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. */ | |
69a80ea3 KH |
215 | int *charbuf = coding->charbuf + coding->charbuf_used; |
216 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
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; |
a6f87d34 KH |
314 | Lisp_Object QCcategory, QCmnemonic, QCdefalut_char; |
315 | Lisp_Object QCdecode_translation_table, QCencode_translation_table; | |
316 | Lisp_Object QCpost_read_conversion, QCpre_write_conversion; | |
4ed46869 KH |
317 | |
318 | extern Lisp_Object Qinsert_file_contents, Qwrite_region; | |
319 | Lisp_Object Qcall_process, Qcall_process_region, Qprocess_argument; | |
320 | Lisp_Object Qstart_process, Qopen_network_stream; | |
321 | Lisp_Object Qtarget_idx; | |
322 | ||
065e3595 KH |
323 | Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source; |
324 | Lisp_Object Qinterrupted, Qinsufficient_memory; | |
325 | ||
5d5bf4d8 KH |
326 | int coding_system_require_warning; |
327 | ||
d46c5b12 KH |
328 | Lisp_Object Vselect_safe_coding_system_function; |
329 | ||
7722baf9 EZ |
330 | /* Mnemonic string for each format of end-of-line. */ |
331 | Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; | |
332 | /* Mnemonic string to indicate format of end-of-line is not yet | |
4ed46869 | 333 | decided. */ |
7722baf9 | 334 | Lisp_Object eol_mnemonic_undecided; |
4ed46869 KH |
335 | |
336 | #ifdef emacs | |
337 | ||
4608c386 KH |
338 | Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
339 | ||
340 | Lisp_Object Qcoding_system_p, Qcoding_system_error; | |
4ed46869 | 341 | |
d46c5b12 KH |
342 | /* Coding system emacs-mule and raw-text are for converting only |
343 | end-of-line format. */ | |
344 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 345 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 346 | |
4ed46869 KH |
347 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
348 | routines by the following three variables. */ | |
349 | /* Coding-system for reading files and receiving data from process. */ | |
350 | Lisp_Object Vcoding_system_for_read; | |
351 | /* Coding-system for writing files and sending data to process. */ | |
352 | Lisp_Object Vcoding_system_for_write; | |
353 | /* Coding-system actually used in the latest I/O. */ | |
354 | Lisp_Object Vlast_coding_system_used; | |
065e3595 KH |
355 | /* Set to non-nil when an error is detected while code conversion. */ |
356 | Lisp_Object Vlast_code_conversion_error; | |
c4825358 | 357 | /* A vector of length 256 which contains information about special |
94487c4e | 358 | Latin codes (especially for dealing with Microsoft codes). */ |
3f003981 | 359 | Lisp_Object Vlatin_extra_code_table; |
c4825358 | 360 | |
9ce27fde KH |
361 | /* Flag to inhibit code conversion of end-of-line format. */ |
362 | int inhibit_eol_conversion; | |
363 | ||
74383408 KH |
364 | /* Flag to inhibit ISO2022 escape sequence detection. */ |
365 | int inhibit_iso_escape_detection; | |
366 | ||
ed29121d EZ |
367 | /* Flag to make buffer-file-coding-system inherit from process-coding. */ |
368 | int inherit_process_coding_system; | |
369 | ||
c4825358 | 370 | /* Coding system to be used to encode text for terminal display. */ |
4ed46869 KH |
371 | struct coding_system terminal_coding; |
372 | ||
c4825358 KH |
373 | /* Coding system to be used to encode text for terminal display when |
374 | terminal coding system is nil. */ | |
375 | struct coding_system safe_terminal_coding; | |
376 | ||
377 | /* Coding system of what is sent from terminal keyboard. */ | |
4ed46869 KH |
378 | struct coding_system keyboard_coding; |
379 | ||
02ba4723 KH |
380 | Lisp_Object Vfile_coding_system_alist; |
381 | Lisp_Object Vprocess_coding_system_alist; | |
382 | Lisp_Object Vnetwork_coding_system_alist; | |
4ed46869 | 383 | |
68c45bf0 PE |
384 | Lisp_Object Vlocale_coding_system; |
385 | ||
4ed46869 KH |
386 | #endif /* emacs */ |
387 | ||
f967223b KH |
388 | /* Flag to tell if we look up translation table on character code |
389 | conversion. */ | |
84fbb8a0 | 390 | Lisp_Object Venable_character_translation; |
f967223b KH |
391 | /* Standard translation table to look up on decoding (reading). */ |
392 | Lisp_Object Vstandard_translation_table_for_decode; | |
393 | /* Standard translation table to look up on encoding (writing). */ | |
394 | Lisp_Object Vstandard_translation_table_for_encode; | |
84fbb8a0 | 395 | |
f967223b KH |
396 | Lisp_Object Qtranslation_table; |
397 | Lisp_Object Qtranslation_table_id; | |
398 | Lisp_Object Qtranslation_table_for_decode; | |
399 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 KH |
400 | |
401 | /* Alist of charsets vs revision number. */ | |
df7492f9 | 402 | static Lisp_Object Vcharset_revision_table; |
4ed46869 | 403 | |
02ba4723 KH |
404 | /* Default coding systems used for process I/O. */ |
405 | Lisp_Object Vdefault_process_coding_system; | |
406 | ||
002fdb44 DL |
407 | /* Char table for translating Quail and self-inserting input. */ |
408 | Lisp_Object Vtranslation_table_for_input; | |
409 | ||
df7492f9 KH |
410 | /* Two special coding systems. */ |
411 | Lisp_Object Vsjis_coding_system; | |
412 | Lisp_Object Vbig5_coding_system; | |
413 | ||
df7492f9 KH |
414 | /* ISO2022 section */ |
415 | ||
416 | #define CODING_ISO_INITIAL(coding, reg) \ | |
417 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
418 | coding_attr_iso_initial), \ | |
419 | reg))) | |
420 | ||
421 | ||
422 | #define CODING_ISO_REQUEST(coding, charset_id) \ | |
423 | ((charset_id <= (coding)->max_charset_id \ | |
424 | ? (coding)->safe_charsets[charset_id] \ | |
425 | : -1)) | |
426 | ||
427 | ||
428 | #define CODING_ISO_FLAGS(coding) \ | |
429 | ((coding)->spec.iso_2022.flags) | |
430 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
431 | ((coding)->spec.iso_2022.current_designation[reg]) | |
432 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
433 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
434 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
435 | ((coding)->spec.iso_2022.single_shifting) | |
436 | #define CODING_ISO_BOL(coding) \ | |
437 | ((coding)->spec.iso_2022.bol) | |
438 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
439 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
440 | ||
441 | /* Control characters of ISO2022. */ | |
442 | /* code */ /* function */ | |
443 | #define ISO_CODE_LF 0x0A /* line-feed */ | |
444 | #define ISO_CODE_CR 0x0D /* carriage-return */ | |
445 | #define ISO_CODE_SO 0x0E /* shift-out */ | |
446 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
447 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
448 | #define ISO_CODE_ESC 0x1B /* escape */ | |
449 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
450 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
451 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
452 | ||
453 | /* All code (1-byte) of ISO2022 is classified into one of the | |
454 | followings. */ | |
455 | enum iso_code_class_type | |
456 | { | |
457 | ISO_control_0, /* Control codes in the range | |
458 | 0x00..0x1F and 0x7F, except for the | |
459 | following 5 codes. */ | |
df7492f9 KH |
460 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
461 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
462 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
463 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
464 | ISO_control_1, /* Control codes in the range | |
465 | 0x80..0x9F, except for the | |
466 | following 3 codes. */ | |
467 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
468 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
469 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
470 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
471 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
472 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
473 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
474 | }; | |
05e6f5dc | 475 | |
df7492f9 KH |
476 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
477 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 478 | |
df7492f9 KH |
479 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
480 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
481 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 482 | |
df7492f9 KH |
483 | /* If set, reset graphic planes and registers at end-of-line to the |
484 | initial state. */ | |
485 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 486 | |
df7492f9 KH |
487 | /* If set, reset graphic planes and registers before any control |
488 | characters to the initial state. */ | |
489 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 490 | |
df7492f9 KH |
491 | /* If set, encode by 7-bit environment. */ |
492 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 493 | |
df7492f9 KH |
494 | /* If set, use locking-shift function. */ |
495 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 496 | |
df7492f9 KH |
497 | /* If set, use single-shift function. Overwrite |
498 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
499 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 500 | |
df7492f9 KH |
501 | /* If set, use designation escape sequence. */ |
502 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 503 | |
df7492f9 KH |
504 | /* If set, produce revision number sequence. */ |
505 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 506 | |
