1807 | } | |
1808 | else | |
1809 | { | |
8f924df7 | 1810 | const unsigned char *src_base = src - 1; |
df7492f9 KH |
1811 | |
1812 | do | |
1813 | { | |
1814 | ONE_MORE_BYTE (c); | |
1815 | } | |
1816 | while (c >= 0xA0); | |
1817 | if (src - src_base != emacs_mule_bytes[*src_base]) | |
1818 | break; | |
ff0dacd7 | 1819 | found = CATEGORY_MASK_EMACS_MULE; |
4ed46869 KH |
1820 | } |
1821 | } | |
ff0dacd7 | 1822 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1823 | return 0; |
1824 | ||
1825 | no_more_source: | |
065e3595 | 1826 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 1827 | { |
ff0dacd7 | 1828 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
89528eb3 KH |
1829 | return 0; |
1830 | } | |
ff0dacd7 KH |
1831 | detect_info->found |= found; |
1832 | return 1; | |
4ed46869 KH |
1833 | } |
1834 | ||
b73bfc1c | 1835 | |
df7492f9 KH |
1836 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
1837 | ||
1838 | /* Decode a character represented as a component of composition | |
1839 | sequence of Emacs 20/21 style at SRC. Set C to that character and | |
1840 | update SRC to the head of next character (or an encoded composition | |
1841 | rule). If SRC doesn't points a composition component, set C to -1. | |
1842 | If SRC points an invalid byte sequence, global exit by a return | |
1843 | value 0. */ | |
1844 | ||
1845 | #define DECODE_EMACS_MULE_COMPOSITION_CHAR(buf) \ | |
1846 | if (1) \ | |
1847 | { \ | |
1848 | int c; \ | |
1849 | int nbytes, nchars; \ | |
1850 | \ | |
1851 | if (src == src_end) \ | |
1852 | break; \ | |
ff0dacd7 | 1853 | c = emacs_mule_char (coding, src, &nbytes, &nchars, NULL);\ |
df7492f9 KH |
1854 | if (c < 0) \ |
1855 | { \ | |
1856 | if (c == -2) \ | |
1857 | break; \ | |
1858 | goto invalid_code; \ | |
1859 | } \ | |
1860 | *buf++ = c; \ | |
1861 | src += nbytes; \ | |
1862 | consumed_chars += nchars; \ | |
1863 | } \ | |
1864 | else | |
1865 | ||
1866 | ||
1867 | /* Decode a composition rule represented as a component of composition | |
781d7a48 KH |
1868 | sequence of Emacs 20 style at SRC. Store the decoded rule in *BUF, |
1869 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1870 | to -1. */ | |
df7492f9 | 1871 | |
781d7a48 | 1872 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(buf) \ |
df7492f9 KH |
1873 | do { \ |
1874 | int c, gref, nref; \ | |
1875 | \ | |
781d7a48 | 1876 | if (src >= src_end) \ |
df7492f9 KH |
1877 | goto invalid_code; \ |
1878 | ONE_MORE_BYTE_NO_CHECK (c); \ | |
781d7a48 | 1879 | c -= 0x20; \ |
df7492f9 KH |
1880 | if (c < 0 || c >= 81) \ |
1881 | goto invalid_code; \ | |
1882 | \ | |
1883 | gref = c / 9, nref = c % 9; \ | |
1884 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1885 | } while (0) | |
1886 | ||
1887 | ||
781d7a48 KH |
1888 | /* Decode a composition rule represented as a component of composition |
1889 | sequence of Emacs 21 style at SRC. Store the decoded rule in *BUF, | |
1890 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1891 | to -1. */ | |
1892 | ||
1893 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(buf) \ | |
1894 | do { \ | |
1895 | int gref, nref; \ | |
1896 | \ | |
1897 | if (src + 1>= src_end) \ | |
1898 | goto invalid_code; \ | |
1899 | ONE_MORE_BYTE_NO_CHECK (gref); \ | |
1900 | gref -= 0x20; \ | |
1901 | ONE_MORE_BYTE_NO_CHECK (nref); \ | |
1902 | nref -= 0x20; \ | |
1903 | if (gref < 0 || gref >= 81 \ | |
1904 | || nref < 0 || nref >= 81) \ | |
1905 | goto invalid_code; \ | |
1906 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1907 | } while (0) | |
1908 | ||
1909 | ||
df7492f9 | 1910 | #define DECODE_EMACS_MULE_21_COMPOSITION(c) \ |
aa72b389 | 1911 | do { \ |
df7492f9 | 1912 | /* Emacs 21 style format. The first three bytes at SRC are \ |
781d7a48 | 1913 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is \ |
df7492f9 KH |
1914 | the byte length of this composition information, CHARS is the \ |
1915 | number of characters composed by this composition. */ \ | |
781d7a48 KH |
1916 | enum composition_method method = c - 0xF2; \ |
1917 | int *charbuf_base = charbuf; \ | |
ff0dacd7 | 1918 | int from, to; \ |
df7492f9 KH |
1919 | int consumed_chars_limit; \ |
1920 | int nbytes, nchars; \ | |
1921 | \ | |
1922 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
1923 | if (c < 0) \ |
1924 | goto invalid_code; \ | |
df7492f9 KH |
1925 | nbytes = c - 0xA0; \ |
1926 | if (nbytes < 3) \ | |
1927 | goto invalid_code; \ | |
1928 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
1929 | if (c < 0) \ |
1930 | goto invalid_code; \ | |
df7492f9 | 1931 | nchars = c - 0xA0; \ |
ff0dacd7 KH |
1932 | from = coding->produced + char_offset; \ |
1933 | to = from + nchars; \ | |
1934 | ADD_COMPOSITION_DATA (charbuf, from, to, method); \ | |
df7492f9 KH |
1935 | consumed_chars_limit = consumed_chars_base + nbytes; \ |
1936 | if (method != COMPOSITION_RELATIVE) \ | |
aa72b389 | 1937 | { \ |
df7492f9 KH |
1938 | int i = 0; \ |
1939 | while (consumed_chars < consumed_chars_limit) \ | |
aa72b389 | 1940 | { \ |
df7492f9 | 1941 | if (i % 2 && method != COMPOSITION_WITH_ALTCHARS) \ |
781d7a48 | 1942 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (charbuf); \ |
df7492f9 KH |
1943 | else \ |
1944 | DECODE_EMACS_MULE_COMPOSITION_CHAR (charbuf); \ | |
781d7a48 | 1945 | i++; \ |
aa72b389 | 1946 | } \ |
df7492f9 KH |
1947 | if (consumed_chars < consumed_chars_limit) \ |
1948 | goto invalid_code; \ | |
781d7a48 | 1949 | charbuf_base[0] -= i; \ |
aa72b389 KH |
1950 | } \ |
1951 | } while (0) | |
93dec019 | 1952 | |
aa72b389 | 1953 | |
df7492f9 KH |
1954 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION(c) \ |
1955 | do { \ | |
1956 | /* Emacs 20 style format for relative composition. */ \ | |
1957 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 1958 | enum composition_method method = COMPOSITION_RELATIVE; \ |
df7492f9 KH |
1959 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
1960 | int *buf = components; \ | |
1961 | int i, j; \ | |
ff0dacd7 | 1962 | int from, to; \ |
df7492f9 KH |
1963 | \ |
1964 | src = src_base; \ | |
1965 | ONE_MORE_BYTE (c); /* skip 0x80 */ \ | |
1966 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
1967 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
1968 | if (i < 2) \ | |
1969 | goto invalid_code; \ | |
ff0dacd7 KH |
1970 | from = coding->produced_char + char_offset; \ |
1971 | to = from + i; \ | |
1972 | ADD_COMPOSITION_DATA (charbuf, from, to, method); \ | |
df7492f9 KH |
1973 | for (j = 0; j < i; j++) \ |
1974 | *charbuf++ = components[j]; \ | |
1975 | } while (0) | |
1976 | ||
1977 | ||
1978 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION(c) \ | |
1979 | do { \ | |
1980 | /* Emacs 20 style format for rule-base composition. */ \ | |
1981 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 1982 | enum composition_method method = COMPOSITION_WITH_RULE; \ |
df7492f9 KH |
1983 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
1984 | int *buf = components; \ | |
1985 | int i, j; \ | |
ff0dacd7 | 1986 | int from, to; \ |
df7492f9 KH |
1987 | \ |
1988 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
1989 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
1990 | { \ | |
781d7a48 | 1991 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (buf); \ |
df7492f9 KH |
1992 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ |
1993 | } \ | |
1994 | if (i < 1 || (buf - components) % 2 == 0) \ | |
1995 | goto invalid_code; \ | |
1996 | if (charbuf + i + (i / 2) + 1 < charbuf_end) \ | |
1997 | goto no_more_source; \ | |
ff0dacd7 KH |
1998 | from = coding->produced_char + char_offset; \ |
1999 | to = from + i; \ | |
2000 | ADD_COMPOSITION_DATA (buf, from, to, method); \ | |
df7492f9 KH |
2001 | for (j = 0; j < i; j++) \ |
2002 | *charbuf++ = components[j]; \ | |
2003 | for (j = 0; j < i; j += 2) \ | |
2004 | *charbuf++ = components[j]; \ | |
2005 | } while (0) | |
2006 | ||
aa72b389 KH |
2007 | |
2008 | static void | |
df7492f9 | 2009 | decode_coding_emacs_mule (coding) |
aa72b389 | 2010 | struct coding_system *coding; |
aa72b389 | 2011 | { |
8f924df7 KH |
2012 | const unsigned char *src = coding->source + coding->consumed; |
2013 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2014 | const unsigned char *src_base; | |
df7492f9 | 2015 | int *charbuf = coding->charbuf; |
ff0dacd7 | 2016 | int *charbuf_end = charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; |
df7492f9 | 2017 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2018 | int multibytep = coding->src_multibyte; |
24a73b0a | 2019 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2020 | int char_offset = coding->produced_char; |
2021 | int last_offset = char_offset; | |
2022 | int last_id = charset_ascii; | |
aa72b389 | 2023 | |
24a73b0a | 2024 | CODING_GET_INFO (coding, attrs, charset_list); |
aa72b389 | 2025 | |
aa72b389 KH |
2026 | while (1) |
2027 | { | |
df7492f9 KH |
2028 | int c; |
2029 | ||
aa72b389 | 2030 | src_base = src; |
df7492f9 KH |
2031 | consumed_chars_base = consumed_chars; |
2032 | ||
2033 | if (charbuf >= charbuf_end) | |
2034 | break; | |
aa72b389 | 2035 | |
df7492f9 | 2036 | ONE_MORE_BYTE (c); |
065e3595 KH |
2037 | if (c < 0) |
2038 | { | |
2039 | *charbuf++ = -c; | |
2040 | char_offset++; | |
2041 | } | |
2042 | else if (c < 0x80) | |
aa72b389 | 2043 | { |
df7492f9 KH |
2044 | *charbuf++ = c; |
2045 | char_offset++; | |
aa72b389 | 2046 | } |
df7492f9 KH |
2047 | else if (c == 0x80) |
2048 | { | |
df7492f9 | 2049 | ONE_MORE_BYTE (c); |
065e3595 KH |
2050 | if (c < 0) |
2051 | goto invalid_code; | |
781d7a48 KH |
2052 | if (c - 0xF2 >= COMPOSITION_RELATIVE |
2053 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) | |
df7492f9 KH |
2054 | DECODE_EMACS_MULE_21_COMPOSITION (c); |
2055 | else if (c < 0xC0) | |
2056 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (c); | |
2057 | else if (c == 0xFF) | |
2058 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (c); | |
2059 | else | |
2060 | goto invalid_code; | |
2061 | } | |
2062 | else if (c < 0xA0 && emacs_mule_bytes[c] > 1) | |
2063 | { | |
2064 | int nbytes, nchars; | |
ff0dacd7 KH |
2065 | int id; |
2066 | ||
781d7a48 KH |
2067 | src = src_base; |
2068 | consumed_chars = consumed_chars_base; | |
ff0dacd7 | 2069 | c = emacs_mule_char (coding, src, &nbytes, &nchars, &id); |
df7492f9 KH |
2070 | if (c < 0) |
2071 | { | |
2072 | if (c == -2) | |
2073 | break; | |
2074 | goto invalid_code; | |
2075 | } | |
ff0dacd7 KH |
2076 | if (last_id != id) |
2077 | { | |
2078 | if (last_id != charset_ascii) | |
2079 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
2080 | last_id = id; | |
2081 | last_offset = char_offset; | |
2082 | } | |
df7492f9 | 2083 | *charbuf++ = c; |
781d7a48 KH |
2084 | src += nbytes; |
2085 | consumed_chars += nchars; | |
df7492f9 KH |
2086 | char_offset++; |
2087 | } | |
2088 | continue; | |
2089 | ||
2090 | invalid_code: | |
2091 | src = src_base; | |
2092 | consumed_chars = consumed_chars_base; | |
2093 | ONE_MORE_BYTE (c); | |
2094 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2095 | char_offset++; |
df7492f9 KH |
2096 | coding->errors++; |
2097 | } | |
2098 | ||
2099 | no_more_source: | |
ff0dacd7 KH |
2100 | if (last_id != charset_ascii) |
2101 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
df7492f9 KH |
2102 | coding->consumed_char += consumed_chars_base; |
2103 | coding->consumed = src_base - coding->source; | |
2104 | coding->charbuf_used = charbuf - coding->charbuf; | |
2105 | } | |
2106 | ||
2107 | ||
2108 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2109 | do { \ | |
2110 | if (id < 0xA0) \ | |
2111 | codes[0] = id, codes[1] = 0; \ | |
2112 | else if (id < 0xE0) \ | |
2113 | codes[0] = 0x9A, codes[1] = id; \ | |
2114 | else if (id < 0xF0) \ | |
2115 | codes[0] = 0x9B, codes[1] = id; \ | |
2116 | else if (id < 0xF5) \ | |
2117 | codes[0] = 0x9C, codes[1] = id; \ | |
2118 | else \ | |
2119 | codes[0] = 0x9D, codes[1] = id; \ | |
2120 | } while (0); | |
2121 | ||
aa72b389 | 2122 | |
df7492f9 KH |
2123 | static int |
2124 | encode_coding_emacs_mule (coding) | |
2125 | struct coding_system *coding; | |
2126 | { | |
2127 | int multibytep = coding->dst_multibyte; | |
2128 | int *charbuf = coding->charbuf; | |
2129 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2130 | unsigned char *dst = coding->destination + coding->produced; | |
2131 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2132 | int safe_room = 8; | |
df7492f9 | 2133 | int produced_chars = 0; |
24a73b0a | 2134 | Lisp_Object attrs, charset_list; |
df7492f9 | 2135 | int c; |
ff0dacd7 | 2136 | int preferred_charset_id = -1; |
df7492f9 | 2137 | |
24a73b0a | 2138 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2139 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2140 | { | |
2141 | CODING_ATTR_CHARSET_LIST (attrs) | |
2142 | = charset_list = Vemacs_mule_charset_list; | |
2143 | } | |
df7492f9 KH |
2144 | |
2145 | while (charbuf < charbuf_end) | |
2146 | { | |
2147 | ASSURE_DESTINATION (safe_room); | |
2148 | c = *charbuf++; | |
ff0dacd7 KH |
2149 | |
2150 | if (c < 0) | |
2151 | { | |
2152 | /* Handle an annotation. */ | |
2153 | switch (*charbuf) | |
2154 | { | |
2155 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2156 | /* Not yet implemented. */ | |
2157 | break; | |
2158 | case CODING_ANNOTATE_CHARSET_MASK: | |
2159 | preferred_charset_id = charbuf[3]; | |
2160 | if (preferred_charset_id >= 0 | |
2161 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2162 | charset_list))) | |
2163 | preferred_charset_id = -1; | |
2164 | break; | |
2165 | default: | |
2166 | abort (); | |
2167 | } | |
2168 | charbuf += -c - 1; | |
2169 | continue; | |
2170 | } | |
2171 | ||
df7492f9 KH |
2172 | if (ASCII_CHAR_P (c)) |
2173 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2174 | else if (CHAR_BYTE8_P (c)) |
2175 | { | |
2176 | c = CHAR_TO_BYTE8 (c); | |
2177 | EMIT_ONE_BYTE (c); | |
2178 | } | |
df7492f9 | 2179 | else |
aa72b389 | 2180 | { |
df7492f9 KH |
2181 | struct charset *charset; |
2182 | unsigned code; | |
2183 | int dimension; | |
2184 | int emacs_mule_id; | |
2185 | unsigned char leading_codes[2]; | |
2186 | ||
ff0dacd7 KH |
2187 | if (preferred_charset_id >= 0) |
2188 | { | |
2189 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
2190 | if (! CHAR_CHARSET_P (c, charset)) | |
2191 | charset = char_charset (c, charset_list, NULL); | |
2192 | } | |
2193 | else | |
2194 | charset = char_charset (c, charset_list, &code); | |
df7492f9 KH |
2195 | if (! charset) |
2196 | { | |
2197 | c = coding->default_char; | |
2198 | if (ASCII_CHAR_P (c)) | |
2199 | { | |
2200 | EMIT_ONE_ASCII_BYTE (c); | |
2201 | continue; | |
2202 | } | |
2203 | charset = char_charset (c, charset_list, &code); | |
2204 | } | |
2205 | dimension = CHARSET_DIMENSION (charset); | |
2206 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2207 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2208 | EMIT_ONE_BYTE (leading_codes[0]); | |
2209 | if (leading_codes[1]) | |
2210 | EMIT_ONE_BYTE (leading_codes[1]); | |
2211 | if (dimension == 1) | |
1fa663f9 | 2212 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2213 | else |
df7492f9 | 2214 | { |
1fa663f9 | 2215 | code |= 0x8080; |
df7492f9 KH |
2216 | EMIT_ONE_BYTE (code >> 8); |
2217 | EMIT_ONE_BYTE (code & 0xFF); | |
2218 | } | |
aa72b389 | 2219 | } |
aa72b389 | 2220 | } |
065e3595 | 2221 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2222 | coding->produced_char += produced_chars; |
2223 | coding->produced = dst - coding->destination; | |
2224 | return 0; | |
aa72b389 | 2225 | } |
b73bfc1c | 2226 | |
4ed46869 | 2227 | \f |
df7492f9 | 2228 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2229 | |
2230 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2231 | Since the intention of this note is to help understand the |
5a936b46 | 2232 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2233 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2234 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2235 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2236 | |
2237 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2238 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2239 | is encoded using bytes less than 128. This may make the encoded |
2240 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2241 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2242 | Significant Bit). |
b73bfc1c | 2243 | |
cfb43547 DL |
2244 | There are two kinds of character sets: control character sets and |
2245 | graphic character sets. The former contain control characters such | |
4ed46869 | 2246 | as `newline' and `escape' to provide control functions (control |
39787efd | 2247 | functions are also provided by escape sequences). The latter |
cfb43547 | 2248 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2249 | two control character sets and many graphic character sets. |
2250 | ||
2251 | Graphic character sets are classified into one of the following | |
39787efd KH |
2252 | four classes, according to the number of bytes (DIMENSION) and |
2253 | number of characters in one dimension (CHARS) of the set: | |
2254 | - DIMENSION1_CHARS94 | |
2255 | - DIMENSION1_CHARS96 | |
2256 | - DIMENSION2_CHARS94 | |
2257 | - DIMENSION2_CHARS96 | |
2258 | ||
2259 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2260 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2261 | hereafter). The <F> of each character set is decided by ECMA(*) |
2262 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2263 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2264 | |
2265 | Note (*): ECMA = European Computer Manufacturers Association | |
2266 | ||
cfb43547 | 2267 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2268 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2269 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2270 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2271 | o DIMENSION2_CHARS96 -- none for the moment | |
2272 | ||
39787efd | 2273 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2274 | C0 [0x00..0x1F] -- control character plane 0 |
2275 | GL [0x20..0x7F] -- graphic character plane 0 | |
2276 | C1 [0x80..0x9F] -- control character plane 1 | |
2277 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2278 | ||
2279 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2280 | C1 by an escape sequence. The most common case is that: |
2281 | - ISO646's control character set is designated/invoked to C0, and | |
2282 | - ISO6429's control character set is designated/invoked to C1, | |
2283 | and usually these designations/invocations are omitted in encoded | |
2284 | text. In a 7-bit environment, only C0 can be used, and a control | |
2285 | character for C1 is encoded by an appropriate escape sequence to | |
2286 | fit into the environment. All control characters for C1 are | |
2287 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2288 | |
2289 | A graphic character set is at first designated to one of four | |
2290 | graphic registers (G0 through G3), then these graphic registers are | |
2291 | invoked to GL or GR. These designations and invocations can be | |
2292 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2293 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2294 | these invocations and designations are omitted in encoded text. | |
2295 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2296 | |
39787efd KH |
2297 | When a graphic character set of CHARS94 is invoked to GL, codes |
2298 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2299 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2300 | be used. | |
4ed46869 KH |
2301 | |
2302 | There are two ways of invocation: locking-shift and single-shift. | |
2303 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2304 | invocation, whereas with single-shift, the invocation affects the |
2305 | following character only and doesn't affect the locking-shift | |
2306 | state. Invocations are done by the following control characters or | |
2307 | escape sequences: | |
4ed46869 KH |
2308 | |
2309 | ---------------------------------------------------------------------- | |
39787efd | 2310 | abbrev function cntrl escape seq description |
4ed46869 | 2311 | ---------------------------------------------------------------------- |
39787efd KH |
2312 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2313 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2314 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2315 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2316 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2317 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2318 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2319 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2320 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2321 | ---------------------------------------------------------------------- |
39787efd KH |
2322 | (*) These are not used by any known coding system. |
2323 | ||
2324 | Control characters for these functions are defined by macros | |
2325 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2326 | |
39787efd | 2327 | Designations are done by the following escape sequences: |
4ed46869 KH |
2328 | ---------------------------------------------------------------------- |
2329 | escape sequence description | |
2330 | ---------------------------------------------------------------------- | |
2331 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2332 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2333 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2334 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2335 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2336 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2337 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2338 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2339 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2340 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2341 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2342 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2343 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2344 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2345 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2346 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2347 | ---------------------------------------------------------------------- | |
2348 | ||
2349 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2350 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2351 | |
2352 | Note (*): Although these designations are not allowed in ISO2022, | |
2353 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2354 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2355 | 7-bit environment, non-locking-shift, and non-single-shift. |
2356 | ||
2357 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2358 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2359 | |
cfb43547 | 2360 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2361 | same multilingual text in ISO2022. Actually, there exist many |
2362 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2363 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2364 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2365 | localized platforms), and all of these are variants of ISO2022. |
2366 | ||
2367 | In addition to the above, Emacs handles two more kinds of escape | |
2368 | sequences: ISO6429's direction specification and Emacs' private | |
2369 | sequence for specifying character composition. | |
2370 | ||
39787efd | 2371 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2372 | o CSI ']' -- end of the current direction |
2373 | o CSI '0' ']' -- end of the current direction | |
2374 | o CSI '1' ']' -- start of left-to-right text | |
2375 | o CSI '2' ']' -- start of right-to-left text | |
2376 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2377 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2378 | ||
2379 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2380 | o ESC '0' -- start relative composition |
2381 | o ESC '1' -- end composition | |
2382 | o ESC '2' -- start rule-base composition (*) | |
2383 | o ESC '3' -- start relative composition with alternate chars (**) | |
2384 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2385 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2386 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2387 | |
5a936b46 DL |
2388 | (*) This form is used only in Emacs 20.7 and older versions, |
2389 | but newer versions can safely decode it. | |
cfb43547 | 2390 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2391 | and older versions can't decode it. |
ec6d2bb8 | 2392 | |
cfb43547 | 2393 | Here's a list of example usages of these composition escape |
b73bfc1c | 2394 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2395 | |
b73bfc1c | 2396 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2397 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2398 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2399 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2400 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2401 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2402 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2403 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2404 | |
2405 | enum iso_code_class_type iso_code_class[256]; | |
2406 | ||
df7492f9 KH |
2407 | #define SAFE_CHARSET_P(coding, id) \ |
2408 | ((id) <= (coding)->max_charset_id \ | |
2409 | && (coding)->safe_charsets[id] >= 0) | |
2410 | ||
2411 | ||
2412 | #define SHIFT_OUT_OK(category) \ | |
2413 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
2414 | ||
2415 | static void | |
f0064e1f DL |
2416 | setup_iso_safe_charsets (attrs) |
2417 | Lisp_Object attrs; | |
df7492f9 KH |
2418 | { |
2419 | Lisp_Object charset_list, safe_charsets; | |
2420 | Lisp_Object request; | |
2421 | Lisp_Object reg_usage; | |
2422 | Lisp_Object tail; | |
2423 | int reg94, reg96; | |
2424 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
2425 | int max_charset_id; | |
2426 | ||
2427 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2428 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2429 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2430 | { | |
2431 | CODING_ATTR_CHARSET_LIST (attrs) | |
2432 | = charset_list = Viso_2022_charset_list; | |
2433 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
2434 | } | |
2435 | ||
2436 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2437 | return; | |
2438 | ||
2439 | max_charset_id = 0; | |
2440 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2441 | { | |
2442 | int id = XINT (XCAR (tail)); | |
2443 | if (max_charset_id < id) | |
2444 | max_charset_id = id; | |
2445 | } | |
d46c5b12 | 2446 | |
df7492f9 KH |
2447 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
2448 | make_number (255)); | |
2449 | request = AREF (attrs, coding_attr_iso_request); | |
2450 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2451 | reg94 = XINT (XCAR (reg_usage)); | |
2452 | reg96 = XINT (XCDR (reg_usage)); | |
2453 | ||
2454 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2455 | { | |
2456 | Lisp_Object id; | |
2457 | Lisp_Object reg; | |
2458 | struct charset *charset; | |
2459 | ||
2460 | id = XCAR (tail); | |
2461 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2462 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2463 | if (! NILP (reg)) |
8f924df7 | 2464 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2465 | else if (charset->iso_chars_96) |
2466 | { | |
2467 | if (reg96 < 4) | |
8f924df7 | 2468 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2469 | } |
2470 | else | |
2471 | { | |
2472 | if (reg94 < 4) | |
8f924df7 | 2473 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2474 | } |
2475 | } | |
2476 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2477 | } | |
d46c5b12 | 2478 | |
b6871cc7 | 2479 | |
4ed46869 | 2480 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
2481 | Check if a text is encoded in one of ISO-2022 based codig systems. |
2482 | If it is, return 1, else return 0. */ | |
4ed46869 | 2483 | |
0a28aafb | 2484 | static int |
ff0dacd7 | 2485 | detect_coding_iso_2022 (coding, detect_info) |
df7492f9 | 2486 | struct coding_system *coding; |
ff0dacd7 | 2487 | struct coding_detection_info *detect_info; |
4ed46869 | 2488 | { |
8f924df7 KH |
2489 | const unsigned char *src = coding->source, *src_base = src; |
2490 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 2491 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 2492 | int single_shifting = 0; |
df7492f9 KH |
2493 | int id; |
2494 | int c, c1; | |
2495 | int consumed_chars = 0; | |
2496 | int i; | |
ff0dacd7 KH |
2497 | int rejected = 0; |
2498 | int found = 0; | |
2499 | ||
2500 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2501 | |
2502 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2503 | { | |
2504 | struct coding_system *this = &(coding_categories[i]); | |
2505 | Lisp_Object attrs, val; | |
2506 | ||
2507 | attrs = CODING_ID_ATTRS (this->id); | |
2508 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
2509 | && ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs), Viso_2022_charset_list)) | |
2510 | setup_iso_safe_charsets (attrs); | |
2511 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
2512 | this->max_charset_id = SCHARS (val) - 1; |
2513 | this->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
2514 | } |
2515 | ||
2516 | /* A coding system of this category is always ASCII compatible. */ | |
2517 | src += coding->head_ascii; | |
3f003981 | 2518 | |
ff0dacd7 | 2519 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 2520 | { |
065e3595 | 2521 | src_base = src; |
df7492f9 | 2522 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2523 | switch (c) |
2524 | { | |
2525 | case ISO_CODE_ESC: | |
74383408 KH |
2526 | if (inhibit_iso_escape_detection) |
2527 | break; | |
f46869e4 | 2528 | single_shifting = 0; |
df7492f9 | 2529 | ONE_MORE_BYTE (c); |
d46c5b12 | 2530 | if (c >= '(' && c <= '/') |
4ed46869 | 2531 | { |
bf9cdd4e | 2532 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 2533 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2534 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2535 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
2536 | /* Invalid designation sequence. Just ignore. */ |
2537 | break; | |
bf9cdd4e KH |
2538 | } |
2539 | else if (c == '$') | |
2540 | { | |
2541 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 2542 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
2543 | if (c >= '@' && c <= 'B') |
2544 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
ff0dacd7 | 2545 | id = iso_charset_table[1][0][c]; |
bf9cdd4e | 2546 | else if (c >= '(' && c <= '/') |
bcf26d6a | 2547 | { |
df7492f9 | 2548 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2549 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2550 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
2551 | /* Invalid designation sequence. Just ignore. */ |
2552 | break; | |
bcf26d6a | 2553 | } |
bf9cdd4e | 2554 | else |
ff0dacd7 | 2555 | /* Invalid designation sequence. Just ignore it. */ |
d46c5b12 KH |
2556 | break; |
2557 | } | |
ae9ff118 | 2558 | else if (c == 'N' || c == 'O') |
d46c5b12 | 2559 | { |
ae9ff118 | 2560 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
2561 | single_shifting = 1; |
2562 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
d46c5b12 | 2563 | break; |
4ed46869 | 2564 | } |
ec6d2bb8 KH |
2565 | else if (c >= '0' && c <= '4') |
2566 | { | |
2567 | /* ESC <Fp> for start/end composition. */ | |
ff0dacd7 | 2568 | found |= CATEGORY_MASK_ISO; |
ec6d2bb8 KH |
2569 | break; |
2570 | } | |
bf9cdd4e | 2571 | else |
df7492f9 | 2572 | { |
ff0dacd7 | 2573 | /* Invalid escape sequence. Just ignore it. */ |
df7492f9 KH |
2574 | break; |
2575 | } | |
d46c5b12 KH |
2576 | |
2577 | /* We found a valid designation sequence for CHARSET. */ | |
ff0dacd7 | 2578 | rejected |= CATEGORY_MASK_ISO_8BIT; |
df7492f9 KH |
2579 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], |
2580 | id)) | |
ff0dacd7 | 2581 | found |= CATEGORY_MASK_ISO_7; |
d46c5b12 | 2582 | else |
ff0dacd7 | 2583 | rejected |= CATEGORY_MASK_ISO_7; |
df7492f9 KH |
2584 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], |
2585 | id)) | |
ff0dacd7 | 2586 | found |= CATEGORY_MASK_ISO_7_TIGHT; |
d46c5b12 | 2587 | else |
ff0dacd7 | 2588 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; |
df7492f9 KH |
2589 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], |
2590 | id)) | |
ff0dacd7 | 2591 | found |= CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 | 2592 | else |
ff0dacd7 | 2593 | rejected |= CATEGORY_MASK_ISO_7_ELSE; |
df7492f9 KH |
2594 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], |
2595 | id)) | |
ff0dacd7 | 2596 | found |= CATEGORY_MASK_ISO_8_ELSE; |
ae9ff118 | 2597 | else |
ff0dacd7 | 2598 | rejected |= CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
2599 | break; |
2600 | ||
4ed46869 | 2601 | case ISO_CODE_SO: |
d46c5b12 | 2602 | case ISO_CODE_SI: |
ff0dacd7 | 2603 | /* Locking shift out/in. */ |
74383408 KH |
2604 | if (inhibit_iso_escape_detection) |
2605 | break; | |
f46869e4 | 2606 | single_shifting = 0; |
ff0dacd7 KH |
2607 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
2608 | found |= CATEGORY_MASK_ISO_ELSE; | |
d46c5b12 KH |
2609 | break; |
2610 | ||
4ed46869 | 2611 | case ISO_CODE_CSI: |
ff0dacd7 | 2612 | /* Control sequence introducer. */ |
f46869e4 | 2613 | single_shifting = 0; |
ff0dacd7 KH |
2614 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2615 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
2616 | goto check_extra_latin; | |
2617 | ||
2618 | ||
4ed46869 KH |
2619 | case ISO_CODE_SS2: |
2620 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
2621 | /* Single shift. */ |
2622 | if (inhibit_iso_escape_detection) | |
2623 | break; | |
2624 | single_shifting = 1; | |
2625 | rejected |= CATEGORY_MASK_ISO_7BIT; | |
2626 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2627 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
2628 | found |= CATEGORY_MASK_ISO_8_1; | |
2629 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) | |
2630 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
2631 | found |= CATEGORY_MASK_ISO_8_2; | |
2632 | goto check_extra_latin; | |
4ed46869 KH |
2633 | |
2634 | default: | |
065e3595 KH |
2635 | if (c < 0) |
2636 | continue; | |
4ed46869 | 2637 | if (c < 0x80) |
f46869e4 KH |
2638 | { |
2639 | single_shifting = 0; | |
2640 | break; | |
2641 | } | |
ff0dacd7 | 2642 | if (c >= 0xA0) |
c4825358 | 2643 | { |
ff0dacd7 KH |
2644 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2645 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 2646 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
2647 | 0xA0..0FF. If the byte length is even, we include |
2648 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
2649 | only when we are not single shifting. */ | |
2650 | if (! single_shifting | |
2651 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 2652 | { |
e17de821 | 2653 | int i = 1; |
b73bfc1c KH |
2654 | while (src < src_end) |
2655 | { | |
df7492f9 | 2656 | ONE_MORE_BYTE (c); |
b73bfc1c KH |
2657 | if (c < 0xA0) |
2658 | break; | |
2659 | i++; | |
2660 | } | |
2661 | ||
2662 | if (i & 1 && src < src_end) | |
ff0dacd7 | 2663 | rejected |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2664 | else |
ff0dacd7 | 2665 | found |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2666 | } |
ff0dacd7 | 2667 | break; |
4ed46869 | 2668 | } |
ff0dacd7 KH |
2669 | check_extra_latin: |
2670 | single_shifting = 0; | |
2671 | if (! VECTORP (Vlatin_extra_code_table) | |
2672 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
2673 | { | |
2674 | rejected = CATEGORY_MASK_ISO; | |
2675 | break; | |
2676 | } | |
2677 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2678 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2679 | found |= CATEGORY_MASK_ISO_8_1; | |
2680 | else | |
2681 | rejected |= CATEGORY_MASK_ISO_8_1; | |
2682 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) | |
2683 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2684 | found |= CATEGORY_MASK_ISO_8_2; | |
2685 | else | |
2686 | rejected |= CATEGORY_MASK_ISO_8_2; | |
4ed46869 KH |
2687 | } |
2688 | } | |
ff0dacd7 KH |
2689 | detect_info->rejected |= CATEGORY_MASK_ISO; |
2690 | return 0; | |
4ed46869 | 2691 | |
df7492f9 | 2692 | no_more_source: |
ff0dacd7 KH |
2693 | detect_info->rejected |= rejected; |
2694 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 2695 | return 1; |
4ed46869 | 2696 | } |
ec6d2bb8 | 2697 | |
4ed46869 KH |
2698 | |
2699 | /* Set designation state into CODING. */ | |
df7492f9 KH |
2700 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
2701 | do { \ | |
2702 | int id, prev; \ | |
2703 | \ | |
2704 | if (final < '0' || final >= 128 \ | |
2705 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
2706 | || !SAFE_CHARSET_P (coding, id)) \ | |
2707 | { \ | |
2708 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
2709 | goto invalid_code; \ | |
2710 | } \ | |
2711 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
2712 | if (id == charset_jisx0201_roman) \ |
2713 | { \ | |
2714 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
2715 | id = charset_ascii; \ | |
2716 | } \ | |
2717 | else if (id == charset_jisx0208_1978) \ | |
2718 | { \ | |
2719 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
2720 | id = charset_jisx0208; \ | |
2721 | } \ | |
df7492f9 KH |
2722 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
2723 | /* If there was an invalid designation to REG previously, and this \ | |
2724 | designation is ASCII to REG, we should keep this designation \ | |
2725 | sequence. */ \ | |
2726 | if (prev == -2 && id == charset_ascii) \ | |
2727 | goto invalid_code; \ | |
4ed46869 KH |
2728 | } while (0) |
2729 | ||
d46c5b12 | 2730 | |
df7492f9 KH |
2731 | #define MAYBE_FINISH_COMPOSITION() \ |
2732 | do { \ | |
2733 | int i; \ | |
2734 | if (composition_state == COMPOSING_NO) \ | |
2735 | break; \ | |
2736 | /* It is assured that we have enough room for producing \ | |
2737 | characters stored in the table `components'. */ \ | |
2738 | if (charbuf + component_idx > charbuf_end) \ | |
2739 | goto no_more_source; \ | |
2740 | composition_state = COMPOSING_NO; \ | |
2741 | if (method == COMPOSITION_RELATIVE \ | |
2742 | || method == COMPOSITION_WITH_ALTCHARS) \ | |
2743 | { \ | |
2744 | for (i = 0; i < component_idx; i++) \ | |
2745 | *charbuf++ = components[i]; \ | |
2746 | char_offset += component_idx; \ | |
2747 | } \ | |
2748 | else \ | |
2749 | { \ | |
2750 | for (i = 0; i < component_idx; i += 2) \ | |
2751 | *charbuf++ = components[i]; \ | |
2752 | char_offset += (component_idx / 2) + 1; \ | |
2753 | } \ | |
2754 | } while (0) | |
2755 | ||
d46c5b12 | 2756 | |
aa72b389 KH |
2757 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
2758 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 | |
2759 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
2760 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
2761 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
aa72b389 | 2762 | */ |
ec6d2bb8 | 2763 | |
df7492f9 KH |
2764 | #define DECODE_COMPOSITION_START(c1) \ |
2765 | do { \ | |
2766 | if (c1 == '0' \ | |
781d7a48 | 2767 | && composition_state == COMPOSING_COMPONENT_RULE) \ |
df7492f9 KH |
2768 | { \ |
2769 | component_len = component_idx; \ | |
2770 | composition_state = COMPOSING_CHAR; \ | |
2771 | } \ | |
2772 | else \ | |
2773 | { \ | |
8f924df7 | 2774 | const unsigned char *p; \ |
df7492f9 KH |
2775 | \ |
2776 | MAYBE_FINISH_COMPOSITION (); \ | |
2777 | if (charbuf + MAX_COMPOSITION_COMPONENTS > charbuf_end) \ | |
2778 | goto no_more_source; \ | |
2779 | for (p = src; p < src_end - 1; p++) \ | |
2780 | if (*p == ISO_CODE_ESC && p[1] == '1') \ | |
2781 | break; \ | |
2782 | if (p == src_end - 1) \ | |
2783 | { \ | |
2784 | if (coding->mode & CODING_MODE_LAST_BLOCK) \ | |
2785 | goto invalid_code; \ | |
2786 | goto no_more_source; \ | |
2787 | } \ | |
2788 | \ | |
2789 | /* This is surely the start of a composition. */ \ | |
2790 | method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
2791 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
2792 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
2793 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
2794 | composition_state = (c1 <= '2' ? COMPOSING_CHAR \ | |
2795 | : COMPOSING_COMPONENT_CHAR); \ | |
2796 | component_idx = component_len = 0; \ | |
2797 | } \ | |
ec6d2bb8 KH |
2798 | } while (0) |
2799 | ||
ec6d2bb8 | 2800 | |
df7492f9 KH |
2801 | /* Handle compositoin end sequence ESC 1. */ |
2802 | ||
2803 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 2804 | do { \ |
df7492f9 KH |
2805 | int nchars = (component_len > 0 ? component_idx - component_len \ |
2806 | : method == COMPOSITION_RELATIVE ? component_idx \ | |
2807 | : (component_idx + 1) / 2); \ | |
2808 | int i; \ | |
2809 | int *saved_charbuf = charbuf; \ | |
8f924df7 | 2810 | int from = char_offset; \ |
ff0dacd7 | 2811 | int to = from + nchars; \ |
df7492f9 | 2812 | \ |
ff0dacd7 | 2813 | ADD_COMPOSITION_DATA (charbuf, from, to, method); \ |
df7492f9 | 2814 | if (method != COMPOSITION_RELATIVE) \ |
ec6d2bb8 | 2815 | { \ |
df7492f9 KH |
2816 | if (component_len == 0) \ |
2817 | for (i = 0; i < component_idx; i++) \ | |
2818 | *charbuf++ = components[i]; \ | |
2819 | else \ | |
2820 | for (i = 0; i < component_len; i++) \ | |
2821 | *charbuf++ = components[i]; \ | |
2822 | *saved_charbuf = saved_charbuf - charbuf; \ | |
ec6d2bb8 | 2823 | } \ |
df7492f9 KH |
2824 | if (method == COMPOSITION_WITH_RULE) \ |
2825 | for (i = 0; i < component_idx; i += 2, char_offset++) \ | |
2826 | *charbuf++ = components[i]; \ | |
ec6d2bb8 | 2827 | else \ |
df7492f9 KH |
2828 | for (i = component_len; i < component_idx; i++, char_offset++) \ |
2829 | *charbuf++ = components[i]; \ | |
2830 | coding->annotated = 1; \ | |
2831 | composition_state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
2832 | } while (0) |
2833 | ||
df7492f9 | 2834 | |
ec6d2bb8 KH |
2835 | /* Decode a composition rule from the byte C1 (and maybe one more byte |
2836 | from SRC) and store one encoded composition rule in | |
2837 | coding->cmp_data. */ | |
2838 | ||
2839 | #define DECODE_COMPOSITION_RULE(c1) \ | |
2840 | do { \ | |
ec6d2bb8 KH |
2841 | (c1) -= 32; \ |
2842 | if (c1 < 81) /* old format (before ver.21) */ \ | |
2843 | { \ | |
2844 | int gref = (c1) / 9; \ | |
2845 | int nref = (c1) % 9; \ | |
2846 | if (gref == 4) gref = 10; \ | |
2847 | if (nref == 4) nref = 10; \ | |
df7492f9 | 2848 | c1 = COMPOSITION_ENCODE_RULE (gref, nref); \ |
ec6d2bb8 | 2849 | } \ |
b73bfc1c | 2850 | else if (c1 < 93) /* new format (after ver.21) */ \ |
ec6d2bb8 KH |
2851 | { \ |
2852 | ONE_MORE_BYTE (c2); \ | |
df7492f9 | 2853 | c1 = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \ |
ec6d2bb8 | 2854 | } \ |
df7492f9 KH |
2855 | else \ |
2856 | c1 = 0; \ | |
ec6d2bb8 | 2857 | } while (0) |
88993dfd | 2858 | |
d46c5b12 | 2859 | |
4ed46869 KH |
2860 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
2861 | ||
b73bfc1c | 2862 | static void |
df7492f9 | 2863 | decode_coding_iso_2022 (coding) |
4ed46869 | 2864 | struct coding_system *coding; |
4ed46869 | 2865 | { |
8f924df7 KH |
2866 | const unsigned char *src = coding->source + coding->consumed; |
2867 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2868 | const unsigned char *src_base; | |
df7492f9 | 2869 | int *charbuf = coding->charbuf; |
ff0dacd7 KH |
2870 | int *charbuf_end |
2871 | = charbuf + coding->charbuf_size - 4 - MAX_ANNOTATION_LENGTH; | |
df7492f9 | 2872 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2873 | int multibytep = coding->src_multibyte; |
4ed46869 | 2874 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
2875 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
2876 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
2877 | struct charset *charset; | |
2878 | int c; | |
2879 | /* For handling composition sequence. */ | |
2880 | #define COMPOSING_NO 0 | |
2881 | #define COMPOSING_CHAR 1 | |
2882 | #define COMPOSING_RULE 2 | |
2883 | #define COMPOSING_COMPONENT_CHAR 3 | |
2884 | #define COMPOSING_COMPONENT_RULE 4 | |
2885 | ||
2886 | int composition_state = COMPOSING_NO; | |
2887 | enum composition_method method; | |
2888 | int components[MAX_COMPOSITION_COMPONENTS * 2 + 1]; | |
2889 | int component_idx; | |
2890 | int component_len; | |
24a73b0a | 2891 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2892 | int char_offset = coding->produced_char; |
2893 | int last_offset = char_offset; | |
2894 | int last_id = charset_ascii; | |
df7492f9 | 2895 | |
24a73b0a | 2896 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 2897 | setup_iso_safe_charsets (attrs); |
b73bfc1c KH |
2898 | |
2899 | while (1) | |
4ed46869 | 2900 | { |
463f5630 | 2901 | int c1, c2; |
b73bfc1c KH |
2902 | |
2903 | src_base = src; | |
df7492f9 KH |
2904 | consumed_chars_base = consumed_chars; |
2905 | ||
2906 | if (charbuf >= charbuf_end) | |
2907 | break; | |
2908 | ||
b73bfc1c | 2909 | ONE_MORE_BYTE (c1); |
065e3595 KH |
2910 | if (c1 < 0) |
2911 | goto invalid_code; | |
4ed46869 | 2912 | |
98725083 | 2913 | /* We produce at most one character. */ |
4ed46869 KH |
2914 | switch (iso_code_class [c1]) |
2915 | { | |
2916 | case ISO_0x20_or_0x7F: | |
df7492f9 | 2917 | if (composition_state != COMPOSING_NO) |
ec6d2bb8 | 2918 | { |
df7492f9 KH |
2919 | if (composition_state == COMPOSING_RULE |
2920 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2921 | { | |
2922 | DECODE_COMPOSITION_RULE (c1); | |
2923 | components[component_idx++] = c1; | |
2924 | composition_state--; | |
2925 | continue; | |
2926 | } | |
4ed46869 | 2927 | } |
df7492f9 KH |
2928 | if (charset_id_0 < 0 |
2929 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
2930 | /* This is SPACE or DEL. */ |
2931 | charset = CHARSET_FROM_ID (charset_ascii); | |
2932 | else | |
2933 | charset = CHARSET_FROM_ID (charset_id_0); | |
2934 | break; | |
4ed46869 KH |
2935 | |
2936 | case ISO_graphic_plane_0: | |
781d7a48 | 2937 | if (composition_state != COMPOSING_NO) |
b73bfc1c | 2938 | { |
781d7a48 KH |
2939 | if (composition_state == COMPOSING_RULE |
2940 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2941 | { | |
2942 | DECODE_COMPOSITION_RULE (c1); | |
2943 | components[component_idx++] = c1; | |
2944 | composition_state--; | |
2945 | continue; | |
2946 | } | |
b73bfc1c | 2947 | } |
df7492f9 | 2948 | charset = CHARSET_FROM_ID (charset_id_0); |
4ed46869 KH |
2949 | break; |
2950 | ||
2951 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
2952 | if (charset_id_1 < 0 |
2953 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
2954 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
2955 | goto invalid_code; | |
4ed46869 KH |
2956 | /* This is a graphic character, we fall down ... */ |
2957 | ||
2958 | case ISO_graphic_plane_1: | |
df7492f9 KH |
2959 | if (charset_id_1 < 0) |
2960 | goto invalid_code; | |
2961 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
2962 | break; |
2963 | ||
df7492f9 KH |
2964 | case ISO_control_0: |
2965 | MAYBE_FINISH_COMPOSITION (); | |
2966 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
2967 | break; |
2968 | ||
df7492f9 KH |
2969 | case ISO_control_1: |
2970 | MAYBE_FINISH_COMPOSITION (); | |
2971 | goto invalid_code; | |
2972 | ||
4ed46869 | 2973 | case ISO_shift_out: |
df7492f9 KH |
2974 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
2975 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
2976 | goto invalid_code; | |
2977 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
2978 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 2979 | continue; |
4ed46869 KH |
2980 | |
2981 | case ISO_shift_in: | |
df7492f9 KH |
2982 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
2983 | goto invalid_code; | |
2984 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
2985 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 2986 | continue; |
4ed46869 KH |
2987 | |
2988 | case ISO_single_shift_2_7: | |
2989 | case ISO_single_shift_2: | |
df7492f9 KH |
2990 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
2991 | goto invalid_code; | |
4ed46869 KH |
2992 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
2993 | c1 = 'N'; | |
2994 | goto label_escape_sequence; | |
2995 | ||
2996 | case ISO_single_shift_3: | |
df7492f9 KH |
2997 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
2998 | goto invalid_code; | |
4ed46869 KH |
2999 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3000 | c1 = 'O'; | |
3001 | goto label_escape_sequence; | |
3002 | ||
3003 | case ISO_control_sequence_introducer: | |
3004 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3005 | c1 = '['; | |
3006 | goto label_escape_sequence; | |
3007 | ||
3008 | case ISO_escape: | |
3009 | ONE_MORE_BYTE (c1); | |
3010 | label_escape_sequence: | |
df7492f9 | 3011 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3012 | designation, direction specification, and character |
3013 | composition specification. */ | |
3014 | switch (c1) | |
3015 | { | |
3016 | case '&': /* revision of following character set */ | |
3017 | ONE_MORE_BYTE (c1); | |
3018 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3019 | goto invalid_code; |
4ed46869 KH |
3020 | ONE_MORE_BYTE (c1); |
3021 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3022 | goto invalid_code; |
4ed46869 KH |
3023 | ONE_MORE_BYTE (c1); |
3024 | goto label_escape_sequence; | |
3025 | ||
3026 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3027 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3028 | goto invalid_code; | |
4ed46869 KH |
3029 | ONE_MORE_BYTE (c1); |
3030 | if (c1 >= '@' && c1 <= 'B') | |
3031 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3032 | or JISX0208.1980 */ |
df7492f9 | 3033 | DECODE_DESIGNATION (0, 2, 0, c1); |
4ed46869 KH |
3034 | } |
3035 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3036 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3037 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3038 | DECODE_DESIGNATION (c1 - 0x28, 2, 0, c2); |
4ed46869 KH |
3039 | } |
3040 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3041 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3042 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3043 | DECODE_DESIGNATION (c1 - 0x2C, 2, 1, c2); |
4ed46869 KH |
3044 | } |
3045 | else | |
df7492f9 | 3046 | goto invalid_code; |
b73bfc1c | 3047 | /* We must update these variables now. */ |
df7492f9 KH |
3048 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3049 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
b73bfc1c | 3050 | continue; |
4ed46869 KH |
3051 | |
3052 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3053 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3054 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3055 | goto invalid_code; | |
3056 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3057 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3058 | continue; |
4ed46869 KH |
3059 | |
3060 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3061 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3062 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3063 | goto invalid_code; | |
3064 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3065 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3066 | continue; |
4ed46869 KH |
3067 | |
3068 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3069 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3070 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3071 | goto invalid_code; | |
3072 | charset = CHARSET_FROM_ID (CODING_ISO_DESIGNATION (coding, 2)); | |
b73bfc1c | 3073 | ONE_MORE_BYTE (c1); |
e7046a18 | 3074 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3075 | goto invalid_code; |
4ed46869 KH |
3076 | break; |
3077 | ||
3078 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3079 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3080 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3081 | goto invalid_code; | |
3082 | charset = CHARSET_FROM_ID (CODING_ISO_DESIGNATION (coding, 3)); | |
b73bfc1c | 3083 | ONE_MORE_BYTE (c1); |
e7046a18 | 3084 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3085 | goto invalid_code; |
4ed46869 KH |
3086 | break; |
3087 | ||
ec6d2bb8 | 3088 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3089 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3090 | goto invalid_code; | |
ec6d2bb8 | 3091 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3092 | continue; |
4ed46869 | 3093 | |
ec6d2bb8 | 3094 | case '1': /* end composition */ |
df7492f9 KH |
3095 | if (composition_state == COMPOSING_NO) |
3096 | goto invalid_code; | |
3097 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3098 | continue; |
4ed46869 KH |
3099 | |
3100 | case '[': /* specification of direction */ | |
df7492f9 KH |
3101 | if (! CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION) |
3102 | goto invalid_code; | |
4ed46869 | 3103 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3104 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
df7492f9 | 3105 | left-to-right, and nozero means right-to-left. */ |
4ed46869 KH |
3106 | ONE_MORE_BYTE (c1); |
3107 | switch (c1) | |
3108 | { | |
3109 | case ']': /* end of the current direction */ | |
d46c5b12 | 3110 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3111 | |
3112 | case '0': /* end of the current direction */ | |
3113 | case '1': /* start of left-to-right direction */ | |
3114 | ONE_MORE_BYTE (c1); | |
3115 | if (c1 == ']') | |
d46c5b12 | 3116 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3117 | else |
df7492f9 | 3118 | goto invalid_code; |
4ed46869 KH |
3119 | break; |
3120 | ||
3121 | case '2': /* start of right-to-left direction */ | |
3122 | ONE_MORE_BYTE (c1); | |
3123 | if (c1 == ']') | |
d46c5b12 | 3124 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3125 | else |
df7492f9 | 3126 | goto invalid_code; |
4ed46869 KH |
3127 | break; |
3128 | ||
3129 | default: | |
df7492f9 | 3130 | goto invalid_code; |
4ed46869 | 3131 | } |
b73bfc1c | 3132 | continue; |
4ed46869 | 3133 | |
103e0180 | 3134 | case '%': |
103e0180 KH |
3135 | ONE_MORE_BYTE (c1); |
3136 | if (c1 == '/') | |
3137 | { | |
3138 | /* CTEXT extended segment: | |
3139 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3140 | We keep these bytes as is for the moment. | |
3141 | They may be decoded by post-read-conversion. */ | |
3142 | int dim, M, L; | |
4776e638 | 3143 | int size; |
8f924df7 | 3144 | |
103e0180 KH |
3145 | ONE_MORE_BYTE (dim); |
3146 | ONE_MORE_BYTE (M); | |
3147 | ONE_MORE_BYTE (L); | |
3148 | size = ((M - 128) * 128) + (L - 128); | |
4776e638 KH |
3149 | if (charbuf + 8 + size > charbuf_end) |
3150 | goto break_loop; | |
3151 | *charbuf++ = ISO_CODE_ESC; | |
3152 | *charbuf++ = '%'; | |
3153 | *charbuf++ = '/'; | |
3154 | *charbuf++ = dim; | |
3155 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3156 | *charbuf++ = BYTE8_TO_CHAR (L); | |
103e0180 KH |
3157 | while (size-- > 0) |
3158 | { | |
3159 | ONE_MORE_BYTE (c1); | |
4776e638 | 3160 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3161 | } |
103e0180 KH |
3162 | } |
3163 | else if (c1 == 'G') | |
3164 | { | |
103e0180 KH |
3165 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3166 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3167 | We keep these bytes as is for the moment. | |
3168 | They may be decoded by post-read-conversion. */ | |
4776e638 KH |
3169 | int *p = charbuf; |
3170 | ||
3171 | if (p + 6 > charbuf_end) | |
3172 | goto break_loop; | |
3173 | *p++ = ISO_CODE_ESC; | |
3174 | *p++ = '%'; | |
3175 | *p++ = 'G'; | |
3176 | while (p < charbuf_end) | |
103e0180 KH |
3177 | { |
3178 | ONE_MORE_BYTE (c1); | |
3179 | if (c1 == ISO_CODE_ESC | |
3180 | && src + 1 < src_end | |
3181 | && src[0] == '%' | |
3182 | && src[1] == '@') | |
3183 | break; | |
4776e638 | 3184 | *p++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3185 | } |
4776e638 KH |
3186 | if (p + 3 > charbuf_end) |
3187 | goto break_loop; | |
3188 | *p++ = ISO_CODE_ESC; | |
3189 | *p++ = '%'; | |
3190 | *p++ = '@'; | |
3191 | charbuf = p; | |
103e0180 KH |
3192 | } |
3193 | else | |
4776e638 | 3194 | goto invalid_code; |
103e0180 | 3195 | continue; |
4776e638 | 3196 | break; |
103e0180 | 3197 | |
4ed46869 | 3198 | default: |
df7492f9 KH |
3199 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3200 | goto invalid_code; | |
4ed46869 KH |
3201 | if (c1 >= 0x28 && c1 <= 0x2B) |
3202 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3203 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3204 | DECODE_DESIGNATION (c1 - 0x28, 1, 0, c2); |
4ed46869 KH |
3205 | } |
3206 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3207 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3208 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3209 | DECODE_DESIGNATION (c1 - 0x2C, 1, 1, c2); |
4ed46869 KH |
3210 | } |
3211 | else | |
df7492f9 | 3212 | goto invalid_code; |
b73bfc1c | 3213 | /* We must update these variables now. */ |
df7492f9 KH |
3214 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3215 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
b73bfc1c | 3216 | continue; |
4ed46869 | 3217 | } |
b73bfc1c | 3218 | } |
4ed46869 | 3219 | |
ff0dacd7 KH |
3220 | if (charset->id != charset_ascii |
3221 | && last_id != charset->id) | |
3222 | { | |
3223 | if (last_id != charset_ascii) | |
3224 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
3225 | last_id = charset->id; | |
3226 | last_offset = char_offset; | |
3227 | } | |
3228 | ||
b73bfc1c | 3229 | /* Now we know CHARSET and 1st position code C1 of a character. |
df7492f9 KH |
3230 | Produce a decoded character while getting 2nd position code |
3231 | C2 if necessary. */ | |
3232 | c1 &= 0x7F; | |
3233 | if (CHARSET_DIMENSION (charset) > 1) | |
b73bfc1c KH |
3234 | { |
3235 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3236 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) |
b73bfc1c | 3237 | /* C2 is not in a valid range. */ |
df7492f9 KH |
3238 | goto invalid_code; |
3239 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3240 | if (CHARSET_DIMENSION (charset) > 2) | |
3241 | { | |
3242 | ONE_MORE_BYTE (c2); | |
3243 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) | |
3244 | /* C2 is not in a valid range. */ | |
3245 | goto invalid_code; | |
3246 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3247 | } | |
3248 | } | |
3249 | ||
3250 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); | |
3251 | if (c < 0) | |
3252 | { | |
3253 | MAYBE_FINISH_COMPOSITION (); | |
3254 | for (; src_base < src; src_base++, char_offset++) | |
3255 | { | |
3256 | if (ASCII_BYTE_P (*src_base)) | |
3257 | *charbuf++ = *src_base; | |
3258 | else | |
3259 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3260 | } | |
3261 | } | |
3262 | else if (composition_state == COMPOSING_NO) | |
3263 | { | |
3264 | *charbuf++ = c; | |
3265 | char_offset++; | |
4ed46869 | 3266 | } |
df7492f9 | 3267 | else |
781d7a48 KH |
3268 | { |
3269 | components[component_idx++] = c; | |
3270 | if (method == COMPOSITION_WITH_RULE | |
3271 | || (method == COMPOSITION_WITH_RULE_ALTCHARS | |
3272 | && composition_state == COMPOSING_COMPONENT_CHAR)) | |
3273 | composition_state++; | |
4ed46869 KH |
3274 | } |
3275 | continue; | |
3276 | ||
df7492f9 KH |
3277 | invalid_code: |
3278 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3279 | src = src_base; |
df7492f9 KH |
3280 | consumed_chars = consumed_chars_base; |
3281 | ONE_MORE_BYTE (c); | |
065e3595 | 3282 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3283 | char_offset++; |
df7492f9 | 3284 | coding->errors++; |
4776e638 KH |
3285 | continue; |
3286 | ||
3287 | break_loop: | |
3288 | break; | |
4ed46869 | 3289 | } |
fb88bf2d | 3290 | |
df7492f9 | 3291 | no_more_source: |
ff0dacd7 KH |
3292 | if (last_id != charset_ascii) |
3293 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
df7492f9 KH |
3294 | coding->consumed_char += consumed_chars_base; |
3295 | coding->consumed = src_base - coding->source; | |
3296 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3297 | } |
3298 | ||
b73bfc1c | 3299 | |
f4dee582 | 3300 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3301 | |
3302 | /* | |
f4dee582 | 3303 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 3304 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 3305 | variant has the following specifications: |
df7492f9 | 3306 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
3307 | 2. Allows short-form designation? |
3308 | 3. ASCII should be designated to G0 before control characters? | |
3309 | 4. ASCII should be designated to G0 at end of line? | |
3310 | 5. 7-bit environment or 8-bit environment? | |
3311 | 6. Use locking-shift? | |
3312 | 7. Use Single-shift? | |
3313 | And the following two are only for Japanese: | |
3314 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
3315 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
3316 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
3317 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 3318 | details. |
4ed46869 KH |
3319 | */ |
3320 | ||
3321 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
3322 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
3323 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
3324 | designation sequence of short-form. */ | |
4ed46869 KH |
3325 | |
3326 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
3327 | do { \ | |
df7492f9 | 3328 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
4ed46869 KH |
3329 | char *intermediate_char_94 = "()*+"; \ |
3330 | char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
3331 | int revision = -1; \ |
3332 | int c; \ | |
3333 | \ | |
3334 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 3335 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
3336 | \ |
3337 | if (revision >= 0) \ | |
70c22245 | 3338 | { \ |
df7492f9 KH |
3339 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
3340 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 3341 | } \ |
df7492f9 | 3342 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
3343 | if (CHARSET_DIMENSION (charset) == 1) \ |
3344 | { \ | |
df7492f9 KH |
3345 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
3346 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 3347 | else \ |
df7492f9 KH |
3348 | c = intermediate_char_96[reg]; \ |
3349 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
3350 | } \ |
3351 | else \ | |
3352 | { \ | |
df7492f9 KH |
3353 | EMIT_ONE_ASCII_BYTE ('$'); \ |
3354 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 3355 | { \ |
df7492f9 | 3356 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
3357 | || reg != 0 \ |
3358 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 3359 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
3360 | } \ |
3361 | else \ | |
df7492f9 | 3362 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 3363 | } \ |
df7492f9 KH |
3364 | EMIT_ONE_ASCII_BYTE (final_char); \ |
3365 | \ | |
3366 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
3367 | } while (0) |
3368 | ||
df7492f9 | 3369 | |
4ed46869 KH |
3370 | /* The following two macros produce codes (control character or escape |
3371 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
3372 | single-shift-3). */ | |
3373 | ||
df7492f9 KH |
3374 | #define ENCODE_SINGLE_SHIFT_2 \ |
3375 | do { \ | |
3376 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3377 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
3378 | else \ | |
3379 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
3380 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3381 | } while (0) |
3382 | ||
df7492f9 KH |
3383 | |
3384 | #define ENCODE_SINGLE_SHIFT_3 \ | |
3385 | do { \ | |
3386 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3387 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
3388 | else \ | |
3389 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
3390 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3391 | } while (0) |
3392 | ||
df7492f9 | 3393 | |
4ed46869 KH |
3394 | /* The following four macros produce codes (control character or |
3395 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
3396 | shift-out, locking-shift-2, and locking-shift-3). */ | |
3397 | ||
df7492f9 KH |
3398 | #define ENCODE_SHIFT_IN \ |
3399 | do { \ | |
3400 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
3401 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
3402 | } while (0) |
3403 | ||
df7492f9 KH |
3404 | |
3405 | #define ENCODE_SHIFT_OUT \ | |
3406 | do { \ | |
3407 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
3408 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
3409 | } while (0) |
3410 | ||
df7492f9 KH |
3411 | |
3412 | #define ENCODE_LOCKING_SHIFT_2 \ | |
3413 | do { \ | |
3414 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3415 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
3416 | } while (0) |
3417 | ||
df7492f9 KH |
3418 | |
3419 | #define ENCODE_LOCKING_SHIFT_3 \ | |
3420 | do { \ | |
3421 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3422 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
3423 | } while (0) |
3424 | ||
df7492f9 | 3425 | |
f4dee582 RS |
3426 | /* Produce codes for a DIMENSION1 character whose character set is |
3427 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
3428 | sequences are also produced in advance if necessary. */ |
3429 | ||
6e85d753 KH |
3430 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
3431 | do { \ | |
df7492f9 | 3432 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3433 | \ |
3434 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3435 | && id == charset_ascii) \ | |
3436 | { \ | |
3437 | id = charset_jisx0201_roman; \ | |
3438 | charset = CHARSET_FROM_ID (id); \ | |
3439 | } \ | |
3440 | \ | |
df7492f9 | 3441 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3442 | { \ |
df7492f9 KH |
3443 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3444 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 3445 | else \ |
df7492f9 KH |
3446 | EMIT_ONE_BYTE (c1 | 0x80); \ |
3447 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3448 | break; \ |
3449 | } \ | |
df7492f9 | 3450 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3451 | { \ |
df7492f9 | 3452 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
3453 | break; \ |
3454 | } \ | |
df7492f9 | 3455 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3456 | { \ |
df7492f9 | 3457 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
3458 | break; \ |
3459 | } \ | |
6e85d753 KH |
3460 | else \ |
3461 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3462 | must invoke it, or, at first, designate it to some graphic \ | |
3463 | register. Then repeat the loop to actually produce the \ | |
3464 | character. */ \ | |
df7492f9 KH |
3465 | dst = encode_invocation_designation (charset, coding, dst, \ |
3466 | &produced_chars); \ | |
4ed46869 KH |
3467 | } while (1) |
3468 | ||
df7492f9 | 3469 | |
f4dee582 RS |
3470 | /* Produce codes for a DIMENSION2 character whose character set is |
3471 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
3472 | invocation codes are also produced in advance if necessary. */ |
3473 | ||
6e85d753 KH |
3474 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
3475 | do { \ | |
df7492f9 | 3476 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3477 | \ |
3478 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3479 | && id == charset_jisx0208) \ | |
3480 | { \ | |
3481 | id = charset_jisx0208_1978; \ | |
3482 | charset = CHARSET_FROM_ID (id); \ | |
3483 | } \ | |
3484 | \ | |
df7492f9 | 3485 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3486 | { \ |
df7492f9 KH |
3487 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3488 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 3489 | else \ |
df7492f9 KH |
3490 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
3491 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3492 | break; \ |
3493 | } \ | |
df7492f9 | 3494 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3495 | { \ |
df7492f9 | 3496 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
3497 | break; \ |
3498 | } \ | |
df7492f9 | 3499 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3500 | { \ |
df7492f9 | 3501 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
3502 | break; \ |
3503 | } \ | |
6e85d753 KH |
3504 | else \ |
3505 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3506 | must invoke it, or, at first, designate it to some graphic \ | |
3507 | register. Then repeat the loop to actually produce the \ | |
3508 | character. */ \ | |
df7492f9 KH |
3509 | dst = encode_invocation_designation (charset, coding, dst, \ |
3510 | &produced_chars); \ | |
4ed46869 KH |
3511 | } while (1) |
3512 | ||
05e6f5dc | 3513 | |
df7492f9 KH |
3514 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
3515 | do { \ | |
3516 | int code = ENCODE_CHAR ((charset),(c)); \ | |
3517 | \ | |
3518 | if (CHARSET_DIMENSION (charset) == 1) \ | |
3519 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
3520 | else \ | |
3521 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 3522 | } while (0) |
bdd9fb48 | 3523 | |
05e6f5dc | 3524 | |
4ed46869 | 3525 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 3526 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
3527 | Return new DST. */ |
3528 | ||
3529 | unsigned char * | |
df7492f9 KH |
3530 | encode_invocation_designation (charset, coding, dst, p_nchars) |
3531 | struct charset *charset; | |
4ed46869 KH |
3532 | struct coding_system *coding; |
3533 | unsigned char *dst; | |
df7492f9 | 3534 | int *p_nchars; |
4ed46869 | 3535 | { |
df7492f9 KH |
3536 | int multibytep = coding->dst_multibyte; |
3537 | int produced_chars = *p_nchars; | |
4ed46869 | 3538 | int reg; /* graphic register number */ |
df7492f9 | 3539 | int id = CHARSET_ID (charset); |
4ed46869 KH |
3540 | |
3541 | /* At first, check designations. */ | |
3542 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 3543 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
3544 | break; |
3545 | ||
3546 | if (reg >= 4) | |
3547 | { | |
3548 | /* CHARSET is not yet designated to any graphic registers. */ | |
3549 | /* At first check the requested designation. */ | |
df7492f9 KH |
3550 | reg = CODING_ISO_REQUEST (coding, id); |
3551 | if (reg < 0) | |
1ba9e4ab KH |
3552 | /* Since CHARSET requests no special designation, designate it |
3553 | to graphic register 0. */ | |
4ed46869 KH |
3554 | reg = 0; |
3555 | ||
3556 | ENCODE_DESIGNATION (charset, reg, coding); | |
3557 | } | |
3558 | ||
df7492f9 KH |
3559 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
3560 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
3561 | { |
3562 | /* Since the graphic register REG is not invoked to any graphic | |
3563 | planes, invoke it to graphic plane 0. */ | |
3564 | switch (reg) | |
3565 | { | |
3566 | case 0: /* graphic register 0 */ | |
3567 | ENCODE_SHIFT_IN; | |
3568 | break; | |
3569 | ||
3570 | case 1: /* graphic register 1 */ | |
3571 | ENCODE_SHIFT_OUT; | |
3572 | break; | |
3573 | ||
3574 | case 2: /* graphic register 2 */ | |
df7492f9 | 3575 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3576 | ENCODE_SINGLE_SHIFT_2; |
3577 | else | |
3578 | ENCODE_LOCKING_SHIFT_2; | |
3579 | break; | |
3580 | ||
3581 | case 3: /* graphic register 3 */ | |
df7492f9 | 3582 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3583 | ENCODE_SINGLE_SHIFT_3; |
3584 | else | |
3585 | ENCODE_LOCKING_SHIFT_3; | |
3586 | break; | |
3587 | } | |
3588 | } | |
b73bfc1c | 3589 | |
df7492f9 | 3590 | *p_nchars = produced_chars; |
4ed46869 KH |
3591 | return dst; |
3592 | } | |
3593 | ||
df7492f9 KH |
3594 | /* The following three macros produce codes for indicating direction |
3595 | of text. */ | |
3596 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 3597 | do { \ |
df7492f9 KH |
3598 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
3599 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 3600 | else \ |
df7492f9 | 3601 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
3602 | } while (0) |
3603 | ||
ec6d2bb8 | 3604 | |
df7492f9 KH |
3605 | #define ENCODE_DIRECTION_R2L() \ |
3606 | do { \ | |
3607 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
3608 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
3609 | } while (0) |
3610 | ||
ec6d2bb8 | 3611 | |
df7492f9 | 3612 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 3613 | do { \ |
df7492f9 KH |
3614 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
3615 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
ec6d2bb8 | 3616 | } while (0) |
4ed46869 | 3617 | |
4ed46869 KH |
3618 | |
3619 | /* Produce codes for designation and invocation to reset the graphic | |
3620 | planes and registers to initial state. */ | |
df7492f9 KH |
3621 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
3622 | do { \ | |
3623 | int reg; \ | |
3624 | struct charset *charset; \ | |
3625 | \ | |
3626 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
3627 | ENCODE_SHIFT_IN; \ | |
3628 | for (reg = 0; reg < 4; reg++) \ | |
3629 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
3630 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
3631 | != CODING_ISO_INITIAL (coding, reg))) \ | |
3632 | { \ | |
3633 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
3634 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
3635 | } \ | |
4ed46869 KH |
3636 | } while (0) |
3637 | ||
df7492f9 | 3638 | |
bdd9fb48 | 3639 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 3640 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
3641 | |
3642 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
3643 | find all the necessary designations. */ |
3644 | ||
b73bfc1c | 3645 | static unsigned char * |
df7492f9 | 3646 | encode_designation_at_bol (coding, charbuf, charbuf_end, dst) |
e0e989f6 | 3647 | struct coding_system *coding; |
df7492f9 KH |
3648 | int *charbuf, *charbuf_end; |
3649 | unsigned char *dst; | |
e0e989f6 | 3650 | { |
df7492f9 | 3651 | struct charset *charset; |
bdd9fb48 KH |
3652 | /* Table of charsets to be designated to each graphic register. */ |
3653 | int r[4]; | |
df7492f9 KH |
3654 | int c, found = 0, reg; |
3655 | int produced_chars = 0; | |
3656 | int multibytep = coding->dst_multibyte; | |
3657 | Lisp_Object attrs; | |
3658 | Lisp_Object charset_list; | |
3659 | ||
3660 | attrs = CODING_ID_ATTRS (coding->id); | |
3661 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
3662 | if (EQ (charset_list, Qiso_2022)) | |
3663 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
3664 | |
3665 | for (reg = 0; reg < 4; reg++) | |
3666 | r[reg] = -1; | |
3667 | ||
b73bfc1c | 3668 | while (found < 4) |
e0e989f6 | 3669 | { |
df7492f9 KH |
3670 | int id; |
3671 | ||
3672 | c = *charbuf++; | |
b73bfc1c KH |
3673 | if (c == '\n') |
3674 | break; | |
df7492f9 KH |
3675 | charset = char_charset (c, charset_list, NULL); |
3676 | id = CHARSET_ID (charset); | |
3677 | reg = CODING_ISO_REQUEST (coding, id); | |
3678 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
3679 | { |