df7492f9 KH |
507 | /* If set, produce ISO6429's direction specifying sequence. */ |
508 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 509 | |
df7492f9 KH |
510 | /* If set, assume designation states are reset at beginning of line on |
511 | output. */ | |
512 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 513 | |
df7492f9 KH |
514 | /* If set, designation sequence should be placed at beginning of line |
515 | on output. */ | |
516 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 517 | |
df7492f9 KH |
518 | /* If set, do not encode unsafe charactes on output. */ |
519 | #define CODING_ISO_FLAG_SAFE 0x0800 | |
aa72b389 | 520 | |
df7492f9 KH |
521 | /* If set, extra latin codes (128..159) are accepted as a valid code |
522 | on input. */ | |
523 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 524 | |
df7492f9 | 525 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 526 | |
df7492f9 | 527 | #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 |
aa72b389 | 528 | |
bf16eb23 | 529 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 530 | |
bf16eb23 | 531 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 532 | |
bf16eb23 | 533 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 534 | |
df7492f9 KH |
535 | /* A character to be produced on output if encoding of the original |
536 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
537 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 538 | |
4ed46869 | 539 | |
df7492f9 KH |
540 | /* UTF-16 section */ |
541 | #define CODING_UTF_16_BOM(coding) \ | |
542 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 543 | |
df7492f9 KH |
544 | #define CODING_UTF_16_ENDIAN(coding) \ |
545 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 546 | |
df7492f9 KH |
547 | #define CODING_UTF_16_SURROGATE(coding) \ |
548 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 549 | |
4ed46869 | 550 | |
df7492f9 KH |
551 | /* CCL section */ |
552 | #define CODING_CCL_DECODER(coding) \ | |
553 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
554 | #define CODING_CCL_ENCODER(coding) \ | |
555 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
556 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 557 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 558 | |
5a936b46 | 559 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 560 | |
df7492f9 KH |
561 | enum coding_category |
562 | { | |
563 | coding_category_iso_7, | |
564 | coding_category_iso_7_tight, | |
565 | coding_category_iso_8_1, | |
566 | coding_category_iso_8_2, | |
567 | coding_category_iso_7_else, | |
568 | coding_category_iso_8_else, | |
569 | coding_category_utf_8, | |
570 | coding_category_utf_16_auto, | |
571 | coding_category_utf_16_be, | |
572 | coding_category_utf_16_le, | |
573 | coding_category_utf_16_be_nosig, | |
574 | coding_category_utf_16_le_nosig, | |
575 | coding_category_charset, | |
576 | coding_category_sjis, | |
577 | coding_category_big5, | |
578 | coding_category_ccl, | |
579 | coding_category_emacs_mule, | |
580 | /* All above are targets of code detection. */ | |
581 | coding_category_raw_text, | |
582 | coding_category_undecided, | |
583 | coding_category_max | |
584 | }; | |
585 | ||
586 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
587 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
588 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
589 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
590 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
591 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
592 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
593 | #define CATEGORY_MASK_UTF_8 (1 << coding_category_utf_8) | |
b49a1807 | 594 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
595 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
596 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
597 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
598 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
599 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
600 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
601 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
602 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
603 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 604 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
605 | |
606 | /* This value is returned if detect_coding_mask () find nothing other | |
607 | than ASCII characters. */ | |
608 | #define CATEGORY_MASK_ANY \ | |
609 | (CATEGORY_MASK_ISO_7 \ | |
610 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
611 | | CATEGORY_MASK_ISO_8_1 \ | |
612 | | CATEGORY_MASK_ISO_8_2 \ | |
613 | | CATEGORY_MASK_ISO_7_ELSE \ | |
614 | | CATEGORY_MASK_ISO_8_ELSE \ | |
615 | | CATEGORY_MASK_UTF_8 \ | |
616 | | CATEGORY_MASK_UTF_16_BE \ | |
617 | | CATEGORY_MASK_UTF_16_LE \ | |
618 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
619 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
620 | | CATEGORY_MASK_CHARSET \ | |
621 | | CATEGORY_MASK_SJIS \ | |
622 | | CATEGORY_MASK_BIG5 \ | |
623 | | CATEGORY_MASK_CCL \ | |
624 | | CATEGORY_MASK_EMACS_MULE) | |
625 | ||
626 | ||
627 | #define CATEGORY_MASK_ISO_7BIT \ | |
628 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
629 | ||
630 | #define CATEGORY_MASK_ISO_8BIT \ | |
631 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
632 | ||
633 | #define CATEGORY_MASK_ISO_ELSE \ | |
634 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
635 | ||
636 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
637 | (CATEGORY_MASK_ISO_7 \ | |
638 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
639 | | CATEGORY_MASK_ISO_7_ELSE \ | |
640 | | CATEGORY_MASK_ISO_8_ELSE) | |
641 | ||
642 | #define CATEGORY_MASK_ISO \ | |
643 | ( CATEGORY_MASK_ISO_7BIT \ | |
644 | | CATEGORY_MASK_ISO_8BIT \ | |
645 | | CATEGORY_MASK_ISO_ELSE) | |
646 | ||
647 | #define CATEGORY_MASK_UTF_16 \ | |
648 | (CATEGORY_MASK_UTF_16_BE \ | |
649 | | CATEGORY_MASK_UTF_16_LE \ | |
650 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
651 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
652 | ||
653 | ||
654 | /* List of symbols `coding-category-xxx' ordered by priority. This | |
655 | variable is exposed to Emacs Lisp. */ | |
656 | static Lisp_Object Vcoding_category_list; | |
657 | ||
658 | /* Table of coding categories (Lisp symbols). This variable is for | |
659 | internal use oly. */ | |
660 | static Lisp_Object Vcoding_category_table; | |
661 | ||
662 | /* Table of coding-categories ordered by priority. */ | |
663 | static enum coding_category coding_priorities[coding_category_max]; | |
664 | ||
665 | /* Nth element is a coding context for the coding system bound to the | |
666 | Nth coding category. */ | |
667 | static struct coding_system coding_categories[coding_category_max]; | |
668 | ||
df7492f9 KH |
669 | /*** Commonly used macros and functions ***/ |
670 | ||
671 | #ifndef min | |
672 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
673 | #endif | |
674 | #ifndef max | |
675 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
676 | #endif | |
4ed46869 | 677 | |
24a73b0a KH |
678 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
679 | do { \ | |
680 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
681 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 682 | } while (0) |
4ed46869 | 683 | |
4ed46869 | 684 | |
df7492f9 KH |
685 | /* Safely get one byte from the source text pointed by SRC which ends |
686 | at SRC_END, and set C to that byte. If there are not enough bytes | |
065e3595 KH |
687 | in the source, it jumps to `no_more_source'. If multibytep is |
688 | nonzero, and a multibyte character is found at SRC, set C to the | |
689 | negative value of the character code. The caller should declare | |
690 | and set these variables appropriately in advance: | |
691 | src, src_end, multibytep */ | |
aa72b389 | 692 | |
065e3595 KH |
693 | #define ONE_MORE_BYTE(c) \ |
694 | do { \ | |
695 | if (src == src_end) \ | |
696 | { \ | |
697 | if (src_base < src) \ | |
698 | record_conversion_result \ | |
699 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
700 | goto no_more_source; \ | |
701 | } \ | |
702 | c = *src++; \ | |
703 | if (multibytep && (c & 0x80)) \ | |
704 | { \ | |
705 | if ((c & 0xFE) == 0xC0) \ | |
706 | c = ((c & 1) << 6) | *src++; \ | |
707 | else \ | |
708 | { \ | |
709 | c = - string_char (--src, &src, NULL); \ | |
710 | record_conversion_result \ | |
711 | (coding, CODING_RESULT_INVALID_SRC); \ | |
712 | } \ | |
713 | } \ | |
714 | consumed_chars++; \ | |
aa72b389 KH |
715 | } while (0) |
716 | ||
aa72b389 | 717 | |
065e3595 KH |
718 | #define ONE_MORE_BYTE_NO_CHECK(c) \ |
719 | do { \ | |
720 | c = *src++; \ | |
721 | if (multibytep && (c & 0x80)) \ | |
722 | { \ | |
723 | if ((c & 0xFE) == 0xC0) \ | |
724 | c = ((c & 1) << 6) | *src++; \ | |
725 | else \ | |
726 | { \ | |
727 | c = - string_char (--src, &src, NULL); \ | |
728 | record_conversion_result \ | |
729 | (coding, CODING_RESULT_INVALID_SRC); \ | |
730 | } \ | |
731 | } \ | |
732 | consumed_chars++; \ | |
aa72b389 KH |
733 | } while (0) |
734 | ||
aa72b389 | 735 | |
df7492f9 KH |
736 | /* Store a byte C in the place pointed by DST and increment DST to the |
737 | next free point, and increment PRODUCED_CHARS. The caller should | |