3680 | found++; | |
df7492f9 | 3681 | r[reg] = id; |
bdd9fb48 | 3682 | } |
bdd9fb48 KH |
3683 | } |
3684 | ||
3685 | if (found) | |
3686 | { | |
3687 | for (reg = 0; reg < 4; reg++) | |
3688 | if (r[reg] >= 0 | |
df7492f9 KH |
3689 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
3690 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 3691 | } |
b73bfc1c KH |
3692 | |
3693 | return dst; | |
e0e989f6 KH |
3694 | } |
3695 | ||
4ed46869 KH |
3696 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
3697 | ||
df7492f9 KH |
3698 | static int |
3699 | encode_coding_iso_2022 (coding) | |
4ed46869 | 3700 | struct coding_system *coding; |
4ed46869 | 3701 | { |
df7492f9 KH |
3702 | int multibytep = coding->dst_multibyte; |
3703 | int *charbuf = coding->charbuf; | |
3704 | int *charbuf_end = charbuf + coding->charbuf_used; | |
3705 | unsigned char *dst = coding->destination + coding->produced; | |
3706 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
3707 | int safe_room = 16; | |
3708 | int bol_designation | |
3709 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
3710 | && CODING_ISO_BOL (coding)); | |
3711 | int produced_chars = 0; | |
3712 | Lisp_Object attrs, eol_type, charset_list; | |
3713 | int ascii_compatible; | |
b73bfc1c | 3714 | int c; |
ff0dacd7 | 3715 | int preferred_charset_id = -1; |
05e6f5dc | 3716 | |
24a73b0a KH |
3717 | CODING_GET_INFO (coding, attrs, charset_list); |
3718 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
3719 | if (VECTORP (eol_type)) | |
3720 | eol_type = Qunix; | |
3721 | ||
004068e4 | 3722 | setup_iso_safe_charsets (attrs); |
ff0dacd7 KH |
3723 | /* Charset list may have been changed. */ |
3724 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); \ | |
8f924df7 | 3725 | coding->safe_charsets = (char *) SDATA (CODING_ATTR_SAFE_CHARSETS(attrs)); |
0eecad43 | 3726 | |
df7492f9 | 3727 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
bdd9fb48 | 3728 | |
df7492f9 | 3729 | while (charbuf < charbuf_end) |
4ed46869 | 3730 | { |
df7492f9 | 3731 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 3732 | |
df7492f9 | 3733 | if (bol_designation) |
b73bfc1c | 3734 | { |
df7492f9 | 3735 | unsigned char *dst_prev = dst; |
4ed46869 | 3736 | |
bdd9fb48 | 3737 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
3738 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
3739 | bol_designation = 0; | |
3740 | /* We are sure that designation sequences are all ASCII bytes. */ | |
3741 | produced_chars += dst - dst_prev; | |
e0e989f6 KH |
3742 | } |
3743 | ||
df7492f9 | 3744 | c = *charbuf++; |
ec6d2bb8 | 3745 | |
ff0dacd7 KH |
3746 | if (c < 0) |
3747 | { | |
3748 | /* Handle an annotation. */ | |
3749 | switch (*charbuf) | |
ec6d2bb8 | 3750 | { |
ff0dacd7 KH |
3751 | case CODING_ANNOTATE_COMPOSITION_MASK: |
3752 | /* Not yet implemented. */ | |
3753 | break; | |
3754 | case CODING_ANNOTATE_CHARSET_MASK: | |
3755 | preferred_charset_id = charbuf[3]; | |
3756 | if (preferred_charset_id >= 0 | |
3757 | && NILP (Fmemq (make_number (preferred_charset_id), | |
3758 | charset_list))) | |
3759 | preferred_charset_id = -1; | |
3760 | break; | |
3761 | default: | |
3762 | abort (); | |
4ed46869 | 3763 | } |
ff0dacd7 KH |
3764 | charbuf += -c - 1; |
3765 | continue; | |
4ed46869 | 3766 | } |
ec6d2bb8 | 3767 | |
b73bfc1c KH |
3768 | /* Now encode the character C. */ |
3769 | if (c < 0x20 || c == 0x7F) | |
3770 | { | |
df7492f9 KH |
3771 | if (c == '\n' |
3772 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 3773 | { |
df7492f9 KH |
3774 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
3775 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3776 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 3777 | { |
df7492f9 KH |
3778 | int i; |
3779 | ||
3780 | for (i = 0; i < 4; i++) | |
3781 | CODING_ISO_DESIGNATION (coding, i) | |
3782 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 3783 | } |
df7492f9 KH |
3784 | bol_designation |
3785 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 3786 | } |
df7492f9 KH |
3787 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
3788 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3789 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 3790 | } |
df7492f9 | 3791 | else if (ASCII_CHAR_P (c)) |
88993dfd | 3792 | { |
df7492f9 KH |
3793 | if (ascii_compatible) |
3794 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 3795 | else |
19a8d9e0 | 3796 | { |
bf16eb23 KH |
3797 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
3798 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 3799 | } |
4ed46869 | 3800 | } |
16eafb5d | 3801 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 3802 | { |
16eafb5d KH |
3803 | c = CHAR_TO_BYTE8 (c); |
3804 | EMIT_ONE_BYTE (c); | |
88993dfd | 3805 | } |
b73bfc1c | 3806 | else |
df7492f9 | 3807 | { |
ff0dacd7 | 3808 | struct charset *charset; |
b73bfc1c | 3809 | |
ff0dacd7 KH |
3810 | if (preferred_charset_id >= 0) |
3811 | { | |
3812 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
3813 | if (! CHAR_CHARSET_P (c, charset)) | |
3814 | charset = char_charset (c, charset_list, NULL); | |
3815 | } | |
3816 | else | |
3817 | charset = char_charset (c, charset_list, NULL); | |
df7492f9 KH |
3818 | if (!charset) |
3819 | { | |
41cbe562 KH |
3820 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
3821 | { | |
3822 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
3823 | charset = CHARSET_FROM_ID (charset_ascii); | |
3824 | } | |
3825 | else | |
3826 | { | |
3827 | c = coding->default_char; | |
3828 | charset = char_charset (c, charset_list, NULL); | |
3829 | } | |
df7492f9 KH |
3830 | } |
3831 | ENCODE_ISO_CHARACTER (charset, c); | |
3832 | } | |
84fbb8a0 | 3833 | } |
b73bfc1c | 3834 | |
df7492f9 KH |
3835 | if (coding->mode & CODING_MODE_LAST_BLOCK |
3836 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
3837 | { | |
3838 | ASSURE_DESTINATION (safe_room); | |
3839 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3840 | } | |
065e3595 | 3841 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
3842 | CODING_ISO_BOL (coding) = bol_designation; |
3843 | coding->produced_char += produced_chars; | |
3844 | coding->produced = dst - coding->destination; | |
3845 | return 0; | |
4ed46869 KH |
3846 | } |
3847 | ||
3848 | \f | |
df7492f9 | 3849 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 3850 | |
df7492f9 | 3851 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
3852 | quite widely. So, for the moment, Emacs supports them in the bare |
3853 | C code. But, in the future, they may be supported only by CCL. */ | |
3854 | ||
3855 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
3856 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
3857 | as is. A character of charset katakana-jisx0201 is encoded by | |
3858 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
3859 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 3860 | so that it fit in the range below. |
4ed46869 KH |
3861 | |
3862 | --- CODE RANGE of SJIS --- | |
3863 | (character set) (range) | |
3864 | ASCII 0x00 .. 0x7F | |
df7492f9 | 3865 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 3866 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 3867 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
3868 | ------------------------------- |
3869 | ||
3870 | */ | |
3871 | ||
3872 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
3873 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 3874 | character set and is encoded in two-byte. |
4ed46869 KH |
3875 | |
3876 | --- CODE RANGE of BIG5 --- | |
3877 | (character set) (range) | |
3878 | ASCII 0x00 .. 0x7F | |
3879 | Big5 (1st byte) 0xA1 .. 0xFE | |
3880 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
3881 | -------------------------- | |
3882 | ||
df7492f9 | 3883 | */ |
4ed46869 KH |
3884 | |
3885 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3886 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 3887 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 3888 | |
0a28aafb | 3889 | static int |
ff0dacd7 | 3890 | detect_coding_sjis (coding, detect_info) |
df7492f9 | 3891 | struct coding_system *coding; |
ff0dacd7 | 3892 | struct coding_detection_info *detect_info; |
4ed46869 | 3893 | { |
065e3595 | 3894 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 3895 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
3896 | int multibytep = coding->src_multibyte; |
3897 | int consumed_chars = 0; | |
3898 | int found = 0; | |
b73bfc1c | 3899 | int c; |
df7492f9 | 3900 | |
ff0dacd7 | 3901 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3902 | /* A coding system of this category is always ASCII compatible. */ |
3903 | src += coding->head_ascii; | |
4ed46869 | 3904 | |
b73bfc1c | 3905 | while (1) |
4ed46869 | 3906 | { |
065e3595 | 3907 | src_base = src; |
df7492f9 | 3908 | ONE_MORE_BYTE (c); |
682169fe KH |
3909 | if (c < 0x80) |
3910 | continue; | |
df7492f9 | 3911 | if ((c >= 0x81 && c <= 0x9F) || (c >= 0xE0 && c <= 0xEF)) |
4ed46869 | 3912 | { |
df7492f9 | 3913 | ONE_MORE_BYTE (c); |
682169fe | 3914 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 3915 | break; |
ff0dacd7 | 3916 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 3917 | } |
df7492f9 | 3918 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 3919 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
3920 | else |
3921 | break; | |
4ed46869 | 3922 | } |
ff0dacd7 | 3923 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3924 | return 0; |
3925 | ||
3926 | no_more_source: | |
065e3595 | 3927 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 3928 | { |
ff0dacd7 | 3929 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 3930 | return 0; |
4ed46869 | 3931 | } |
ff0dacd7 KH |
3932 | detect_info->found |= found; |
3933 | return 1; | |
4ed46869 KH |
3934 | } |
3935 | ||
3936 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3937 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 3938 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 3939 | |
0a28aafb | 3940 | static int |
ff0dacd7 | 3941 | detect_coding_big5 (coding, detect_info) |
df7492f9 | 3942 | struct coding_system *coding; |
ff0dacd7 | 3943 | struct coding_detection_info *detect_info; |
4ed46869 | 3944 | { |
065e3595 | 3945 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 3946 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
3947 | int multibytep = coding->src_multibyte; |
3948 | int consumed_chars = 0; | |
3949 | int found = 0; | |
b73bfc1c | 3950 | int c; |
fa42c37f | 3951 | |
ff0dacd7 | 3952 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
3953 | /* A coding system of this category is always ASCII compatible. */ |
3954 | src += coding->head_ascii; | |
fa42c37f | 3955 | |
b73bfc1c | 3956 | while (1) |
fa42c37f | 3957 | { |
065e3595 | 3958 | src_base = src; |
df7492f9 KH |
3959 | ONE_MORE_BYTE (c); |
3960 | if (c < 0x80) | |
fa42c37f | 3961 | continue; |
df7492f9 | 3962 | if (c >= 0xA1) |
fa42c37f | 3963 | { |
df7492f9 KH |
3964 | ONE_MORE_BYTE (c); |
3965 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 3966 | return 0; |
ff0dacd7 | 3967 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 3968 | } |
df7492f9 KH |
3969 | else |
3970 | break; | |
fa42c37f | 3971 | } |
ff0dacd7 | 3972 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 3973 | return 0; |
fa42c37f | 3974 | |
df7492f9 | 3975 | no_more_source: |
065e3595 | 3976 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 3977 | { |
ff0dacd7 | 3978 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
3979 | return 0; |
3980 | } | |
ff0dacd7 KH |
3981 | detect_info->found |= found; |
3982 | return 1; | |
fa42c37f KH |
3983 | } |
3984 | ||
4ed46869 KH |
3985 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
3986 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
fa42c37f | 3987 | |
b73bfc1c | 3988 | static void |
df7492f9 | 3989 | decode_coding_sjis (coding) |
4ed46869 | 3990 | struct coding_system *coding; |
4ed46869 | 3991 | { |
8f924df7 KH |
3992 | const unsigned char *src = coding->source + coding->consumed; |
3993 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
3994 | const unsigned char *src_base; | |
df7492f9 | 3995 | int *charbuf = coding->charbuf; |
ff0dacd7 | 3996 | int *charbuf_end = charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; |
df7492f9 KH |
3997 | int consumed_chars = 0, consumed_chars_base; |
3998 | int multibytep = coding->src_multibyte; | |
3999 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
24a73b0a | 4000 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4001 | int char_offset = coding->produced_char; |
4002 | int last_offset = char_offset; | |
4003 | int last_id = charset_ascii; | |
a5d301df | 4004 | |
24a73b0a | 4005 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4006 | |
4007 | val = charset_list; | |
4008 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 KH |
4009 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4010 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4011 | |
b73bfc1c | 4012 | while (1) |
4ed46869 | 4013 | { |
df7492f9 | 4014 | int c, c1; |
24a73b0a | 4015 | struct charset *charset; |
fa42c37f | 4016 | |
b73bfc1c | 4017 | src_base = src; |
df7492f9 | 4018 | consumed_chars_base = consumed_chars; |
fa42c37f | 4019 | |
df7492f9 KH |
4020 | if (charbuf >= charbuf_end) |
4021 | break; | |
4022 | ||
4023 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4024 | if (c < 0) |
4025 | goto invalid_code; | |
24a73b0a KH |
4026 | if (c < 0x80) |
4027 | charset = charset_roman; | |
8e921c4b KH |
4028 | else if (c == 0x80) |
4029 | goto invalid_code; | |
54f78171 | 4030 | else |
df7492f9 | 4031 | { |
24a73b0a KH |
4032 | if (c >= 0xF0) |
4033 | goto invalid_code; | |
4034 | if (c < 0xA0 || c >= 0xE0) | |
4ed46869 | 4035 | { |
24a73b0a KH |
4036 | /* SJIS -> JISX0208 */ |
4037 | ONE_MORE_BYTE (c1); | |
4038 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
7487494c | 4039 | goto invalid_code; |
24a73b0a KH |
4040 | c = (c << 8) | c1; |
4041 | SJIS_TO_JIS (c); | |
4042 | charset = charset_kanji; | |
df7492f9 | 4043 | } |
24a73b0a | 4044 | else if (c > 0xA0) |
ff0dacd7 | 4045 | { |
24a73b0a KH |
4046 | /* SJIS -> JISX0201-Kana */ |
4047 | c &= 0x7F; | |
4048 | charset = charset_kana; | |
ff0dacd7 | 4049 | } |
24a73b0a KH |
4050 | else |
4051 | goto invalid_code; | |
df7492f9 | 4052 | } |
24a73b0a KH |
4053 | if (charset->id != charset_ascii |
4054 | && last_id != charset->id) | |
4055 | { | |
4056 | if (last_id != charset_ascii) | |
4057 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
4058 | last_id = charset->id; | |
4059 | last_offset = char_offset; | |
4060 | } | |
4061 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4062 | *charbuf++ = c; |
ff0dacd7 | 4063 | char_offset++; |
df7492f9 | 4064 | continue; |
b73bfc1c | 4065 | |
df7492f9 KH |
4066 | invalid_code: |
4067 | src = src_base; | |
4068 | consumed_chars = consumed_chars_base; | |
4069 | ONE_MORE_BYTE (c); | |
065e3595 | 4070 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4071 | char_offset++; |
df7492f9 KH |
4072 | coding->errors++; |
4073 | } | |
fa42c37f | 4074 | |
df7492f9 | 4075 | no_more_source: |
ff0dacd7 KH |
4076 | if (last_id != charset_ascii) |
4077 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
df7492f9 KH |
4078 | coding->consumed_char += consumed_chars_base; |
4079 | coding->consumed = src_base - coding->source; | |
4080 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4081 | } |
4082 | ||
b73bfc1c | 4083 | static void |
df7492f9 | 4084 | decode_coding_big5 (coding) |
4ed46869 | 4085 | struct coding_system *coding; |
4ed46869 | 4086 | { |
8f924df7 KH |
4087 | const unsigned char *src = coding->source + coding->consumed; |
4088 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4089 | const unsigned char *src_base; | |
df7492f9 | 4090 | int *charbuf = coding->charbuf; |
ff0dacd7 | 4091 | int *charbuf_end = charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; |
df7492f9 KH |
4092 | int consumed_chars = 0, consumed_chars_base; |
4093 | int multibytep = coding->src_multibyte; | |
4094 | struct charset *charset_roman, *charset_big5; | |
24a73b0a | 4095 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4096 | int char_offset = coding->produced_char; |
4097 | int last_offset = char_offset; | |
4098 | int last_id = charset_ascii; | |
df7492f9 | 4099 | |
24a73b0a | 4100 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4101 | val = charset_list; |
4102 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4103 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4104 | |
b73bfc1c | 4105 | while (1) |
4ed46869 | 4106 | { |
df7492f9 | 4107 | int c, c1; |
24a73b0a | 4108 | struct charset *charset; |
b73bfc1c KH |
4109 | |
4110 | src_base = src; | |
df7492f9 KH |
4111 | consumed_chars_base = consumed_chars; |
4112 | ||
4113 | if (charbuf >= charbuf_end) | |
4114 | break; | |
4115 | ||
4116 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4117 | |
065e3595 KH |
4118 | if (c < 0) |
4119 | goto invalid_code; | |
24a73b0a KH |
4120 | if (c < 0x80) |
4121 | charset = charset_roman; | |
4122 | else | |
4ed46869 | 4123 | { |
24a73b0a KH |
4124 | /* BIG5 -> Big5 */ |
4125 | if (c < 0xA1 || c > 0xFE) | |
4126 | goto invalid_code; | |
4127 | ONE_MORE_BYTE (c1); | |
4128 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4129 | goto invalid_code; | |
4130 | c = c << 8 | c1; | |
4131 | charset = charset_big5; | |
4ed46869 | 4132 | } |
24a73b0a KH |
4133 | if (charset->id != charset_ascii |
4134 | && last_id != charset->id) | |
df7492f9 | 4135 | { |
24a73b0a KH |
4136 | if (last_id != charset_ascii) |
4137 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
4138 | last_id = charset->id; | |
4139 | last_offset = char_offset; | |
4ed46869 | 4140 | } |
24a73b0a | 4141 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4142 | *charbuf++ = c; |
ff0dacd7 | 4143 | char_offset++; |
fb88bf2d KH |
4144 | continue; |
4145 | ||
df7492f9 | 4146 | invalid_code: |
4ed46869 | 4147 | src = src_base; |
df7492f9 KH |
4148 | consumed_chars = consumed_chars_base; |
4149 | ONE_MORE_BYTE (c); | |
065e3595 | 4150 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4151 | char_offset++; |
df7492f9 | 4152 | coding->errors++; |
fb88bf2d | 4153 | } |
d46c5b12 | 4154 | |
df7492f9 | 4155 | no_more_source: |
ff0dacd7 KH |
4156 | if (last_id != charset_ascii) |
4157 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
df7492f9 KH |
4158 | coding->consumed_char += consumed_chars_base; |
4159 | coding->consumed = src_base - coding->source; | |
4160 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4161 | } |
4162 | ||
4163 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4164 | This function can encode charsets `ascii', `katakana-jisx0201', |
4165 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4166 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
4167 | (i.e. do not have extended leading-codes). Characters of other |
4168 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
4169 | SJIS text, else encode BIG5 text. */ | |
4170 | ||
df7492f9 KH |
4171 | static int |
4172 | encode_coding_sjis (coding) | |
4ed46869 | 4173 | struct coding_system *coding; |
4ed46869 | 4174 | { |
df7492f9 KH |
4175 | int multibytep = coding->dst_multibyte; |
4176 | int *charbuf = coding->charbuf; | |
4177 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4178 | unsigned char *dst = coding->destination + coding->produced; | |
4179 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4180 | int safe_room = 4; | |
4181 | int produced_chars = 0; | |
24a73b0a | 4182 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4183 | int ascii_compatible; |
4184 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
4185 | int c; | |
a5d301df | 4186 | |
24a73b0a | 4187 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4188 | val = charset_list; |
4189 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4190 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4191 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4192 | |
df7492f9 | 4193 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4194 | |
df7492f9 KH |
4195 | while (charbuf < charbuf_end) |
4196 | { | |
4197 | ASSURE_DESTINATION (safe_room); | |
4198 | c = *charbuf++; | |
b73bfc1c | 4199 | /* Now encode the character C. */ |
df7492f9 KH |
4200 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4201 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4202 | else if (CHAR_BYTE8_P (c)) |
4203 | { | |
4204 | c = CHAR_TO_BYTE8 (c); | |
4205 | EMIT_ONE_BYTE (c); | |
4206 | } | |
df7492f9 | 4207 | else |
b73bfc1c | 4208 | { |
df7492f9 KH |
4209 | unsigned code; |
4210 | struct charset *charset = char_charset (c, charset_list, &code); | |
4211 | ||
4212 | if (!charset) | |
4ed46869 | 4213 | { |
41cbe562 | 4214 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4215 | { |
41cbe562 KH |
4216 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4217 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4218 | } |
41cbe562 | 4219 | else |
b73bfc1c | 4220 | { |
41cbe562 KH |
4221 | c = coding->default_char; |
4222 | charset = char_charset (c, charset_list, &code); | |
b73bfc1c | 4223 | } |
b73bfc1c | 4224 | } |
df7492f9 KH |
4225 | if (code == CHARSET_INVALID_CODE (charset)) |
4226 | abort (); | |
4227 | if (charset == charset_kanji) | |
4228 | { | |
4229 | int c1, c2; | |
4230 | JIS_TO_SJIS (code); | |
4231 | c1 = code >> 8, c2 = code & 0xFF; | |
4232 | EMIT_TWO_BYTES (c1, c2); | |
4233 | } | |
4234 | else if (charset == charset_kana) | |
4235 | EMIT_ONE_BYTE (code | 0x80); | |
4236 | else | |
4237 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4238 | } | |
4239 | } | |
065e3595 | 4240 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4241 | coding->produced_char += produced_chars; |
4242 | coding->produced = dst - coding->destination; | |
4243 | return 0; | |
4244 | } | |
4245 | ||
4246 | static int | |
4247 | encode_coding_big5 (coding) | |
4248 | struct coding_system *coding; | |
4249 | { | |
4250 | int multibytep = coding->dst_multibyte; | |
4251 | int *charbuf = coding->charbuf; | |
4252 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4253 | unsigned char *dst = coding->destination + coding->produced; | |
4254 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4255 | int safe_room = 4; | |
4256 | int produced_chars = 0; | |
24a73b0a | 4257 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4258 | int ascii_compatible; |
4259 | struct charset *charset_roman, *charset_big5; | |
4260 | int c; | |
4261 | ||
24a73b0a | 4262 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4263 | val = charset_list; |
4264 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4265 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4266 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
4267 | ||
4268 | while (charbuf < charbuf_end) | |
4269 | { | |
4270 | ASSURE_DESTINATION (safe_room); | |
4271 | c = *charbuf++; | |
4272 | /* Now encode the character C. */ | |
4273 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
4274 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4275 | else if (CHAR_BYTE8_P (c)) |
4276 | { | |
4277 | c = CHAR_TO_BYTE8 (c); | |
4278 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
4279 | } |
4280 | else | |
4281 | { | |
df7492f9 KH |
4282 | unsigned code; |
4283 | struct charset *charset = char_charset (c, charset_list, &code); | |
4284 | ||
4285 | if (! charset) | |
b73bfc1c | 4286 | { |
41cbe562 | 4287 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4288 | { |
41cbe562 KH |
4289 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4290 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4291 | } |
41cbe562 | 4292 | else |
0eecad43 | 4293 | { |
41cbe562 KH |
4294 | c = coding->default_char; |
4295 | charset = char_charset (c, charset_list, &code); | |
0eecad43 | 4296 | } |
4ed46869 | 4297 | } |
df7492f9 KH |
4298 | if (code == CHARSET_INVALID_CODE (charset)) |
4299 | abort (); | |
4300 | if (charset == charset_big5) | |
b73bfc1c | 4301 | { |
df7492f9 KH |
4302 | int c1, c2; |
4303 | ||
4304 | c1 = code >> 8, c2 = code & 0xFF; | |
4305 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 4306 | } |
df7492f9 KH |
4307 | else |
4308 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 4309 | } |
4ed46869 | 4310 | } |
065e3595 | 4311 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4312 | coding->produced_char += produced_chars; |
4313 | coding->produced = dst - coding->destination; | |
4314 | return 0; | |
4ed46869 KH |
4315 | } |
4316 | ||
4317 | \f | |
df7492f9 | 4318 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
4319 | |
4320 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4321 | Check if a text is encoded in a coding system of which | |
4322 | encoder/decoder are written in CCL program. If it is, return | |
df7492f9 | 4323 | CATEGORY_MASK_CCL, else return 0. */ |
1397dc18 | 4324 | |
0a28aafb | 4325 | static int |
ff0dacd7 | 4326 | detect_coding_ccl (coding, detect_info) |
df7492f9 | 4327 | struct coding_system *coding; |
ff0dacd7 | 4328 | struct coding_detection_info *detect_info; |
1397dc18 | 4329 | { |
065e3595 | 4330 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4331 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4332 | int multibytep = coding->src_multibyte; |
4333 | int consumed_chars = 0; | |
4334 | int found = 0; | |
4335 | unsigned char *valids = CODING_CCL_VALIDS (coding); | |
4336 | int head_ascii = coding->head_ascii; | |
4337 | Lisp_Object attrs; | |
4338 | ||
ff0dacd7 KH |
4339 | detect_info->checked |= CATEGORY_MASK_CCL; |
4340 | ||
df7492f9 KH |
4341 | coding = &coding_categories[coding_category_ccl]; |
4342 | attrs = CODING_ID_ATTRS (coding->id); | |
4343 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4344 | src += head_ascii; | |
1397dc18 | 4345 | |
b73bfc1c | 4346 | while (1) |
1397dc18 | 4347 | { |
df7492f9 | 4348 | int c; |
065e3595 KH |
4349 | |
4350 | src_base = src; | |
df7492f9 | 4351 | ONE_MORE_BYTE (c); |
065e3595 | 4352 | if (c < 0 || ! valids[c]) |
df7492f9 | 4353 | break; |
ff0dacd7 KH |
4354 | if ((valids[c] > 1)) |
4355 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 4356 | } |
ff0dacd7 | 4357 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
4358 | return 0; |
4359 | ||
4360 | no_more_source: | |
ff0dacd7 KH |
4361 | detect_info->found |= found; |
4362 | return 1; | |
df7492f9 KH |
4363 | } |
4364 | ||
4365 | static void | |
4366 | decode_coding_ccl (coding) | |
4367 | struct coding_system *coding; | |
4368 | { | |
7c78e542 | 4369 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 4370 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4371 | int *charbuf = coding->charbuf; |
4372 | int *charbuf_end = charbuf + coding->charbuf_size; | |
4373 | int consumed_chars = 0; | |
4374 | int multibytep = coding->src_multibyte; | |
4375 | struct ccl_program ccl; | |
4376 | int source_charbuf[1024]; | |
4377 | int source_byteidx[1024]; | |
24a73b0a | 4378 | Lisp_Object attrs, charset_list; |
df7492f9 | 4379 | |
24a73b0a | 4380 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4381 | setup_ccl_program (&ccl, CODING_CCL_DECODER (coding)); |
4382 | ||
4383 | while (src < src_end) | |
4384 | { | |
7c78e542 | 4385 | const unsigned char *p = src; |
df7492f9 KH |
4386 | int *source, *source_end; |
4387 | int i = 0; | |
4388 | ||
4389 | if (multibytep) | |
4390 | while (i < 1024 && p < src_end) | |
4391 | { | |
4392 | source_byteidx[i] = p - src; | |
4393 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
4394 | } | |
4395 | else | |
4396 | while (i < 1024 && p < src_end) | |
4397 | source_charbuf[i++] = *p++; | |
8f924df7 | 4398 | |
df7492f9 KH |
4399 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
4400 | ccl.last_block = 1; | |
4401 | ||
4402 | source = source_charbuf; | |
4403 | source_end = source + i; | |
4404 | while (source < source_end) | |
4405 | { | |
4406 | ccl_driver (&ccl, source, charbuf, | |
8dcbea82 KH |
4407 | source_end - source, charbuf_end - charbuf, |
4408 | charset_list); | |
df7492f9 KH |
4409 | source += ccl.consumed; |
4410 | charbuf += ccl.produced; | |
4411 | if (ccl.status != CCL_STAT_SUSPEND_BY_DST) | |
4412 | break; | |
4413 | } | |
4414 | if (source < source_end) | |
4415 | src += source_byteidx[source - source_charbuf]; | |
4416 | else | |
4417 | src = p; | |
4418 | consumed_chars += source - source_charbuf; | |
4419 | ||
4420 | if (ccl.status != CCL_STAT_SUSPEND_BY_SRC | |
4421 | && ccl.status != CODING_RESULT_INSUFFICIENT_SRC) | |
4422 | break; | |
4423 | } | |
4424 | ||
4425 | switch (ccl.status) | |
4426 | { | |
4427 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4428 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4429 | break; |
4430 | case CCL_STAT_SUSPEND_BY_DST: | |
4431 | break; | |
4432 | case CCL_STAT_QUIT: | |
4433 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4434 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4435 | break; |
4436 | default: | |
065e3595 | 4437 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4438 | break; |
4439 | } | |
4440 | coding->consumed_char += consumed_chars; | |
4441 | coding->consumed = src - coding->source; | |
4442 | coding->charbuf_used = charbuf - coding->charbuf; | |
4443 | } | |
4444 | ||
4445 | static int | |
4446 | encode_coding_ccl (coding) | |
4447 | struct coding_system *coding; | |
4448 | { | |
4449 | struct ccl_program ccl; | |
4450 | int multibytep = coding->dst_multibyte; | |
4451 | int *charbuf = coding->charbuf; | |
4452 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4453 | unsigned char *dst = coding->destination + coding->produced; | |
4454 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4455 | unsigned char *adjusted_dst_end = dst_end - 1; | |
4456 | int destination_charbuf[1024]; | |
4457 | int i, produced_chars = 0; | |
24a73b0a | 4458 | Lisp_Object attrs, charset_list; |
df7492f9 | 4459 | |
24a73b0a | 4460 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4461 | setup_ccl_program (&ccl, CODING_CCL_ENCODER (coding)); |
4462 | ||
4463 | ccl.last_block = coding->mode & CODING_MODE_LAST_BLOCK; | |
4464 | ccl.dst_multibyte = coding->dst_multibyte; | |
4465 | ||
4466 | while (charbuf < charbuf_end && dst < adjusted_dst_end) | |
4467 | { | |
4468 | int dst_bytes = dst_end - dst; | |
4469 | if (dst_bytes > 1024) | |
4470 | dst_bytes = 1024; | |
4471 | ||
4472 | ccl_driver (&ccl, charbuf, destination_charbuf, | |
8dcbea82 | 4473 | charbuf_end - charbuf, dst_bytes, charset_list); |
df7492f9 KH |
4474 | charbuf += ccl.consumed; |
4475 | if (multibytep) | |
4476 | for (i = 0; i < ccl.produced; i++) | |
4477 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); | |
4478 | else | |
4479 | { | |
4480 | for (i = 0; i < ccl.produced; i++) | |
4481 | *dst++ = destination_charbuf[i] & 0xFF; | |
4482 | produced_chars += ccl.produced; | |
4483 | } | |
4484 | } | |
4485 | ||
4486 | switch (ccl.status) | |
4487 | { | |
4488 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4489 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4490 | break; |
4491 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 4492 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
4493 | break; |
4494 | case CCL_STAT_QUIT: | |
4495 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4496 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4497 | break; |
4498 | default: | |
065e3595 | 4499 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 4500 | break; |
1397dc18 | 4501 | } |
df7492f9 KH |
4502 | |
4503 | coding->produced_char += produced_chars; | |
4504 | coding->produced = dst - coding->destination; | |
4505 | return 0; | |
1397dc18 KH |
4506 | } |
4507 | ||
df7492f9 | 4508 | |
1397dc18 | 4509 | \f |
df7492f9 | 4510 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 4511 | |
b73bfc1c | 4512 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 4513 | |
b73bfc1c | 4514 | static void |
df7492f9 | 4515 | decode_coding_raw_text (coding) |
4ed46869 | 4516 | struct coding_system *coding; |
4ed46869 | 4517 | { |
df7492f9 | 4518 | coding->chars_at_source = 1; |
2c78b7e1 KH |
4519 | coding->consumed_char = 0; |
4520 | coding->consumed = 0; | |
065e3595 | 4521 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 4522 | } |
4ed46869 | 4523 | |
df7492f9 KH |
4524 | static int |
4525 | encode_coding_raw_text (coding) | |
4526 | struct coding_system *coding; | |
4527 | { | |
4528 | int multibytep = coding->dst_multibyte; | |
4529 | int *charbuf = coding->charbuf; | |
4530 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
4531 | unsigned char *dst = coding->destination + coding->produced; | |
4532 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4533 | int produced_chars = 0; | |
b73bfc1c KH |
4534 | int c; |
4535 | ||
df7492f9 | 4536 | if (multibytep) |
b73bfc1c | 4537 | { |
df7492f9 | 4538 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 4539 | |
df7492f9 KH |
4540 | if (coding->src_multibyte) |
4541 | while (charbuf < charbuf_end) | |
4542 | { | |
4543 | ASSURE_DESTINATION (safe_room); | |
4544 | c = *charbuf++; | |
4545 | if (ASCII_CHAR_P (c)) | |
4546 | EMIT_ONE_ASCII_BYTE (c); | |
4547 | else if (CHAR_BYTE8_P (c)) | |
4548 | { | |
4549 | c = CHAR_TO_BYTE8 (c); | |
4550 | EMIT_ONE_BYTE (c); | |
4551 | } | |
4552 | else | |
4553 | { | |
4554 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 4555 | |
df7492f9 KH |
4556 | CHAR_STRING_ADVANCE (c, p1); |
4557 | while (p0 < p1) | |
9d123124 KH |
4558 | { |
4559 | EMIT_ONE_BYTE (*p0); | |
4560 | p0++; | |
4561 | } | |
df7492f9 KH |
4562 | } |
4563 | } | |
b73bfc1c | 4564 | else |
df7492f9 KH |
4565 | while (charbuf < charbuf_end) |
4566 | { | |
4567 | ASSURE_DESTINATION (safe_room); | |
4568 | c = *charbuf++; | |
4569 | EMIT_ONE_BYTE (c); | |
4570 | } | |
4571 | } | |
4572 | else | |
4ed46869 | 4573 | { |
df7492f9 | 4574 | if (coding->src_multibyte) |
d46c5b12 | 4575 | { |
df7492f9 KH |
4576 | int safe_room = MAX_MULTIBYTE_LENGTH; |
4577 | ||
4578 | while (charbuf < charbuf_end) | |
d46c5b12 | 4579 | { |
df7492f9 KH |
4580 | ASSURE_DESTINATION (safe_room); |
4581 | c = *charbuf++; | |
4582 | if (ASCII_CHAR_P (c)) | |
4583 | *dst++ = c; | |
4584 | else if (CHAR_BYTE8_P (c)) | |
4585 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 4586 | else |
df7492f9 KH |
4587 | CHAR_STRING_ADVANCE (c, dst); |
4588 | produced_chars++; | |
d46c5b12 KH |
4589 | } |
4590 | } | |
df7492f9 KH |
4591 | else |
4592 | { | |
4593 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
4594 | while (charbuf < charbuf_end && dst < dst_end) | |
4595 | *dst++ = *charbuf++; | |
4596 | produced_chars = dst - (coding->destination + coding->dst_bytes); | |
8f924df7 | 4597 | } |
4ed46869 | 4598 | } |
065e3595 | 4599 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4600 | coding->produced_char += produced_chars; |
4601 | coding->produced = dst - coding->destination; | |
4602 | return 0; | |
4ed46869 KH |
4603 | } |
4604 | ||
ff0dacd7 KH |
4605 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
4606 | Check if a text is encoded in a charset-based coding system. If it | |
4607 | is, return 1, else return 0. */ | |
4608 | ||
0a28aafb | 4609 | static int |
ff0dacd7 | 4610 | detect_coding_charset (coding, detect_info) |
df7492f9 | 4611 | struct coding_system *coding; |
ff0dacd7 | 4612 | struct coding_detection_info *detect_info; |
1397dc18 | 4613 | { |
065e3595 | 4614 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4615 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4616 | int multibytep = coding->src_multibyte; |
4617 | int consumed_chars = 0; | |
4618 | Lisp_Object attrs, valids; | |
584948ac | 4619 | int found = 0; |
1397dc18 | 4620 | |
ff0dacd7 KH |
4621 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
4622 | ||
df7492f9 KH |
4623 | coding = &coding_categories[coding_category_charset]; |
4624 | attrs = CODING_ID_ATTRS (coding->id); | |
4625 | valids = AREF (attrs, coding_attr_charset_valids); | |
4626 | ||
4627 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4628 | src += coding->head_ascii; | |
1397dc18 | 4629 | |
b73bfc1c | 4630 | while (1) |
1397dc18 | 4631 | { |
df7492f9 | 4632 | int c; |
1397dc18 | 4633 | |
065e3595 | 4634 | src_base = src; |
df7492f9 | 4635 | ONE_MORE_BYTE (c); |
065e3595 KH |
4636 | if (c < 0) |
4637 | continue; | |
df7492f9 KH |
4638 | if (NILP (AREF (valids, c))) |
4639 | break; | |
584948ac | 4640 | if (c >= 0x80) |
ff0dacd7 | 4641 | found = CATEGORY_MASK_CHARSET; |
df7492f9 | 4642 | } |
ff0dacd7 | 4643 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 4644 | return 0; |
4ed46869 | 4645 | |
df7492f9 | 4646 | no_more_source: |
ff0dacd7 KH |
4647 | detect_info->found |= found; |
4648 | return 1; | |
df7492f9 | 4649 | } |
b73bfc1c | 4650 | |
b73bfc1c | 4651 | static void |
df7492f9 | 4652 | decode_coding_charset (coding) |
4ed46869 | 4653 | struct coding_system *coding; |
4ed46869 | 4654 | { |
8f924df7 KH |
4655 | const unsigned char *src = coding->source + coding->consumed; |
4656 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4657 | const unsigned char *src_base; | |
df7492f9 | 4658 | int *charbuf = coding->charbuf; |
ff0dacd7 | 4659 | int *charbuf_end = charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; |
df7492f9 KH |
4660 | int consumed_chars = 0, consumed_chars_base; |
4661 | int multibytep = coding->src_multibyte; | |
24a73b0a | 4662 | Lisp_Object attrs, charset_list, valids; |
ff0dacd7 KH |
4663 | int char_offset = coding->produced_char; |
4664 | int last_offset = char_offset; | |
4665 | int last_id = charset_ascii; | |
df7492f9 | 4666 | |
24a73b0a | 4667 | CODING_GET_INFO (coding, attrs, charset_list); |
4eb6d3f1 | 4668 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 4669 | |