738 | assure that C is 0..127, and declare and set the variable `dst' | |
739 | appropriately in advance. | |
740 | */ | |
aa72b389 KH |
741 | |
742 | ||
df7492f9 KH |
743 | #define EMIT_ONE_ASCII_BYTE(c) \ |
744 | do { \ | |
745 | produced_chars++; \ | |
746 | *dst++ = (c); \ | |
b6871cc7 | 747 | } while (0) |
aa72b389 KH |
748 | |
749 | ||
df7492f9 | 750 | /* Like EMIT_ONE_ASCII_BYTE byt store two bytes; C1 and C2. */ |
aa72b389 | 751 | |
df7492f9 KH |
752 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
753 | do { \ | |
754 | produced_chars += 2; \ | |
755 | *dst++ = (c1), *dst++ = (c2); \ | |
756 | } while (0) | |
aa72b389 KH |
757 | |
758 | ||
df7492f9 KH |
759 | /* Store a byte C in the place pointed by DST and increment DST to the |
760 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is | |
761 | nonzero, store in an appropriate multibyte from. The caller should | |
762 | declare and set the variables `dst' and `multibytep' appropriately | |
763 | in advance. */ | |
764 | ||
765 | #define EMIT_ONE_BYTE(c) \ | |
766 | do { \ | |
767 | produced_chars++; \ | |
768 | if (multibytep) \ | |
769 | { \ | |
770 | int ch = (c); \ | |
771 | if (ch >= 0x80) \ | |
772 | ch = BYTE8_TO_CHAR (ch); \ | |
773 | CHAR_STRING_ADVANCE (ch, dst); \ | |
774 | } \ | |
775 | else \ | |
776 | *dst++ = (c); \ | |
aa72b389 | 777 | } while (0) |
aa72b389 | 778 | |
aa72b389 | 779 | |
df7492f9 | 780 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 781 | |
e19c3639 KH |
782 | #define EMIT_TWO_BYTES(c1, c2) \ |
783 | do { \ | |
784 | produced_chars += 2; \ | |
785 | if (multibytep) \ | |
786 | { \ | |
787 | int ch; \ | |
788 | \ | |
789 | ch = (c1); \ | |
790 | if (ch >= 0x80) \ | |
791 | ch = BYTE8_TO_CHAR (ch); \ | |
792 | CHAR_STRING_ADVANCE (ch, dst); \ | |
793 | ch = (c2); \ | |
794 | if (ch >= 0x80) \ | |
795 | ch = BYTE8_TO_CHAR (ch); \ | |
796 | CHAR_STRING_ADVANCE (ch, dst); \ | |
797 | } \ | |
798 | else \ | |
799 | { \ | |
800 | *dst++ = (c1); \ | |
801 | *dst++ = (c2); \ | |
802 | } \ | |
aa72b389 KH |
803 | } while (0) |
804 | ||
805 | ||
df7492f9 KH |
806 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
807 | do { \ | |
808 | EMIT_ONE_BYTE (c1); \ | |
809 | EMIT_TWO_BYTES (c2, c3); \ | |
810 | } while (0) | |
aa72b389 | 811 | |
aa72b389 | 812 | |
df7492f9 KH |
813 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
814 | do { \ | |
815 | EMIT_TWO_BYTES (c1, c2); \ | |
816 | EMIT_TWO_BYTES (c3, c4); \ | |
817 | } while (0) | |
aa72b389 | 818 | |
aa72b389 | 819 | |
f6cbaf43 KH |
820 | /* Prototypes for static functions. */ |
821 | static void record_conversion_result P_ ((struct coding_system *coding, | |
822 | enum coding_result_code result)); | |
823 | static int detect_coding_utf_8 P_ ((struct coding_system *, | |
824 | struct coding_detection_info *info)); | |
825 | static void decode_coding_utf_8 P_ ((struct coding_system *)); | |
826 | static int encode_coding_utf_8 P_ ((struct coding_system *)); | |
827 | ||
828 | static int detect_coding_utf_16 P_ ((struct coding_system *, | |
829 | struct coding_detection_info *info)); | |
830 | static void decode_coding_utf_16 P_ ((struct coding_system *)); | |
831 | static int encode_coding_utf_16 P_ ((struct coding_system *)); | |
832 | ||
833 | static int detect_coding_iso_2022 P_ ((struct coding_system *, | |
834 | struct coding_detection_info *info)); | |
835 | static void decode_coding_iso_2022 P_ ((struct coding_system *)); | |
836 | static int encode_coding_iso_2022 P_ ((struct coding_system *)); | |
837 | ||
838 | static int detect_coding_emacs_mule P_ ((struct coding_system *, | |
839 | struct coding_detection_info *info)); | |
840 | static void decode_coding_emacs_mule P_ ((struct coding_system *)); | |
841 | static int encode_coding_emacs_mule P_ ((struct coding_system *)); | |
842 | ||
843 | static int detect_coding_sjis P_ ((struct coding_system *, | |
844 | struct coding_detection_info *info)); | |
845 | static void decode_coding_sjis P_ ((struct coding_system *)); | |
846 | static int encode_coding_sjis P_ ((struct coding_system *)); | |
847 | ||
848 | static int detect_coding_big5 P_ ((struct coding_system *, | |
849 | struct coding_detection_info *info)); | |
850 | static void decode_coding_big5 P_ ((struct coding_system *)); | |
851 | static int encode_coding_big5 P_ ((struct coding_system *)); | |
852 | ||
853 | static int detect_coding_ccl P_ ((struct coding_system *, | |
854 | struct coding_detection_info *info)); | |
855 | static void decode_coding_ccl P_ ((struct coding_system *)); | |
856 | static int encode_coding_ccl P_ ((struct coding_system *)); | |
857 | ||
858 | static void decode_coding_raw_text P_ ((struct coding_system *)); | |
859 | static int encode_coding_raw_text P_ ((struct coding_system *)); | |
860 | ||
861 | static void coding_set_source P_ ((struct coding_system *)); | |
862 | static void coding_set_destination P_ ((struct coding_system *)); | |
863 | static void coding_alloc_by_realloc P_ ((struct coding_system *, EMACS_INT)); | |
864 | static void coding_alloc_by_making_gap P_ ((struct coding_system *, | |
865 | EMACS_INT)); | |
866 | static unsigned char *alloc_destination P_ ((struct coding_system *, | |
867 | EMACS_INT, unsigned char *)); | |
868 | static void setup_iso_safe_charsets P_ ((Lisp_Object)); | |
869 | static unsigned char *encode_designation_at_bol P_ ((struct coding_system *, | |
870 | int *, int *, | |
871 | unsigned char *)); | |
872 | static int detect_eol P_ ((const unsigned char *, | |
873 | EMACS_INT, enum coding_category)); | |
874 | static Lisp_Object adjust_coding_eol_type P_ ((struct coding_system *, int)); | |
875 | static void decode_eol P_ ((struct coding_system *)); | |
876 | static Lisp_Object get_translation_table P_ ((Lisp_Object, int, int *)); | |
877 | static Lisp_Object get_translation P_ ((Lisp_Object, int *, int *, | |
878 | int, int *, int *)); | |
879 | static int produce_chars P_ ((struct coding_system *, Lisp_Object, int)); | |
880 | static INLINE void produce_composition P_ ((struct coding_system *, int *, | |
881 | EMACS_INT)); | |
882 | static INLINE void produce_charset P_ ((struct coding_system *, int *, | |
883 | EMACS_INT)); | |
884 | static void produce_annotation P_ ((struct coding_system *, EMACS_INT)); | |
885 | static int decode_coding P_ ((struct coding_system *)); | |
886 | static INLINE int *handle_composition_annotation P_ ((EMACS_INT, EMACS_INT, | |
887 | struct coding_system *, | |
888 | int *, EMACS_INT *)); | |
889 | static INLINE int *handle_charset_annotation P_ ((EMACS_INT, EMACS_INT, | |
890 | struct coding_system *, | |
891 | int *, EMACS_INT *)); | |
892 | static void consume_chars P_ ((struct coding_system *, Lisp_Object, int)); | |
893 | static int encode_coding P_ ((struct coding_system *)); | |
894 | static Lisp_Object make_conversion_work_buffer P_ ((int)); | |
895 | static Lisp_Object code_conversion_restore P_ ((Lisp_Object)); | |
896 | static INLINE int char_encodable_p P_ ((int, Lisp_Object)); | |
897 | static Lisp_Object make_subsidiaries P_ ((Lisp_Object)); | |
898 | ||
065e3595 KH |
899 | static void |
900 | record_conversion_result (struct coding_system *coding, | |
901 | enum coding_result_code result) | |
902 | { | |
903 | coding->result = result; | |
904 | switch (result) | |
905 | { | |
906 | case CODING_RESULT_INSUFFICIENT_SRC: | |
907 | Vlast_code_conversion_error = Qinsufficient_source; | |
908 | break; | |
909 | case CODING_RESULT_INCONSISTENT_EOL: | |
910 | Vlast_code_conversion_error = Qinconsistent_eol; | |
911 | break; | |
912 | case CODING_RESULT_INVALID_SRC: | |
913 | Vlast_code_conversion_error = Qinvalid_source; | |
914 | break; | |
915 | case CODING_RESULT_INTERRUPT: | |
916 | Vlast_code_conversion_error = Qinterrupted; | |
917 | break; | |
918 | case CODING_RESULT_INSUFFICIENT_MEM: | |
919 | Vlast_code_conversion_error = Qinsufficient_memory; | |
920 | break; | |
921 | } | |
922 | } | |
923 | ||
df7492f9 KH |
924 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
925 | do { \ | |
926 | charset_map_loaded = 0; \ | |
927 | c = DECODE_CHAR (charset, code); \ | |
928 | if (charset_map_loaded) \ | |
929 | { \ | |
8f924df7 | 930 | const unsigned char *orig = coding->source; \ |
df7492f9 KH |
931 | EMACS_INT offset; \ |
932 | \ | |
933 | coding_set_source (coding); \ | |
934 | offset = coding->source - orig; \ | |
935 | src += offset; \ | |
936 | src_base += offset; \ | |
937 | src_end += offset; \ | |
938 | } \ | |
aa72b389 KH |
939 | } while (0) |
940 | ||
941 | ||
df7492f9 KH |
942 | #define ASSURE_DESTINATION(bytes) \ |
943 | do { \ | |
944 | if (dst + (bytes) >= dst_end) \ | |
945 | { \ | |
946 | int more_bytes = charbuf_end - charbuf + (bytes); \ | |
947 | \ | |
948 | dst = alloc_destination (coding, more_bytes, dst); \ | |
949 | dst_end = coding->destination + coding->dst_bytes; \ | |
950 | } \ | |
951 | } while (0) | |
aa72b389 | 952 | |
aa72b389 | 953 | |
aa72b389 | 954 | |
df7492f9 KH |
955 | static void |
956 | coding_set_source (coding) | |
aa72b389 | 957 | struct coding_system *coding; |
aa72b389 | 958 | { |
df7492f9 KH |
959 | if (BUFFERP (coding->src_object)) |
960 | { | |
2cb26057 | 961 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 962 | |
df7492f9 | 963 | if (coding->src_pos < 0) |
2cb26057 | 964 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 965 | else |