df7492f9 | 4670 | while (1) |
4ed46869 | 4671 | { |
4eb6d3f1 | 4672 | int c; |
24a73b0a KH |
4673 | Lisp_Object val; |
4674 | struct charset *charset; | |
4675 | int dim; | |
4676 | int len = 1; | |
4677 | unsigned code; | |
df7492f9 KH |
4678 | |
4679 | src_base = src; | |
4680 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 4681 | |
df7492f9 KH |
4682 | if (charbuf >= charbuf_end) |
4683 | break; | |
4684 | ||
4eb6d3f1 | 4685 | ONE_MORE_BYTE (c); |
065e3595 KH |
4686 | if (c < 0) |
4687 | goto invalid_code; | |
24a73b0a KH |
4688 | code = c; |
4689 | ||
4690 | val = AREF (valids, c); | |
4691 | if (NILP (val)) | |
4692 | goto invalid_code; | |
4693 | if (INTEGERP (val)) | |
d46c5b12 | 4694 | { |
24a73b0a KH |
4695 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
4696 | dim = CHARSET_DIMENSION (charset); | |
4697 | while (len < dim) | |
b73bfc1c | 4698 | { |
24a73b0a KH |
4699 | ONE_MORE_BYTE (c); |
4700 | code = (code << 8) | c; | |
4701 | len++; | |
b73bfc1c | 4702 | } |
24a73b0a KH |
4703 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
4704 | charset, code, c); | |
d46c5b12 | 4705 | } |
df7492f9 | 4706 | else |
d46c5b12 | 4707 | { |
24a73b0a KH |
4708 | /* VAL is a list of charset IDs. It is assured that the |
4709 | list is sorted by charset dimensions (smaller one | |
4710 | comes first). */ | |
4711 | while (CONSP (val)) | |
4eb6d3f1 | 4712 | { |
24a73b0a | 4713 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 4714 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 4715 | while (len < dim) |
4eb6d3f1 | 4716 | { |
acb2a965 KH |
4717 | ONE_MORE_BYTE (c); |
4718 | code = (code << 8) | c; | |
f9d71dcd | 4719 | len++; |
4eb6d3f1 | 4720 | } |
24a73b0a KH |
4721 | CODING_DECODE_CHAR (coding, src, src_base, |
4722 | src_end, charset, code, c); | |
4723 | if (c >= 0) | |
4724 | break; | |
4725 | val = XCDR (val); | |
ff0dacd7 | 4726 | } |
d46c5b12 | 4727 | } |
24a73b0a KH |
4728 | if (c < 0) |
4729 | goto invalid_code; | |
4730 | if (charset->id != charset_ascii | |
4731 | && last_id != charset->id) | |
4732 | { | |
4733 | if (last_id != charset_ascii) | |
4734 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
4735 | last_id = charset->id; | |
4736 | last_offset = char_offset; | |
4737 | } | |
4738 | ||
df7492f9 | 4739 | *charbuf++ = c; |
ff0dacd7 | 4740 | char_offset++; |
df7492f9 KH |
4741 | continue; |
4742 | ||
4743 | invalid_code: | |
4744 | src = src_base; | |
4745 | consumed_chars = consumed_chars_base; | |
4746 | ONE_MORE_BYTE (c); | |
065e3595 | 4747 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4748 | char_offset++; |
df7492f9 | 4749 | coding->errors++; |
4ed46869 KH |
4750 | } |
4751 | ||
df7492f9 | 4752 | no_more_source: |
ff0dacd7 KH |
4753 | if (last_id != charset_ascii) |
4754 | ADD_CHARSET_DATA (charbuf, last_offset, char_offset, last_id); | |
df7492f9 KH |
4755 | coding->consumed_char += consumed_chars_base; |
4756 | coding->consumed = src_base - coding->source; | |
4757 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4758 | } |
4759 | ||
df7492f9 KH |
4760 | static int |
4761 | encode_coding_charset (coding) | |
4ed46869 | 4762 | struct coding_system *coding; |
4ed46869 | 4763 | { |
df7492f9 KH |
4764 | int multibytep = coding->dst_multibyte; |
4765 | int *charbuf = coding->charbuf; | |
4766 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4767 | unsigned char *dst = coding->destination + coding->produced; | |
4768 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4769 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
4770 | int produced_chars = 0; | |
24a73b0a | 4771 | Lisp_Object attrs, charset_list; |
df7492f9 | 4772 | int ascii_compatible; |
b73bfc1c | 4773 | int c; |
b73bfc1c | 4774 | |
24a73b0a | 4775 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 4776 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 4777 | |
df7492f9 | 4778 | while (charbuf < charbuf_end) |
4ed46869 | 4779 | { |
4eb6d3f1 | 4780 | struct charset *charset; |
df7492f9 | 4781 | unsigned code; |
8f924df7 | 4782 | |
df7492f9 KH |
4783 | ASSURE_DESTINATION (safe_room); |
4784 | c = *charbuf++; | |
4785 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
4786 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 4787 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 4788 | { |
16eafb5d KH |
4789 | c = CHAR_TO_BYTE8 (c); |
4790 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 4791 | } |
d46c5b12 | 4792 | else |
b73bfc1c | 4793 | { |
4eb6d3f1 KH |
4794 | charset = char_charset (c, charset_list, &code); |
4795 | if (charset) | |
4796 | { | |
4797 | if (CHARSET_DIMENSION (charset) == 1) | |
4798 | EMIT_ONE_BYTE (code); | |
4799 | else if (CHARSET_DIMENSION (charset) == 2) | |
4800 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
4801 | else if (CHARSET_DIMENSION (charset) == 3) | |
4802 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
4803 | else | |
4804 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
4805 | (code >> 8) & 0xFF, code & 0xFF); | |
4806 | } | |
4807 | else | |
41cbe562 KH |
4808 | { |
4809 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
4810 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4811 | else | |
4812 | c = coding->default_char; | |
4813 | EMIT_ONE_BYTE (c); | |
4814 | } | |
4ed46869 | 4815 | } |
4ed46869 KH |
4816 | } |
4817 | ||
065e3595 | 4818 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4819 | coding->produced_char += produced_chars; |
4820 | coding->produced = dst - coding->destination; | |
4821 | return 0; | |
4ed46869 KH |
4822 | } |
4823 | ||
4824 | \f | |
1397dc18 | 4825 | /*** 7. C library functions ***/ |
4ed46869 | 4826 | |
df7492f9 KH |
4827 | /* Setup coding context CODING from information about CODING_SYSTEM. |
4828 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
4829 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 4830 | |
ec6d2bb8 | 4831 | void |
e0e989f6 KH |
4832 | setup_coding_system (coding_system, coding) |
4833 | Lisp_Object coding_system; | |
4ed46869 KH |
4834 | struct coding_system *coding; |
4835 | { | |
df7492f9 KH |
4836 | Lisp_Object attrs; |
4837 | Lisp_Object eol_type; | |
4838 | Lisp_Object coding_type; | |
4608c386 | 4839 | Lisp_Object val; |
4ed46869 | 4840 | |
df7492f9 KH |
4841 | if (NILP (coding_system)) |
4842 | coding_system = Qno_conversion; | |
c07c8e12 | 4843 | |
df7492f9 | 4844 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 4845 | |
df7492f9 KH |
4846 | attrs = CODING_ID_ATTRS (coding->id); |
4847 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
1f5dbf34 | 4848 | |
df7492f9 KH |
4849 | coding->mode = 0; |
4850 | coding->head_ascii = -1; | |
4851 | coding->common_flags | |
4852 | = (VECTORP (eol_type) ? CODING_REQUIRE_DETECTION_MASK : 0); | |
5e5c78be KH |
4853 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
4854 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
4855 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
4856 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
4857 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
4858 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 4859 | |
df7492f9 | 4860 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 KH |
4861 | coding->max_charset_id = SCHARS (val) - 1; |
4862 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 | 4863 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
4608c386 | 4864 | |
df7492f9 KH |
4865 | coding_type = CODING_ATTR_TYPE (attrs); |
4866 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 4867 | { |
df7492f9 KH |
4868 | coding->detector = NULL; |
4869 | coding->decoder = decode_coding_raw_text; | |
4870 | coding->encoder = encode_coding_raw_text; | |
4871 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 4872 | } |
df7492f9 | 4873 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 4874 | { |
df7492f9 KH |
4875 | int i; |
4876 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
4877 | ||
4878 | /* Invoke graphic register 0 to plane 0. */ | |
4879 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
4880 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
4881 | CODING_ISO_INVOCATION (coding, 1) | |
4882 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
4883 | /* Setup the initial status of designation. */ | |
4884 | for (i = 0; i < 4; i++) | |
4885 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
4886 | /* Not single shifting initially. */ | |
4887 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
4888 | /* Beginning of buffer should also be regarded as bol. */ | |
4889 | CODING_ISO_BOL (coding) = 1; | |
4890 | coding->detector = detect_coding_iso_2022; | |
4891 | coding->decoder = decode_coding_iso_2022; | |
4892 | coding->encoder = encode_coding_iso_2022; | |
4893 | if (flags & CODING_ISO_FLAG_SAFE) | |
4894 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 4895 | coding->common_flags |
df7492f9 KH |
4896 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
4897 | | CODING_REQUIRE_FLUSHING_MASK); | |
4898 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
4899 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
4900 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
4901 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
4902 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
4903 | { | |
4904 | setup_iso_safe_charsets (attrs); | |
4905 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
4906 | coding->max_charset_id = SCHARS (val) - 1; |
4907 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
4908 | } |
4909 | CODING_ISO_FLAGS (coding) = flags; | |
d46c5b12 | 4910 | } |
df7492f9 | 4911 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 4912 | { |
df7492f9 KH |
4913 | coding->detector = detect_coding_charset; |
4914 | coding->decoder = decode_coding_charset; | |
4915 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 4916 | coding->common_flags |
df7492f9 | 4917 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 4918 | } |
df7492f9 | 4919 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 4920 | { |
df7492f9 KH |
4921 | coding->detector = detect_coding_utf_8; |
4922 | coding->decoder = decode_coding_utf_8; | |
4923 | coding->encoder = encode_coding_utf_8; | |
4924 | coding->common_flags | |
4925 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
4926 | } | |
4927 | else if (EQ (coding_type, Qutf_16)) | |
4928 | { | |
4929 | val = AREF (attrs, coding_attr_utf_16_bom); | |
4930 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_16_detect_bom | |
4931 | : EQ (val, Qt) ? utf_16_with_bom | |
4932 | : utf_16_without_bom); | |
4933 | val = AREF (attrs, coding_attr_utf_16_endian); | |
b49a1807 | 4934 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 4935 | : utf_16_little_endian); |
e19c3639 | 4936 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
4937 | coding->detector = detect_coding_utf_16; |
4938 | coding->decoder = decode_coding_utf_16; | |
4939 | coding->encoder = encode_coding_utf_16; | |
4940 | coding->common_flags | |
4941 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
b49a1807 KH |
4942 | if (CODING_UTF_16_BOM (coding) == utf_16_detect_bom) |
4943 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 4944 | } |
df7492f9 | 4945 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 4946 | { |
df7492f9 KH |
4947 | coding->detector = detect_coding_ccl; |
4948 | coding->decoder = decode_coding_ccl; | |
4949 | coding->encoder = encode_coding_ccl; | |
c952af22 | 4950 | coding->common_flags |
df7492f9 KH |
4951 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
4952 | | CODING_REQUIRE_FLUSHING_MASK); | |
4953 | } | |
4954 | else if (EQ (coding_type, Qemacs_mule)) | |
4955 | { | |
4956 | coding->detector = detect_coding_emacs_mule; | |
4957 | coding->decoder = decode_coding_emacs_mule; | |
4958 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 4959 | coding->common_flags |
df7492f9 KH |
4960 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
4961 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
4962 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
4963 | { | |
4964 | Lisp_Object tail, safe_charsets; | |
4965 | int max_charset_id = 0; | |
4966 | ||
4967 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
4968 | tail = XCDR (tail)) | |
4969 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
4970 | max_charset_id = XFASTINT (XCAR (tail)); | |
4971 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), | |
4972 | make_number (255)); | |
4973 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
4974 | tail = XCDR (tail)) | |
8f924df7 | 4975 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 4976 | coding->max_charset_id = max_charset_id; |
8f924df7 | 4977 | coding->safe_charsets = (char *) SDATA (safe_charsets); |
df7492f9 KH |
4978 | } |
4979 | } | |
4980 | else if (EQ (coding_type, Qshift_jis)) | |
4981 | { | |
4982 | coding->detector = detect_coding_sjis; | |
4983 | coding->decoder = decode_coding_sjis; | |
4984 | coding->encoder = encode_coding_sjis; | |
c952af22 | 4985 | coding->common_flags |
df7492f9 KH |
4986 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
4987 | } | |
4988 | else if (EQ (coding_type, Qbig5)) | |
4989 | { | |
4990 | coding->detector = detect_coding_big5; | |
4991 | coding->decoder = decode_coding_big5; | |
4992 | coding->encoder = encode_coding_big5; | |
c952af22 | 4993 | coding->common_flags |
df7492f9 KH |
4994 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
4995 | } | |
4996 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 4997 | { |
df7492f9 KH |
4998 | coding->detector = NULL; |
4999 | coding->decoder = decode_coding_raw_text; | |
5000 | coding->encoder = encode_coding_raw_text; | |
4ed46869 | 5001 | } |
4ed46869 | 5002 | |
df7492f9 | 5003 | return; |
4ed46869 KH |
5004 | } |
5005 | ||
df7492f9 KH |
5006 | /* Return raw-text or one of its subsidiaries that has the same |
5007 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5008 | |
df7492f9 KH |
5009 | Lisp_Object |
5010 | raw_text_coding_system (coding_system) | |
5011 | Lisp_Object coding_system; | |
ec6d2bb8 | 5012 | { |
0be8721c | 5013 | Lisp_Object spec, attrs; |
df7492f9 | 5014 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5015 | |
d3e4cb56 KH |
5016 | if (NILP (coding_system)) |
5017 | return Qraw_text; | |
df7492f9 KH |
5018 | spec = CODING_SYSTEM_SPEC (coding_system); |
5019 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5020 | |
df7492f9 KH |
5021 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5022 | return coding_system; | |
ec6d2bb8 | 5023 | |
df7492f9 KH |
5024 | eol_type = AREF (spec, 2); |
5025 | if (VECTORP (eol_type)) | |
5026 | return Qraw_text; | |
5027 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5028 | raw_text_eol_type = AREF (spec, 2); | |
5029 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5030 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5031 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5032 | } |
5033 | ||
54f78171 | 5034 | |
df7492f9 KH |
5035 | /* If CODING_SYSTEM doesn't specify end-of-line format but PARENT |
5036 | does, return one of the subsidiary that has the same eol-spec as | |
5037 | PARENT. Otherwise, return CODING_SYSTEM. */ | |
5038 | ||
5039 | Lisp_Object | |
5040 | coding_inherit_eol_type (coding_system, parent) | |
b74e4686 | 5041 | Lisp_Object coding_system, parent; |
54f78171 | 5042 | { |
3e139625 | 5043 | Lisp_Object spec, eol_type; |
54f78171 | 5044 | |
d3e4cb56 KH |
5045 | if (NILP (coding_system)) |
5046 | coding_system = Qraw_text; | |
df7492f9 | 5047 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5048 | eol_type = AREF (spec, 2); |
d3e4cb56 KH |
5049 | if (VECTORP (eol_type) |
5050 | && ! NILP (parent)) | |
df7492f9 KH |
5051 | { |
5052 | Lisp_Object parent_spec; | |
df7492f9 KH |
5053 | Lisp_Object parent_eol_type; |
5054 | ||
5055 | parent_spec | |
5056 | = CODING_SYSTEM_SPEC (buffer_defaults.buffer_file_coding_system); | |
5057 | parent_eol_type = AREF (parent_spec, 2); | |
5058 | if (EQ (parent_eol_type, Qunix)) | |
5059 | coding_system = AREF (eol_type, 0); | |
5060 | else if (EQ (parent_eol_type, Qdos)) | |
5061 | coding_system = AREF (eol_type, 1); | |
5062 | else if (EQ (parent_eol_type, Qmac)) | |
5063 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5064 | } |
df7492f9 | 5065 | return coding_system; |
54f78171 KH |
5066 | } |
5067 | ||
4ed46869 KH |
5068 | /* Emacs has a mechanism to automatically detect a coding system if it |
5069 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
5070 | it's impossible to distinguish some coding systems accurately | |
5071 | because they use the same range of codes. So, at first, coding | |
5072 | systems are categorized into 7, those are: | |
5073 | ||
0ef69138 | 5074 | o coding-category-emacs-mule |
4ed46869 KH |
5075 | |
5076 | The category for a coding system which has the same code range | |
5077 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 5078 | symbol) `emacs-mule' by default. |
4ed46869 KH |
5079 | |
5080 | o coding-category-sjis | |
5081 | ||
5082 | The category for a coding system which has the same code range | |
5083 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 5084 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
5085 | |
5086 | o coding-category-iso-7 | |
5087 | ||
5088 | The category for a coding system which has the same code range | |
7717c392 | 5089 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
5090 | shift and single shift functions. This can encode/decode all |
5091 | charsets. Assigned the coding-system (Lisp symbol) | |
5092 | `iso-2022-7bit' by default. | |
5093 | ||
5094 | o coding-category-iso-7-tight | |
5095 | ||
5096 | Same as coding-category-iso-7 except that this can | |
5097 | encode/decode only the specified charsets. | |
4ed46869 KH |
5098 | |
5099 | o coding-category-iso-8-1 | |
5100 | ||
5101 | The category for a coding system which has the same code range | |
5102 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5103 | for DIMENSION1 charset. This doesn't use any locking shift |
5104 | and single shift functions. Assigned the coding-system (Lisp | |
5105 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
5106 | |
5107 | o coding-category-iso-8-2 | |
5108 | ||
5109 | The category for a coding system which has the same code range | |
5110 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5111 | for DIMENSION2 charset. This doesn't use any locking shift |
5112 | and single shift functions. Assigned the coding-system (Lisp | |
5113 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 5114 | |
7717c392 | 5115 | o coding-category-iso-7-else |
4ed46869 KH |
5116 | |
5117 | The category for a coding system which has the same code range | |
df7492f9 | 5118 | as ISO2022 of 7-bit environemnt but uses locking shift or |
7717c392 KH |
5119 | single shift functions. Assigned the coding-system (Lisp |
5120 | symbol) `iso-2022-7bit-lock' by default. | |
5121 | ||
5122 | o coding-category-iso-8-else | |
5123 | ||
5124 | The category for a coding system which has the same code range | |
df7492f9 | 5125 | as ISO2022 of 8-bit environemnt but uses locking shift or |
7717c392 KH |
5126 | single shift functions. Assigned the coding-system (Lisp |
5127 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
5128 | |
5129 | o coding-category-big5 | |
5130 | ||
5131 | The category for a coding system which has the same code range | |
5132 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5133 | `cn-big5' by default. |
4ed46869 | 5134 | |
fa42c37f KH |
5135 | o coding-category-utf-8 |
5136 | ||
5137 | The category for a coding system which has the same code range | |
5138 | as UTF-8 (cf. RFC2279). Assigned the coding-system (Lisp | |
5139 | symbol) `utf-8' by default. | |
5140 | ||
5141 | o coding-category-utf-16-be | |
5142 | ||
5143 | The category for a coding system in which a text has an | |
5144 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
5145 | endian at the head. Assigned the coding-system (Lisp symbol) | |
5146 | `utf-16-be' by default. | |
5147 | ||
5148 | o coding-category-utf-16-le | |
5149 | ||
5150 | The category for a coding system in which a text has an | |
5151 | Unicode signature (cf. Unicode Standard) in the order of | |
5152 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
5153 | symbol) `utf-16-le' by default. | |
5154 | ||
1397dc18 KH |
5155 | o coding-category-ccl |
5156 | ||
5157 | The category for a coding system of which encoder/decoder is | |
5158 | written in CCL programs. The default value is nil, i.e., no | |
5159 | coding system is assigned. | |
5160 | ||
4ed46869 KH |
5161 | o coding-category-binary |
5162 | ||
5163 | The category for a coding system not categorized in any of the | |
5164 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5165 | `no-conversion' by default. |
4ed46869 KH |
5166 | |
5167 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 5168 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
5169 | What Emacs does actually is to detect a category of coding system. |
5170 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 5171 | decide only one possible category, it selects a category of the |
4ed46869 KH |
5172 | highest priority. Priorities of categories are also specified by a |
5173 | user in a Lisp variable `coding-category-list'. | |
5174 | ||
5175 | */ | |
5176 | ||
df7492f9 KH |
5177 | #define EOL_SEEN_NONE 0 |
5178 | #define EOL_SEEN_LF 1 | |
5179 | #define EOL_SEEN_CR 2 | |
5180 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 5181 | |
ff0dacd7 KH |
5182 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
5183 | SOURCE is encoded. If CATEGORY is one of | |
5184 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
5185 | two-byte, else they are encoded by one-byte. | |
5186 | ||
5187 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 5188 | |
bc4bc72a | 5189 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
5190 | |
5191 | static int | |
89528eb3 | 5192 | detect_eol (source, src_bytes, category) |
d46c5b12 | 5193 | unsigned char *source; |
df7492f9 | 5194 | EMACS_INT src_bytes; |
89528eb3 | 5195 | enum coding_category category; |
4ed46869 | 5196 | { |
d46c5b12 | 5197 | unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 5198 | unsigned char c; |
df7492f9 KH |
5199 | int total = 0; |
5200 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 5201 | |
89528eb3 | 5202 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 5203 | { |
df7492f9 | 5204 | int msb, lsb; |
fa42c37f | 5205 | |
89528eb3 KH |
5206 | msb = category == (coding_category_utf_16_le |
5207 | | coding_category_utf_16_le_nosig); | |
df7492f9 | 5208 | lsb = 1 - msb; |
fa42c37f | 5209 | |
df7492f9 | 5210 | while (src + 1 < src_end) |
fa42c37f | 5211 | { |
df7492f9 KH |
5212 | c = src[lsb]; |
5213 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 5214 | { |
df7492f9 KH |
5215 | int this_eol; |
5216 | ||
5217 | if (c == '\n') | |
5218 | this_eol = EOL_SEEN_LF; | |
5219 | else if (src + 3 >= src_end | |
5220 | || src[msb + 2] != 0 | |
5221 | || src[lsb + 2] != '\n') | |
5222 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 5223 | else |
8f924df7 | 5224 | this_eol = EOL_SEEN_CRLF; |
df7492f9 KH |
5225 | |
5226 | if (eol_seen == EOL_SEEN_NONE) | |
5227 | /* This is the first end-of-line. */ | |
5228 | eol_seen = this_eol; | |
5229 | else if (eol_seen != this_eol) | |
fa42c37f | 5230 | { |
df7492f9 KH |
5231 | /* The found type is different from what found before. */ |
5232 | eol_seen = EOL_SEEN_LF; | |
5233 | break; | |
fa42c37f | 5234 | } |
df7492f9 KH |
5235 | if (++total == MAX_EOL_CHECK_COUNT) |
5236 | break; | |
fa42c37f | 5237 | } |
df7492f9 | 5238 | src += 2; |
fa42c37f | 5239 | } |
bcf26d6a | 5240 | } |
d46c5b12 | 5241 | else |
c4825358 | 5242 | { |
df7492f9 | 5243 | while (src < src_end) |
27901516 | 5244 | { |
df7492f9 KH |
5245 | c = *src++; |
5246 | if (c == '\n' || c == '\r') | |
5247 | { | |
5248 | int this_eol; | |
d46c5b12 | 5249 | |
df7492f9 KH |
5250 | if (c == '\n') |
5251 | this_eol = EOL_SEEN_LF; | |
5252 | else if (src >= src_end || *src != '\n') | |
5253 | this_eol = EOL_SEEN_CR; | |
5254 | else | |
5255 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 5256 | |
df7492f9 KH |
5257 | if (eol_seen == EOL_SEEN_NONE) |
5258 | /* This is the first end-of-line. */ | |
5259 | eol_seen = this_eol; | |
5260 | else if (eol_seen != this_eol) | |
5261 | { | |
5262 | /* The found type is different from what found before. */ | |
5263 | eol_seen = EOL_SEEN_LF; | |
5264 | break; | |
5265 | } | |
5266 | if (++total == MAX_EOL_CHECK_COUNT) | |
5267 | break; | |
5268 | } | |
5269 | } | |
73be902c | 5270 | } |
df7492f9 | 5271 | return eol_seen; |
73be902c KH |
5272 | } |
5273 | ||
df7492f9 | 5274 | |
24a73b0a | 5275 | static Lisp_Object |
df7492f9 KH |
5276 | adjust_coding_eol_type (coding, eol_seen) |
5277 | struct coding_system *coding; | |
5278 | int eol_seen; | |
73be902c | 5279 | { |
0be8721c | 5280 | Lisp_Object eol_type; |
8f924df7 | 5281 | |
df7492f9 KH |
5282 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
5283 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
5284 | { |
5285 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
5286 | eol_type = Qunix; | |
5287 | } | |
6f197c07 | 5288 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
5289 | { |
5290 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
5291 | eol_type = Qdos; | |
5292 | } | |
6f197c07 | 5293 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
5294 | { |
5295 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
5296 | eol_type = Qmac; | |
5297 | } | |
5298 | return eol_type; | |
d46c5b12 | 5299 | } |
4ed46869 | 5300 | |
df7492f9 KH |
5301 | /* Detect how a text specified in CODING is encoded. If a coding |
5302 | system is detected, update fields of CODING by the detected coding | |
5303 | system. */ | |
0a28aafb | 5304 | |
df7492f9 KH |
5305 | void |
5306 | detect_coding (coding) | |
d46c5b12 | 5307 | struct coding_system *coding; |
d46c5b12 | 5308 | { |
8f924df7 | 5309 | const unsigned char *src, *src_end; |
df7492f9 | 5310 | Lisp_Object attrs, coding_type; |
d46c5b12 | 5311 | |
df7492f9 KH |
5312 | coding->consumed = coding->consumed_char = 0; |
5313 | coding->produced = coding->produced_char = 0; | |
5314 | coding_set_source (coding); | |
1c3478b0 | 5315 | |
df7492f9 | 5316 | src_end = coding->source + coding->src_bytes; |
1c3478b0 | 5317 | |
df7492f9 KH |
5318 | /* If we have not yet decided the text encoding type, detect it |
5319 | now. */ | |
5320 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 5321 | { |
df7492f9 KH |
5322 | int c, i; |
5323 | ||
24a73b0a | 5324 | for (i = 0, src = coding->source; src < src_end; i++, src++) |
d46c5b12 | 5325 | { |
df7492f9 | 5326 | c = *src; |
24a73b0a KH |
5327 | if (c & 0x80 || (c < 0x20 && (c == 0 |
5328 | || c == ISO_CODE_ESC | |
df7492f9 KH |
5329 | || c == ISO_CODE_SI |
5330 | || c == ISO_CODE_SO))) | |
5331 | break; | |
d46c5b12 | 5332 | } |
df7492f9 KH |
5333 | coding->head_ascii = src - (coding->source + coding->consumed); |
5334 | ||
5335 | if (coding->head_ascii < coding->src_bytes) | |
d46c5b12 | 5336 | { |
ff0dacd7 KH |
5337 | struct coding_detection_info detect_info; |
5338 | enum coding_category category; | |
5339 | struct coding_system *this; | |
df7492f9 | 5340 | |
ff0dacd7 | 5341 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
df7492f9 | 5342 | for (i = 0; i < coding_category_raw_text; i++) |
d46c5b12 | 5343 | { |
ff0dacd7 KH |
5344 | category = coding_priorities[i]; |
5345 | this = coding_categories + category; | |
df7492f9 | 5346 | if (this->id < 0) |
fa42c37f | 5347 | { |
df7492f9 | 5348 | /* No coding system of this category is defined. */ |
ff0dacd7 | 5349 | detect_info.rejected |= (1 << category); |
fa42c37f | 5350 | } |
ff0dacd7 | 5351 | else if (category >= coding_category_raw_text) |
89528eb3 | 5352 | continue; |
ff0dacd7 | 5353 | else if (detect_info.checked & (1 << category)) |
fa42c37f | 5354 | { |
ff0dacd7 KH |
5355 | if (detect_info.found & (1 << category)) |
5356 | break; | |
fa42c37f | 5357 | } |
ff0dacd7 KH |
5358 | else if ((*(this->detector)) (coding, &detect_info) |
5359 | && detect_info.found & (1 << category)) | |
24a73b0a KH |
5360 | { |
5361 | if (category == coding_category_utf_16_auto) | |
5362 | { | |
5363 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
5364 | category = coding_category_utf_16_le; | |
5365 | else | |
5366 | category = coding_category_utf_16_be; | |
5367 | } | |
5368 | break; | |
5369 | } | |
d46c5b12 | 5370 | } |
ff0dacd7 KH |
5371 | if (i < coding_category_raw_text) |
5372 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5373 | else if (detect_info.rejected == CATEGORY_MASK_ANY) | |
df7492f9 | 5374 | setup_coding_system (Qraw_text, coding); |
ff0dacd7 | 5375 | else if (detect_info.rejected) |
df7492f9 | 5376 | for (i = 0; i < coding_category_raw_text; i++) |
ff0dacd7 KH |
5377 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) |
5378 | { | |
5379 | this = coding_categories + coding_priorities[i]; | |
5380 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5381 | break; | |
5382 | } | |
d46c5b12 | 5383 | } |
b73bfc1c | 5384 | } |
24a73b0a KH |
5385 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
5386 | == coding_category_utf_16_auto) | |
b49a1807 KH |
5387 | { |
5388 | Lisp_Object coding_systems; | |
5389 | struct coding_detection_info detect_info; | |
5390 | ||
5391 | coding_systems | |
5392 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_16_bom); | |
5393 | detect_info.found = detect_info.rejected = 0; | |
5394 | if (CONSP (coding_systems) | |
24a73b0a | 5395 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
5396 | { |
5397 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
5398 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 5399 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
5400 | setup_coding_system (XCDR (coding_systems), coding); |
5401 | } | |
5402 | } | |
4ed46869 | 5403 | } |
4ed46869 | 5404 | |
d46c5b12 | 5405 | |
aaaf0b1e | 5406 | static void |
df7492f9 | 5407 | decode_eol (coding) |
aaaf0b1e | 5408 | struct coding_system *coding; |
aaaf0b1e | 5409 | { |
24a73b0a KH |
5410 | Lisp_Object eol_type; |
5411 | unsigned char *p, *pbeg, *pend; | |
5412 | ||
5413 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
5414 | if (EQ (eol_type, Qunix)) | |
5415 | return; | |
5416 | ||
5417 | if (NILP (coding->dst_object)) | |
5418 | pbeg = coding->destination; | |
5419 | else | |
5420 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
5421 | pend = pbeg + coding->produced; | |
5422 | ||
5423 | if (VECTORP (eol_type)) | |
aaaf0b1e | 5424 | { |
df7492f9 | 5425 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 5426 | |
24a73b0a | 5427 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 5428 | { |
df7492f9 KH |
5429 | if (*p == '\n') |
5430 | eol_seen |= EOL_SEEN_LF; | |
5431 | else if (*p == '\r') | |
aaaf0b1e | 5432 | { |
df7492f9 | 5433 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 5434 | { |
df7492f9 KH |
5435 | eol_seen |= EOL_SEEN_CRLF; |
5436 | p++; | |
aaaf0b1e | 5437 | } |
aaaf0b1e | 5438 | else |
df7492f9 | 5439 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 5440 | } |
aaaf0b1e | 5441 | } |
24a73b0a KH |
5442 | if (eol_seen != EOL_SEEN_NONE |
5443 | && eol_seen != EOL_SEEN_LF | |
5444 | && eol_seen != EOL_SEEN_CRLF | |
5445 | && eol_seen != EOL_SEEN_CR) | |
5446 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 5447 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 5448 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 5449 | } |
d46c5b12 | 5450 | |
24a73b0a | 5451 | if (EQ (eol_type, Qmac)) |
27901516 | 5452 | { |
24a73b0a | 5453 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
5454 | if (*p == '\r') |
5455 | *p = '\n'; | |
4ed46869 | 5456 | } |
24a73b0a | 5457 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 5458 | { |
24a73b0a | 5459 | int n = 0; |
b73bfc1c | 5460 | |
24a73b0a KH |
5461 | if (NILP (coding->dst_object)) |
5462 | { | |
5463 | for (p = pend - 2; p >= pbeg; p--) | |
5464 | if (*p == '\r') | |
5465 | { | |
5466 | safe_bcopy ((char *) (p + 1), (char *) p, pend-- - p - 1); | |
5467 | n++; | |
5468 | } | |
5469 | } | |
5470 | else | |
5471 | { | |
5472 | for (p = pend - 2; p >= pbeg; p--) | |
5473 | if (*p == '\r') | |
5474 | { | |
5475 | int pos_byte = coding->dst_pos_byte + (p - pbeg); | |
5476 | int pos = BYTE_TO_CHAR (pos_byte); | |
5477 | ||
5478 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
5479 | n++; | |
5480 | } | |
5481 | } | |
5482 | coding->produced -= n; | |
5483 | coding->produced_char -= n; | |
aaaf0b1e | 5484 | } |
4ed46869 KH |
5485 | } |
5486 | ||
7d64c6ad KH |
5487 | |
5488 | /* Return a translation table from coding system attribute vector ATTRS | |
5489 | for encoding (ENCODEP is nonzero) or decoding (ENCODEP is zeor). */ | |
5490 | ||
5491 | static INLINE | |
5492 | get_translation_table (attrs, encodep) | |
5493 | { | |
5494 | Lisp_Object standard, translation_table; | |
5495 | ||
5496 | if (encodep) | |
5497 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
5498 | standard = Vstandard_translation_table_for_encode; | |
5499 | else | |
5500 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
5501 | standard = Vstandard_translation_table_for_decode; | |
5502 | if (! NILP (translation_table) && SYMBOLP (translation_table)) | |
5503 | translation_table = Fget (translation_table, Qtranslation_table); | |
5504 | if (NILP (translation_table)) | |
5505 | translation_table = standard; | |
5506 | if (! CHAR_TABLE_P (translation_table)) | |
5507 | translation_table = Qnil; | |
5508 | return translation_table; | |
5509 | } | |
5510 | ||
5511 | ||
df7492f9 KH |
5512 | static void |
5513 | translate_chars (coding, table) | |
4ed46869 | 5514 | struct coding_system *coding; |
df7492f9 | 5515 | Lisp_Object table; |
4ed46869 | 5516 | { |
df7492f9 KH |
5517 | int *charbuf = coding->charbuf; |
5518 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5519 | int c; | |
d46c5b12 | 5520 | |
df7492f9 KH |
5521 | if (coding->chars_at_source) |
5522 | return; | |
4ed46869 | 5523 | |
df7492f9 | 5524 | while (charbuf < charbuf_end) |
8844fa83 | 5525 | { |
df7492f9 KH |
5526 | c = *charbuf; |
5527 | if (c < 0) | |
7d64c6ad | 5528 | charbuf += -c; |
df7492f9 KH |
5529 | else |
5530 | *charbuf++ = translate_char (table, c); | |
8844fa83 | 5531 | } |
df7492f9 | 5532 | } |
bc4bc72a | 5533 | |
d46c5b12 | 5534 | static int |
df7492f9 KH |
5535 | produce_chars (coding) |
5536 | struct coding_system *coding; | |
4ed46869 | 5537 | { |
df7492f9 KH |
5538 | unsigned char *dst = coding->destination + coding->produced; |
5539 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5540 | int produced; | |
5541 | int produced_chars = 0; | |
4ed46869 | 5542 | |
df7492f9 | 5543 | if (! coding->chars_at_source) |
4ed46869 | 5544 | { |
df7492f9 | 5545 | /* Characters are in coding->charbuf. */ |
fba4576f AS |
5546 | int *buf = coding->charbuf; |
5547 | int *buf_end = buf + coding->charbuf_used; | |
df7492f9 | 5548 | unsigned char *adjusted_dst_end; |
4ed46869 | 5549 | |
df7492f9 KH |
5550 | if (BUFFERP (coding->src_object) |
5551 | && EQ (coding->src_object, coding->dst_object)) | |
8f924df7 | 5552 | dst_end = ((unsigned char *) coding->source) + coding->consumed; |
df7492f9 | 5553 | adjusted_dst_end = dst_end - MAX_MULTIBYTE_LENGTH; |
4ed46869 | 5554 | |
df7492f9 | 5555 | while (buf < buf_end) |
4ed46869 | 5556 | { |
df7492f9 | 5557 | int c = *buf++; |
bc4bc72a | 5558 | |
df7492f9 | 5559 | if (dst >= adjusted_dst_end) |
d46c5b12 | 5560 | { |
df7492f9 KH |
5561 | dst = alloc_destination (coding, |
5562 | buf_end - buf + MAX_MULTIBYTE_LENGTH, | |
5563 | dst); | |
5564 | dst_end = coding->destination + coding->dst_bytes; | |
5565 | adjusted_dst_end = dst_end - MAX_MULTIBYTE_LENGTH; | |
5566 | } | |
5567 | if (c >= 0) | |
5568 | { | |
5569 | if (coding->dst_multibyte | |
5570 | || ! CHAR_BYTE8_P (c)) | |
5571 | CHAR_STRING_ADVANCE (c, dst); | |
5572 | else | |
5573 | *dst++ = CHAR_TO_BYTE8 (c); | |
5574 | produced_chars++; | |
d46c5b12 | 5575 | } |
df7492f9 | 5576 | else |
d3e4cb56 KH |
5577 | /* This is an annotation datum. (-C) is the length of |
5578 | it. */ | |
5579 | buf += -c - 1; | |
4ed46869 KH |
5580 | } |
5581 | } | |
fa42c37f | 5582 | else |
fa42c37f | 5583 | { |
8f924df7 KH |
5584 | const unsigned char *src = coding->source; |
5585 | const unsigned char *src_end = src + coding->src_bytes; | |
df7492f9 | 5586 | Lisp_Object eol_type; |
fa42c37f | 5587 | |
df7492f9 | 5588 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
4ed46869 | 5589 | |
df7492f9 | 5590 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 5591 | { |
df7492f9 | 5592 | if (coding->src_multibyte) |
fa42c37f | 5593 | { |
71c81426 | 5594 | int multibytep = 1; |
df7492f9 | 5595 | int consumed_chars; |
d46c5b12 | 5596 | |
df7492f9 KH |
5597 | while (1) |
5598 | { | |
8f924df7 | 5599 | const unsigned char *src_base = src; |
df7492f9 | 5600 | int c; |
b73bfc1c | 5601 | |
df7492f9 KH |
5602 | ONE_MORE_BYTE (c); |
5603 | if (c == '\r') | |
5604 | { | |
5605 | if (EQ (eol_type, Qdos)) | |
5606 | { | |
98725083 KH |
5607 | if (src == src_end) |
5608 | { | |
065e3595 KH |
5609 | record_conversion_result |
5610 | (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
98725083 KH |
5611 | goto no_more_source; |
5612 | } | |
5613 | if (*src == '\n') | |
df7492f9 KH |
5614 | c = *src++; |
5615 | } | |
5616 | else if (EQ (eol_type, Qmac)) | |
5617 | c = '\n'; | |
5618 | } | |
5619 | if (dst == dst_end) | |
5620 | { | |
2c78b7e1 | 5621 | coding->consumed = src - coding->source; |
b73bfc1c | 5622 | |
2c78b7e1 | 5623 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5624 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5625 | if (dst == dst_end) |
5626 | { | |
5627 | dst = alloc_destination (coding, src_end - src + 1, | |
5628 | dst); | |
5629 | dst_end = coding->destination + coding->dst_bytes; | |
5630 | coding_set_source (coding); | |
5631 | src = coding->source + coding->consumed; | |
5632 | src_end = coding->source + coding->src_bytes; | |
5633 | } | |
df7492f9 KH |
5634 | } |
5635 | *dst++ = c; | |
5636 | produced_chars++; | |
5637 | } | |
5638 | no_more_source: | |
5639 | ; | |
fa42c37f KH |
5640 | } |
5641 | else | |
df7492f9 KH |
5642 | while (src < src_end) |
5643 | { | |
71c81426 | 5644 | int multibytep = 1; |
df7492f9 | 5645 | int c = *src++; |
b73bfc1c | 5646 | |
df7492f9 KH |
5647 | if (c == '\r') |
5648 | { | |
5649 | if (EQ (eol_type, Qdos)) | |
5650 | { | |
5651 | if (src < src_end | |
5652 | && *src == '\n') | |
5653 | c = *src++; | |
5654 | } | |
5655 | else if (EQ (eol_type, Qmac)) | |
5656 | c = '\n'; | |
5657 | } | |
5658 | if (dst >= dst_end - 1) | |
5659 | { | |
2c78b7e1 | 5660 | coding->consumed = src - coding->source; |
df7492f9 | 5661 | |
2c78b7e1 | 5662 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5663 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5664 | if (dst >= dst_end - 1) |
5665 | { | |
5666 | dst = alloc_destination (coding, src_end - src + 2, | |
5667 | dst); | |
5668 | dst_end = coding->destination + coding->dst_bytes; | |
5669 | coding_set_source (coding); | |
5670 | src = coding->source + coding->consumed; | |
5671 | src_end = coding->source + coding->src_bytes; | |
5672 | } | |
df7492f9 KH |
5673 | } |
5674 | EMIT_ONE_BYTE (c); | |
5675 | } | |
d46c5b12 | 5676 | } |
df7492f9 KH |
5677 | else |
5678 | { | |
5679 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 5680 | { |
df7492f9 | 5681 | int require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 5682 | |
df7492f9 | 5683 | if (require > 0) |
fa42c37f | 5684 | { |
df7492f9 KH |
5685 | EMACS_INT offset = src - coding->source; |
5686 | ||
5687 | dst = alloc_destination (coding, require, dst); | |
5688 | coding_set_source (coding); | |
5689 | src = coding->source + offset; | |
5690 | src_end = coding->source + coding->src_bytes; | |
fa42c37f KH |
5691 | } |
5692 | } | |
df7492f9 KH |
5693 | produced_chars = coding->src_chars; |
5694 | while (src < src_end) | |
fa42c37f | 5695 | { |
df7492f9 KH |
5696 | int c = *src++; |
5697 | ||
5698 | if (c == '\r') | |
5699 | { | |
5700 | if (EQ (eol_type, Qdos)) | |
5701 | { | |
5702 | if (src < src_end | |
5703 | && *src == '\n') | |
5704 | c = *src++; | |
5705 | produced_chars--; | |
5706 | } | |
5707 | else if (EQ (eol_type, Qmac)) | |
5708 | c = '\n'; | |
5709 | } | |
5710 | *dst++ = c; | |
fa42c37f KH |
5711 | } |
5712 | } | |
2c78b7e1 KH |
5713 | coding->consumed = coding->src_bytes; |
5714 | coding->consumed_char = coding->src_chars; | |
fa42c37f KH |
5715 | } |
5716 | ||
df7492f9 KH |
5717 | produced = dst - (coding->destination + coding->produced); |
5718 | if (BUFFERP (coding->dst_object)) | |
5719 | insert_from_gap (produced_chars, produced); | |
5720 | coding->produced += produced; | |
5721 | coding->produced_char += produced_chars; | |
5722 | return produced_chars; | |
fa42c37f KH |
5723 | } |
5724 | ||
ff0dacd7 KH |
5725 | /* Compose text in CODING->object according to the annotation data at |
5726 | CHARBUF. CHARBUF is an array: | |
5727 | [ -LENGTH ANNOTATION_MASK FROM TO METHOD COMP_LEN [ COMPONENTS... ] ] | |
df7492f9 | 5728 | */ |
4ed46869 | 5729 | |
df7492f9 KH |
5730 | static INLINE void |
5731 | produce_composition (coding, charbuf) | |
4ed46869 | 5732 | struct coding_system *coding; |
df7492f9 | 5733 | int *charbuf; |
4ed46869 | 5734 | { |
df7492f9 | 5735 | int len; |
ff0dacd7 | 5736 | EMACS_INT from, to; |
df7492f9 | 5737 | enum composition_method method; |
df7492f9 | 5738 | Lisp_Object components; |
fa42c37f | 5739 | |
df7492f9 | 5740 | len = -charbuf[0]; |
ff0dacd7 KH |
5741 | from = coding->dst_pos + charbuf[2]; |
5742 | to = coding->dst_pos + charbuf[3]; | |
5743 | method = (enum composition_method) (charbuf[4]); | |
d46c5b12 | 5744 | |
df7492f9 KH |
5745 | if (method == COMPOSITION_RELATIVE) |
5746 | components = Qnil; | |
d46c5b12 | 5747 | else |
d46c5b12 | 5748 | { |
df7492f9 KH |
5749 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
5750 | int i; | |
b73bfc1c | 5751 | |
df7492f9 KH |
5752 | len -= 5; |
5753 | charbuf += 5; | |
5754 | for (i = 0; i < len; i++) | |
5755 | args[i] = make_number (charbuf[i]); | |
5756 | components = (method == COMPOSITION_WITH_ALTCHARS | |
5757 | ? Fstring (len, args) : Fvector (len, args)); | |
d46c5b12 | 5758 | } |
ff0dacd7 | 5759 | compose_text (from, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
5760 | } |
5761 | ||
d46c5b12 | 5762 | |
ff0dacd7 KH |
5763 | /* Put `charset' property on text in CODING->object according to |
5764 | the annotation data at CHARBUF. CHARBUF is an array: | |
5765 | [ -LENGTH ANNOTATION_MASK FROM TO CHARSET-ID ] | |
5766 | */ | |
d46c5b12 | 5767 | |
ff0dacd7 KH |
5768 | static INLINE void |
5769 | produce_charset (coding, charbuf) | |
d46c5b12 | 5770 | struct coding_system *coding; |
ff0dacd7 | 5771 | int *charbuf; |
d46c5b12 | 5772 | { |
ff0dacd7 KH |
5773 | EMACS_INT from = coding->dst_pos + charbuf[2]; |
5774 | EMACS_INT to = coding->dst_pos + charbuf[3]; | |
5775 | struct charset *charset = CHARSET_FROM_ID (charbuf[4]); | |
b73bfc1c | 5776 | |
ff0dacd7 KH |
5777 | Fput_text_property (make_number (from), make_number (to), |
5778 | Qcharset, CHARSET_NAME (charset), | |
5779 | coding->dst_object); | |
d46c5b12 KH |
5780 | } |
5781 | ||
d46c5b12 | 5782 | |
df7492f9 KH |
5783 | #define CHARBUF_SIZE 0x4000 |
5784 | ||
5785 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
5786 | do { \ | |
5787 | int size = CHARBUF_SIZE;; \ | |
5788 | \ | |
5789 | coding->charbuf = NULL; \ | |
5790 | while (size > 1024) \ | |
5791 | { \ | |
5792 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
5793 | if (coding->charbuf) \ | |
5794 | break; \ | |
5795 | size >>= 1; \ | |
5796 | } \ | |
5797 | if (! coding->charbuf) \ | |
5798 | { \ | |
065e3595 | 5799 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
df7492f9 KH |
5800 | return coding->result; \ |
5801 | } \ | |
5802 | coding->charbuf_size = size; \ | |
5803 | } while (0) | |
4ed46869 | 5804 | |
d46c5b12 KH |
5805 | |
5806 | static void | |
df7492f9 | 5807 | produce_annotation (coding) |
d46c5b12 | 5808 | struct coding_system *coding; |
d46c5b12 | 5809 | { |
df7492f9 KH |
5810 | int *charbuf = coding->charbuf; |
5811 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 5812 | |
ff0dacd7 KH |
5813 | if (NILP (coding->dst_object)) |
5814 | return; | |
d46c5b12 | 5815 | |
df7492f9 | 5816 | while (charbuf < charbuf_end) |
a84f1519 | 5817 | { |
df7492f9 KH |
5818 | if (*charbuf >= 0) |
5819 | charbuf++; | |
d46c5b12 | 5820 | else |
d46c5b12 | 5821 | { |
df7492f9 | 5822 | int len = -*charbuf; |
ff0dacd7 | 5823 | switch (charbuf[1]) |
df7492f9 KH |
5824 | { |
5825 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
5826 | produce_composition (coding, charbuf); | |
5827 | break; | |
ff0dacd7 KH |
5828 | case CODING_ANNOTATE_CHARSET_MASK: |
5829 | produce_charset (coding, charbuf); | |
5830 | break; | |
df7492f9 KH |
5831 | default: |
5832 | abort (); | |
5833 | } | |
5834 | charbuf += len; | |
d46c5b12 | 5835 | } |
a84f1519 | 5836 | } |
d46c5b12 KH |
5837 | } |
5838 | ||
df7492f9 KH |
5839 | /* Decode the data at CODING->src_object into CODING->dst_object. |
5840 | CODING->src_object is a buffer, a string, or nil. | |
5841 | CODING->dst_object is a buffer. | |
d46c5b12 | 5842 | |
df7492f9 KH |
5843 | If CODING->src_object is a buffer, it must be the current buffer. |
5844 | In this case, if CODING->src_pos is positive, it is a position of | |
5845 | the source text in the buffer, otherwise, the source text is in the | |
5846 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
5847 | the text from GPT (which must be the same as PT). If this is the | |
5848 | same buffer as CODING->dst_object, CODING->src_pos must be | |
5849 | negative. | |
d46c5b12 | 5850 | |
df7492f9 KH |
5851 | If CODING->src_object is a string, CODING->src_pos in an index to |
5852 | that string. | |
d46c5b12 | 5853 | |
df7492f9 KH |
5854 | If CODING->src_object is nil, CODING->source must already point to |
5855 | the non-relocatable memory area. In this case, CODING->src_pos is | |
5856 | an offset from CODING->source. | |
73be902c | 5857 | |
df7492f9 KH |
5858 | The decoded data is inserted at the current point of the buffer |
5859 | CODING->dst_object. | |
5860 | */ | |
d46c5b12 | 5861 | |
df7492f9 KH |
5862 | static int |
5863 | decode_coding (coding) | |
d46c5b12 | 5864 | struct coding_system *coding; |
d46c5b12 | 5865 | { |
df7492f9 | 5866 | Lisp_Object attrs; |
24a73b0a | 5867 | Lisp_Object undo_list; |
7d64c6ad | 5868 | Lisp_Object translation_table; |
d46c5b12 | 5869 | |
df7492f9 KH |
5870 | if (BUFFERP (coding->src_object) |
5871 | && coding->src_pos > 0 | |
5872 | && coding->src_pos < GPT | |
5873 | && coding->src_pos + coding->src_chars > GPT) | |
5874 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 5875 | |
24a73b0a | 5876 | undo_list = Qt; |
df7492f9 | 5877 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 5878 | { |
df7492f9 KH |
5879 | if (current_buffer != XBUFFER (coding->dst_object)) |
5880 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
5881 | if (GPT != PT) | |
5882 | move_gap_both (PT, PT_BYTE); | |
24a73b0a KH |
5883 | undo_list = current_buffer->undo_list; |
5884 | current_buffer->undo_list = Qt; | |
1c3478b0 KH |
5885 | } |
5886 | ||
df7492f9 KH |
5887 | coding->consumed = coding->consumed_char = 0; |
5888 | coding->produced = coding->produced_char = 0; | |
5889 | coding->chars_at_source = 0; | |
065e3595 | 5890 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 5891 | coding->errors = 0; |
1c3478b0 | 5892 | |
df7492f9 KH |
5893 | ALLOC_CONVERSION_WORK_AREA (coding); |
5894 | ||
5895 | attrs = CODING_ID_ATTRS (coding->id); | |
7d64c6ad | 5896 | translation_table = get_translation_table (attrs, 1); |
df7492f9 KH |
5897 | |
5898 | do | |
b73bfc1c | 5899 | { |
df7492f9 KH |
5900 | coding_set_source (coding); |
5901 | coding->annotated = 0; | |
5902 | (*(coding->decoder)) (coding); | |
7d64c6ad KH |
5903 | if (!NILP (translation_table)) |
5904 | translate_chars (coding, translation_table); | |
df7492f9 KH |
5905 | coding_set_destination (coding); |
5906 | produce_chars (coding); | |
5907 | if (coding->annotated) | |
5908 | produce_annotation (coding); | |
d46c5b12 | 5909 | } |
df7492f9 KH |
5910 | while (coding->consumed < coding->src_bytes |
5911 | && ! coding->result); | |
d46c5b12 | 5912 | |
df7492f9 KH |
5913 | coding->carryover_bytes = 0; |
5914 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 5915 | { |
df7492f9 | 5916 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 5917 | const unsigned char *src; |
df7492f9 KH |
5918 | |
5919 | coding_set_source (coding); | |
5920 | coding_set_destination (coding); | |
5921 | src = coding->source + coding->consumed; | |
5922 | ||
5923 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 5924 | { |
df7492f9 KH |
5925 | /* Flush out unprocessed data as binary chars. We are sure |
5926 | that the number of data is less than the size of | |
5927 | coding->charbuf. */ | |
065e3595 | 5928 | coding->charbuf_used = 0; |
df7492f9 | 5929 | while (nbytes-- > 0) |
1c3478b0 | 5930 | { |
df7492f9 | 5931 | int c = *src++; |
98725083 KH |
5932 | |
5933 | coding->charbuf[coding->charbuf_used++] = (c & 0x80 ? - c : c); | |
1c3478b0 | 5934 | } |
df7492f9 | 5935 | produce_chars (coding); |
d46c5b12 | 5936 | } |
d46c5b12 | 5937 | else |
df7492f9 KH |
5938 | { |
5939 | /* Record unprocessed bytes in coding->carryover. We are | |
5940 | sure that the number of data is less than the size of | |
5941 | coding->carryover. */ | |
5942 | unsigned char *p = coding->carryover; | |
5943 | ||
5944 | coding->carryover_bytes = nbytes; | |
5945 | while (nbytes-- > 0) | |
5946 | *p++ = *src++; | |
1c3478b0 | 5947 | } |
df7492f9 | 5948 | coding->consumed = coding->src_bytes; |
b73bfc1c | 5949 | } |
69f76525 | 5950 | |
24a73b0a KH |
5951 | if (BUFFERP (coding->dst_object)) |
5952 | { | |
5953 | current_buffer->undo_list = undo_list; | |
5954 | record_insert (coding->dst_pos, coding->produced_char); | |
5955 | } | |
5956 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix)) | |
5957 | decode_eol (coding); | |
73be902c | 5958 | return coding->result; |
4ed46869 KH |
5959 | } |
5960 | ||
aaaf0b1e | 5961 | |
e1c23804 | 5962 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
5963 | ending before LIMIT of CODING->src_object (buffer or string), store |
5964 | the data in BUF, set *STOP to a starting position of the next | |
5965 | composition (if any) or to LIMIT, and return the address of the | |
5966 | next element of BUF. | |
5967 | ||
5968 | If such an annotation is not found, set *STOP to a starting | |
5969 | position of a composition after POS (if any) or to LIMIT, and | |
5970 | return BUF. */ | |
5971 | ||
5972 | static INLINE int * | |
5973 | handle_composition_annotation (pos, limit, coding, buf, stop) | |
5974 | EMACS_INT pos, limit; | |
aaaf0b1e | 5975 | struct coding_system *coding; |
ff0dacd7 KH |
5976 | int *buf; |
5977 | EMACS_INT *stop; | |
aaaf0b1e | 5978 | { |
ff0dacd7 KH |
5979 | EMACS_INT start, end; |
5980 | Lisp_Object prop; | |
aaaf0b1e | 5981 | |
ff0dacd7 KH |
5982 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
5983 | || end > limit) | |
5984 | *stop = limit; | |
5985 | else if (start > pos) | |
5986 | *stop = start; | |
5987 | else | |
aaaf0b1e | 5988 | { |
ff0dacd7 | 5989 | if (start == pos) |
aaaf0b1e | 5990 | { |
ff0dacd7 KH |
5991 | /* We found a composition. Store the corresponding |
5992 | annotation data in BUF. */ | |
5993 | int *head = buf; | |
5994 | enum composition_method method = COMPOSITION_METHOD (prop); | |
5995 | int nchars = COMPOSITION_LENGTH (prop); | |
5996 | ||
5997 | ADD_COMPOSITION_DATA (buf, 0, nchars, method); | |
5998 | if (method != COMPOSITION_RELATIVE) | |
aaaf0b1e | 5999 | { |
ff0dacd7 KH |
6000 | Lisp_Object components; |
6001 | int len, i, i_byte; | |
6002 | ||
6003 | components = COMPOSITION_COMPONENTS (prop); | |
6004 | if (VECTORP (components)) | |
aaaf0b1e | 6005 | { |
ff0dacd7 KH |
6006 | len = XVECTOR (components)->size; |
6007 | for (i = 0; i < len; i++) | |
6008 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 6009 | } |
ff0dacd7 | 6010 | else if (STRINGP (components)) |
aaaf0b1e | 6011 | { |
8f924df7 | 6012 | len = SCHARS (components); |
ff0dacd7 KH |
6013 | i = i_byte = 0; |
6014 | while (i < len) | |
6015 | { | |
6016 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
6017 | buf++; | |
6018 | } | |
6019 | } | |
6020 | else if (INTEGERP (components)) | |
6021 | { | |
6022 | len = 1; | |
6023 | *buf++ = XINT (components); | |
6024 | } | |
6025 | else if (CONSP (components)) | |
6026 | { | |
6027 | for (len = 0; CONSP (components); | |
6028 | len++, components = XCDR (components)) | |
6029 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 6030 | } |
aaaf0b1e | 6031 | else |
ff0dacd7 KH |
6032 | abort (); |
6033 | *head -= len; | |
aaaf0b1e | 6034 | } |
aaaf0b1e | 6035 | } |
ff0dacd7 KH |
6036 | |
6037 | if (find_composition (end, limit, &start, &end, &prop, | |
6038 | coding->src_object) | |
6039 | && end <= limit) | |
6040 | *stop = start; | |
6041 | else | |
6042 | *stop = limit; | |
aaaf0b1e | 6043 | } |
ff0dacd7 KH |
6044 | return buf; |
6045 | } | |
6046 | ||
6047 | ||
e1c23804 | 6048 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
6049 | CODING->src_object (buffer of string), store the data in BUF, set |
6050 | *STOP to the position where the value of `charset' property changes | |
6051 | (limiting by LIMIT), and return the address of the next element of | |
6052 | BUF. | |
6053 | ||
6054 | If the property value is nil, set *STOP to the position where the | |
6055 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
6056 | ||
6057 | static INLINE int * | |
6058 | handle_charset_annotation (pos, limit, coding, buf, stop) | |
6059 | EMACS_INT pos, limit; | |
6060 | struct coding_system *coding; | |
6061 | int *buf; | |
6062 | EMACS_INT *stop; | |
6063 | { | |
6064 | Lisp_Object val, next; | |
6065 | int id; | |
6066 | ||
6067 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
6068 | if (! NILP (val) && CHARSETP (val)) | |
6069 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
6070 | else | |
6071 | id = -1; | |
6072 | ADD_CHARSET_DATA (buf, 0, 0, id); | |
6073 | next = Fnext_single_property_change (make_number (pos), Qcharset, | |
6074 | coding->src_object, | |
6075 | make_number (limit)); | |
6076 | *stop = XINT (next); | |
6077 | return buf; | |
6078 | } | |
6079 | ||
6080 | ||
df7492f9 KH |
6081 | static void |
6082 | consume_chars (coding) | |
6083 | struct coding_system *coding; | |
6084 | { | |
6085 | int *buf = coding->charbuf; | |
ff0dacd7 | 6086 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 6087 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 6088 | const unsigned char *src_end = coding->source + coding->src_bytes; |
ff0dacd7 KH |
6089 | EMACS_INT pos = coding->src_pos + coding->consumed_char; |
6090 | EMACS_INT end_pos = coding->src_pos + coding->src_chars; | |
df7492f9 KH |
6091 | int multibytep = coding->src_multibyte; |
6092 | Lisp_Object eol_type; | |
6093 | int c; | |
ff0dacd7 | 6094 | EMACS_INT stop, stop_composition, stop_charset; |
88993dfd | 6095 | |
df7492f9 KH |
6096 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6097 | if (VECTORP (eol_type)) | |
6098 | eol_type = Qunix; | |
88993dfd | 6099 | |
df7492f9 KH |
6100 | /* Note: composition handling is not yet implemented. */ |
6101 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 6102 | |
0b5670c9 KH |
6103 | if (NILP (coding->src_object)) |
6104 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 6105 | else |
0b5670c9 KH |
6106 | { |
6107 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
6108 | stop = stop_composition = pos; | |
6109 | else | |
6110 | stop = stop_composition = end_pos; | |
6111 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
6112 | stop = stop_charset = pos; | |
6113 | else | |
6114 | stop_charset = end_pos; | |
6115 | } | |
ec6d2bb8 | 6116 | |
24a73b0a | 6117 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 6118 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 6119 | while (buf < buf_end) |
aaaf0b1e | 6120 | { |
df7492f9 | 6121 | if (pos == stop) |
ec6d2bb8 | 6122 | { |
df7492f9 KH |
6123 | if (pos == end_pos) |
6124 | break; | |
ff0dacd7 KH |
6125 | if (pos == stop_composition) |
6126 | buf = handle_composition_annotation (pos, end_pos, coding, | |
6127 | buf, &stop_composition); | |
6128 | if (pos == stop_charset) | |
6129 | buf = handle_charset_annotation (pos, end_pos, coding, | |
6130 | buf, &stop_charset); | |
6131 | stop = (stop_composition < stop_charset | |
6132 | ? stop_composition : stop_charset); | |
df7492f9 KH |
6133 | } |
6134 | ||
6135 | if (! multibytep) | |
4776e638 | 6136 | { |
d3e4cb56 | 6137 | EMACS_INT bytes; |
aaaf0b1e | 6138 | |
d3e4cb56 KH |
6139 | if (! CODING_FOR_UNIBYTE (coding) |
6140 | && (bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
4776e638 KH |
6141 | c = STRING_CHAR_ADVANCE (src), pos += bytes; |
6142 | else | |
6143 | c = *src++, pos++; | |
6144 | } | |
df7492f9 | 6145 | else |
4776e638 | 6146 | c = STRING_CHAR_ADVANCE (src), pos++; |
df7492f9 KH |
6147 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
6148 | c = '\n'; | |
6149 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 6150 | { |
df7492f9 | 6151 | if (c == '\n') |
aaaf0b1e | 6152 | { |
df7492f9 KH |
6153 | if (EQ (eol_type, Qdos)) |
6154 | *buf++ = '\r'; | |
6155 | else | |
6156 | c = '\r'; | |
aaaf0b1e KH |
6157 | } |
6158 | } | |
df7492f9 | 6159 | *buf++ = c; |
aaaf0b1e | 6160 | } |
ec6d2bb8 | 6161 | |
df7492f9 KH |
6162 | coding->consumed = src - coding->source; |
6163 | coding->consumed_char = pos - coding->src_pos; | |
6164 | coding->charbuf_used = buf - coding->charbuf; | |
6165 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
6166 | } |
6167 | ||
4ed46869 | 6168 | |
df7492f9 KH |
6169 | /* Encode the text at CODING->src_object into CODING->dst_object. |
6170 | CODING->src_object is a buffer or a string. | |
6171 | CODING->dst_object is a buffer or nil. | |
6172 | ||
6173 | If CODING->src_object is a buffer, it must be the current buffer. | |
6174 | In this case, if CODING->src_pos is positive, it is a position of | |
6175 | the source text in the buffer, otherwise. the source text is in the | |
6176 | gap area of the buffer, and coding->src_pos specifies the offset of | |
6177 | the text from GPT (which must be the same as PT). If this is the | |
6178 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6179 | negative and CODING should not have `pre-write-conversion'. | |
6180 | ||
6181 | If CODING->src_object is a string, CODING should not have | |
6182 | `pre-write-conversion'. | |
6183 | ||
6184 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
6185 | the current point of that buffer. | |
6186 | ||
6187 | If CODING->dst_object is nil, the encoded data is placed at the | |
6188 | memory area specified by CODING->destination. */ | |
6189 | ||
6190 | static int | |
6191 | encode_coding (coding) | |
4ed46869 | 6192 | struct coding_system *coding; |
4ed46869 | 6193 | { |
df7492f9 | 6194 | Lisp_Object attrs; |
7d64c6ad | 6195 | Lisp_Object translation_table; |
9861e777 | 6196 | |
df7492f9 | 6197 | attrs = CODING_ID_ATTRS (coding->id); |
7d64c6ad | 6198 | translation_table = get_translation_table (attrs, 1); |
4ed46869 | 6199 | |
df7492f9 | 6200 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 6201 | { |
df7492f9 KH |
6202 | set_buffer_internal (XBUFFER (coding->dst_object)); |
6203 | coding->dst_multibyte | |
6204 | = ! NILP (current_buffer->enable_multibyte_characters); | |
8844fa83 | 6205 | } |
4ed46869 | 6206 | |
b73bfc1c | 6207 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 6208 | coding->produced = coding->produced_char = 0; |
065e3595 | 6209 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 6210 | coding->errors = 0; |
b73bfc1c | 6211 | |
df7492f9 | 6212 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 6213 | |
df7492f9 KH |
6214 | do { |
6215 | coding_set_source (coding); | |
6216 | consume_chars (coding); | |
4ed46869 | 6217 | |
7d64c6ad KH |
6218 | if (!NILP (translation_table)) |
6219 | translate_chars (coding, translation_table); | |
b73bfc1c | 6220 | |
df7492f9 KH |
6221 | coding_set_destination (coding); |
6222 | (*(coding->encoder)) (coding); | |
6223 | } while (coding->consumed_char < coding->src_chars); | |
6224 | ||
6225 | if (BUFFERP (coding->dst_object)) | |
6226 | insert_from_gap (coding->produced_char, coding->produced); | |
6227 | ||
6228 | return (coding->result); | |
ec6d2bb8 KH |
6229 | } |
6230 | ||
fb88bf2d | 6231 | |
24a73b0a KH |
6232 | /* Name (or base name) of work buffer for code conversion. */ |
6233 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 6234 | |
24a73b0a KH |
6235 | /* A working buffer used by the top level conversion. Once it is |
6236 | created, it is never destroyed. It has the name | |
6237 | Vcode_conversion_workbuf_name. The other working buffers are | |
6238 | destroyed after the use is finished, and their names are modified | |
6239 | versions of Vcode_conversion_workbuf_name. */ | |
6240 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 6241 | |
24a73b0a KH |
6242 | /* 1 iff Vcode_conversion_reused_workbuf is already in use. */ |
6243 | static int reused_workbuf_in_use; | |
4ed46869 | 6244 | |
24a73b0a KH |
6245 | |
6246 | /* Return a working buffer of code convesion. MULTIBYTE specifies the | |
6247 | multibyteness of returning buffer. */ | |
b73bfc1c | 6248 | |
df7492f9 | 6249 | Lisp_Object |
24a73b0a | 6250 | make_conversion_work_buffer (multibyte) |
df7492f9 | 6251 | { |
24a73b0a KH |
6252 | Lisp_Object name, workbuf; |
6253 | struct buffer *current; | |
4ed46869 | 6254 | |
24a73b0a | 6255 | if (reused_workbuf_in_use++) |
065e3595 KH |
6256 | { |
6257 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
6258 | workbuf = Fget_buffer_create (name); | |
6259 | } | |
df7492f9 | 6260 | else |
065e3595 KH |
6261 | { |
6262 | name = Vcode_conversion_workbuf_name; | |
6263 | workbuf = Fget_buffer_create (name); | |
6264 | if (NILP (Vcode_conversion_reused_workbuf)) | |
6265 | Vcode_conversion_reused_workbuf = workbuf; | |
6266 | } | |
24a73b0a KH |
6267 | current = current_buffer; |
6268 | set_buffer_internal (XBUFFER (workbuf)); | |
6269 | Ferase_buffer (); | |
df7492f9 | 6270 | current_buffer->undo_list = Qt; |
24a73b0a | 6271 | current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil; |
df7492f9 | 6272 | set_buffer_internal (current); |
24a73b0a | 6273 | return workbuf; |
df7492f9 | 6274 | } |
d46c5b12 | 6275 | |
24a73b0a | 6276 | |
4776e638 | 6277 | static Lisp_Object |
24a73b0a KH |
6278 | code_conversion_restore (arg) |
6279 | Lisp_Object arg; | |
4776e638 | 6280 | { |
24a73b0a KH |
6281 | Lisp_Object current, workbuf; |
6282 | ||
6283 | current = XCAR (arg); | |
6284 | workbuf = XCDR (arg); | |
6285 | if (! NILP (workbuf)) | |
6286 | { | |
6287 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
6288 | reused_workbuf_in_use = 0; | |
6289 | else if (! NILP (Fbuffer_live_p (workbuf))) | |
6290 | Fkill_buffer (workbuf); | |
6291 | } | |
6292 | set_buffer_internal (XBUFFER (current)); | |
4776e638 KH |
6293 | return Qnil; |
6294 | } | |
b73bfc1c | 6295 | |
24a73b0a KH |
6296 | Lisp_Object |
6297 | code_conversion_save (with_work_buf, multibyte) | |
4776e638 | 6298 | int with_work_buf, multibyte; |
df7492f9 | 6299 | { |
24a73b0a | 6300 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 6301 | |
4776e638 | 6302 | if (with_work_buf) |
24a73b0a KH |
6303 | workbuf = make_conversion_work_buffer (multibyte); |
6304 | record_unwind_protect (code_conversion_restore, | |
6305 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 6306 | return workbuf; |
df7492f9 | 6307 | } |
d46c5b12 | 6308 | |
df7492f9 KH |
6309 | int |
6310 | decode_coding_gap (coding, chars, bytes) | |
6311 | struct coding_system *coding; | |
6312 | EMACS_INT chars, bytes; | |
6313 | { | |
6314 | int count = specpdl_ptr - specpdl; | |
5e5c78be | 6315 | Lisp_Object attrs; |
fb88bf2d | 6316 | |
24a73b0a | 6317 | code_conversion_save (0, 0); |
ec6d2bb8 | 6318 | |
24a73b0a | 6319 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6320 | coding->src_chars = chars; |
6321 | coding->src_bytes = bytes; | |
6322 | coding->src_pos = -chars; | |
6323 | coding->src_pos_byte = -bytes; | |
6324 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 6325 | coding->dst_object = coding->src_object; |
df7492f9 KH |
6326 | coding->dst_pos = PT; |
6327 | coding->dst_pos_byte = PT_BYTE; | |
71c81426 | 6328 | coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters); |
98725083 | 6329 | coding->mode |= CODING_MODE_LAST_BLOCK; |
4ed46869 | 6330 | |
df7492f9 KH |
6331 | if (CODING_REQUIRE_DETECTION (coding)) |
6332 | detect_coding (coding); | |
8f924df7 | 6333 | |
df7492f9 | 6334 | decode_coding (coding); |
d46c5b12 | 6335 | |
5e5c78be KH |
6336 | attrs = CODING_ID_ATTRS (coding->id); |
6337 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 6338 | { |
5e5c78be KH |
6339 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
6340 | Lisp_Object val; | |
6341 | ||
6342 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
6343 | val = call1 (CODING_ATTR_POST_READ (attrs), |
6344 | make_number (coding->produced_char)); | |
5e5c78be KH |
6345 | CHECK_NATNUM (val); |
6346 | coding->produced_char += Z - prev_Z; | |
6347 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 6348 | } |
4ed46869 | 6349 | |
df7492f9 | 6350 | unbind_to (count, Qnil); |
b73bfc1c KH |
6351 | return coding->result; |
6352 | } | |
52d41803 | 6353 | |
4ed46869 | 6354 | int |
df7492f9 | 6355 | encode_coding_gap (coding, chars, bytes) |
4ed46869 | 6356 | struct coding_system *coding; |
df7492f9 | 6357 | EMACS_INT chars, bytes; |
4ed46869 | 6358 | { |
df7492f9 | 6359 | int count = specpdl_ptr - specpdl; |
4ed46869 | 6360 | |
24a73b0a | 6361 | code_conversion_save (0, 0); |
4ed46869 | 6362 | |
24a73b0a | 6363 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6364 | coding->src_chars = chars; |
6365 | coding->src_bytes = bytes; | |
6366 | coding->src_pos = -chars; | |
6367 | coding->src_pos_byte = -bytes; | |
6368 | coding->src_multibyte = chars < bytes; | |
6369 | coding->dst_object = coding->src_object; | |
6370 | coding->dst_pos = PT; | |
6371 | coding->dst_pos_byte = PT_BYTE; | |
4ed46869 | 6372 | |
df7492f9 | 6373 | encode_coding (coding); |
b73bfc1c | 6374 | |
df7492f9 KH |
6375 | unbind_to (count, Qnil); |
6376 | return coding->result; | |
6377 | } | |
4ed46869 | 6378 | |
d46c5b12 | 6379 | |
df7492f9 KH |
6380 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
6381 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 6382 | |
df7492f9 | 6383 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 6384 | |
df7492f9 KH |
6385 | If it is a buffer, the text is at point of the buffer. FROM and TO |
6386 | are positions in the buffer. | |
b73bfc1c | 6387 | |
df7492f9 KH |
6388 | If it is a string, the text is at the beginning of the string. |
6389 | FROM and TO are indices to the string. | |
4ed46869 | 6390 | |
df7492f9 KH |
6391 | If it is nil, the text is at coding->source. FROM and TO are |
6392 | indices to coding->source. | |
bb10be8b | 6393 | |
df7492f9 | 6394 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 6395 | |
df7492f9 KH |
6396 | If it is a buffer, the decoded text is inserted at point of the |
6397 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
6398 | is deleted. | |
4ed46869 | 6399 | |
df7492f9 KH |
6400 | If it is Qt, a string is made from the decoded text, and |
6401 | set in CODING->dst_object. | |
d46c5b12 | 6402 | |
df7492f9 | 6403 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 6404 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
6405 | CODING->destination by xmalloc. If the decoded text is longer than |
6406 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
6407 | */ | |
d46c5b12 | 6408 | |
df7492f9 KH |
6409 | void |
6410 | decode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6411 | dst_object) | |
d46c5b12 | 6412 | struct coding_system *coding; |
df7492f9 KH |
6413 | Lisp_Object src_object; |
6414 | EMACS_INT from, from_byte, to, to_byte; | |
6415 | Lisp_Object dst_object; | |
d46c5b12 | 6416 | { |
df7492f9 KH |
6417 | int count = specpdl_ptr - specpdl; |
6418 | unsigned char *destination; | |
6419 | EMACS_INT dst_bytes; | |
6420 | EMACS_INT chars = to - from; | |
6421 | EMACS_INT bytes = to_byte - from_byte; | |
6422 | Lisp_Object attrs; | |
4776e638 KH |
6423 | Lisp_Object buffer; |
6424 | int saved_pt = -1, saved_pt_byte; | |
d46c5b12 | 6425 | |
4776e638 | 6426 | buffer = Fcurrent_buffer (); |
93dec019 | 6427 | |
df7492f9 | 6428 | if (NILP (dst_object)) |
d46c5b12 | 6429 | { |
df7492f9 KH |
6430 | destination = coding->destination; |
6431 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 6432 | } |
93dec019 | 6433 | |
df7492f9 KH |
6434 | coding->src_object = src_object; |
6435 | coding->src_chars = chars; | |
6436 | coding->src_bytes = bytes; | |
6437 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 6438 | |
df7492f9 | 6439 | if (STRINGP (src_object)) |
d46c5b12 | 6440 | { |
df7492f9 KH |
6441 | coding->src_pos = from; |
6442 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6443 | } |
df7492f9 | 6444 | else if (BUFFERP (src_object)) |
88993dfd | 6445 | { |
df7492f9 KH |
6446 | set_buffer_internal (XBUFFER (src_object)); |
6447 | if (from != GPT) | |
6448 | move_gap_both (from, from_byte); | |
6449 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 6450 | { |
4776e638 | 6451 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6452 | TEMP_SET_PT_BOTH (from, from_byte); |
6453 | del_range_both (from, from_byte, to, to_byte, 1); | |
6454 | coding->src_pos = -chars; | |
6455 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 6456 | } |
df7492f9 | 6457 | else |
fb88bf2d | 6458 | { |
df7492f9 KH |
6459 | coding->src_pos = from; |
6460 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 6461 | } |
88993dfd KH |
6462 | } |
6463 | ||
df7492f9 KH |
6464 | if (CODING_REQUIRE_DETECTION (coding)) |
6465 | detect_coding (coding); | |
6466 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 6467 | |
2cb26057 KH |
6468 | if (EQ (dst_object, Qt) |
6469 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
6470 | && NILP (dst_object))) | |
b73bfc1c | 6471 | { |
24a73b0a | 6472 | coding->dst_object = code_conversion_save (1, 1); |
df7492f9 KH |
6473 | coding->dst_pos = BEG; |
6474 | coding->dst_pos_byte = BEG_BYTE; | |
6475 | coding->dst_multibyte = 1; | |
b73bfc1c | 6476 | } |
df7492f9 | 6477 | else if (BUFFERP (dst_object)) |
d46c5b12 | 6478 | { |
24a73b0a | 6479 | code_conversion_save (0, 0); |
df7492f9 KH |
6480 | coding->dst_object = dst_object; |
6481 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6482 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6483 | coding->dst_multibyte | |
6484 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
d46c5b12 KH |
6485 | } |
6486 | else | |
6487 | { | |
24a73b0a | 6488 | code_conversion_save (0, 0); |
df7492f9 KH |
6489 | coding->dst_object = Qnil; |
6490 | coding->dst_multibyte = 1; | |
d46c5b12 KH |
6491 | } |
6492 | ||
df7492f9 | 6493 | decode_coding (coding); |
fa46990e | 6494 | |
df7492f9 KH |
6495 | if (BUFFERP (coding->dst_object)) |
6496 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 6497 | |
df7492f9 | 6498 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 6499 | { |
df7492f9 KH |
6500 | struct gcpro gcpro1, gcpro2; |
6501 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; | |
2b4f9037 | 6502 | Lisp_Object val; |
d46c5b12 | 6503 | |
c0cc7f7f | 6504 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
df7492f9 KH |
6505 | GCPRO2 (coding->src_object, coding->dst_object); |
6506 | val = call1 (CODING_ATTR_POST_READ (attrs), | |
6507 | make_number (coding->produced_char)); | |
6508 | UNGCPRO; | |
6509 | CHECK_NATNUM (val); | |
6510 | coding->produced_char += Z - prev_Z; | |
6511 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 6512 | } |
de79a6a5 | 6513 | |
df7492f9 | 6514 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 6515 | { |
df7492f9 KH |
6516 | coding->dst_object = Fbuffer_string (); |
6517 | } | |
6518 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
6519 | { | |
6520 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6521 | if (dst_bytes < coding->produced) | |
6522 | { | |
6523 | destination | |
6524 | = (unsigned char *) xrealloc (destination, coding->produced); | |
6525 | if (! destination) | |
6526 | { | |
065e3595 KH |
6527 | record_conversion_result (coding, |
6528 | CODING_RESULT_INSUFFICIENT_DST); | |
df7492f9 KH |
6529 | unbind_to (count, Qnil); |
6530 | return; | |
6531 | } | |
6532 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
6533 | move_gap_both (BEGV, BEGV_BYTE); | |
6534 | bcopy (BEGV_ADDR, destination, coding->produced); | |
6535 | coding->destination = destination; | |
d46c5b12 | 6536 | } |
ec6d2bb8 | 6537 | } |
b73bfc1c | 6538 | |
4776e638 KH |
6539 | if (saved_pt >= 0) |
6540 | { | |
6541 | /* This is the case of: | |
6542 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
6543 | As we have moved PT while replacing the original buffer | |
6544 | contents, we must recover it now. */ | |
6545 | set_buffer_internal (XBUFFER (src_object)); | |
6546 | if (saved_pt < from) | |
6547 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
6548 | else if (saved_pt < from + chars) | |
6549 | TEMP_SET_PT_BOTH (from, from_byte); | |
6550 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
6551 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
6552 | saved_pt_byte + (coding->produced - bytes)); | |
6553 | else | |
6554 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
6555 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 6556 | } |
4776e638 | 6557 | |
065e3595 | 6558 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
6559 | } |
6560 | ||
d46c5b12 | 6561 | |
df7492f9 KH |
6562 | void |
6563 | encode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6564 | dst_object) | |
d46c5b12 | 6565 | struct coding_system *coding; |
df7492f9 KH |
6566 | Lisp_Object src_object; |
6567 | EMACS_INT from, from_byte, to, to_byte; | |
6568 | Lisp_Object dst_object; | |
d46c5b12 | 6569 | { |
b73bfc1c | 6570 | int count = specpdl_ptr - specpdl; |
df7492f9 KH |
6571 | EMACS_INT chars = to - from; |
6572 | EMACS_INT bytes = to_byte - from_byte; | |
6573 | Lisp_Object attrs; | |
4776e638 KH |
6574 | Lisp_Object buffer; |
6575 | int saved_pt = -1, saved_pt_byte; | |
df7492f9 | 6576 | |
4776e638 | 6577 | buffer = Fcurrent_buffer (); |
df7492f9 KH |
6578 | |
6579 | coding->src_object = src_object; | |
6580 | coding->src_chars = chars; | |
6581 | coding->src_bytes = bytes; | |
6582 | coding->src_multibyte = chars < bytes; | |
6583 | ||
6584 | attrs = CODING_ID_ATTRS (coding->id); | |
6585 | ||
6586 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
6bac5b12 | 6587 | { |
24a73b0a | 6588 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
6589 | set_buffer_internal (XBUFFER (coding->src_object)); |
6590 | if (STRINGP (src_object)) | |
6591 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
6592 | else if (BUFFERP (src_object)) | |