2cb26057 | 966 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 967 | } |
df7492f9 | 968 | else if (STRINGP (coding->src_object)) |
aa72b389 | 969 | { |
8f924df7 | 970 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 971 | } |
df7492f9 KH |
972 | else |
973 | /* Otherwise, the source is C string and is never relocated | |
974 | automatically. Thus we don't have to update anything. */ | |
975 | ; | |
976 | } | |
aa72b389 | 977 | |
df7492f9 KH |
978 | static void |
979 | coding_set_destination (coding) | |
980 | struct coding_system *coding; | |
981 | { | |
982 | if (BUFFERP (coding->dst_object)) | |
aa72b389 | 983 | { |
df7492f9 | 984 | if (coding->src_pos < 0) |
aa72b389 | 985 | { |
28f67a95 KH |
986 | coding->destination = BEG_ADDR + coding->dst_pos_byte - 1; |
987 | coding->dst_bytes = (GAP_END_ADDR | |
988 | - (coding->src_bytes - coding->consumed) | |
989 | - coding->destination); | |
aa72b389 | 990 | } |
df7492f9 | 991 | else |
28f67a95 KH |
992 | { |
993 | /* We are sure that coding->dst_pos_byte is before the gap | |
994 | of the buffer. */ | |
995 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
996 | + coding->dst_pos_byte - 1); | |
997 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) | |
998 | - coding->destination); | |
999 | } | |
df7492f9 KH |
1000 | } |
1001 | else | |
1002 | /* Otherwise, the destination is C string and is never relocated | |
1003 | automatically. Thus we don't have to update anything. */ | |
1004 | ; | |
1005 | } | |
1006 | ||
1007 | ||
1008 | static void | |
1009 | coding_alloc_by_realloc (coding, bytes) | |
1010 | struct coding_system *coding; | |
1011 | EMACS_INT bytes; | |
1012 | { | |
1013 | coding->destination = (unsigned char *) xrealloc (coding->destination, | |
1014 | coding->dst_bytes + bytes); | |
1015 | coding->dst_bytes += bytes; | |
1016 | } | |
1017 | ||
1018 | static void | |
1019 | coding_alloc_by_making_gap (coding, bytes) | |
1020 | struct coding_system *coding; | |
1021 | EMACS_INT bytes; | |
1022 | { | |
2c78b7e1 KH |
1023 | if (BUFFERP (coding->dst_object) |
1024 | && EQ (coding->src_object, coding->dst_object)) | |
df7492f9 KH |
1025 | { |
1026 | EMACS_INT add = coding->src_bytes - coding->consumed; | |
1027 | ||
1028 | GAP_SIZE -= add; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
1029 | make_gap (bytes); | |
1030 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
1031 | } | |
1032 | else | |
1033 | { | |
2c78b7e1 KH |
1034 | Lisp_Object this_buffer; |
1035 | ||
1036 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
1037 | set_buffer_internal (XBUFFER (coding->dst_object)); |
1038 | make_gap (bytes); | |
1039 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 1040 | } |
df7492f9 | 1041 | } |
8f924df7 | 1042 | |
df7492f9 KH |
1043 | |
1044 | static unsigned char * | |
1045 | alloc_destination (coding, nbytes, dst) | |
1046 | struct coding_system *coding; | |
3e139625 | 1047 | EMACS_INT nbytes; |
df7492f9 KH |
1048 | unsigned char *dst; |
1049 | { | |
1050 | EMACS_INT offset = dst - coding->destination; | |
1051 | ||
1052 | if (BUFFERP (coding->dst_object)) | |
1053 | coding_alloc_by_making_gap (coding, nbytes); | |
aa72b389 | 1054 | else |
df7492f9 | 1055 | coding_alloc_by_realloc (coding, nbytes); |
065e3595 | 1056 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1057 | coding_set_destination (coding); |
1058 | dst = coding->destination + offset; | |
1059 | return dst; | |
1060 | } | |
aa72b389 | 1061 | |
ff0dacd7 KH |
1062 | /** Macros for annotations. */ |
1063 | ||
1064 | /* Maximum length of annotation data (sum of annotations for | |
1065 | composition and charset). */ | |
69a80ea3 | 1066 | #define MAX_ANNOTATION_LENGTH (4 + (MAX_COMPOSITION_COMPONENTS * 2) - 1 + 4) |
ff0dacd7 KH |
1067 | |
1068 | /* An annotation data is stored in the array coding->charbuf in this | |
1069 | format: | |
69a80ea3 | 1070 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1071 | LENGTH is the number of elements in the annotation. |
1072 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1073 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1074 | |
1075 | The format of the following elements depend on ANNOTATION_MASK. | |
1076 | ||
1077 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1078 | follows: | |
1079 | ... METHOD [ COMPOSITION-COMPONENTS ... ] | |
1080 | METHOD is one of enum composition_method. | |
1081 | Optionnal COMPOSITION-COMPONENTS are characters and composition | |
1082 | rules. | |
1083 | ||
1084 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
1085 | follows. */ | |
1086 | ||
69a80ea3 | 1087 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1088 | do { \ |
1089 | *(buf)++ = -(len); \ | |
1090 | *(buf)++ = (mask); \ | |
69a80ea3 | 1091 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1092 | coding->annotated = 1; \ |
1093 | } while (0); | |
1094 | ||
69a80ea3 KH |
1095 | #define ADD_COMPOSITION_DATA(buf, nchars, method) \ |
1096 | do { \ | |
1097 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ | |
1098 | *buf++ = method; \ | |
ff0dacd7 KH |
1099 | } while (0) |
1100 | ||
1101 | ||
69a80ea3 KH |
1102 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1103 | do { \ | |
1104 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1105 | *buf++ = id; \ | |
ff0dacd7 KH |
1106 | } while (0) |
1107 | ||
df7492f9 KH |
1108 | \f |
1109 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1110 | ||
1111 | ||
1112 | ||
1113 | \f | |
1114 | /*** 3. UTF-8 ***/ | |
1115 | ||
1116 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1117 | Check if a text is encoded in UTF-8. If it is, return 1, else |
1118 | return 0. */ | |
df7492f9 KH |
1119 | |
1120 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1121 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1122 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1123 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1124 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1125 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1126 | ||
1127 | static int | |
ff0dacd7 | 1128 | detect_coding_utf_8 (coding, detect_info) |
df7492f9 | 1129 | struct coding_system *coding; |
ff0dacd7 | 1130 | struct coding_detection_info *detect_info; |
df7492f9 | 1131 | { |
065e3595 | 1132 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1133 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1134 | int multibytep = coding->src_multibyte; |
1135 | int consumed_chars = 0; | |
1136 | int found = 0; | |
1137 | ||
ff0dacd7 | 1138 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1139 | /* A coding system of this category is always ASCII compatible. */ |
1140 | src += coding->head_ascii; | |
1141 | ||
1142 | while (1) | |
aa72b389 | 1143 | { |
df7492f9 | 1144 | int c, c1, c2, c3, c4; |
aa72b389 | 1145 | |
065e3595 | 1146 | src_base = src; |
df7492f9 | 1147 | ONE_MORE_BYTE (c); |
065e3595 | 1148 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1149 | continue; |
1150 | ONE_MORE_BYTE (c1); | |
065e3595 | 1151 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1152 | break; |
1153 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1154 | { |
ff0dacd7 | 1155 | found = CATEGORY_MASK_UTF_8; |
df7492f9 | 1156 | continue; |
aa72b389 | 1157 | } |
df7492f9 | 1158 | ONE_MORE_BYTE (c2); |
065e3595 | 1159 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1160 | break; |
1161 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1162 | { |
ff0dacd7 | 1163 | found = CATEGORY_MASK_UTF_8; |
df7492f9 | 1164 | continue; |
aa72b389 | 1165 | } |
df7492f9 | 1166 | ONE_MORE_BYTE (c3); |
065e3595 | 1167 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1168 | break; |
1169 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1170 | { |
ff0dacd7 | 1171 | found = CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1172 | continue; |
1173 | } | |
1174 | ONE_MORE_BYTE (c4); | |
065e3595 | 1175 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1176 | break; |
1177 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1178 | { | |
ff0dacd7 | 1179 | found = CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1180 | continue; |
1181 | } | |
1182 | break; | |
aa72b389 | 1183 | } |
ff0dacd7 | 1184 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1185 | return 0; |
aa72b389 | 1186 | |
df7492f9 | 1187 | no_more_source: |
065e3595 | 1188 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1189 | { |
ff0dacd7 | 1190 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1191 | return 0; |
aa72b389 | 1192 | } |
ff0dacd7 KH |
1193 | detect_info->found |= found; |
1194 | return 1; | |
aa72b389 KH |
1195 | } |
1196 | ||
4ed46869 | 1197 | |
b73bfc1c | 1198 | static void |
df7492f9 | 1199 | decode_coding_utf_8 (coding) |
b73bfc1c | 1200 | struct coding_system *coding; |
b73bfc1c | 1201 | { |
8f924df7 KH |
1202 | const unsigned char *src = coding->source + coding->consumed; |
1203 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1204 | const unsigned char *src_base; | |
69a80ea3 KH |
1205 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1206 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
1207 | int consumed_chars = 0, consumed_chars_base; |
1208 | int multibytep = coding->src_multibyte; | |
24a73b0a | 1209 | Lisp_Object attr, charset_list; |
4ed46869 | 1210 | |