6593 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
6594 | else | |
6595 | insert_1_both (coding->source + from, chars, bytes, 0, 0, 0); | |
d46c5b12 | 6596 | |
df7492f9 KH |
6597 | if (EQ (src_object, dst_object)) |
6598 | { | |
6599 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 6600 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6601 | del_range_both (from, from_byte, to, to_byte, 1); |
6602 | set_buffer_internal (XBUFFER (coding->src_object)); | |
6603 | } | |
6604 | ||
ac87bbef KH |
6605 | call2 (CODING_ATTR_PRE_WRITE (attrs), |
6606 | make_number (BEG), make_number (Z)); | |
6607 | coding->src_object = Fcurrent_buffer (); | |
df7492f9 KH |
6608 | if (BEG != GPT) |
6609 | move_gap_both (BEG, BEG_BYTE); | |
6610 | coding->src_chars = Z - BEG; | |
6611 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
6612 | coding->src_pos = BEG; | |
6613 | coding->src_pos_byte = BEG_BYTE; | |
6614 | coding->src_multibyte = Z < Z_BYTE; | |
6615 | } | |
6616 | else if (STRINGP (src_object)) | |
d46c5b12 | 6617 | { |
24a73b0a | 6618 | code_conversion_save (0, 0); |
df7492f9 KH |
6619 | coding->src_pos = from; |
6620 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 6621 | } |
df7492f9 | 6622 | else if (BUFFERP (src_object)) |
b73bfc1c | 6623 | { |
24a73b0a | 6624 | code_conversion_save (0, 0); |
df7492f9 | 6625 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 6626 | if (EQ (src_object, dst_object)) |
d46c5b12 | 6627 | { |
4776e638 | 6628 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
6629 | coding->src_object = del_range_1 (from, to, 1, 1); |
6630 | coding->src_pos = 0; | |
6631 | coding->src_pos_byte = 0; | |
d46c5b12 | 6632 | } |
df7492f9 | 6633 | else |
d46c5b12 | 6634 | { |
ff0dacd7 KH |
6635 | if (from < GPT && to >= GPT) |
6636 | move_gap_both (from, from_byte); | |
df7492f9 KH |
6637 | coding->src_pos = from; |
6638 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6639 | } |
d46c5b12 | 6640 | } |
4776e638 | 6641 | else |
24a73b0a | 6642 | code_conversion_save (0, 0); |
d46c5b12 | 6643 | |
df7492f9 | 6644 | if (BUFFERP (dst_object)) |
88993dfd | 6645 | { |
df7492f9 | 6646 | coding->dst_object = dst_object; |
28f67a95 KH |
6647 | if (EQ (src_object, dst_object)) |
6648 | { | |
6649 | coding->dst_pos = from; | |
6650 | coding->dst_pos_byte = from_byte; | |
6651 | } | |
6652 | else | |
6653 | { | |
6654 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6655 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6656 | } | |
df7492f9 KH |
6657 | coding->dst_multibyte |
6658 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
88993dfd | 6659 | } |
df7492f9 | 6660 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 6661 | { |
df7492f9 | 6662 | coding->dst_object = Qnil; |
df7492f9 | 6663 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
6664 | if (coding->dst_bytes == 0) |
6665 | coding->dst_bytes = 1; | |
6666 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 6667 | coding->dst_multibyte = 0; |
d46c5b12 KH |
6668 | } |
6669 | else | |
6670 | { | |
df7492f9 KH |
6671 | coding->dst_object = Qnil; |
6672 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
6673 | } |
6674 | ||
df7492f9 | 6675 | encode_coding (coding); |
d46c5b12 | 6676 | |
df7492f9 | 6677 | if (EQ (dst_object, Qt)) |
d46c5b12 | 6678 | { |
df7492f9 KH |
6679 | if (BUFFERP (coding->dst_object)) |
6680 | coding->dst_object = Fbuffer_string (); | |
6681 | else | |
d46c5b12 | 6682 | { |
df7492f9 KH |
6683 | coding->dst_object |
6684 | = make_unibyte_string ((char *) coding->destination, | |
6685 | coding->produced); | |
6686 | xfree (coding->destination); | |
d46c5b12 | 6687 | } |
4ed46869 | 6688 | } |
d46c5b12 | 6689 | |
4776e638 KH |
6690 | if (saved_pt >= 0) |
6691 | { | |
6692 | /* This is the case of: | |
6693 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
6694 | As we have moved PT while replacing the original buffer | |
6695 | contents, we must recover it now. */ | |
6696 | set_buffer_internal (XBUFFER (src_object)); | |
6697 | if (saved_pt < from) | |
6698 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
6699 | else if (saved_pt < from + chars) | |
6700 | TEMP_SET_PT_BOTH (from, from_byte); | |
6701 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
6702 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
6703 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 6704 | else |
4776e638 KH |
6705 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
6706 | saved_pt_byte + (coding->produced - bytes)); | |
6707 | } | |
6708 | ||
df7492f9 | 6709 | unbind_to (count, Qnil); |
b73bfc1c KH |
6710 | } |
6711 | ||
df7492f9 | 6712 | |
b73bfc1c | 6713 | Lisp_Object |
df7492f9 | 6714 | preferred_coding_system () |
b73bfc1c | 6715 | { |
df7492f9 | 6716 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 6717 | |
df7492f9 | 6718 | return CODING_ID_NAME (id); |
4ed46869 KH |
6719 | } |
6720 | ||
6721 | \f | |
6722 | #ifdef emacs | |
1397dc18 | 6723 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 6724 | |
4ed46869 | 6725 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 6726 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 6727 | See the documentation of `define-coding-system' for information |
48b0f3ae PJ |
6728 | about coding-system objects. */) |
6729 | (obj) | |
4ed46869 KH |
6730 | Lisp_Object obj; |
6731 | { | |
df7492f9 | 6732 | return ((NILP (obj) || CODING_SYSTEM_P (obj)) ? Qt : Qnil); |
4ed46869 KH |
6733 | } |
6734 | ||
9d991de8 RS |
6735 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
6736 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae PJ |
6737 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
6738 | (prompt) | |
4ed46869 KH |
6739 | Lisp_Object prompt; |
6740 | { | |
e0e989f6 | 6741 | Lisp_Object val; |
9d991de8 RS |
6742 | do |
6743 | { | |
4608c386 KH |
6744 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
6745 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 6746 | } |
8f924df7 | 6747 | while (SCHARS (val) == 0); |
e0e989f6 | 6748 | return (Fintern (val, Qnil)); |
4ed46869 KH |
6749 | } |
6750 | ||
9b787f3e | 6751 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae PJ |
6752 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
6753 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. */) | |
6754 | (prompt, default_coding_system) | |
9b787f3e | 6755 | Lisp_Object prompt, default_coding_system; |
4ed46869 | 6756 | { |
f44d27ce | 6757 | Lisp_Object val; |
9b787f3e | 6758 | if (SYMBOLP (default_coding_system)) |
a3181084 | 6759 | XSETSTRING (default_coding_system, XPNTR (SYMBOL_NAME (default_coding_system))); |
4608c386 | 6760 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
6761 | Qt, Qnil, Qcoding_system_history, |
6762 | default_coding_system, Qnil); | |
8f924df7 | 6763 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
6764 | } |
6765 | ||
6766 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
6767 | 1, 1, 0, | |
48b0f3ae | 6768 | doc: /* Check validity of CODING-SYSTEM. |
b054002f | 6769 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. */) |
df7492f9 | 6770 | (coding_system) |
4ed46869 KH |
6771 | Lisp_Object coding_system; |
6772 | { | |
b7826503 | 6773 | CHECK_SYMBOL (coding_system); |
4ed46869 KH |
6774 | if (!NILP (Fcoding_system_p (coding_system))) |
6775 | return coding_system; | |
6776 | while (1) | |
02ba4723 | 6777 | Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil)); |
4ed46869 | 6778 | } |
df7492f9 | 6779 | |
3a73fa5d | 6780 | \f |
89528eb3 KH |
6781 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
6782 | HIGHEST is nonzero, return the coding system of the highest | |
6783 | priority among the detected coding systems. Otherwize return a | |
6784 | list of detected coding systems sorted by their priorities. If | |
6785 | MULTIBYTEP is nonzero, it is assumed that the bytes are in correct | |
6786 | multibyte form but contains only ASCII and eight-bit chars. | |
6787 | Otherwise, the bytes are raw bytes. | |
6788 | ||
6789 | CODING-SYSTEM controls the detection as below: | |
6790 | ||
6791 | If it is nil, detect both text-format and eol-format. If the | |
6792 | text-format part of CODING-SYSTEM is already specified | |
6793 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
6794 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
6795 | detect only text-format. */ | |
6796 | ||
d46c5b12 | 6797 | Lisp_Object |
24a73b0a KH |
6798 | detect_coding_system (src, src_chars, src_bytes, highest, multibytep, |
6799 | coding_system) | |
8f924df7 | 6800 | const unsigned char *src; |
24a73b0a | 6801 | int src_chars, src_bytes, highest; |
0a28aafb | 6802 | int multibytep; |
df7492f9 | 6803 | Lisp_Object coding_system; |
4ed46869 | 6804 | { |
8f924df7 | 6805 | const unsigned char *src_end = src + src_bytes; |
df7492f9 KH |
6806 | Lisp_Object attrs, eol_type; |
6807 | Lisp_Object val; | |
6808 | struct coding_system coding; | |
89528eb3 | 6809 | int id; |
ff0dacd7 | 6810 | struct coding_detection_info detect_info; |
24a73b0a | 6811 | enum coding_category base_category; |
b73bfc1c | 6812 | |
df7492f9 KH |
6813 | if (NILP (coding_system)) |
6814 | coding_system = Qundecided; | |
6815 | setup_coding_system (coding_system, &coding); | |
6816 | attrs = CODING_ID_ATTRS (coding.id); | |
6817 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 6818 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 6819 | |
df7492f9 | 6820 | coding.source = src; |
24a73b0a | 6821 | coding.src_chars = src_chars; |
df7492f9 KH |
6822 | coding.src_bytes = src_bytes; |
6823 | coding.src_multibyte = multibytep; | |
6824 | coding.consumed = 0; | |
89528eb3 | 6825 | coding.mode |= CODING_MODE_LAST_BLOCK; |
d46c5b12 | 6826 | |
ff0dacd7 | 6827 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 6828 | |
89528eb3 | 6829 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
6830 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
6831 | if (base_category == coding_category_undecided) | |
4ed46869 | 6832 | { |
ff0dacd7 KH |
6833 | enum coding_category category; |
6834 | struct coding_system *this; | |
6835 | int c, i; | |
88993dfd | 6836 | |
24a73b0a KH |
6837 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
6838 | for (i = 0; src < src_end; i++, src++) | |
4ed46869 | 6839 | { |
df7492f9 | 6840 | c = *src; |
24a73b0a KH |
6841 | if (c & 0x80 || (c < 0x20 && (c == 0 |
6842 | || c == ISO_CODE_ESC | |
6843 | || c == ISO_CODE_SI | |
6844 | || c == ISO_CODE_SO))) | |
d46c5b12 | 6845 | break; |
4ed46869 | 6846 | } |
df7492f9 | 6847 | coding.head_ascii = src - coding.source; |
88993dfd | 6848 | |
df7492f9 KH |
6849 | if (src < src_end) |
6850 | for (i = 0; i < coding_category_raw_text; i++) | |
6851 | { | |
ff0dacd7 KH |
6852 | category = coding_priorities[i]; |
6853 | this = coding_categories + category; | |
b843d1ae | 6854 | |
df7492f9 KH |
6855 | if (this->id < 0) |
6856 | { | |
6857 | /* No coding system of this category is defined. */ | |
ff0dacd7 | 6858 | detect_info.rejected |= (1 << category); |
df7492f9 | 6859 | } |
ff0dacd7 | 6860 | else if (category >= coding_category_raw_text) |
89528eb3 | 6861 | continue; |
ff0dacd7 KH |
6862 | else if (detect_info.checked & (1 << category)) |
6863 | { | |
6864 | if (highest | |
6865 | && (detect_info.found & (1 << category))) | |
6866 | break; | |
6867 | } | |
df7492f9 KH |
6868 | else |
6869 | { | |
ff0dacd7 | 6870 | if ((*(this->detector)) (&coding, &detect_info) |
89528eb3 | 6871 | && highest |
ff0dacd7 | 6872 | && (detect_info.found & (1 << category))) |
24a73b0a KH |
6873 | { |
6874 | if (category == coding_category_utf_16_auto) | |
6875 | { | |
6876 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6877 | category = coding_category_utf_16_le; | |
6878 | else | |
6879 | category = coding_category_utf_16_be; | |
6880 | } | |
6881 | break; | |
6882 | } | |
df7492f9 KH |
6883 | } |
6884 | } | |
ec6d2bb8 | 6885 | |
ff0dacd7 | 6886 | if (detect_info.rejected == CATEGORY_MASK_ANY) |
ec6d2bb8 | 6887 | { |
ff0dacd7 | 6888 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
89528eb3 KH |
6889 | id = coding_categories[coding_category_raw_text].id; |
6890 | val = Fcons (make_number (id), Qnil); | |
6891 | } | |
ff0dacd7 | 6892 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 6893 | { |
ff0dacd7 | 6894 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
6895 | id = coding_categories[coding_category_undecided].id; |
6896 | val = Fcons (make_number (id), Qnil); | |
6897 | } | |
6898 | else if (highest) | |
6899 | { | |
ff0dacd7 | 6900 | if (detect_info.found) |
ec6d2bb8 | 6901 | { |
ff0dacd7 KH |
6902 | detect_info.found = 1 << category; |
6903 | val = Fcons (make_number (this->id), Qnil); | |
6904 | } | |
6905 | else | |
6906 | for (i = 0; i < coding_category_raw_text; i++) | |
6907 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
6908 | { | |
6909 | detect_info.found = 1 << coding_priorities[i]; | |
6910 | id = coding_categories[coding_priorities[i]].id; | |
6911 | val = Fcons (make_number (id), Qnil); | |
6912 | break; | |
6913 | } | |
6914 | } | |
89528eb3 KH |
6915 | else |
6916 | { | |
ff0dacd7 KH |
6917 | int mask = detect_info.rejected | detect_info.found; |
6918 | int found = 0; | |
89528eb3 | 6919 | val = Qnil; |
ec6d2bb8 | 6920 | |
89528eb3 | 6921 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
6922 | { |
6923 | category = coding_priorities[i]; | |
6924 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 6925 | { |
ff0dacd7 KH |
6926 | found |= 1 << category; |
6927 | id = coding_categories[category].id; | |
6928 | val = Fcons (make_number (id), val); | |
6929 | } | |
6930 | } | |
6931 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
6932 | { | |
6933 | category = coding_priorities[i]; | |
6934 | if (detect_info.found & (1 << category)) | |
6935 | { | |
6936 | id = coding_categories[category].id; | |
6937 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 6938 | } |
ec6d2bb8 | 6939 | } |
ff0dacd7 | 6940 | detect_info.found |= found; |
ec6d2bb8 | 6941 | } |
ec6d2bb8 | 6942 | } |
24a73b0a KH |
6943 | else if (base_category == coding_category_utf_16_auto) |
6944 | { | |
6945 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
6946 | { | |
6947 | enum coding_category category; | |
6948 | struct coding_system *this; | |
6949 | ||
6950 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6951 | this = coding_categories + coding_category_utf_16_le; | |
6952 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
6953 | this = coding_categories + coding_category_utf_16_be; | |
6954 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
6955 | this = coding_categories + coding_category_utf_16_be_nosig; | |
6956 | else | |
6957 | this = coding_categories + coding_category_utf_16_le_nosig; | |
6958 | val = Fcons (make_number (this->id), Qnil); | |
6959 | } | |
6960 | } | |
df7492f9 KH |
6961 | else |
6962 | { | |
ff0dacd7 | 6963 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 6964 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 6965 | } |
df7492f9 | 6966 | |
89528eb3 | 6967 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 6968 | { |
89528eb3 | 6969 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol; |
df7492f9 KH |
6970 | Lisp_Object tail; |
6971 | ||
89528eb3 KH |
6972 | if (VECTORP (eol_type)) |
6973 | { | |
ff0dacd7 | 6974 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
89528eb3 KH |
6975 | normal_eol = detect_eol (coding.source, src_bytes, |
6976 | coding_category_raw_text); | |
ff0dacd7 KH |
6977 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
6978 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
6979 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
6980 | coding_category_utf_16_be); | |
ff0dacd7 KH |
6981 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
6982 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
6983 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
6984 | coding_category_utf_16_le); | |
6985 | } | |
6986 | else | |
6987 | { | |
6988 | if (EQ (eol_type, Qunix)) | |
6989 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
6990 | else if (EQ (eol_type, Qdos)) | |
6991 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
6992 | else | |
6993 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
6994 | } | |
6995 | ||
df7492f9 KH |
6996 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
6997 | { | |
89528eb3 | 6998 | enum coding_category category; |
df7492f9 | 6999 | int this_eol; |
89528eb3 KH |
7000 | |
7001 | id = XINT (XCAR (tail)); | |
7002 | attrs = CODING_ID_ATTRS (id); | |
7003 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
7004 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
7005 | if (VECTORP (eol_type)) |
7006 | { | |
89528eb3 KH |
7007 | if (category == coding_category_utf_16_be |
7008 | || category == coding_category_utf_16_be_nosig) | |
7009 | this_eol = utf_16_be_eol; | |
7010 | else if (category == coding_category_utf_16_le | |
7011 | || category == coding_category_utf_16_le_nosig) | |
7012 | this_eol = utf_16_le_eol; | |
df7492f9 | 7013 | else |
89528eb3 KH |
7014 | this_eol = normal_eol; |
7015 | ||
df7492f9 KH |
7016 | if (this_eol == EOL_SEEN_LF) |
7017 | XSETCAR (tail, AREF (eol_type, 0)); | |
7018 | else if (this_eol == EOL_SEEN_CRLF) | |
7019 | XSETCAR (tail, AREF (eol_type, 1)); | |
7020 | else if (this_eol == EOL_SEEN_CR) | |
7021 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
7022 | else |
7023 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 7024 | } |
89528eb3 KH |
7025 | else |
7026 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
7027 | } |
7028 | } | |
ec6d2bb8 | 7029 | |
03699b14 | 7030 | return (highest ? XCAR (val) : val); |
ec6d2bb8 KH |
7031 | } |
7032 | ||
ec6d2bb8 | 7033 | |
d46c5b12 KH |
7034 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
7035 | 2, 3, 0, | |
48b0f3ae PJ |
7036 | doc: /* Detect coding system of the text in the region between START and END. |
7037 | Return a list of possible coding systems ordered by priority. | |
ec6d2bb8 | 7038 | |
48b0f3ae PJ |
7039 | If only ASCII characters are found, it returns a list of single element |
7040 | `undecided' or its subsidiary coding system according to a detected | |
7041 | end-of-line format. | |
ec6d2bb8 | 7042 | |
48b0f3ae PJ |
7043 | If optional argument HIGHEST is non-nil, return the coding system of |
7044 | highest priority. */) | |
7045 | (start, end, highest) | |
d46c5b12 KH |
7046 | Lisp_Object start, end, highest; |
7047 | { | |
7048 | int from, to; | |
7049 | int from_byte, to_byte; | |
ec6d2bb8 | 7050 | |
b7826503 PJ |
7051 | CHECK_NUMBER_COERCE_MARKER (start); |
7052 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 7053 | |
d46c5b12 KH |
7054 | validate_region (&start, &end); |
7055 | from = XINT (start), to = XINT (end); | |
7056 | from_byte = CHAR_TO_BYTE (from); | |
7057 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 7058 | |
d46c5b12 KH |
7059 | if (from < GPT && to >= GPT) |
7060 | move_gap_both (to, to_byte); | |
c210f766 | 7061 | |
d46c5b12 | 7062 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 7063 | to - from, to_byte - from_byte, |
0a28aafb KH |
7064 | !NILP (highest), |
7065 | !NILP (current_buffer | |
df7492f9 KH |
7066 | ->enable_multibyte_characters), |
7067 | Qnil); | |
ec6d2bb8 KH |
7068 | } |
7069 | ||
d46c5b12 KH |
7070 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
7071 | 1, 2, 0, | |
48b0f3ae PJ |
7072 | doc: /* Detect coding system of the text in STRING. |
7073 | Return a list of possible coding systems ordered by priority. | |
fb88bf2d | 7074 | |
48b0f3ae PJ |
7075 | If only ASCII characters are found, it returns a list of single element |
7076 | `undecided' or its subsidiary coding system according to a detected | |
7077 | end-of-line format. | |
d46c5b12 | 7078 | |
48b0f3ae PJ |
7079 | If optional argument HIGHEST is non-nil, return the coding system of |
7080 | highest priority. */) | |
7081 | (string, highest) | |
d46c5b12 KH |
7082 | Lisp_Object string, highest; |
7083 | { | |
b7826503 | 7084 | CHECK_STRING (string); |
b73bfc1c | 7085 | |
24a73b0a KH |
7086 | return detect_coding_system (SDATA (string), |
7087 | SCHARS (string), SBYTES (string), | |
8f924df7 | 7088 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 7089 | Qnil); |
4ed46869 | 7090 | } |
4ed46869 | 7091 | |
b73bfc1c | 7092 | |
df7492f9 KH |
7093 | static INLINE int |
7094 | char_encodable_p (c, attrs) | |
7095 | int c; | |
7096 | Lisp_Object attrs; | |
05e6f5dc | 7097 | { |
df7492f9 | 7098 | Lisp_Object tail; |
df7492f9 | 7099 | struct charset *charset; |
7d64c6ad | 7100 | Lisp_Object translation_table; |
d46c5b12 | 7101 | |
7d64c6ad KH |
7102 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
7103 | if (CHAR_TABLE_P (translation_table)) | |
7104 | c = translate_char (translation_table, c); | |
df7492f9 KH |
7105 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
7106 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 7107 | { |
df7492f9 KH |
7108 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
7109 | if (CHAR_CHARSET_P (c, charset)) | |
7110 | break; | |
e133c8fa | 7111 | } |
df7492f9 | 7112 | return (! NILP (tail)); |
05e6f5dc | 7113 | } |
83fa074f | 7114 | |
fb88bf2d | 7115 | |
df7492f9 KH |
7116 | /* Return a list of coding systems that safely encode the text between |
7117 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
7118 | systems not to check. The returned list doesn't contain any such | |
48468dac | 7119 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 7120 | unibyte, return t. */ |
e077cc80 | 7121 | |
df7492f9 KH |
7122 | DEFUN ("find-coding-systems-region-internal", |
7123 | Ffind_coding_systems_region_internal, | |
7124 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
7125 | doc: /* Internal use only. */) | |
7126 | (start, end, exclude) | |
7127 | Lisp_Object start, end, exclude; | |
7128 | { | |
7129 | Lisp_Object coding_attrs_list, safe_codings; | |
7130 | EMACS_INT start_byte, end_byte; | |
7c78e542 | 7131 | const unsigned char *p, *pbeg, *pend; |
df7492f9 KH |
7132 | int c; |
7133 | Lisp_Object tail, elt; | |
d46c5b12 | 7134 | |
df7492f9 KH |
7135 | if (STRINGP (start)) |
7136 | { | |
7137 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 7138 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
7139 | return Qt; |
7140 | start_byte = 0; | |
8f924df7 | 7141 | end_byte = SBYTES (start); |
df7492f9 KH |
7142 | } |
7143 | else | |
d46c5b12 | 7144 | { |
df7492f9 KH |
7145 | CHECK_NUMBER_COERCE_MARKER (start); |
7146 | CHECK_NUMBER_COERCE_MARKER (end); | |
7147 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
7148 | args_out_of_range (start, end); | |
7149 | if (NILP (current_buffer->enable_multibyte_characters)) | |
7150 | return Qt; | |
7151 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7152 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7153 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
7154 | return Qt; | |
d46c5b12 | 7155 | |
e1c23804 | 7156 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 7157 | { |
e1c23804 DL |
7158 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7159 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7160 | else |
e1c23804 | 7161 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
7162 | } |
7163 | } | |
7164 | ||
df7492f9 KH |
7165 | coding_attrs_list = Qnil; |
7166 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
7167 | if (NILP (exclude) | |
7168 | || NILP (Fmemq (XCAR (tail), exclude))) | |
7169 | { | |
7170 | Lisp_Object attrs; | |
d46c5b12 | 7171 | |
df7492f9 KH |
7172 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
7173 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
7174 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
7175 | { |
7176 | ASET (attrs, coding_attr_trans_tbl, | |
7177 | get_translation_table (attrs, 1)); | |
7178 | coding_attrs_list = Fcons (attrs, coding_attrs_list); | |
7179 | } | |
df7492f9 | 7180 | } |
d46c5b12 | 7181 | |
df7492f9 | 7182 | if (STRINGP (start)) |
8f924df7 | 7183 | p = pbeg = SDATA (start); |
df7492f9 KH |
7184 | else |
7185 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
7186 | pend = p + (end_byte - start_byte); | |
b843d1ae | 7187 | |
df7492f9 KH |
7188 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
7189 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 7190 | |
05e6f5dc | 7191 | while (p < pend) |
72d1a715 | 7192 | { |
df7492f9 KH |
7193 | if (ASCII_BYTE_P (*p)) |
7194 | p++; | |
72d1a715 RS |
7195 | else |
7196 | { | |
df7492f9 | 7197 | c = STRING_CHAR_ADVANCE (p); |
12410ef1 | 7198 | |
df7492f9 KH |
7199 | charset_map_loaded = 0; |
7200 | for (tail = coding_attrs_list; CONSP (tail);) | |
7201 | { | |
7202 | elt = XCAR (tail); | |
7203 | if (NILP (elt)) | |
7204 | tail = XCDR (tail); | |
7205 | else if (char_encodable_p (c, elt)) | |
7206 | tail = XCDR (tail); | |
7207 | else if (CONSP (XCDR (tail))) | |
7208 | { | |
7209 | XSETCAR (tail, XCAR (XCDR (tail))); | |
7210 | XSETCDR (tail, XCDR (XCDR (tail))); | |
7211 | } | |
7212 | else | |
7213 | { | |
7214 | XSETCAR (tail, Qnil); | |
7215 | tail = XCDR (tail); | |
7216 | } | |
7217 | } | |
7218 | if (charset_map_loaded) | |
7219 | { | |
7220 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 7221 | |
df7492f9 | 7222 | if (STRINGP (start)) |
8f924df7 | 7223 | pbeg = SDATA (start); |
df7492f9 KH |
7224 | else |
7225 | pbeg = BYTE_POS_ADDR (start_byte); | |
7226 | p = pbeg + p_offset; | |
7227 | pend = pbeg + pend_offset; | |
7228 | } | |
7229 | } | |
ec6d2bb8 | 7230 | } |
fb88bf2d | 7231 | |
df7492f9 KH |
7232 | safe_codings = Qnil; |
7233 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) | |
7234 | if (! NILP (XCAR (tail))) | |
7235 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 7236 | |
05e6f5dc KH |
7237 | return safe_codings; |
7238 | } | |
4956c225 | 7239 | |
d46c5b12 | 7240 | |
8f924df7 KH |
7241 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
7242 | Sunencodable_char_position, 3, 5, 0, | |
7243 | doc: /* | |
7244 | Return position of first un-encodable character in a region. | |
7245 | START and END specfiy the region and CODING-SYSTEM specifies the | |
7246 | encoding to check. Return nil if CODING-SYSTEM does encode the region. | |
d46c5b12 | 7247 | |
8f924df7 KH |
7248 | If optional 4th argument COUNT is non-nil, it specifies at most how |
7249 | many un-encodable characters to search. In this case, the value is a | |
7250 | list of positions. | |
d46c5b12 | 7251 | |
8f924df7 KH |
7252 | If optional 5th argument STRING is non-nil, it is a string to search |
7253 | for un-encodable characters. In that case, START and END are indexes | |
7254 | to the string. */) | |
7255 | (start, end, coding_system, count, string) | |
7256 | Lisp_Object start, end, coding_system, count, string; | |
7257 | { | |
7258 | int n; | |
7259 | struct coding_system coding; | |
7d64c6ad | 7260 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 KH |
7261 | Lisp_Object positions; |
7262 | int from, to; | |
7263 | const unsigned char *p, *stop, *pend; | |
7264 | int ascii_compatible; | |
fb88bf2d | 7265 | |
8f924df7 KH |
7266 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
7267 | attrs = CODING_ID_ATTRS (coding.id); | |
7268 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
7269 | return Qnil; | |
7270 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
7271 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
7d64c6ad | 7272 | translation_table = get_translation_table (attrs, 1); |
fb88bf2d | 7273 | |
8f924df7 KH |
7274 | if (NILP (string)) |
7275 | { | |
7276 | validate_region (&start, &end); | |
7277 | from = XINT (start); | |
7278 | to = XINT (end); | |
7279 | if (NILP (current_buffer->enable_multibyte_characters) | |
7280 | || (ascii_compatible | |
7281 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
7282 | return Qnil; | |
7283 | p = CHAR_POS_ADDR (from); | |
7284 | pend = CHAR_POS_ADDR (to); | |
7285 | if (from < GPT && to >= GPT) | |
7286 | stop = GPT_ADDR; | |
7287 | else | |
7288 | stop = pend; | |
7289 | } | |
7290 | else | |
7291 | { | |
7292 | CHECK_STRING (string); | |
7293 | CHECK_NATNUM (start); | |
7294 | CHECK_NATNUM (end); | |
7295 | from = XINT (start); | |
7296 | to = XINT (end); | |
7297 | if (from > to | |
7298 | || to > SCHARS (string)) | |
7299 | args_out_of_range_3 (string, start, end); | |
7300 | if (! STRING_MULTIBYTE (string)) | |
7301 | return Qnil; | |
7302 | p = SDATA (string) + string_char_to_byte (string, from); | |
7303 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
7304 | if (ascii_compatible && (to - from) == (pend - p)) | |
7305 | return Qnil; | |
7306 | } | |
f2558efd | 7307 | |
8f924df7 KH |
7308 | if (NILP (count)) |
7309 | n = 1; | |
7310 | else | |
b73bfc1c | 7311 | { |
8f924df7 KH |
7312 | CHECK_NATNUM (count); |
7313 | n = XINT (count); | |
b73bfc1c KH |
7314 | } |
7315 | ||
8f924df7 KH |
7316 | positions = Qnil; |
7317 | while (1) | |
d46c5b12 | 7318 | { |
8f924df7 | 7319 | int c; |
ec6d2bb8 | 7320 | |
8f924df7 KH |
7321 | if (ascii_compatible) |
7322 | while (p < stop && ASCII_BYTE_P (*p)) | |
7323 | p++, from++; | |
7324 | if (p >= stop) | |
0e79d667 | 7325 | { |
8f924df7 KH |
7326 | if (p >= pend) |
7327 | break; | |
7328 | stop = pend; | |
7329 | p = GAP_END_ADDR; | |
0e79d667 | 7330 | } |
ec6d2bb8 | 7331 | |
8f924df7 KH |
7332 | c = STRING_CHAR_ADVANCE (p); |
7333 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
7334 | && ! char_charset (translate_char (translation_table, c), |
7335 | charset_list, NULL)) | |
ec6d2bb8 | 7336 | { |
8f924df7 KH |
7337 | positions = Fcons (make_number (from), positions); |
7338 | n--; | |
7339 | if (n == 0) | |
7340 | break; | |
ec6d2bb8 KH |
7341 | } |
7342 | ||
8f924df7 KH |
7343 | from++; |
7344 | } | |
d46c5b12 | 7345 | |
8f924df7 KH |
7346 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
7347 | } | |
d46c5b12 | 7348 | |
d46c5b12 | 7349 | |
df7492f9 KH |
7350 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
7351 | Scheck_coding_systems_region, 3, 3, 0, | |
7352 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 7353 | |
df7492f9 KH |
7354 | START and END are buffer positions specifying the region. |
7355 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 7356 | |
df7492f9 KH |
7357 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
7358 | CODING-SYSTEM is a member of CODING-SYSTEM-LIst and can't encode the | |
7359 | whole region, POS0, POS1, ... are buffer positions where non-encodable | |
7360 | characters are found. | |
93dec019 | 7361 | |
df7492f9 KH |
7362 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
7363 | value is nil. | |
93dec019 | 7364 | |
df7492f9 KH |
7365 | START may be a string. In that case, check if the string is |
7366 | encodable, and the value contains indices to the string instead of | |
7367 | buffer positions. END is ignored. */) | |
7368 | (start, end, coding_system_list) | |
7369 | Lisp_Object start, end, coding_system_list; | |
05e6f5dc | 7370 | { |
df7492f9 KH |
7371 | Lisp_Object list; |
7372 | EMACS_INT start_byte, end_byte; | |
7373 | int pos; | |
7c78e542 | 7374 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 7375 | int c; |
7d64c6ad | 7376 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 7377 | |
05e6f5dc KH |
7378 | if (STRINGP (start)) |
7379 | { | |
df7492f9 | 7380 | if (!STRING_MULTIBYTE (start) |
8f924df7 | 7381 | && SCHARS (start) != SBYTES (start)) |
df7492f9 KH |
7382 | return Qnil; |
7383 | start_byte = 0; | |
8f924df7 | 7384 | end_byte = SBYTES (start); |
df7492f9 | 7385 | pos = 0; |
d46c5b12 | 7386 | } |
05e6f5dc | 7387 | else |
b73bfc1c | 7388 | { |
b7826503 PJ |
7389 | CHECK_NUMBER_COERCE_MARKER (start); |
7390 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
7391 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
7392 | args_out_of_range (start, end); | |
7393 | if (NILP (current_buffer->enable_multibyte_characters)) | |
df7492f9 KH |
7394 | return Qnil; |
7395 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7396 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7397 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
05e6f5dc | 7398 | return Qt; |
df7492f9 | 7399 | |
e1c23804 | 7400 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 7401 | { |
e1c23804 DL |
7402 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7403 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7404 | else |
e1c23804 | 7405 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 7406 | } |
e1c23804 | 7407 | pos = XINT (start); |
b73bfc1c | 7408 | } |
7553d0e1 | 7409 | |
df7492f9 KH |
7410 | list = Qnil; |
7411 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 7412 | { |
df7492f9 | 7413 | elt = XCAR (tail); |
7d64c6ad KH |
7414 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
7415 | ASET (attrs, coding_attr_trans_tbl, get_translation_table (attrs, 1)); | |
7416 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); | |
12410ef1 KH |
7417 | } |
7418 | ||
df7492f9 | 7419 | if (STRINGP (start)) |
8f924df7 | 7420 | p = pbeg = SDATA (start); |
72d1a715 | 7421 | else |
df7492f9 KH |
7422 | p = pbeg = BYTE_POS_ADDR (start_byte); |
7423 | pend = p + (end_byte - start_byte); | |
4ed46869 | 7424 | |
df7492f9 KH |
7425 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
7426 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 7427 | |
df7492f9 | 7428 | while (p < pend) |
d46c5b12 | 7429 | { |
df7492f9 KH |
7430 | if (ASCII_BYTE_P (*p)) |
7431 | p++; | |
e133c8fa | 7432 | else |
05e6f5dc | 7433 | { |
df7492f9 KH |
7434 | c = STRING_CHAR_ADVANCE (p); |
7435 | ||
7436 | charset_map_loaded = 0; | |
7437 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
7438 | { | |
7439 | elt = XCDR (XCAR (tail)); | |
7440 | if (! char_encodable_p (c, XCAR (elt))) | |
7441 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
7442 | } | |
7443 | if (charset_map_loaded) | |
7444 | { | |
7445 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
7446 | ||
7447 | if (STRINGP (start)) | |
8f924df7 | 7448 | pbeg = SDATA (start); |
df7492f9 KH |
7449 | else |
7450 | pbeg = BYTE_POS_ADDR (start_byte); | |
7451 | p = pbeg + p_offset; | |
7452 | pend = pbeg + pend_offset; | |
7453 | } | |
05e6f5dc | 7454 | } |
df7492f9 | 7455 | pos++; |
d46c5b12 | 7456 | } |
4ed46869 | 7457 | |
df7492f9 KH |
7458 | tail = list; |
7459 | list = Qnil; | |
7460 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 7461 | { |
df7492f9 KH |
7462 | elt = XCAR (tail); |
7463 | if (CONSP (XCDR (XCDR (elt)))) | |
7464 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
7465 | list); | |
ec6d2bb8 | 7466 | } |
2b4f9037 | 7467 | |
df7492f9 | 7468 | return list; |
d46c5b12 KH |
7469 | } |
7470 | ||
3fd9494b | 7471 | |
b73bfc1c KH |
7472 | |
7473 | Lisp_Object | |
df7492f9 KH |
7474 | code_convert_region (start, end, coding_system, dst_object, encodep, norecord) |
7475 | Lisp_Object start, end, coding_system, dst_object; | |
7476 | int encodep, norecord; | |
4ed46869 | 7477 | { |
3a73fa5d | 7478 | struct coding_system coding; |
df7492f9 KH |
7479 | EMACS_INT from, from_byte, to, to_byte; |
7480 | Lisp_Object src_object; | |
4ed46869 | 7481 | |
b7826503 PJ |
7482 | CHECK_NUMBER_COERCE_MARKER (start); |
7483 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
7484 | if (NILP (coding_system)) |
7485 | coding_system = Qno_conversion; | |
7486 | else | |
7487 | CHECK_CODING_SYSTEM (coding_system); | |
7488 | src_object = Fcurrent_buffer (); | |
7489 | if (NILP (dst_object)) | |
7490 | dst_object = src_object; | |
7491 | else if (! EQ (dst_object, Qt)) | |
7492 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 7493 | |
d46c5b12 KH |
7494 | validate_region (&start, &end); |
7495 | from = XFASTINT (start); | |
df7492f9 | 7496 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 7497 | to = XFASTINT (end); |
df7492f9 | 7498 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 7499 | |
df7492f9 KH |
7500 | setup_coding_system (coding_system, &coding); |
7501 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 7502 | |
df7492f9 KH |
7503 | if (encodep) |
7504 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7505 | dst_object); | |
7506 | else | |
7507 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7508 | dst_object); | |
7509 | if (! norecord) | |
7510 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 7511 | |
df7492f9 KH |
7512 | return (BUFFERP (dst_object) |
7513 | ? make_number (coding.produced_char) | |
7514 | : coding.dst_object); | |
4031e2bf | 7515 | } |
78108bcd | 7516 | |
4ed46869 | 7517 | |
4031e2bf | 7518 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 7519 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 7520 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
7521 | When called from a program, takes four arguments: |
7522 | START, END, CODING-SYSTEM, and DESTINATION. | |
7523 | START and END are buffer positions. | |
8844fa83 | 7524 | |
df7492f9 KH |
7525 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
7526 | If nil, the region between START and END is replace by the decoded text. | |
7527 | If buffer, the decoded text is inserted in the buffer. | |
7528 | If t, the decoded text is returned. | |
8844fa83 | 7529 | |
48b0f3ae PJ |
7530 | This function sets `last-coding-system-used' to the precise coding system |
7531 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7532 | not fully specified.) | |
7533 | It returns the length of the decoded text. */) | |
df7492f9 KH |
7534 | (start, end, coding_system, destination) |
7535 | Lisp_Object start, end, coding_system, destination; | |
4031e2bf | 7536 | { |
df7492f9 | 7537 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 7538 | } |
8844fa83 | 7539 | |
3a73fa5d | 7540 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