24a73b0a | 1211 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 KH |
1212 | |
1213 | while (1) | |
b73bfc1c | 1214 | { |
df7492f9 | 1215 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1216 | |
df7492f9 KH |
1217 | src_base = src; |
1218 | consumed_chars_base = consumed_chars; | |
4af310db | 1219 | |
df7492f9 KH |
1220 | if (charbuf >= charbuf_end) |
1221 | break; | |
1222 | ||
1223 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1224 | if (c1 < 0) |
1225 | { | |
1226 | c = - c1; | |
1227 | } | |
1228 | else if (UTF_8_1_OCTET_P(c1)) | |
df7492f9 KH |
1229 | { |
1230 | c = c1; | |
4af310db | 1231 | } |
df7492f9 | 1232 | else |
4af310db | 1233 | { |
df7492f9 | 1234 | ONE_MORE_BYTE (c2); |
065e3595 | 1235 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1236 | goto invalid_code; |
1237 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1238 | { |
b0edb2c5 DL |
1239 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1240 | /* Reject overlong sequences here and below. Encoders | |
1241 | producing them are incorrect, they can be misleading, | |
1242 | and they mess up read/write invariance. */ | |
1243 | if (c < 128) | |
1244 | goto invalid_code; | |
4af310db | 1245 | } |
df7492f9 | 1246 | else |
aa72b389 | 1247 | { |
df7492f9 | 1248 | ONE_MORE_BYTE (c3); |
065e3595 | 1249 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1250 | goto invalid_code; |
1251 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1252 | { |
1253 | c = (((c1 & 0xF) << 12) | |
1254 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1255 | if (c < 0x800 |
1256 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1257 | goto invalid_code; |
1258 | } | |
df7492f9 KH |
1259 | else |
1260 | { | |
1261 | ONE_MORE_BYTE (c4); | |
065e3595 | 1262 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1263 | goto invalid_code; |
1264 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1265 | { |
df7492f9 KH |
1266 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1267 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1268 | if (c < 0x10000) |
1269 | goto invalid_code; | |
1270 | } | |
df7492f9 KH |
1271 | else |
1272 | { | |
1273 | ONE_MORE_BYTE (c5); | |
065e3595 | 1274 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1275 | goto invalid_code; |
1276 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1277 | { | |
1278 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1279 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1280 | | (c5 & 0x3F)); | |
b0edb2c5 | 1281 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1282 | goto invalid_code; |
1283 | } | |
1284 | else | |
1285 | goto invalid_code; | |
1286 | } | |
1287 | } | |
aa72b389 | 1288 | } |
b73bfc1c | 1289 | } |
df7492f9 KH |
1290 | |
1291 | *charbuf++ = c; | |
1292 | continue; | |
1293 | ||
1294 | invalid_code: | |
1295 | src = src_base; | |
1296 | consumed_chars = consumed_chars_base; | |
1297 | ONE_MORE_BYTE (c); | |
1298 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1299 | coding->errors++; | |
aa72b389 KH |
1300 | } |
1301 | ||
df7492f9 KH |
1302 | no_more_source: |
1303 | coding->consumed_char += consumed_chars_base; | |
1304 | coding->consumed = src_base - coding->source; | |
1305 | coding->charbuf_used = charbuf - coding->charbuf; | |
1306 | } | |
1307 | ||
1308 | ||
1309 | static int | |
1310 | encode_coding_utf_8 (coding) | |
1311 | struct coding_system *coding; | |
1312 | { | |
1313 | int multibytep = coding->dst_multibyte; | |
1314 | int *charbuf = coding->charbuf; | |
1315 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1316 | unsigned char *dst = coding->destination + coding->produced; | |
1317 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
e19c3639 | 1318 | int produced_chars = 0; |
df7492f9 KH |
1319 | int c; |
1320 | ||
1321 | if (multibytep) | |
aa72b389 | 1322 | { |
df7492f9 KH |
1323 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1324 | ||
1325 | while (charbuf < charbuf_end) | |
b73bfc1c | 1326 | { |
df7492f9 | 1327 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1328 | |
df7492f9 KH |
1329 | ASSURE_DESTINATION (safe_room); |
1330 | c = *charbuf++; | |
28f67a95 KH |
1331 | if (CHAR_BYTE8_P (c)) |
1332 | { | |
1333 | c = CHAR_TO_BYTE8 (c); | |
1334 | EMIT_ONE_BYTE (c); | |
1335 | } | |
1336 | else | |
1337 | { | |
1338 | CHAR_STRING_ADVANCE (c, pend); | |
1339 | for (p = str; p < pend; p++) | |
1340 | EMIT_ONE_BYTE (*p); | |
1341 | } | |
b73bfc1c | 1342 | } |
aa72b389 | 1343 | } |
df7492f9 KH |
1344 | else |
1345 | { | |
1346 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1347 | ||
1348 | while (charbuf < charbuf_end) | |
b73bfc1c | 1349 | { |
df7492f9 KH |
1350 | ASSURE_DESTINATION (safe_room); |
1351 | c = *charbuf++; | |
f03caae0 KH |
1352 | if (CHAR_BYTE8_P (c)) |
1353 | *dst++ = CHAR_TO_BYTE8 (c); | |
1354 | else | |
1355 | dst += CHAR_STRING (c, dst); | |
df7492f9 | 1356 | produced_chars++; |
4ed46869 KH |
1357 | } |
1358 | } | |
065e3595 | 1359 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1360 | coding->produced_char += produced_chars; |
1361 | coding->produced = dst - coding->destination; | |
1362 | return 0; | |
4ed46869 KH |
1363 | } |
1364 | ||
b73bfc1c | 1365 | |
df7492f9 | 1366 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
1367 | Check if a text is encoded in one of UTF-16 based coding systems. |
1368 | If it is, return 1, else return 0. */ | |
aa72b389 | 1369 | |
df7492f9 KH |
1370 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1371 | (((val) & 0xFC00) == 0xD800) | |
1372 | ||
1373 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1374 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1375 | |
df7492f9 KH |
1376 | #define UTF_16_INVALID_P(val) \ |
1377 | (((val) == 0xFFFE) \ | |
1378 | || ((val) == 0xFFFF) \ | |
1379 | || UTF_16_LOW_SURROGATE_P (val)) | |
aa72b389 | 1380 | |
aa72b389 | 1381 | |
df7492f9 | 1382 | static int |
ff0dacd7 | 1383 | detect_coding_utf_16 (coding, detect_info) |
aa72b389 | 1384 | struct coding_system *coding; |
ff0dacd7 | 1385 | struct coding_detection_info *detect_info; |
aa72b389 | 1386 | { |
8f924df7 KH |
1387 | const unsigned char *src = coding->source, *src_base = src; |
1388 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
1389 | int multibytep = coding->src_multibyte; |
1390 | int consumed_chars = 0; | |
1391 | int c1, c2; | |
aa72b389 | 1392 | |
ff0dacd7 | 1393 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1394 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1395 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1396 | { |
1397 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1398 | return 0; | |
1399 | } | |
24a73b0a | 1400 | |
df7492f9 KH |
1401 | ONE_MORE_BYTE (c1); |
1402 | ONE_MORE_BYTE (c2); | |
df7492f9 | 1403 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1404 | { |
b49a1807 KH |
1405 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1406 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1407 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1408 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1409 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1410 | } |
df7492f9 | 1411 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1412 | { |
b49a1807 KH |
1413 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1414 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1415 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1416 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1417 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1418 | } | |
065e3595 | 1419 | else if (c1 >= 0 && c2 >= 0) |
24a73b0a | 1420 | { |
24a73b0a KH |
1421 | detect_info->rejected |
1422 | |= (CATEGORY_MASK_UTF_16_BE | CATEGORY_MASK_UTF_16_LE); | |
ff0dacd7 | 1423 | } |
df7492f9 | 1424 | no_more_source: |
ff0dacd7 | 1425 | return 1; |
df7492f9 | 1426 | } |
aa72b389 | 1427 | |
df7492f9 KH |
1428 | static void |
1429 | decode_coding_utf_16 (coding) | |
1430 | struct coding_system *coding; | |
1431 | { | |
8f924df7 KH |
1432 | const unsigned char *src = coding->source + coding->consumed; |
1433 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1434 | const unsigned char *src_base; | |
69a80ea3 KH |
1435 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1436 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
1437 | int consumed_chars = 0, consumed_chars_base; |
1438 | int multibytep = coding->src_multibyte; | |
1439 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1440 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); | |
1441 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
24a73b0a | 1442 | Lisp_Object attr, charset_list; |
df7492f9 | 1443 | |
24a73b0a | 1444 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1445 | |
b49a1807 | 1446 | if (bom == utf_16_with_bom) |
aa72b389 | 1447 | { |
df7492f9 | 1448 | int c, c1, c2; |
4af310db | 1449 | |
aa72b389 | 1450 | src_base = src; |
df7492f9 KH |
1451 | ONE_MORE_BYTE (c1); |
1452 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1453 | c = (c1 << 8) | c2; |
aa72b389 | 1454 | |
b49a1807 KH |
1455 | if (endian == utf_16_big_endian |
1456 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1457 | { |
b49a1807 KH |
1458 | /* The first two bytes are not BOM. Treat them as bytes |
1459 | for a normal character. */ | |
1460 | src = src_base; | |
1461 | coding->errors++; | |
aa72b389 | 1462 | } |