7541 | 3, 4, "r\nzCoding system: ", |
7542 | doc: /* Encode the current region by specified coding system. | |
48b0f3ae PJ |
7543 | When called from a program, takes three arguments: |
7544 | START, END, and CODING-SYSTEM. START and END are buffer positions. | |
d46c5b12 | 7545 | |
df7492f9 KH |
7546 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
7547 | If nil, the region between START and END is replace by the encoded text. | |
7548 | If buffer, the encoded text is inserted in the buffer. | |
7549 | If t, the encoded text is returned. | |
2391eaa4 | 7550 | |
48b0f3ae PJ |
7551 | This function sets `last-coding-system-used' to the precise coding system |
7552 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7553 | not fully specified.) | |
7554 | It returns the length of the encoded text. */) | |
df7492f9 KH |
7555 | (start, end, coding_system, destination) |
7556 | Lisp_Object start, end, coding_system, destination; | |
3a73fa5d | 7557 | { |
df7492f9 | 7558 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
7559 | } |
7560 | ||
7561 | Lisp_Object | |
df7492f9 KH |
7562 | code_convert_string (string, coding_system, dst_object, |
7563 | encodep, nocopy, norecord) | |
7564 | Lisp_Object string, coding_system, dst_object; | |
7565 | int encodep, nocopy, norecord; | |
b73bfc1c | 7566 | { |
4031e2bf | 7567 | struct coding_system coding; |
df7492f9 | 7568 | EMACS_INT chars, bytes; |
ec6d2bb8 | 7569 | |
b7826503 | 7570 | CHECK_STRING (string); |
d46c5b12 | 7571 | if (NILP (coding_system)) |
4956c225 | 7572 | { |
df7492f9 KH |
7573 | if (! norecord) |
7574 | Vlast_coding_system_used = Qno_conversion; | |
7575 | if (NILP (dst_object)) | |
7576 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 7577 | } |
b73bfc1c | 7578 | |
df7492f9 KH |
7579 | if (NILP (coding_system)) |
7580 | coding_system = Qno_conversion; | |
7581 | else | |
7582 | CHECK_CODING_SYSTEM (coding_system); | |
7583 | if (NILP (dst_object)) | |
7584 | dst_object = Qt; | |
7585 | else if (! EQ (dst_object, Qt)) | |
7586 | CHECK_BUFFER (dst_object); | |
73be902c | 7587 | |
df7492f9 | 7588 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 7589 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
7590 | chars = SCHARS (string); |
7591 | bytes = SBYTES (string); | |
df7492f9 KH |
7592 | if (encodep) |
7593 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7594 | else | |
7595 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7596 | if (! norecord) | |
7597 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 7598 | |
df7492f9 KH |
7599 | return (BUFFERP (dst_object) |
7600 | ? make_number (coding.produced_char) | |
7601 | : coding.dst_object); | |
4ed46869 | 7602 | } |
73be902c | 7603 | |
b73bfc1c | 7604 | |
ecec61c1 | 7605 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 7606 | Do not set Vlast_coding_system_used. |
4ed46869 | 7607 | |
ec6d2bb8 KH |
7608 | This function is called only from macros DECODE_FILE and |
7609 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 7610 | |
ecec61c1 KH |
7611 | Lisp_Object |
7612 | code_convert_string_norecord (string, coding_system, encodep) | |
7613 | Lisp_Object string, coding_system; | |
7614 | int encodep; | |
4ed46869 | 7615 | { |
0be8721c | 7616 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
7617 | } |
7618 | ||
4ed46869 | 7619 | |
df7492f9 KH |
7620 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
7621 | 2, 4, 0, | |
7622 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
7623 | ||
7624 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
7625 | if the decoding operation is trivial. | |
ecec61c1 | 7626 | |
df7492f9 | 7627 | Optional fourth arg BUFFER non-nil meant that the decoded text is |
a3f6ee6d | 7628 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 | 7629 | the return value is BUFFER. |
ecec61c1 | 7630 | |
df7492f9 KH |
7631 | This function sets `last-coding-system-used' to the precise coding system |
7632 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7633 | not fully specified. */) | |
7634 | (string, coding_system, nocopy, buffer) | |
7635 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 7636 | { |
df7492f9 KH |
7637 | return code_convert_string (string, coding_system, buffer, |
7638 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
7639 | } |
7640 | ||
df7492f9 KH |
7641 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
7642 | 2, 4, 0, | |
7643 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
7644 | ||
7645 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
7646 | itself if the encoding operation is trivial. | |
7647 | ||
7648 | Optional fourth arg BUFFER non-nil meant that the encoded text is | |
a3f6ee6d | 7649 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 KH |
7650 | the return value is BUFFER. |
7651 | ||
7652 | This function sets `last-coding-system-used' to the precise coding system | |
7653 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7654 | not fully specified.) */) | |
7655 | (string, coding_system, nocopy, buffer) | |
7656 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 7657 | { |
df7492f9 | 7658 | return code_convert_string (string, coding_system, buffer, |
c197f191 | 7659 | 1, ! NILP (nocopy), 1); |
4ed46869 | 7660 | } |
df7492f9 | 7661 | |
3a73fa5d | 7662 | \f |
4ed46869 | 7663 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
7664 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
7665 | Return the corresponding character. */) | |
7666 | (code) | |
4ed46869 | 7667 | Lisp_Object code; |
4ed46869 | 7668 | { |
df7492f9 KH |
7669 | Lisp_Object spec, attrs, val; |
7670 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
7671 | int c; | |
4ed46869 | 7672 | |
df7492f9 KH |
7673 | CHECK_NATNUM (code); |
7674 | c = XFASTINT (code); | |
7675 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
7676 | attrs = AREF (spec, 0); | |
4ed46869 | 7677 | |
df7492f9 KH |
7678 | if (ASCII_BYTE_P (c) |
7679 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7680 | return code; | |
4ed46869 | 7681 | |
df7492f9 KH |
7682 | val = CODING_ATTR_CHARSET_LIST (attrs); |
7683 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
7684 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
7685 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 7686 | |
df7492f9 KH |
7687 | if (c <= 0x7F) |
7688 | charset = charset_roman; | |
7689 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 7690 | { |
df7492f9 KH |
7691 | charset = charset_kana; |
7692 | c -= 0x80; | |
4ed46869 | 7693 | } |
55ab7be3 | 7694 | else |
4ed46869 | 7695 | { |
004068e4 | 7696 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
7697 | |
7698 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
7699 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
7700 | error ("Invalid code: %d", code); | |
7701 | SJIS_TO_JIS (c); | |
7702 | charset = charset_kanji; | |
4ed46869 | 7703 | } |
df7492f9 KH |
7704 | c = DECODE_CHAR (charset, c); |
7705 | if (c < 0) | |
7706 | error ("Invalid code: %d", code); | |
7707 | return make_number (c); | |
93dec019 | 7708 | } |
4ed46869 | 7709 | |
48b0f3ae | 7710 | |
4ed46869 | 7711 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
7712 | doc: /* Encode a Japanese character CHAR to shift_jis encoding. |
7713 | Return the corresponding code in SJIS. */) | |
7714 | (ch) | |
df7492f9 | 7715 | Lisp_Object ch; |
4ed46869 | 7716 | { |
df7492f9 KH |
7717 | Lisp_Object spec, attrs, charset_list; |
7718 | int c; | |
7719 | struct charset *charset; | |
7720 | unsigned code; | |
48b0f3ae | 7721 | |
df7492f9 KH |
7722 | CHECK_CHARACTER (ch); |
7723 | c = XFASTINT (ch); | |
7724 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
7725 | attrs = AREF (spec, 0); | |
7726 | ||
7727 | if (ASCII_CHAR_P (c) | |
7728 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7729 | return ch; | |
7730 | ||
7731 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
7732 | charset = char_charset (c, charset_list, &code); | |
7733 | if (code == CHARSET_INVALID_CODE (charset)) | |
7734 | error ("Can't encode by shift_jis encoding: %d", c); | |
7735 | JIS_TO_SJIS (code); | |
7736 | ||
7737 | return make_number (code); | |
4ed46869 KH |
7738 | } |
7739 | ||
7740 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
7741 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
7742 | Return the corresponding character. */) | |
7743 | (code) | |
4ed46869 | 7744 | Lisp_Object code; |
d46c5b12 | 7745 | { |
df7492f9 KH |
7746 | Lisp_Object spec, attrs, val; |
7747 | struct charset *charset_roman, *charset_big5, *charset; | |
7748 | int c; | |
6289dd10 | 7749 | |
df7492f9 KH |
7750 | CHECK_NATNUM (code); |
7751 | c = XFASTINT (code); | |
7752 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
7753 | attrs = AREF (spec, 0); | |
4ed46869 | 7754 | |
df7492f9 KH |
7755 | if (ASCII_BYTE_P (c) |
7756 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7757 | return code; | |
6289dd10 | 7758 | |
df7492f9 KH |
7759 | val = CODING_ATTR_CHARSET_LIST (attrs); |
7760 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
7761 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 7762 | |
df7492f9 KH |
7763 | if (c <= 0x7F) |
7764 | charset = charset_roman; | |
c28a9453 KH |
7765 | else |
7766 | { | |
df7492f9 KH |
7767 | int b1 = c >> 8, b2 = c & 0x7F; |
7768 | if (b1 < 0xA1 || b1 > 0xFE | |
7769 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
7770 | error ("Invalid code: %d", code); | |
7771 | charset = charset_big5; | |
c28a9453 | 7772 | } |
df7492f9 KH |
7773 | c = DECODE_CHAR (charset, (unsigned )c); |
7774 | if (c < 0) | |
7775 | error ("Invalid code: %d", code); | |
7776 | return make_number (c); | |
d46c5b12 | 7777 | } |
6289dd10 | 7778 | |
4ed46869 | 7779 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
48b0f3ae PJ |
7780 | doc: /* Encode the Big5 character CHAR to BIG5 coding system. |
7781 | Return the corresponding character code in Big5. */) | |
7782 | (ch) | |
4ed46869 KH |
7783 | Lisp_Object ch; |
7784 | { | |
df7492f9 KH |
7785 | Lisp_Object spec, attrs, charset_list; |
7786 | struct charset *charset; | |
7787 | int c; | |
7788 | unsigned code; | |
7789 | ||
7790 | CHECK_CHARACTER (ch); | |
7791 | c = XFASTINT (ch); | |
7792 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
7793 | attrs = AREF (spec, 0); | |
7794 | if (ASCII_CHAR_P (c) | |
7795 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7796 | return ch; | |
7797 | ||
7798 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
7799 | charset = char_charset (c, charset_list, &code); | |
7800 | if (code == CHARSET_INVALID_CODE (charset)) | |
7801 | error ("Can't encode by Big5 encoding: %d", c); | |
7802 | ||
7803 | return make_number (code); | |
4ed46869 | 7804 | } |
48b0f3ae | 7805 | |
3a73fa5d | 7806 | \f |
1ba9e4ab KH |
7807 | DEFUN ("set-terminal-coding-system-internal", |
7808 | Fset_terminal_coding_system_internal, | |
48b0f3ae PJ |
7809 | Sset_terminal_coding_system_internal, 1, 1, 0, |
7810 | doc: /* Internal use only. */) | |
7811 | (coding_system) | |
b74e4686 | 7812 | Lisp_Object coding_system; |
4ed46869 | 7813 | { |
b7826503 | 7814 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
7815 | setup_coding_system (Fcheck_coding_system (coding_system), |
7816 | &terminal_coding); | |
48b0f3ae | 7817 | |
70c22245 | 7818 | /* We had better not send unsafe characters to terminal. */ |
df7492f9 KH |
7819 | terminal_coding.mode |= CODING_MODE_SAFE_ENCODING; |
7820 | /* Characer composition should be disabled. */ | |
7821 | terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
7822 | terminal_coding.src_multibyte = 1; |
7823 | terminal_coding.dst_multibyte = 0; | |
4ed46869 KH |
7824 | return Qnil; |
7825 | } | |
7826 | ||
c4825358 KH |
7827 | DEFUN ("set-safe-terminal-coding-system-internal", |
7828 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 7829 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 7830 | doc: /* Internal use only. */) |
48b0f3ae | 7831 | (coding_system) |
b74e4686 | 7832 | Lisp_Object coding_system; |
d46c5b12 | 7833 | { |
b7826503 | 7834 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
7835 | setup_coding_system (Fcheck_coding_system (coding_system), |
7836 | &safe_terminal_coding); | |
df7492f9 KH |
7837 | /* Characer composition should be disabled. */ |
7838 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
7839 | safe_terminal_coding.src_multibyte = 1; |
7840 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
7841 | return Qnil; |
7842 | } | |
4ed46869 | 7843 | |
4ed46869 KH |
7844 | DEFUN ("terminal-coding-system", |
7845 | Fterminal_coding_system, Sterminal_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
7846 | doc: /* Return coding system specified for terminal output. */) |
7847 | () | |
4ed46869 | 7848 | { |
df7492f9 | 7849 | return CODING_ID_NAME (terminal_coding.id); |
4ed46869 KH |
7850 | } |
7851 | ||
1ba9e4ab KH |
7852 | DEFUN ("set-keyboard-coding-system-internal", |
7853 | Fset_keyboard_coding_system_internal, | |
48b0f3ae PJ |
7854 | Sset_keyboard_coding_system_internal, 1, 1, 0, |
7855 | doc: /* Internal use only. */) | |
7856 | (coding_system) | |
4ed46869 KH |
7857 | Lisp_Object coding_system; |
7858 | { | |
b7826503 | 7859 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
7860 | setup_coding_system (Fcheck_coding_system (coding_system), |
7861 | &keyboard_coding); | |
7862 | /* Characer composition should be disabled. */ | |
7863 | keyboard_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
7864 | return Qnil; |
7865 | } | |
7866 | ||
7867 | DEFUN ("keyboard-coding-system", | |
7868 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
7869 | doc: /* Return coding system specified for decoding keyboard input. */) |
7870 | () | |
4ed46869 | 7871 | { |
df7492f9 | 7872 | return CODING_ID_NAME (keyboard_coding.id); |
4ed46869 KH |
7873 | } |
7874 | ||
4ed46869 | 7875 | \f |
a5d301df KH |
7876 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
7877 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
7878 | doc: /* Choose a coding system for an operation based on the target name. |
7879 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
7880 | DECODING-SYSTEM is the coding system to use for decoding | |
7881 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
7882 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 7883 | |
48b0f3ae PJ |
7884 | The first argument OPERATION specifies an I/O primitive: |
7885 | For file I/O, `insert-file-contents' or `write-region'. | |
7886 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
7887 | For network I/O, `open-network-stream'. | |
05e6f5dc | 7888 | |
48b0f3ae PJ |
7889 | The remaining arguments should be the same arguments that were passed |
7890 | to the primitive. Depending on which primitive, one of those arguments | |
7891 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
7892 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 7893 | |
48b0f3ae PJ |
7894 | TARGET has a meaning which depends on OPERATION: |
7895 | For file I/O, TARGET is a file name. | |
7896 | For process I/O, TARGET is a process name. | |
7897 | For network I/O, TARGET is a service name or a port number | |
05e6f5dc | 7898 | |
48b0f3ae PJ |
7899 | This function looks up what specified for TARGET in, |
7900 | `file-coding-system-alist', `process-coding-system-alist', | |
7901 | or `network-coding-system-alist' depending on OPERATION. | |
7902 | They may specify a coding system, a cons of coding systems, | |
7903 | or a function symbol to call. | |
7904 | In the last case, we call the function with one argument, | |
7905 | which is a list of all the arguments given to this function. | |
7906 | ||
7907 | usage: (find-operation-coding-system OPERATION ARGUMENTS ...) */) | |
7908 | (nargs, args) | |
4ed46869 KH |
7909 | int nargs; |
7910 | Lisp_Object *args; | |
6b89e3aa | 7911 | { |
4ed46869 KH |
7912 | Lisp_Object operation, target_idx, target, val; |
7913 | register Lisp_Object chain; | |
177c0ea7 | 7914 | |
4ed46869 KH |
7915 | if (nargs < 2) |
7916 | error ("Too few arguments"); | |
7917 | operation = args[0]; | |
7918 | if (!SYMBOLP (operation) | |
7919 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
df7492f9 | 7920 | error ("Invalid first arguement"); |
4ed46869 KH |
7921 | if (nargs < 1 + XINT (target_idx)) |
7922 | error ("Too few arguments for operation: %s", | |
8f924df7 | 7923 | SDATA (SYMBOL_NAME (operation))); |
4ed46869 KH |
7924 | target = args[XINT (target_idx) + 1]; |
7925 | if (!(STRINGP (target) | |
7926 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) | |
df7492f9 | 7927 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
4ed46869 | 7928 | |
2e34157c RS |
7929 | chain = ((EQ (operation, Qinsert_file_contents) |
7930 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 7931 | ? Vfile_coding_system_alist |
2e34157c | 7932 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
7933 | ? Vnetwork_coding_system_alist |
7934 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
7935 | if (NILP (chain)) |
7936 | return Qnil; | |
7937 | ||
03699b14 | 7938 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 7939 | { |
f44d27ce | 7940 | Lisp_Object elt; |
6b89e3aa | 7941 | |
df7492f9 | 7942 | elt = XCAR (chain); |
4ed46869 KH |
7943 | if (CONSP (elt) |
7944 | && ((STRINGP (target) | |
03699b14 KR |
7945 | && STRINGP (XCAR (elt)) |
7946 | && fast_string_match (XCAR (elt), target) >= 0) | |
7947 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 7948 | { |
03699b14 | 7949 | val = XCDR (elt); |
b19fd4c5 KH |
7950 | /* Here, if VAL is both a valid coding system and a valid |
7951 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
7952 | if (CONSP (val)) |
7953 | return val; | |
7954 | if (! SYMBOLP (val)) | |
7955 | return Qnil; | |
7956 | if (! NILP (Fcoding_system_p (val))) | |
7957 | return Fcons (val, val); | |
b19fd4c5 | 7958 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 7959 | { |
b19fd4c5 KH |
7960 | val = call1 (val, Flist (nargs, args)); |
7961 | if (CONSP (val)) | |
7962 | return val; | |
7963 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
7964 | return Fcons (val, val); | |
6b89e3aa | 7965 | } |
02ba4723 | 7966 | return Qnil; |
6b89e3aa KH |
7967 | } |
7968 | } | |
4ed46869 | 7969 | return Qnil; |
6b89e3aa KH |
7970 | } |
7971 | ||
df7492f9 | 7972 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 7973 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 7974 | doc: /* Assign higher priority to the coding systems given as arguments. |
ff563fce | 7975 | If multiple coding systems belongs to the same category, |
a3181084 DL |
7976 | all but the first one are ignored. |
7977 | ||
7978 | usage: (set-coding-system-priority ...) */) | |
df7492f9 KH |
7979 | (nargs, args) |
7980 | int nargs; | |
7981 | Lisp_Object *args; | |
7982 | { | |
7983 | int i, j; | |
7984 | int changed[coding_category_max]; | |
7985 | enum coding_category priorities[coding_category_max]; | |
7986 | ||
7987 | bzero (changed, sizeof changed); | |
6b89e3aa | 7988 | |
df7492f9 | 7989 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 7990 | { |
df7492f9 KH |
7991 | enum coding_category category; |
7992 | Lisp_Object spec, attrs; | |
6b89e3aa | 7993 | |
df7492f9 KH |
7994 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
7995 | attrs = AREF (spec, 0); | |
7996 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
7997 | if (changed[category]) | |
7998 | /* Ignore this coding system because a coding system of the | |
7999 | same category already had a higher priority. */ | |
8000 | continue; | |
8001 | changed[category] = 1; | |
8002 | priorities[j++] = category; | |
8003 | if (coding_categories[category].id >= 0 | |
8004 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
8005 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 8006 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 8007 | } |
6b89e3aa | 8008 | |
df7492f9 KH |
8009 | /* Now we have decided top J priorities. Reflect the order of the |
8010 | original priorities to the remaining priorities. */ | |
6b89e3aa | 8011 | |
df7492f9 | 8012 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 8013 | { |
df7492f9 KH |
8014 | while (j < coding_category_max |
8015 | && changed[coding_priorities[j]]) | |
8016 | j++; | |
8017 | if (j == coding_category_max) | |
8018 | abort (); | |
8019 | priorities[i] = coding_priorities[j]; | |
8020 | } | |
6b89e3aa | 8021 | |
df7492f9 | 8022 | bcopy (priorities, coding_priorities, sizeof priorities); |
177c0ea7 | 8023 | |
ff563fce KH |
8024 | /* Update `coding-category-list'. */ |
8025 | Vcoding_category_list = Qnil; | |
8026 | for (i = coding_category_max - 1; i >= 0; i--) | |
8027 | Vcoding_category_list | |
8028 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
8029 | Vcoding_category_list); | |
6b89e3aa | 8030 | |
df7492f9 | 8031 | return Qnil; |
6b89e3aa KH |
8032 | } |
8033 | ||
df7492f9 KH |
8034 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
8035 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 DL |
8036 | doc: /* Return a list of coding systems ordered by their priorities. |
8037 | HIGHESTP non-nil means just return the highest priority one. */) | |
df7492f9 KH |
8038 | (highestp) |
8039 | Lisp_Object highestp; | |
d46c5b12 KH |
8040 | { |
8041 | int i; | |
df7492f9 | 8042 | Lisp_Object val; |
6b89e3aa | 8043 | |
df7492f9 | 8044 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 8045 | { |
df7492f9 KH |
8046 | enum coding_category category = coding_priorities[i]; |
8047 | int id = coding_categories[category].id; | |
8048 | Lisp_Object attrs; | |
068a9dbd | 8049 | |
df7492f9 KH |
8050 | if (id < 0) |
8051 | continue; | |
8052 | attrs = CODING_ID_ATTRS (id); | |
8053 | if (! NILP (highestp)) | |
8054 | return CODING_ATTR_BASE_NAME (attrs); | |
8055 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
8056 | } | |
8057 | return Fnreverse (val); | |
8058 | } | |
068a9dbd | 8059 | |
f0064e1f | 8060 | static char *suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
8061 | |
8062 | static Lisp_Object | |
df7492f9 KH |
8063 | make_subsidiaries (base) |
8064 | Lisp_Object base; | |
068a9dbd | 8065 | { |
df7492f9 | 8066 | Lisp_Object subsidiaries; |
8f924df7 | 8067 | int base_name_len = SBYTES (SYMBOL_NAME (base)); |
df7492f9 KH |
8068 | char *buf = (char *) alloca (base_name_len + 6); |
8069 | int i; | |
068a9dbd | 8070 | |
8f924df7 | 8071 | bcopy (SDATA (SYMBOL_NAME (base)), buf, base_name_len); |
df7492f9 KH |
8072 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
8073 | for (i = 0; i < 3; i++) | |
068a9dbd | 8074 | { |
df7492f9 KH |
8075 | bcopy (suffixes[i], buf + base_name_len, strlen (suffixes[i]) + 1); |
8076 | ASET (subsidiaries, i, intern (buf)); | |
068a9dbd | 8077 | } |
df7492f9 | 8078 | return subsidiaries; |
068a9dbd KH |
8079 | } |
8080 | ||
8081 | ||
df7492f9 KH |
8082 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
8083 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
8084 | doc: /* For internal use only. |
8085 | usage: (define-coding-system-internal ...) */) | |
df7492f9 KH |
8086 | (nargs, args) |
8087 | int nargs; | |
8088 | Lisp_Object *args; | |
068a9dbd | 8089 | { |
df7492f9 KH |
8090 | Lisp_Object name; |
8091 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
8092 | Lisp_Object attrs; /* Vector of attributes. */ | |
8093 | Lisp_Object eol_type; | |
8094 | Lisp_Object aliases; | |
8095 | Lisp_Object coding_type, charset_list, safe_charsets; | |
8096 | enum coding_category category; | |
8097 | Lisp_Object tail, val; | |
8098 | int max_charset_id = 0; | |
8099 | int i; | |
068a9dbd | 8100 | |
df7492f9 KH |
8101 | if (nargs < coding_arg_max) |
8102 | goto short_args; | |
068a9dbd | 8103 | |
df7492f9 | 8104 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 8105 | |
df7492f9 KH |
8106 | name = args[coding_arg_name]; |
8107 | CHECK_SYMBOL (name); | |
8108 | CODING_ATTR_BASE_NAME (attrs) = name; | |
068a9dbd | 8109 | |
df7492f9 KH |
8110 | val = args[coding_arg_mnemonic]; |
8111 | if (! STRINGP (val)) | |
8112 | CHECK_CHARACTER (val); | |
8113 | CODING_ATTR_MNEMONIC (attrs) = val; | |
068a9dbd | 8114 | |
df7492f9 KH |
8115 | coding_type = args[coding_arg_coding_type]; |
8116 | CHECK_SYMBOL (coding_type); | |
8117 | CODING_ATTR_TYPE (attrs) = coding_type; | |
068a9dbd | 8118 | |
df7492f9 KH |
8119 | charset_list = args[coding_arg_charset_list]; |
8120 | if (SYMBOLP (charset_list)) | |
8121 | { | |
8122 | if (EQ (charset_list, Qiso_2022)) | |
8123 | { | |
8124 | if (! EQ (coding_type, Qiso_2022)) | |
8125 | error ("Invalid charset-list"); | |
8126 | charset_list = Viso_2022_charset_list; | |
8127 | } | |
8128 | else if (EQ (charset_list, Qemacs_mule)) | |
8129 | { | |
8130 | if (! EQ (coding_type, Qemacs_mule)) | |
8131 | error ("Invalid charset-list"); | |
8132 | charset_list = Vemacs_mule_charset_list; | |
8133 | } | |
8134 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8135 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
8136 | max_charset_id = XFASTINT (XCAR (tail)); | |
8137 | } | |
068a9dbd KH |
8138 | else |
8139 | { | |
df7492f9 KH |
8140 | charset_list = Fcopy_sequence (charset_list); |
8141 | for (tail = charset_list; !NILP (tail); tail = Fcdr (tail)) | |
068a9dbd | 8142 | { |
df7492f9 KH |
8143 | struct charset *charset; |
8144 | ||
8145 | val = Fcar (tail); | |
8146 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8147 | if (EQ (coding_type, Qiso_2022) | |
8148 | ? CHARSET_ISO_FINAL (charset) < 0 | |
8149 | : EQ (coding_type, Qemacs_mule) | |
8150 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
8151 | : 0) | |
8152 | error ("Can't handle charset `%s'", | |
8f924df7 | 8153 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 8154 | |
8f924df7 | 8155 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
8156 | if (max_charset_id < charset->id) |
8157 | max_charset_id = charset->id; | |
068a9dbd KH |
8158 | } |
8159 | } | |
df7492f9 | 8160 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; |
068a9dbd | 8161 | |
df7492f9 KH |
8162 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
8163 | make_number (255)); | |
8164 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8f924df7 | 8165 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 8166 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; |
068a9dbd | 8167 | |
584948ac | 8168 | CODING_ATTR_ASCII_COMPAT (attrs) = args[coding_arg_ascii_compatible_p]; |
3a73fa5d | 8169 | |
df7492f9 | 8170 | val = args[coding_arg_decode_translation_table]; |
7d64c6ad KH |
8171 | if (! CHAR_TABLE_P (val)) |
8172 | CHECK_SYMBOL (val); | |
df7492f9 | 8173 | CODING_ATTR_DECODE_TBL (attrs) = val; |
3a73fa5d | 8174 | |
df7492f9 | 8175 | val = args[coding_arg_encode_translation_table]; |
7d64c6ad KH |
8176 | if (! CHAR_TABLE_P (val)) |
8177 | CHECK_SYMBOL (val); | |
df7492f9 | 8178 | CODING_ATTR_ENCODE_TBL (attrs) = val; |
d46c5b12 | 8179 | |
df7492f9 KH |
8180 | val = args[coding_arg_post_read_conversion]; |
8181 | CHECK_SYMBOL (val); | |
8182 | CODING_ATTR_POST_READ (attrs) = val; | |
d46c5b12 | 8183 | |
df7492f9 KH |
8184 | val = args[coding_arg_pre_write_conversion]; |
8185 | CHECK_SYMBOL (val); | |
8186 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
3a73fa5d | 8187 | |
df7492f9 KH |
8188 | val = args[coding_arg_default_char]; |
8189 | if (NILP (val)) | |
8190 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
8191 | else | |
8192 | { | |
8f924df7 | 8193 | CHECK_CHARACTER (val); |
df7492f9 KH |
8194 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; |
8195 | } | |
4031e2bf | 8196 | |
8f924df7 KH |
8197 | val = args[coding_arg_for_unibyte]; |
8198 | CODING_ATTR_FOR_UNIBYTE (attrs) = NILP (val) ? Qnil : Qt; | |
3a73fa5d | 8199 | |
df7492f9 KH |
8200 | val = args[coding_arg_plist]; |
8201 | CHECK_LIST (val); | |
8202 | CODING_ATTR_PLIST (attrs) = val; | |
3a73fa5d | 8203 | |
df7492f9 KH |
8204 | if (EQ (coding_type, Qcharset)) |
8205 | { | |
c7c66a95 KH |
8206 | /* Generate a lisp vector of 256 elements. Each element is nil, |
8207 | integer, or a list of charset IDs. | |
3a73fa5d | 8208 | |
c7c66a95 KH |
8209 | If Nth element is nil, the byte code N is invalid in this |
8210 | coding system. | |
4ed46869 | 8211 | |
c7c66a95 KH |
8212 | If Nth element is a number NUM, N is the first byte of a |
8213 | charset whose ID is NUM. | |
4ed46869 | 8214 | |
c7c66a95 KH |
8215 | If Nth element is a list of charset IDs, N is the first byte |
8216 | of one of them. The list is sorted by dimensions of the | |
2bc515e4 | 8217 | charsets. A charset of smaller dimension comes firtst. */ |
df7492f9 | 8218 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 8219 | |
5c99c2e6 | 8220 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 8221 | { |
c7c66a95 KH |
8222 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
8223 | int dim = CHARSET_DIMENSION (charset); | |
8224 | int idx = (dim - 1) * 4; | |
4ed46869 | 8225 | |
5c99c2e6 | 8226 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
584948ac | 8227 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
4031e2bf | 8228 | |
15d143f7 KH |
8229 | for (i = charset->code_space[idx]; |
8230 | i <= charset->code_space[idx + 1]; i++) | |
8231 | { | |
c7c66a95 KH |
8232 | Lisp_Object tmp, tmp2; |
8233 | int dim2; | |
ec6d2bb8 | 8234 | |
c7c66a95 KH |
8235 | tmp = AREF (val, i); |
8236 | if (NILP (tmp)) | |
8237 | tmp = XCAR (tail); | |
8238 | else if (NUMBERP (tmp)) | |
8239 | { | |
8240 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
8241 | if (dim < dim2) | |
c7c66a95 | 8242 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
8243 | else |
8244 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 8245 | } |
15d143f7 | 8246 | else |
c7c66a95 KH |
8247 | { |
8248 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
8249 | { | |
8250 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
8251 | if (dim < dim2) | |
8252 | break; | |
8253 | } | |
8254 | if (NILP (tmp2)) | |
8255 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
8256 | else | |
8257 | { | |
8258 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
8259 | XSETCAR (tmp2, XCAR (tail)); | |
8260 | } | |
8261 | } | |
8262 | ASET (val, i, tmp); | |
15d143f7 | 8263 | } |
df7492f9 KH |
8264 | } |
8265 | ASET (attrs, coding_attr_charset_valids, val); | |
8266 | category = coding_category_charset; | |
8267 | } | |
8268 | else if (EQ (coding_type, Qccl)) | |
8269 | { | |
8270 | Lisp_Object valids; | |
ecec61c1 | 8271 | |
df7492f9 KH |
8272 | if (nargs < coding_arg_ccl_max) |
8273 | goto short_args; | |
ecec61c1 | 8274 | |
df7492f9 KH |
8275 | val = args[coding_arg_ccl_decoder]; |
8276 | CHECK_CCL_PROGRAM (val); | |
8277 | if (VECTORP (val)) | |
8278 | val = Fcopy_sequence (val); | |
8279 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 8280 | |
df7492f9 KH |
8281 | val = args[coding_arg_ccl_encoder]; |
8282 | CHECK_CCL_PROGRAM (val); | |
8283 | if (VECTORP (val)) | |
8284 | val = Fcopy_sequence (val); | |
8285 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 8286 | |
df7492f9 KH |
8287 | val = args[coding_arg_ccl_valids]; |
8288 | valids = Fmake_string (make_number (256), make_number (0)); | |
8289 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
8290 | { | |
8dcbea82 | 8291 | int from, to; |
ecec61c1 | 8292 | |
df7492f9 KH |
8293 | val = Fcar (tail); |
8294 | if (INTEGERP (val)) | |
8dcbea82 KH |
8295 | { |
8296 | from = to = XINT (val); | |
8297 | if (from < 0 || from > 255) | |
8298 | args_out_of_range_3 (val, make_number (0), make_number (255)); | |
8299 | } | |
df7492f9 KH |
8300 | else |
8301 | { | |
df7492f9 | 8302 | CHECK_CONS (val); |
8f924df7 KH |
8303 | CHECK_NATNUM_CAR (val); |
8304 | CHECK_NATNUM_CDR (val); | |
df7492f9 | 8305 | from = XINT (XCAR (val)); |
8f924df7 | 8306 | if (from > 255) |
8dcbea82 KH |
8307 | args_out_of_range_3 (XCAR (val), |
8308 | make_number (0), make_number (255)); | |
df7492f9 | 8309 | to = XINT (XCDR (val)); |
8dcbea82 KH |
8310 | if (to < from || to > 255) |
8311 | args_out_of_range_3 (XCDR (val), | |
8312 | XCAR (val), make_number (255)); | |
df7492f9 | 8313 | } |
8dcbea82 | 8314 | for (i = from; i <= to; i++) |
8f924df7 | 8315 | SSET (valids, i, 1); |
df7492f9 KH |
8316 | } |
8317 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 8318 | |
df7492f9 | 8319 | category = coding_category_ccl; |
55ab7be3 | 8320 | } |
df7492f9 | 8321 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 8322 | { |
df7492f9 | 8323 | Lisp_Object bom, endian; |
4ed46869 | 8324 | |
584948ac | 8325 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; |
4ed46869 | 8326 | |
df7492f9 KH |
8327 | if (nargs < coding_arg_utf16_max) |
8328 | goto short_args; | |
4ed46869 | 8329 | |
df7492f9 KH |
8330 | bom = args[coding_arg_utf16_bom]; |
8331 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
8332 | { | |
8333 | CHECK_CONS (bom); | |
8f924df7 KH |
8334 | val = XCAR (bom); |
8335 | CHECK_CODING_SYSTEM (val); | |
8336 | val = XCDR (bom); | |
8337 | CHECK_CODING_SYSTEM (val); | |
df7492f9 KH |
8338 | } |
8339 | ASET (attrs, coding_attr_utf_16_bom, bom); | |
8340 | ||
8341 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
8342 | CHECK_SYMBOL (endian); |
8343 | if (NILP (endian)) | |
8344 | endian = Qbig; | |
8345 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 8346 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
8347 | ASET (attrs, coding_attr_utf_16_endian, endian); |
8348 | ||
8349 | category = (CONSP (bom) | |
8350 | ? coding_category_utf_16_auto | |
8351 | : NILP (bom) | |
b49a1807 | 8352 | ? (EQ (endian, Qbig) |
df7492f9 KH |
8353 | ? coding_category_utf_16_be_nosig |
8354 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 8355 | : (EQ (endian, Qbig) |
df7492f9 KH |
8356 | ? coding_category_utf_16_be |
8357 | : coding_category_utf_16_le)); | |
8358 | } | |
8359 | else if (EQ (coding_type, Qiso_2022)) | |
8360 | { | |
8361 | Lisp_Object initial, reg_usage, request, flags; | |
4776e638 | 8362 | int i; |
1397dc18 | 8363 | |
df7492f9 KH |
8364 | if (nargs < coding_arg_iso2022_max) |
8365 | goto short_args; | |
8366 | ||
8367 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
8368 | CHECK_VECTOR (initial); | |
8369 | for (i = 0; i < 4; i++) | |
8370 | { | |
8371 | val = Faref (initial, make_number (i)); | |
8372 | if (! NILP (val)) | |
8373 | { | |
584948ac KH |
8374 | struct charset *charset; |
8375 | ||
8376 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8377 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
8378 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
8379 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8380 | } |
8381 | else | |
8382 | ASET (initial, i, make_number (-1)); | |
8383 | } | |
8384 | ||
8385 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
8386 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
8387 | CHECK_NUMBER_CAR (reg_usage); |
8388 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
8389 | |
8390 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
8391 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 8392 | { |
df7492f9 | 8393 | int id; |
8f924df7 | 8394 | Lisp_Object tmp; |
df7492f9 KH |
8395 | |
8396 | val = Fcar (tail); | |
8397 | CHECK_CONS (val); | |
8f924df7 KH |
8398 | tmp = XCAR (val); |
8399 | CHECK_CHARSET_GET_ID (tmp, id); | |
8400 | CHECK_NATNUM_CDR (val); | |
df7492f9 KH |
8401 | if (XINT (XCDR (val)) >= 4) |
8402 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
8f924df7 | 8403 | XSETCAR (val, make_number (id)); |
1397dc18 | 8404 | } |
4ed46869 | 8405 | |
df7492f9 KH |
8406 | flags = args[coding_arg_iso2022_flags]; |
8407 | CHECK_NATNUM (flags); | |
8408 | i = XINT (flags); | |
8409 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
8410 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
8411 | ||
8412 | ASET (attrs, coding_attr_iso_initial, initial); | |
8413 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
8414 | ASET (attrs, coding_attr_iso_request, request); | |
8415 | ASET (attrs, coding_attr_iso_flags, flags); | |
8416 | setup_iso_safe_charsets (attrs); | |
8417 | ||
8418 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
8419 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
8420 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
8421 | ? coding_category_iso_7_else | |
8422 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
8423 | ? coding_category_iso_7 | |
8424 | : coding_category_iso_7_tight); | |
8425 | else | |
8426 | { | |
8427 | int id = XINT (AREF (initial, 1)); | |
8428 | ||
c6fb6e98 | 8429 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
8430 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
8431 | || id < 0) | |
8432 | ? coding_category_iso_8_else | |
8433 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
8434 | ? coding_category_iso_8_1 | |
8435 | : coding_category_iso_8_2); | |
8436 | } | |
0ce7886f KH |
8437 | if (category != coding_category_iso_8_1 |
8438 | && category != coding_category_iso_8_2) | |
8439 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; | |
df7492f9 KH |
8440 | } |
8441 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 8442 | { |
df7492f9 KH |
8443 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
8444 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
584948ac | 8445 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
df7492f9 | 8446 | category = coding_category_emacs_mule; |
c28a9453 | 8447 | } |
df7492f9 | 8448 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 8449 | { |
df7492f9 KH |
8450 | |
8451 | struct charset *charset; | |
8452 | ||
7d64c6ad KH |
8453 | if (XINT (Flength (charset_list)) != 3 |
8454 | || XINT (Flength (charset_list)) != 4) | |
8455 | error ("There should be three or four charsets"); | |
df7492f9 KH |
8456 | |
8457 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8458 | if (CHARSET_DIMENSION (charset) != 1) | |
8459 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8460 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8461 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8462 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8463 | |
8464 | charset_list = XCDR (charset_list); | |
8465 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8466 | if (CHARSET_DIMENSION (charset) != 1) | |
8467 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8468 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
8469 | |
8470 | charset_list = XCDR (charset_list); | |
8471 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8472 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
8473 | error ("Dimension of charset %s is not two", |
8474 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
8475 | ||
8476 | charset_list = XCDR (charset_list); | |
8477 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8478 | if (CHARSET_DIMENSION (charset) != 2) | |
df7492f9 | 8479 | error ("Dimension of charset %s is not two", |
8f924df7 | 8480 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
8481 | |
8482 | category = coding_category_sjis; | |
8483 | Vsjis_coding_system = name; | |
c28a9453 | 8484 | } |
df7492f9 KH |
8485 | else if (EQ (coding_type, Qbig5)) |
8486 | { | |
8487 | struct charset *charset; | |
4ed46869 | 8488 | |
df7492f9 KH |
8489 | if (XINT (Flength (charset_list)) != 2) |
8490 | error ("There should be just two charsets"); | |
8491 | ||
8492 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8493 | if (CHARSET_DIMENSION (charset) != 1) | |
8494 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8495 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8496 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8497 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8498 | |
8499 | charset_list = XCDR (charset_list); | |
8500 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8501 | if (CHARSET_DIMENSION (charset) != 2) | |
8502 | error ("Dimension of charset %s is not two", | |
8f924df7 | 8503 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 8504 | |
df7492f9 KH |
8505 | category = coding_category_big5; |
8506 | Vbig5_coding_system = name; | |
8507 | } | |
8508 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 8509 | { |
584948ac KH |
8510 | category = coding_category_raw_text; |
8511 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
c28a9453 | 8512 | } |
df7492f9 | 8513 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 8514 | { |
584948ac KH |
8515 | category = coding_category_utf_8; |
8516 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
4ed46869 | 8517 | } |
df7492f9 KH |
8518 | else if (EQ (coding_type, Qundecided)) |
8519 | category = coding_category_undecided; | |
4ed46869 | 8520 | else |
df7492f9 | 8521 | error ("Invalid coding system type: %s", |
8f924df7 | 8522 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 8523 | |
df7492f9 | 8524 | CODING_ATTR_CATEGORY (attrs) = make_number (category); |
01378f49 KH |
8525 | CODING_ATTR_PLIST (attrs) |
8526 | = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category), | |
8527 | CODING_ATTR_PLIST (attrs))); | |
c4825358 | 8528 | |
df7492f9 KH |
8529 | eol_type = args[coding_arg_eol_type]; |
8530 | if (! NILP (eol_type) | |
8531 | && ! EQ (eol_type, Qunix) | |
8532 | && ! EQ (eol_type, Qdos) | |
8533 | && ! EQ (eol_type, Qmac)) | |
8534 | error ("Invalid eol-type"); | |
4ed46869 | 8535 | |
df7492f9 | 8536 | aliases = Fcons (name, Qnil); |
4ed46869 | 8537 | |
df7492f9 KH |
8538 | if (NILP (eol_type)) |
8539 | { | |
8540 | eol_type = make_subsidiaries (name); | |
8541 | for (i = 0; i < 3; i++) | |
1397dc18 | 8542 | { |
df7492f9 KH |
8543 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
8544 | ||
8545 | this_name = AREF (eol_type, i); | |
8546 | this_aliases = Fcons (this_name, Qnil); | |
8547 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
8548 | this_spec = Fmake_vector (make_number (3), attrs); | |
8549 | ASET (this_spec, 1, this_aliases); | |
8550 | ASET (this_spec, 2, this_eol_type); | |
8551 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
8552 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
8553 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
8554 | Vcoding_system_alist); | |
1397dc18 | 8555 | } |
d46c5b12 | 8556 | } |
4ed46869 | 8557 | |
df7492f9 KH |
8558 | spec_vec = Fmake_vector (make_number (3), attrs); |
8559 | ASET (spec_vec, 1, aliases); | |
8560 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 8561 | |
df7492f9 KH |
8562 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
8563 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
8564 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
8565 | Vcoding_system_alist); | |
48b0f3ae | 8566 | |
df7492f9 KH |
8567 | { |
8568 | int id = coding_categories[category].id; | |
48b0f3ae | 8569 | |
df7492f9 KH |
8570 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
8571 | setup_coding_system (name, &coding_categories[category]); | |
8572 | } | |
48b0f3ae | 8573 | |
d46c5b12 | 8574 | return Qnil; |
48b0f3ae | 8575 | |
df7492f9 KH |
8576 | short_args: |
8577 | return Fsignal (Qwrong_number_of_arguments, | |
8578 | Fcons (intern ("define-coding-system-internal"), | |
8579 | make_number (nargs))); | |
d46c5b12 | 8580 | } |
4ed46869 | 8581 | |
d6925f38 | 8582 | |
df7492f9 KH |
8583 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
8584 | Sdefine_coding_system_alias, 2, 2, 0, | |
8585 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
8586 | (alias, coding_system) | |
8587 | Lisp_Object alias, coding_system; | |
66cfb530 | 8588 | { |
df7492f9 | 8589 | Lisp_Object spec, aliases, eol_type; |
4ed46869 | 8590 | |
df7492f9 KH |
8591 | CHECK_SYMBOL (alias); |
8592 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8593 | aliases = AREF (spec, 1); | |
d6925f38 KH |
8594 | /* ALISES should be a list of length more than zero, and the first |
8595 | element is a base coding system. Append ALIAS at the tail of the | |
8596 | list. */ | |
df7492f9 KH |
8597 | while (!NILP (XCDR (aliases))) |
8598 | aliases = XCDR (aliases); | |
8f924df7 | 8599 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 8600 | |
df7492f9 KH |
8601 | eol_type = AREF (spec, 2); |
8602 | if (VECTORP (eol_type)) | |
4ed46869 | 8603 | { |
df7492f9 KH |
8604 | Lisp_Object subsidiaries; |
8605 | int i; | |
4ed46869 | 8606 | |
df7492f9 KH |
8607 | subsidiaries = make_subsidiaries (alias); |
8608 | for (i = 0; i < 3; i++) | |
8609 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
8610 | AREF (eol_type, i)); | |
4ed46869 | 8611 | } |
df7492f9 KH |
8612 | |
8613 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 8614 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
5bad0796 DL |
8615 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), |
8616 | Vcoding_system_alist); | |
66cfb530 | 8617 | |
4ed46869 KH |
8618 | return Qnil; |
8619 | } | |
8620 | ||
df7492f9 KH |
8621 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
8622 | 1, 1, 0, | |
8623 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 8624 | Any alias or subsidiary coding system is not a base coding system. */) |
df7492f9 KH |
8625 | (coding_system) |
8626 | Lisp_Object coding_system; | |
d46c5b12 | 8627 | { |
df7492f9 | 8628 | Lisp_Object spec, attrs; |
d46c5b12 | 8629 | |
df7492f9 KH |
8630 | if (NILP (coding_system)) |
8631 | return (Qno_conversion); | |
8632 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8633 | attrs = AREF (spec, 0); | |
8634 | return CODING_ATTR_BASE_NAME (attrs); | |
8635 | } | |
1397dc18 | 8636 | |
df7492f9 KH |
8637 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
8638 | 1, 1, 0, | |
8639 | doc: "Return the property list of CODING-SYSTEM.") | |
8640 | (coding_system) | |
8641 | Lisp_Object coding_system; | |
8642 | { | |
8643 | Lisp_Object spec, attrs; | |
1397dc18 | 8644 | |
df7492f9 KH |
8645 | if (NILP (coding_system)) |
8646 | coding_system = Qno_conversion; | |
8647 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8648 | attrs = AREF (spec, 0); | |
8649 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
8650 | } |
8651 | ||
df7492f9 KH |
8652 | |
8653 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
8654 | 1, 1, 0, | |
da7db224 | 8655 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
df7492f9 KH |
8656 | (coding_system) |
8657 | Lisp_Object coding_system; | |
66cfb530 | 8658 | { |
df7492f9 | 8659 | Lisp_Object spec; |
84d60297 | 8660 | |
df7492f9 KH |
8661 | if (NILP (coding_system)) |
8662 | coding_system = Qno_conversion; | |
8663 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 8664 | return AREF (spec, 1); |
df7492f9 | 8665 | } |
66cfb530 | 8666 | |
df7492f9 KH |
8667 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
8668 | Scoding_system_eol_type, 1, 1, 0, | |
8669 | doc: /* Return eol-type of CODING-SYSTEM. | |
8670 | An eol-type is integer 0, 1, 2, or a vector of coding systems. | |
66cfb530 | 8671 | |
df7492f9 KH |
8672 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
8673 | and CR respectively. | |
66cfb530 | 8674 | |
df7492f9 KH |
8675 | A vector value indicates that a format of end-of-line should be |
8676 | detected automatically. Nth element of the vector is the subsidiary | |
8677 | coding system whose eol-type is N. */) | |
6b89e3aa KH |
8678 | (coding_system) |
8679 | Lisp_Object coding_system; | |
8680 | { | |
df7492f9 KH |
8681 | Lisp_Object spec, eol_type; |
8682 | int n; | |
6b89e3aa | 8683 | |
df7492f9 KH |
8684 | if (NILP (coding_system)) |
8685 | coding_system = Qno_conversion; | |
8686 | if (! CODING_SYSTEM_P (coding_system)) | |
8687 | return Qnil; | |
8688 | spec = CODING_SYSTEM_SPEC (coding_system); | |
8689 | eol_type = AREF (spec, 2); | |
8690 | if (VECTORP (eol_type)) | |
8691 | return Fcopy_sequence (eol_type); | |
8692 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
8693 | return make_number (n); | |
6b89e3aa KH |
8694 | } |
8695 | ||
4ed46869 KH |
8696 | #endif /* emacs */ |
8697 | ||
8698 | \f | |
1397dc18 | 8699 | /*** 9. Post-amble ***/ |
4ed46869 | 8700 | |
dfcf069d | 8701 | void |
4ed46869 KH |
8702 | init_coding_once () |
8703 | { | |
8704 | int i; | |
8705 | ||
df7492f9 KH |
8706 | for (i = 0; i < coding_category_max; i++) |
8707 | { | |
8708 | coding_categories[i].id = -1; | |
8709 | coding_priorities[i] = i; | |
8710 | } | |
4ed46869 KH |
8711 | |
8712 | /* ISO2022 specific initialize routine. */ | |
8713 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 8714 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
8715 | for (i = 0x21; i < 0x7F; i++) |
8716 | iso_code_class[i] = ISO_graphic_plane_0; | |
8717 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 8718 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
8719 | for (i = 0xA1; i < 0xFF; i++) |
8720 | iso_code_class[i] = ISO_graphic_plane_1; | |
8721 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
8722 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
8723 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
8724 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
8725 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
8726 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
8727 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
8728 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
8729 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
8730 | ||
df7492f9 KH |
8731 | for (i = 0; i < 256; i++) |
8732 | { | |
8733 | emacs_mule_bytes[i] = 1; | |
8734 | } | |
7c78e542 KH |
8735 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
8736 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
8737 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
8738 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
8739 | } |
8740 | ||
8741 | #ifdef emacs | |
8742 | ||
dfcf069d | 8743 | void |
e0e989f6 KH |
8744 | syms_of_coding () |
8745 | { | |
df7492f9 | 8746 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
8747 | { |
8748 | Lisp_Object args[2]; | |
8749 | args[0] = QCtest; | |
8750 | args[1] = Qeq; | |
8751 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
8752 | } | |
df7492f9 KH |
8753 | |
8754 | staticpro (&Vsjis_coding_system); | |
8755 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 8756 | |
df7492f9 KH |
8757 | staticpro (&Vbig5_coding_system); |
8758 | Vbig5_coding_system = Qnil; | |
8759 | ||
24a73b0a KH |
8760 | staticpro (&Vcode_conversion_reused_workbuf); |
8761 | Vcode_conversion_reused_workbuf = Qnil; | |
8762 | ||
8763 | staticpro (&Vcode_conversion_workbuf_name); | |
8764 | Vcode_conversion_workbuf_name = build_string (" *code-conversion-work*"); | |
e0e989f6 | 8765 | |
24a73b0a | 8766 | reused_workbuf_in_use = 0; |
df7492f9 KH |
8767 | |
8768 | DEFSYM (Qcharset, "charset"); | |
8769 | DEFSYM (Qtarget_idx, "target-idx"); | |
8770 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
8771 | Fset (Qcoding_system_history, Qnil); |
8772 | ||
9ce27fde | 8773 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 8774 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 8775 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
8776 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
8777 | ||
df7492f9 | 8778 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 8779 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
8780 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
8781 | ||
df7492f9 | 8782 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 8783 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
8784 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
8785 | ||
df7492f9 | 8786 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 8787 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
8788 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
8789 | ||
df7492f9 | 8790 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 8791 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
8792 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
8793 | ||
df7492f9 KH |
8794 | DEFSYM (Qcoding_system, "coding-system"); |
8795 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 8796 | |
df7492f9 KH |
8797 | DEFSYM (Qeol_type, "eol-type"); |
8798 | DEFSYM (Qunix, "unix"); | |
8799 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 8800 | |
df7492f9 KH |
8801 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
8802 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
8803 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
8804 | DEFSYM (Qdefault_char, "default-char"); | |
8805 | DEFSYM (Qundecided, "undecided"); | |
8806 | DEFSYM (Qno_conversion, "no-conversion"); | |
8807 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 8808 | |
df7492f9 | 8809 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 8810 | |
df7492f9 | 8811 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 8812 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 8813 | |
df7492f9 | 8814 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
8815 | DEFSYM (Qbig, "big"); |
8816 | DEFSYM (Qlittle, "little"); | |
27901516 | 8817 | |
df7492f9 KH |
8818 | DEFSYM (Qshift_jis, "shift-jis"); |
8819 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 8820 | |
df7492f9 | 8821 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 8822 | |
df7492f9 | 8823 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 KH |
8824 | Fput (Qcoding_system_error, Qerror_conditions, |
8825 | Fcons (Qcoding_system_error, Fcons (Qerror, Qnil))); | |
8826 | Fput (Qcoding_system_error, Qerror_message, | |
9ce27fde | 8827 | build_string ("Invalid coding system")); |
4ed46869 | 8828 | |
05e6f5dc KH |
8829 | /* Intern this now in case it isn't already done. |
8830 | Setting this variable twice is harmless. | |
8831 | But don't staticpro it here--that is done in alloc.c. */ | |
8832 | Qchar_table_extra_slots = intern ("char-table-extra-slots"); | |
70c22245 | 8833 | |
df7492f9 | 8834 | DEFSYM (Qtranslation_table, "translation-table"); |
1397dc18 | 8835 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (1)); |
df7492f9 KH |
8836 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
8837 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
8838 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 8839 | |
df7492f9 | 8840 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 8841 | |
df7492f9 | 8842 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 8843 | |
01378f49 KH |
8844 | DEFSYM (QCcategory, ":category"); |
8845 | ||
df7492f9 KH |
8846 | Vcoding_category_table |
8847 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
8848 | staticpro (&Vcoding_category_table); | |
8849 | /* Followings are target of code detection. */ | |
8850 | ASET (Vcoding_category_table, coding_category_iso_7, | |
8851 | intern ("coding-category-iso-7")); | |
8852 | ASET (Vcoding_category_table, coding_category_iso_7_tight, | |
8853 | intern ("coding-category-iso-7-tight")); | |
8854 | ASET (Vcoding_category_table, coding_category_iso_8_1, | |
8855 | intern ("coding-category-iso-8-1")); | |
8856 | ASET (Vcoding_category_table, coding_category_iso_8_2, | |
8857 | intern ("coding-category-iso-8-2")); | |
8858 | ASET (Vcoding_category_table, coding_category_iso_7_else, | |
8859 | intern ("coding-category-iso-7-else")); | |
8860 | ASET (Vcoding_category_table, coding_category_iso_8_else, | |
8861 | intern ("coding-category-iso-8-else")); | |
8862 | ASET (Vcoding_category_table, coding_category_utf_8, | |
8863 | intern ("coding-category-utf-8")); | |
8864 | ASET (Vcoding_category_table, coding_category_utf_16_be, | |
8865 | intern ("coding-category-utf-16-be")); | |
ff563fce KH |
8866 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
8867 | intern ("coding-category-utf-16-auto")); | |
df7492f9 KH |
8868 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
8869 | intern ("coding-category-utf-16-le")); | |
8870 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, | |
8871 | intern ("coding-category-utf-16-be-nosig")); | |
8872 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, | |
8873 | intern ("coding-category-utf-16-le-nosig")); | |
8874 | ASET (Vcoding_category_table, coding_category_charset, | |
8875 | intern ("coding-category-charset")); | |
8876 | ASET (Vcoding_category_table, coding_category_sjis, | |
8877 | intern ("coding-category-sjis")); | |
8878 | ASET (Vcoding_category_table, coding_category_big5, | |
8879 | intern ("coding-category-big5")); | |
8880 | ASET (Vcoding_category_table, coding_category_ccl, | |
8881 | intern ("coding-category-ccl")); | |
8882 | ASET (Vcoding_category_table, coding_category_emacs_mule, | |
8883 | intern ("coding-category-emacs-mule")); | |
8884 | /* Followings are NOT target of code detection. */ | |
8885 | ASET (Vcoding_category_table, coding_category_raw_text, | |
8886 | intern ("coding-category-raw-text")); | |
8887 | ASET (Vcoding_category_table, coding_category_undecided, | |
8888 | intern ("coding-category-undecided")); | |
ecf488bc | 8889 | |
065e3595 KH |
8890 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
8891 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
8892 | DEFSYM (Qinvalid_source, "invalid-source"); | |
8893 | DEFSYM (Qinterrupted, "interrupted"); | |
8894 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
8895 | ||
4ed46869 KH |
8896 | defsubr (&Scoding_system_p); |
8897 | defsubr (&Sread_coding_system); | |
8898 | defsubr (&Sread_non_nil_coding_system); | |
8899 | defsubr (&Scheck_coding_system); | |
8900 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 8901 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 8902 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 8903 | defsubr (&Sunencodable_char_position); |
df7492f9 | 8904 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
8905 | defsubr (&Sdecode_coding_region); |
8906 | defsubr (&Sencode_coding_region); | |
8907 | defsubr (&Sdecode_coding_string); | |
8908 | defsubr (&Sencode_coding_string); | |
8909 | defsubr (&Sdecode_sjis_char); | |
8910 | defsubr (&Sencode_sjis_char); | |
8911 | defsubr (&Sdecode_big5_char); | |
8912 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 8913 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 8914 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 8915 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 8916 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 8917 | defsubr (&Skeyboard_coding_system); |
a5d301df | 8918 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 8919 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 8920 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 KH |
8921 | defsubr (&Sdefine_coding_system_alias); |
8922 | defsubr (&Scoding_system_base); | |
8923 | defsubr (&Scoding_system_plist); | |
8924 | defsubr (&Scoding_system_aliases); | |
8925 | defsubr (&Scoding_system_eol_type); | |
8926 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 8927 | |
4608c386 | 8928 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
48b0f3ae PJ |
8929 | doc: /* List of coding systems. |
8930 | ||
8931 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 8932 | updated by the functions `define-coding-system' and |
48b0f3ae | 8933 | `define-coding-system-alias'. */); |
4608c386 KH |
8934 | Vcoding_system_list = Qnil; |
8935 | ||
8936 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, | |
48b0f3ae PJ |
8937 | doc: /* Alist of coding system names. |
8938 | Each element is one element list of coding system name. | |
8939 | This variable is given to `completing-read' as TABLE argument. | |
8940 | ||
8941 | Do not alter the value of this variable manually. This variable should be | |
8942 | updated by the functions `make-coding-system' and | |
8943 | `define-coding-system-alias'. */); | |
4608c386 KH |
8944 | Vcoding_system_alist = Qnil; |
8945 | ||
4ed46869 | 8946 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
48b0f3ae PJ |
8947 | doc: /* List of coding-categories (symbols) ordered by priority. |
8948 | ||
8949 | On detecting a coding system, Emacs tries code detection algorithms | |
8950 | associated with each coding-category one by one in this order. When | |
8951 | one algorithm agrees with a byte sequence of source text, the coding | |
8952 | system bound to the corresponding coding-category is selected. */); | |
4ed46869 KH |
8953 | { |
8954 | int i; | |
8955 | ||
8956 | Vcoding_category_list = Qnil; | |
df7492f9 | 8957 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 8958 | Vcoding_category_list |
d46c5b12 KH |
8959 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
8960 | Vcoding_category_list); | |
4ed46869 KH |
8961 | } |
8962 | ||
8963 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, | |
48b0f3ae PJ |
8964 | doc: /* Specify the coding system for read operations. |
8965 | It is useful to bind this variable with `let', but do not set it globally. | |
8966 | If the value is a coding system, it is used for decoding on read operation. | |
8967 | If not, an appropriate element is used from one of the coding system alists: | |
8968 | There are three such tables, `file-coding-system-alist', | |
8969 | `process-coding-system-alist', and `network-coding-system-alist'. */); | |
4ed46869 KH |
8970 | Vcoding_system_for_read = Qnil; |
8971 | ||
8972 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, | |
48b0f3ae PJ |
8973 | doc: /* Specify the coding system for write operations. |
8974 | Programs bind this variable with `let', but you should not set it globally. | |
8975 | If the value is a coding system, it is used for encoding of output, | |
8976 | when writing it to a file and when sending it to a file or subprocess. | |
8977 | ||
8978 | If this does not specify a coding system, an appropriate element | |
8979 | is used from one of the coding system alists: | |
8980 | There are three such tables, `file-coding-system-alist', | |
8981 | `process-coding-system-alist', and `network-coding-system-alist'. | |
8982 | For output to files, if the above procedure does not specify a coding system, | |
8983 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
8984 | Vcoding_system_for_write = Qnil; |
8985 | ||
8986 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, | |
df7492f9 KH |
8987 | doc: /* |
8988 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
8989 | Vlast_coding_system_used = Qnil; |
8990 | ||
065e3595 KH |
8991 | DEFVAR_LISP ("last-code-conversion-error", &Vlast_code_conversion_error, |
8992 | doc: /* | |
8993 | Error status of the last code conversion. | |
8994 | ||
8995 | When an error was detected in the last code conversion, this variable | |
8996 | is set to one of the following symbols. | |
8997 | `insufficient-source' | |
8998 | `inconsistent-eol' | |
8999 | `invalid-source' | |
9000 | `interrupted' | |
9001 | `insufficient-memory' | |
9002 | When no error was detected, the value doesn't change. So, to check | |
9003 | the error status of a code conversion by this variable, you must | |
9004 | explicitly set this variable to nil before performing code | |
9005 | conversion. */); | |
9006 | Vlast_code_conversion_error = Qnil; | |
9007 | ||
9ce27fde | 9008 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
df7492f9 KH |
9009 | doc: /* |
9010 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
9011 | See info node `Coding Systems' and info node `Text and Binary' concerning |
9012 | such conversion. */); | |
9ce27fde KH |
9013 | inhibit_eol_conversion = 0; |
9014 | ||
ed29121d | 9015 | DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
df7492f9 KH |
9016 | doc: /* |
9017 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
9018 | Bind it to t if the process output is to be treated as if it were a file |
9019 | read from some filesystem. */); | |
ed29121d EZ |
9020 | inherit_process_coding_system = 0; |
9021 | ||
02ba4723 | 9022 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
df7492f9 KH |
9023 | doc: /* |
9024 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
9025 | The format is ((PATTERN . VAL) ...), |
9026 | where PATTERN is a regular expression matching a file name, | |
9027 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9028 | If VAL is a coding system, it is used for both decoding and encoding | |
9029 | the file contents. | |
9030 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9031 | and the cdr part is used for encoding. | |
9032 | If VAL is a function symbol, the function must return a coding system | |
0192762c DL |
9033 | or a cons of coding systems which are used as above. The function gets |
9034 | the arguments with which `find-operation-coding-systems' was called. | |
48b0f3ae PJ |
9035 | |
9036 | See also the function `find-operation-coding-system' | |
9037 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
9038 | Vfile_coding_system_alist = Qnil; |
9039 | ||
9040 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, | |
df7492f9 KH |
9041 | doc: /* |
9042 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
9043 | The format is ((PATTERN . VAL) ...), |
9044 | where PATTERN is a regular expression matching a program name, | |
9045 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9046 | If VAL is a coding system, it is used for both decoding what received | |
9047 | from the program and encoding what sent to the program. | |
9048 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9049 | and the cdr part is used for encoding. | |
9050 | If VAL is a function symbol, the function must return a coding system | |
9051 | or a cons of coding systems which are used as above. | |
9052 | ||
9053 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
9054 | Vprocess_coding_system_alist = Qnil; |
9055 | ||
9056 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, | |
df7492f9 KH |
9057 | doc: /* |
9058 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
9059 | The format is ((PATTERN . VAL) ...), |
9060 | where PATTERN is a regular expression matching a network service name | |
9061 | or is a port number to connect to, | |
9062 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9063 | If VAL is a coding system, it is used for both decoding what received | |
9064 | from the network stream and encoding what sent to the network stream. | |
9065 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9066 | and the cdr part is used for encoding. | |
9067 | If VAL is a function symbol, the function must return a coding system | |
9068 | or a cons of coding systems which are used as above. | |
9069 | ||
9070 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 9071 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 9072 | |
68c45bf0 | 9073 | DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
75205970 RS |
9074 | doc: /* Coding system to use with system messages. |
9075 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
9076 | Vlocale_coding_system = Qnil; |
9077 | ||
005f0d35 | 9078 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
7722baf9 | 9079 | DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
df7492f9 KH |
9080 | doc: /* |
9081 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
7722baf9 | 9082 | eol_mnemonic_unix = build_string (":"); |
4ed46869 | 9083 | |
7722baf9 | 9084 | DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
df7492f9 KH |
9085 | doc: /* |
9086 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
7722baf9 | 9087 | eol_mnemonic_dos = build_string ("\\"); |
4ed46869 | 9088 | |
7722baf9 | 9089 | DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
df7492f9 KH |
9090 | doc: /* |
9091 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
7722baf9 | 9092 | eol_mnemonic_mac = build_string ("/"); |
4ed46869 | 9093 | |
7722baf9 | 9094 | DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
df7492f9 KH |
9095 | doc: /* |
9096 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
7722baf9 | 9097 | eol_mnemonic_undecided = build_string (":"); |
4ed46869 | 9098 | |
84fbb8a0 | 9099 | DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
df7492f9 KH |
9100 | doc: /* |
9101 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 9102 | Venable_character_translation = Qt; |
bdd9fb48 | 9103 | |
f967223b | 9104 | DEFVAR_LISP ("standard-translation-table-for-decode", |
48b0f3ae PJ |
9105 | &Vstandard_translation_table_for_decode, |
9106 | doc: /* Table for translating characters while decoding. */); | |
f967223b | 9107 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 9108 | |
f967223b | 9109 | DEFVAR_LISP ("standard-translation-table-for-encode", |
48b0f3ae PJ |
9110 | &Vstandard_translation_table_for_encode, |
9111 | doc: /* Table for translating characters while encoding. */); | |
f967223b | 9112 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 9113 | |
df7492f9 | 9114 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table, |
48b0f3ae PJ |
9115 | doc: /* Alist of charsets vs revision numbers. |
9116 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
9117 | designate it with the escape sequence identifying revision (cdr part |
9118 | of the element). */); | |
9119 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
9120 | |
9121 | DEFVAR_LISP ("default-process-coding-system", | |
9122 | &Vdefault_process_coding_system, | |
48b0f3ae PJ |
9123 | doc: /* Cons of coding systems used for process I/O by default. |
9124 | The car part is used for decoding a process output, | |
9125 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 9126 | Vdefault_process_coding_system = Qnil; |
c4825358 | 9127 | |
3f003981 | 9128 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
df7492f9 KH |
9129 | doc: /* |
9130 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
9131 | This is a vector of length 256. |
9132 | If Nth element is non-nil, the existence of code N in a file | |
9133 | \(or output of subprocess) doesn't prevent it to be detected as | |
9134 | a coding system of ISO 2022 variant which has a flag | |
9135 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
9136 | or reading output of a subprocess. | |
9137 | Only 128th through 159th elements has a meaning. */); | |
3f003981 | 9138 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
9139 | |
9140 | DEFVAR_LISP ("select-safe-coding-system-function", | |
9141 | &Vselect_safe_coding_system_function, | |
df7492f9 KH |
9142 | doc: /* |
9143 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
9144 | |
9145 | If set, this function is called to force a user to select a proper | |
9146 | coding system which can encode the text in the case that a default | |
9147 | coding system used in each operation can't encode the text. | |
9148 | ||
9149 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
9150 | Vselect_safe_coding_system_function = Qnil; |
9151 | ||
5d5bf4d8 KH |
9152 | DEFVAR_BOOL ("coding-system-require-warning", |
9153 | &coding_system_require_warning, | |
9154 | doc: /* Internal use only. | |
6b89e3aa KH |
9155 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
9156 | called even if `coding-system-for-write' is non-nil. The command | |
9157 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
9158 | coding_system_require_warning = 0; |
9159 | ||
9160 | ||
22ab2303 | 9161 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
74383408 | 9162 | &inhibit_iso_escape_detection, |
df7492f9 KH |
9163 | doc: /* |
9164 | If non-nil, Emacs ignores ISO2022's escape sequence on code detection. | |
48b0f3ae PJ |
9165 | |
9166 | By default, on reading a file, Emacs tries to detect how the text is | |
9167 | encoded. This code detection is sensitive to escape sequences. If | |
9168 | the sequence is valid as ISO2022, the code is determined as one of | |
9169 | the ISO2022 encodings, and the file is decoded by the corresponding | |
9170 | coding system (e.g. `iso-2022-7bit'). | |
9171 | ||
9172 | However, there may be a case that you want to read escape sequences in | |
9173 | a file as is. In such a case, you can set this variable to non-nil. | |
9174 | Then, as the code detection ignores any escape sequences, no file is | |
9175 | detected as encoded in some ISO2022 encoding. The result is that all | |
9176 | escape sequences become visible in a buffer. | |
9177 | ||
9178 | The default value is nil, and it is strongly recommended not to change | |
9179 | it. That is because many Emacs Lisp source files that contain | |
9180 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
9181 | in Emacs's distribution, and they won't be decoded correctly on | |
9182 | reading if you suppress escape sequence detection. | |
9183 | ||
9184 | The other way to read escape sequences in a file without decoding is | |
9185 | to explicitly specify some coding system that doesn't use ISO2022's | |
9186 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); | |
74383408 | 9187 | inhibit_iso_escape_detection = 0; |
002fdb44 DL |
9188 | |
9189 | DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input, | |
15c8f9d1 DL |
9190 | doc: /* Char table for translating self-inserting characters. |
9191 | This is applied to the result of input methods, not their input. See also | |
9192 | `keyboard-translate-table'. */); | |
002fdb44 | 9193 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 9194 | |
2c78b7e1 KH |
9195 | { |
9196 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 9197 | Lisp_Object plist[16]; |
2c78b7e1 KH |
9198 | int i; |
9199 | ||
9200 | for (i = 0; i < coding_arg_max; i++) | |
9201 | args[i] = Qnil; | |
9202 | ||
9203 | plist[0] = intern (":name"); | |
9204 | plist[1] = args[coding_arg_name] = Qno_conversion; | |
9205 | plist[2] = intern (":mnemonic"); | |
9206 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); | |
9207 | plist[4] = intern (":coding-type"); | |
9208 | plist[5] = args[coding_arg_coding_type] = Qraw_text; | |
9209 | plist[6] = intern (":ascii-compatible-p"); | |
9210 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; | |
9211 | plist[8] = intern (":default-char"); | |
9212 | plist[9] = args[coding_arg_default_char] = make_number (0); | |
8f924df7 KH |
9213 | plist[10] = intern (":for-unibyte"); |
9214 | plist[11] = args[coding_arg_for_unibyte] = Qt; | |
9215 | plist[12] = intern (":docstring"); | |
9216 | plist[13] = build_string ("Do no conversion.\n\ | |
2c78b7e1 KH |
9217 | \n\ |
9218 | When you visit a file with this coding, the file is read into a\n\ | |
9219 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
9220 | character."); | |
8f924df7 KH |
9221 | plist[14] = intern (":eol-type"); |
9222 | plist[15] = args[coding_arg_eol_type] = Qunix; | |
9223 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 KH |
9224 | Fdefine_coding_system_internal (coding_arg_max, args); |
9225 | } | |
9226 | ||
9227 | setup_coding_system (Qno_conversion, &keyboard_coding); | |
9228 | setup_coding_system (Qno_conversion, &terminal_coding); | |
9229 | setup_coding_system (Qno_conversion, &safe_terminal_coding); | |
ff563fce KH |
9230 | |
9231 | { | |
9232 | int i; | |
9233 | ||
9234 | for (i = 0; i < coding_category_max; i++) | |
9235 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
9236 | } | |
4ed46869 KH |
9237 | } |
9238 | ||
68c45bf0 PE |
9239 | char * |
9240 | emacs_strerror (error_number) | |
9241 | int error_number; | |
9242 | { | |
9243 | char *str; | |
9244 | ||
ca9c0567 | 9245 | synchronize_system_messages_locale (); |
68c45bf0 PE |
9246 | str = strerror (error_number); |
9247 | ||
9248 | if (! NILP (Vlocale_coding_system)) | |
9249 | { | |
9250 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
9251 | Vlocale_coding_system, | |
9252 | 0); | |
d5db4077 | 9253 | str = (char *) SDATA (dec); |
68c45bf0 PE |
9254 | } |
9255 | ||
9256 | return str; | |
9257 | } | |
9258 | ||
4ed46869 | 9259 | #endif /* emacs */ |