b49a1807 KH |
1463 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1464 | } | |
1465 | else if (bom == utf_16_detect_bom) | |
1466 | { | |
1467 | /* We have already tried to detect BOM and failed in | |
1468 | detect_coding. */ | |
1469 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; | |
df7492f9 | 1470 | } |
aa72b389 | 1471 | |
df7492f9 KH |
1472 | while (1) |
1473 | { | |
1474 | int c, c1, c2; | |
1475 | ||
1476 | src_base = src; | |
1477 | consumed_chars_base = consumed_chars; | |
1478 | ||
1479 | if (charbuf + 2 >= charbuf_end) | |
1480 | break; | |
1481 | ||
1482 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1483 | if (c1 < 0) |
1484 | { | |
1485 | *charbuf++ = -c1; | |
1486 | continue; | |
1487 | } | |
df7492f9 | 1488 | ONE_MORE_BYTE (c2); |
065e3595 KH |
1489 | if (c2 < 0) |
1490 | { | |
1491 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1492 | *charbuf++ = -c2; | |
1493 | continue; | |
1494 | } | |
df7492f9 | 1495 | c = (endian == utf_16_big_endian |
e19c3639 | 1496 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
df7492f9 | 1497 | if (surrogate) |
fd3ae0b9 | 1498 | { |
df7492f9 | 1499 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1500 | { |
df7492f9 KH |
1501 | if (endian == utf_16_big_endian) |
1502 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1503 | else | |
1504 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1505 | *charbuf++ = c1; | |
1506 | *charbuf++ = c2; | |
1507 | coding->errors++; | |
1508 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1509 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1510 | else |
df7492f9 | 1511 | *charbuf++ = c; |
fd3ae0b9 KH |
1512 | } |
1513 | else | |
df7492f9 KH |
1514 | { |
1515 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1516 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1517 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1518 | } |
fd3ae0b9 | 1519 | } |
aa72b389 | 1520 | else |
df7492f9 KH |
1521 | { |
1522 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1523 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1524 | else | |
1525 | *charbuf++ = c; | |
8f924df7 | 1526 | } |
aa72b389 | 1527 | } |
df7492f9 KH |
1528 | |
1529 | no_more_source: | |
1530 | coding->consumed_char += consumed_chars_base; | |
1531 | coding->consumed = src_base - coding->source; | |
1532 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1533 | } |
b73bfc1c | 1534 | |
df7492f9 KH |
1535 | static int |
1536 | encode_coding_utf_16 (coding) | |
1537 | struct coding_system *coding; | |
1538 | { | |
1539 | int multibytep = coding->dst_multibyte; | |
1540 | int *charbuf = coding->charbuf; | |
1541 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1542 | unsigned char *dst = coding->destination + coding->produced; | |
1543 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1544 | int safe_room = 8; | |
1545 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1546 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; | |
1547 | int produced_chars = 0; | |
24a73b0a | 1548 | Lisp_Object attrs, charset_list; |
df7492f9 | 1549 | int c; |
4ed46869 | 1550 | |
24a73b0a | 1551 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 1552 | |
b49a1807 | 1553 | if (bom != utf_16_without_bom) |
df7492f9 KH |
1554 | { |
1555 | ASSURE_DESTINATION (safe_room); | |
1556 | if (big_endian) | |
df7492f9 | 1557 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1558 | else |
1559 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
df7492f9 KH |
1560 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1561 | } | |
1562 | ||
1563 | while (charbuf < charbuf_end) | |
1564 | { | |
1565 | ASSURE_DESTINATION (safe_room); | |
1566 | c = *charbuf++; | |
e19c3639 KH |
1567 | if (c >= MAX_UNICODE_CHAR) |
1568 | c = coding->default_char; | |
df7492f9 KH |
1569 | |
1570 | if (c < 0x10000) | |
1571 | { | |
1572 | if (big_endian) | |
1573 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1574 | else | |
1575 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1576 | } | |
1577 | else | |
1578 | { | |
1579 | int c1, c2; | |
1580 | ||
1581 | c -= 0x10000; | |
1582 | c1 = (c >> 10) + 0xD800; | |
1583 | c2 = (c & 0x3FF) + 0xDC00; | |
1584 | if (big_endian) | |
1585 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1586 | else | |
1587 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1588 | } | |
1589 | } | |
065e3595 | 1590 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1591 | coding->produced = dst - coding->destination; |
1592 | coding->produced_char += produced_chars; | |
1593 | return 0; | |
1594 | } | |
1595 | ||
1596 | \f | |
1597 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1598 | ||
1599 | /* Emacs' internal format for representation of multiple character | |
1600 | sets is a kind of multi-byte encoding, i.e. characters are | |
1601 | represented by variable-length sequences of one-byte codes. | |
1602 | ||
1603 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1604 | represented by one-byte sequences which are their ASCII codes, in | |
1605 | the range 0x00 through 0x7F. | |
1606 | ||
1607 | 8-bit characters of the range 0x80..0x9F are represented by | |
1608 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1609 | code + 0x20). | |
1610 | ||
1611 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1612 | one-byte sequences which are their 8-bit code. | |
1613 | ||
1614 | The other characters are represented by a sequence of `base | |
1615 | leading-code', optional `extended leading-code', and one or two | |
1616 | `position-code's. The length of the sequence is determined by the | |
1617 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1618 | whereas extended leading-code and position-code take the range 0xA0 | |
1619 | through 0xFF. See `charset.h' for more details about leading-code | |
1620 | and position-code. | |
1621 | ||
1622 | --- CODE RANGE of Emacs' internal format --- | |
1623 | character set range | |
1624 | ------------- ----- | |
1625 | ascii 0x00..0x7F | |
1626 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1627 | eight-bit-graphic 0xA0..0xBF | |
1628 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1629 | --------------------------------------------- | |
1630 | ||
1631 | As this is the internal character representation, the format is | |
1632 | usually not used externally (i.e. in a file or in a data sent to a | |
1633 | process). But, it is possible to have a text externally in this | |
1634 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1635 | ||
1636 | In that case, a sequence of one-byte codes has a slightly different | |
1637 | form. | |
1638 | ||
1639 | At first, all characters in eight-bit-control are represented by | |
1640 | one-byte sequences which are their 8-bit code. | |
1641 | ||
1642 | Next, character composition data are represented by the byte | |
1643 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1644 | where, | |
1645 | METHOD is 0xF0 plus one of composition method (enum | |
1646 | composition_method), | |
1647 | ||
1648 | BYTES is 0xA0 plus a byte length of this composition data, | |
1649 | ||
1650 | CHARS is 0x20 plus a number of characters composed by this | |
1651 | data, | |
1652 | ||
1653 | COMPONENTs are characters of multibye form or composition | |
1654 | rules encoded by two-byte of ASCII codes. | |
1655 | ||
1656 | In addition, for backward compatibility, the following formats are | |
1657 | also recognized as composition data on decoding. | |
1658 | ||
1659 | 0x80 MSEQ ... | |
1660 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1661 | ||
1662 | Here, | |
1663 | MSEQ is a multibyte form but in these special format: | |
1664 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1665 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1666 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1667 | represents a composition rule. | |
1668 | */ | |
1669 | ||
1670 | char emacs_mule_bytes[256]; | |
1671 | ||
df7492f9 | 1672 | int |
ff0dacd7 | 1673 | emacs_mule_char (coding, src, nbytes, nchars, id) |
df7492f9 | 1674 | struct coding_system *coding; |
065e3595 | 1675 | const unsigned char *src; |
ff0dacd7 | 1676 | int *nbytes, *nchars, *id; |
df7492f9 | 1677 | { |
8f924df7 KH |
1678 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1679 | const unsigned char *src_base = src; | |
df7492f9 | 1680 | int multibytep = coding->src_multibyte; |
df7492f9 KH |
1681 | struct charset *charset; |
1682 | unsigned code; | |
1683 | int c; | |
1684 | int consumed_chars = 0; | |
1685 | ||
1686 | ONE_MORE_BYTE (c); | |
065e3595 | 1687 | if (c < 0) |
df7492f9 | 1688 | { |
065e3595 KH |
1689 | c = -c; |
1690 | charset = emacs_mule_charset[0]; | |
1691 | } | |
1692 | else | |
1693 | { | |
1694 | switch (emacs_mule_bytes[c]) | |
b73bfc1c | 1695 | { |
065e3595 | 1696 | case 2: |
df7492f9 KH |
1697 | if (! (charset = emacs_mule_charset[c])) |
1698 | goto invalid_code; | |
1699 | ONE_MORE_BYTE (c); | |
9ffd559c | 1700 | if (c < 0xA0) |
065e3595 | 1701 | goto invalid_code; |
df7492f9 | 1702 | code = c & 0x7F; |
065e3595 KH |
1703 | break; |
1704 | ||
1705 | case 3: | |
1706 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
1707 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
1708 | { | |
1709 | ONE_MORE_BYTE (c); | |
9ffd559c | 1710 | if (c < 0xA0 || ! (charset = emacs_mule_charset[c])) |
065e3595 KH |
1711 | goto invalid_code; |
1712 | ONE_MORE_BYTE (c); | |
9ffd559c | 1713 | if (c < 0xA0) |
065e3595 KH |
1714 | goto invalid_code; |
1715 | code = c & 0x7F; | |
1716 | } | |
1717 | else | |
1718 | { | |
1719 | if (! (charset = emacs_mule_charset[c])) | |
1720 | goto invalid_code; | |
1721 | ONE_MORE_BYTE (c); | |
9ffd559c | 1722 | if (c < 0xA0) |
065e3595 KH |
1723 | goto invalid_code; |
1724 | code = (c & 0x7F) << 8; | |
1725 | ONE_MORE_BYTE (c); | |
9ffd559c | 1726 | if (c < 0xA0) |
065e3595 KH |
1727 | goto invalid_code; |
1728 | code |= c & 0x7F; | |
1729 | } | |
1730 | break; | |
1731 | ||
1732 | case 4: | |
1733 | ONE_MORE_BYTE (c); | |
1734 | if (c < 0 || ! (charset = emacs_mule_charset[c])) | |
df7492f9 KH |
1735 | goto invalid_code; |
1736 | ONE_MORE_BYTE (c); | |
9ffd559c | 1737 | if (c < 0xA0) |
065e3595 | 1738 | goto invalid_code; |
781d7a48 | 1739 | code = (c & 0x7F) << 8; |
df7492f9 | 1740 | ONE_MORE_BYTE (c); |
9ffd559c | 1741 | if (c < 0xA0) |
065e3595 | 1742 | goto invalid_code; |
df7492f9 | 1743 | code |= c & 0x7F; |
065e3595 | 1744 | break; |
df7492f9 | 1745 | |
065e3595 KH |
1746 | case 1: |
1747 | code = c; | |
1748 | charset = CHARSET_FROM_ID (ASCII_BYTE_P (code) | |
1749 | ? charset_ascii : charset_eight_bit); | |
1750 | break; | |
df7492f9 | 1751 | |
065e3595 KH |
1752 | default: |
1753 | abort (); | |
1754 | } | |
1755 | c = DECODE_CHAR (charset, code); | |
1756 | if (c < 0) | |
1757 | goto invalid_code; | |
df7492f9 | 1758 | } |
df7492f9 KH |
1759 | *nbytes = src - src_base; |
1760 | *nchars = consumed_chars; | |
ff0dacd7 KH |
1761 | if (id) |
1762 | *id = charset->id; | |
df7492f9 KH |
1763 | return c; |
1764 | ||
1765 | no_more_source: | |
1766 | return -2; | |
1767 | ||
1768 | invalid_code: | |
1769 | return -1; | |
1770 | } | |
1771 | ||
1772 | ||
1773 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1774 | Check if a text is encoded in `emacs-mule'. If it is, return 1, |
1775 | else return 0. */ | |
df7492f9 KH |
1776 | |
1777 | static int | |
ff0dacd7 | 1778 | detect_coding_emacs_mule (coding, detect_info) |
df7492f9 | 1779 | struct coding_system *coding; |
ff0dacd7 | 1780 | struct coding_detection_info *detect_info; |
df7492f9 | 1781 | { |
065e3595 | 1782 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1783 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1784 | int multibytep = coding->src_multibyte; |
1785 | int consumed_chars = 0; | |
1786 | int c; | |
1787 | int found = 0; | |
1788 | ||
ff0dacd7 | 1789 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1790 | /* A coding system of this category is always ASCII compatible. */ |
1791 | src += coding->head_ascii; | |
1792 | ||
1793 | while (1) | |
1794 | { | |
065e3595 | 1795 | src_base = src; |
df7492f9 | 1796 | ONE_MORE_BYTE (c); |
065e3595 KH |
1797 | if (c < 0) |
1798 | continue; | |
df7492f9 KH |
1799 | if (c == 0x80) |
1800 | { | |
1801 | /* Perhaps the start of composite character. We simple skip | |
1802 | it because analyzing it is too heavy for detecting. But, | |
1803 | at least, we check that the composite character | |
1804 | constitues of more than 4 bytes. */ | |
8f924df7 | 1805 | const unsigned char *src_base; |
df7492f9 KH |
1806 | |
1807 | repeat: | |
1808 | src_base = src; | |
1809 | do | |
1810 | { | |
1811 | ONE_MORE_BYTE (c); | |
1812 | } | |
1813 | while (c >= 0xA0); | |
1814 | ||
1815 | if (src - src_base <= 4) | |
1816 | break; | |
ff0dacd7 | 1817 | found = CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1818 | if (c == 0x80) |
1819 | goto repeat; | |
b73bfc1c | 1820 | } |
df7492f9 KH |
1821 | |
1822 | if (c < 0x80) | |
b73bfc1c | 1823 | { |
df7492f9 KH |
1824 | if (c < 0x20 |
1825 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1826 | break; | |
1827 | } | |
1828 | else | |
1829 | { | |
0e219d54 | 1830 | int more_bytes = emacs_mule_bytes[*src_base] - 1; |
df7492f9 | 1831 | |
0e219d54 | 1832 | while (more_bytes > 0) |
df7492f9 KH |
1833 | { |
1834 | ONE_MORE_BYTE (c); | |
0e219d54 KH |
1835 | if (c < 0xA0) |
1836 | { | |
1837 | src--; /* Unread the last byte. */ | |
1838 | break; | |
1839 | } | |
1840 | more_bytes--; | |
df7492f9 | 1841 | } |
0e219d54 | 1842 | if (more_bytes != 0) |
df7492f9 | 1843 | break; |
ff0dacd7 | 1844 | found = CATEGORY_MASK_EMACS_MULE; |
4ed46869 KH |
1845 | } |
1846 | } | |
ff0dacd7 | 1847 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1848 | return 0; |
1849 | ||
1850 | no_more_source: | |
065e3595 | 1851 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 1852 | { |
ff0dacd7 | 1853 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
89528eb3 KH |
1854 | return 0; |
1855 | } | |
ff0dacd7 KH |
1856 | detect_info->found |= found; |
1857 | return 1; | |
4ed46869 KH |
1858 | } |
1859 | ||
b73bfc1c | 1860 | |
df7492f9 KH |
1861 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
1862 | ||
1863 | /* Decode a character represented as a component of composition | |
1864 | sequence of Emacs 20/21 style at SRC. Set C to that character and | |
1865 | update SRC to the head of next character (or an encoded composition | |
1866 | rule). If SRC doesn't points a composition component, set C to -1. | |
1867 | If SRC points an invalid byte sequence, global exit by a return | |
1868 | value 0. */ | |
1869 | ||
1870 | #define DECODE_EMACS_MULE_COMPOSITION_CHAR(buf) \ | |
1871 | if (1) \ | |
1872 | { \ | |
1873 | int c; \ | |
1874 | int nbytes, nchars; \ | |
1875 | \ | |
1876 | if (src == src_end) \ | |
1877 | break; \ | |
ff0dacd7 | 1878 | c = emacs_mule_char (coding, src, &nbytes, &nchars, NULL);\ |
df7492f9 KH |
1879 | if (c < 0) \ |
1880 | { \ | |
1881 | if (c == -2) \ | |
1882 | break; \ | |
1883 | goto invalid_code; \ | |
1884 | } \ | |
1885 | *buf++ = c; \ | |
1886 | src += nbytes; \ | |
1887 | consumed_chars += nchars; \ | |
1888 | } \ | |
1889 | else | |
1890 | ||
1891 | ||
1892 | /* Decode a composition rule represented as a component of composition | |
781d7a48 KH |
1893 | sequence of Emacs 20 style at SRC. Store the decoded rule in *BUF, |
1894 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1895 | to -1. */ | |
df7492f9 | 1896 | |
781d7a48 | 1897 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(buf) \ |
df7492f9 KH |
1898 | do { \ |
1899 | int c, gref, nref; \ | |
1900 | \ | |
781d7a48 | 1901 | if (src >= src_end) \ |
df7492f9 KH |
1902 | goto invalid_code; \ |
1903 | ONE_MORE_BYTE_NO_CHECK (c); \ | |
781d7a48 | 1904 | c -= 0x20; \ |
df7492f9 KH |
1905 | if (c < 0 || c >= 81) \ |
1906 | goto invalid_code; \ | |
1907 | \ | |
1908 | gref = c / 9, nref = c % 9; \ | |
1909 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1910 | } while (0) | |
1911 | ||
1912 | ||
781d7a48 KH |
1913 | /* Decode a composition rule represented as a component of composition |
1914 | sequence of Emacs 21 style at SRC. Store the decoded rule in *BUF, | |
1915 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1916 | to -1. */ | |
1917 | ||
1918 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(buf) \ | |
1919 | do { \ | |
1920 | int gref, nref; \ | |
1921 | \ | |
1922 | if (src + 1>= src_end) \ | |
1923 | goto invalid_code; \ | |
1924 | ONE_MORE_BYTE_NO_CHECK (gref); \ | |
1925 | gref -= 0x20; \ | |
1926 | ONE_MORE_BYTE_NO_CHECK (nref); \ | |
1927 | nref -= 0x20; \ | |
1928 | if (gref < 0 || gref >= 81 \ | |
1929 | || nref < 0 || nref >= 81) \ | |
1930 | goto invalid_code; \ | |
1931 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1932 | } while (0) | |
1933 | ||
1934 | ||
df7492f9 | 1935 | #define DECODE_EMACS_MULE_21_COMPOSITION(c) \ |
aa72b389 | 1936 | do { \ |
df7492f9 | 1937 | /* Emacs 21 style format. The first three bytes at SRC are \ |
781d7a48 | 1938 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is \ |
df7492f9 KH |
1939 | the byte length of this composition information, CHARS is the \ |
1940 | number of characters composed by this composition. */ \ | |
781d7a48 KH |
1941 | enum composition_method method = c - 0xF2; \ |
1942 | int *charbuf_base = charbuf; \ | |
df7492f9 KH |
1943 | int consumed_chars_limit; \ |
1944 | int nbytes, nchars; \ | |
1945 | \ | |
1946 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
1947 | if (c < 0) \ |
1948 | goto invalid_code; \ | |
df7492f9 KH |
1949 | nbytes = c - 0xA0; \ |
1950 | if (nbytes < 3) \ | |
1951 | goto invalid_code; \ | |
1952 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
1953 | if (c < 0) \ |
1954 | goto invalid_code; \ | |
df7492f9 | 1955 | nchars = c - 0xA0; \ |
69a80ea3 | 1956 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ |
df7492f9 KH |
1957 | consumed_chars_limit = consumed_chars_base + nbytes; \ |
1958 | if (method != COMPOSITION_RELATIVE) \ | |
aa72b389 | 1959 | { \ |
df7492f9 KH |
1960 | int i = 0; \ |
1961 | while (consumed_chars < consumed_chars_limit) \ | |
aa72b389 | 1962 | { \ |
df7492f9 | 1963 | if (i % 2 && method != COMPOSITION_WITH_ALTCHARS) \ |
781d7a48 | 1964 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (charbuf); \ |
df7492f9 KH |
1965 | else \ |
1966 | DECODE_EMACS_MULE_COMPOSITION_CHAR (charbuf); \ | |
781d7a48 | 1967 | i++; \ |
aa72b389 | 1968 | } \ |
df7492f9 KH |
1969 | if (consumed_chars < consumed_chars_limit) \ |
1970 | goto invalid_code; \ | |
781d7a48 | 1971 | charbuf_base[0] -= i; \ |
aa72b389 KH |
1972 | } \ |
1973 | } while (0) | |
93dec019 | 1974 | |
aa72b389 | 1975 | |
df7492f9 KH |
1976 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION(c) \ |
1977 | do { \ | |
1978 | /* Emacs 20 style format for relative composition. */ \ | |
1979 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 1980 | enum composition_method method = COMPOSITION_RELATIVE; \ |
df7492f9 KH |
1981 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
1982 | int *buf = components; \ | |
1983 | int i, j; \ | |
1984 | \ | |
1985 | src = src_base; \ | |
1986 | ONE_MORE_BYTE (c); /* skip 0x80 */ \ | |
1987 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
1988 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
1989 | if (i < 2) \ | |
1990 | goto invalid_code; \ | |
69a80ea3 | 1991 | ADD_COMPOSITION_DATA (charbuf, i, method); \ |
df7492f9 KH |
1992 | for (j = 0; j < i; j++) \ |
1993 | *charbuf++ = components[j]; \ | |
1994 | } while (0) | |
1995 | ||
1996 | ||
1997 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION(c) \ | |
1998 | do { \ | |
1999 | /* Emacs 20 style format for rule-base composition. */ \ | |
2000 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 2001 | enum composition_method method = COMPOSITION_WITH_RULE; \ |
df7492f9 KH |
2002 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
2003 | int *buf = components; \ | |
2004 | int i, j; \ | |
2005 | \ | |
2006 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
2007 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
2008 | { \ | |
781d7a48 | 2009 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (buf); \ |
df7492f9 KH |
2010 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ |
2011 | } \ | |
2012 | if (i < 1 || (buf - components) % 2 == 0) \ | |
2013 | goto invalid_code; \ | |
2014 | if (charbuf + i + (i / 2) + 1 < charbuf_end) \ | |
2015 | goto no_more_source; \ | |
69a80ea3 | 2016 | ADD_COMPOSITION_DATA (buf, i, method); \ |
df7492f9 KH |
2017 | for (j = 0; j < i; j++) \ |
2018 | *charbuf++ = components[j]; \ | |
2019 | for (j = 0; j < i; j += 2) \ | |
2020 | *charbuf++ = components[j]; \ | |
2021 | } while (0) | |
2022 | ||
aa72b389 KH |
2023 | |
2024 | static void | |
df7492f9 | 2025 | decode_coding_emacs_mule (coding) |
aa72b389 | 2026 | struct coding_system *coding; |
aa72b389 | 2027 | { |
8f924df7 KH |
2028 | const unsigned char *src = coding->source + coding->consumed; |
2029 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2030 | const unsigned char *src_base; | |
69a80ea3 KH |
2031 | int *charbuf = coding->charbuf + coding->charbuf_used; |
2032 | int *charbuf_end | |
2033 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 | 2034 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2035 | int multibytep = coding->src_multibyte; |
24a73b0a | 2036 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2037 | int char_offset = coding->produced_char; |
2038 | int last_offset = char_offset; | |
2039 | int last_id = charset_ascii; | |
aa72b389 | 2040 | |
24a73b0a | 2041 | CODING_GET_INFO (coding, attrs, charset_list); |
aa72b389 | 2042 | |
aa72b389 KH |
2043 | while (1) |
2044 | { | |
df7492f9 KH |
2045 | int c; |
2046 | ||
aa72b389 | 2047 | src_base = src; |
df7492f9 KH |
2048 | consumed_chars_base = consumed_chars; |
2049 | ||
2050 | if (charbuf >= charbuf_end) | |
2051 | break; | |
aa72b389 | 2052 | |
df7492f9 | 2053 | ONE_MORE_BYTE (c); |
065e3595 KH |
2054 | if (c < 0) |
2055 | { | |
2056 | *charbuf++ = -c; | |
2057 | char_offset++; | |
2058 | } | |
2059 | else if (c < 0x80) | |
aa72b389 | 2060 | { |
df7492f9 KH |
2061 | *charbuf++ = c; |
2062 | char_offset++; | |
aa72b389 | 2063 | } |
df7492f9 KH |
2064 | else if (c == 0x80) |
2065 | { | |
df7492f9 | 2066 | ONE_MORE_BYTE (c); |
065e3595 KH |
2067 | if (c < 0) |
2068 | goto invalid_code; | |
781d7a48 KH |
2069 | if (c - 0xF2 >= COMPOSITION_RELATIVE |
2070 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) | |
df7492f9 KH |
2071 | DECODE_EMACS_MULE_21_COMPOSITION (c); |
2072 | else if (c < 0xC0) | |
2073 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (c); | |
2074 | else if (c == 0xFF) | |
2075 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (c); | |
2076 | else | |
2077 | goto invalid_code; | |
2078 | } | |
2079 | else if (c < 0xA0 && emacs_mule_bytes[c] > 1) | |
2080 | { | |
2081 | int nbytes, nchars; | |
ff0dacd7 KH |
2082 | int id; |
2083 | ||
781d7a48 KH |
2084 | src = src_base; |
2085 | consumed_chars = consumed_chars_base; | |
ff0dacd7 | 2086 | c = emacs_mule_char (coding, src, &nbytes, &nchars, &id); |
df7492f9 KH |
2087 | if (c < 0) |
2088 | { | |
2089 | if (c == -2) | |
2090 | break; | |
2091 | goto invalid_code; | |
2092 | } | |
ff0dacd7 KH |
2093 | if (last_id != id) |
2094 | { | |
2095 | if (last_id != charset_ascii) | |
69a80ea3 | 2096 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
2097 | last_id = id; |
2098 | last_offset = char_offset; | |
2099 | } | |
df7492f9 | 2100 | *charbuf++ = c; |
781d7a48 KH |
2101 | src += nbytes; |
2102 | consumed_chars += nchars; | |
df7492f9 KH |
2103 | char_offset++; |
2104 | } | |
2105 | continue; | |
2106 | ||
2107 | invalid_code: | |
2108 | src = src_base; | |
2109 | consumed_chars = consumed_chars_base; | |
2110 | ONE_MORE_BYTE (c); | |
2111 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2112 | char_offset++; |
df7492f9 KH |
2113 | coding->errors++; |
2114 | } | |
2115 | ||
2116 | no_more_source: | |
ff0dacd7 | 2117 | if (last_id != charset_ascii) |
69a80ea3 | 2118 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2119 | coding->consumed_char += consumed_chars_base; |
2120 | coding->consumed = src_base - coding->source; | |
2121 | coding->charbuf_used = charbuf - coding->charbuf; | |
2122 | } | |
2123 | ||
2124 | ||
2125 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2126 | do { \ | |
2127 | if (id < 0xA0) \ | |
2128 | codes[0] = id, codes[1] = 0; \ | |
2129 | else if (id < 0xE0) \ | |
2130 | codes[0] = 0x9A, codes[1] = id; \ | |
2131 | else if (id < 0xF0) \ | |
2132 | codes[0] = 0x9B, codes[1] = id; \ | |
2133 | else if (id < 0xF5) \ | |
2134 | codes[0] = 0x9C, codes[1] = id; \ | |
2135 | else \ | |
2136 | codes[0] = 0x9D, codes[1] = id; \ | |
2137 | } while (0); | |
2138 | ||
aa72b389 | 2139 | |
df7492f9 KH |
2140 | static int |
2141 | encode_coding_emacs_mule (coding) | |
2142 | struct coding_system *coding; | |
2143 | { | |
2144 | int multibytep = coding->dst_multibyte; | |
2145 | int *charbuf = coding->charbuf; | |
2146 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2147 | unsigned char *dst = coding->destination + coding->produced; | |
2148 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2149 | int safe_room = 8; | |
df7492f9 | 2150 | int produced_chars = 0; |
24a73b0a | 2151 | Lisp_Object attrs, charset_list; |
df7492f9 | 2152 | int c; |
ff0dacd7 | 2153 | int preferred_charset_id = -1; |
df7492f9 | 2154 | |
24a73b0a | 2155 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2156 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2157 | { | |
2158 | CODING_ATTR_CHARSET_LIST (attrs) | |
2159 | = charset_list = Vemacs_mule_charset_list; | |
2160 | } | |
df7492f9 KH |
2161 | |
2162 | while (charbuf < charbuf_end) | |
2163 | { | |
2164 | ASSURE_DESTINATION (safe_room); | |
2165 | c = *charbuf++; | |
ff0dacd7 KH |
2166 | |
2167 | if (c < 0) | |
2168 | { | |
2169 | /* Handle an annotation. */ | |
2170 | switch (*charbuf) | |
2171 | { | |
2172 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2173 | /* Not yet implemented. */ | |
2174 | break; | |
2175 | case CODING_ANNOTATE_CHARSET_MASK: | |
2176 | preferred_charset_id = charbuf[3]; | |
2177 | if (preferred_charset_id >= 0 | |
2178 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2179 | charset_list))) | |
2180 | preferred_charset_id = -1; | |
2181 | break; | |
2182 | default: | |
2183 | abort (); | |
2184 | } | |
2185 | charbuf += -c - 1; | |
2186 | continue; | |
2187 | } | |
2188 | ||
df7492f9 KH |
2189 | if (ASCII_CHAR_P (c)) |
2190 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2191 | else if (CHAR_BYTE8_P (c)) |
2192 | { | |
2193 | c = CHAR_TO_BYTE8 (c); | |
2194 | EMIT_ONE_BYTE (c); | |
2195 | } | |
df7492f9 | 2196 | else |
aa72b389 | 2197 | { |
df7492f9 KH |
2198 | struct charset *charset; |
2199 | unsigned code; | |
2200 | int dimension; | |
2201 | int emacs_mule_id; | |
2202 | unsigned char leading_codes[2]; | |
2203 | ||
ff0dacd7 KH |
2204 | if (preferred_charset_id >= 0) |
2205 | { | |
2206 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
2207 | if (! CHAR_CHARSET_P (c, charset)) | |
2208 | charset = char_charset (c, charset_list, NULL); | |
2209 | } | |
2210 | else | |
2211 | charset = char_charset (c, charset_list, &code); | |
df7492f9 KH |
2212 | if (! charset) |
2213 | { | |
2214 | c = coding->default_char; | |
2215 | if (ASCII_CHAR_P (c)) | |
2216 | { | |
2217 | EMIT_ONE_ASCII_BYTE (c); | |
2218 | continue; | |
2219 | } | |
2220 | charset = char_charset (c, charset_list, &code); | |
2221 | } | |
2222 | dimension = CHARSET_DIMENSION (charset); | |
2223 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2224 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2225 | EMIT_ONE_BYTE (leading_codes[0]); | |
2226 | if (leading_codes[1]) | |
2227 | EMIT_ONE_BYTE (leading_codes[1]); | |
2228 | if (dimension == 1) | |
1fa663f9 | 2229 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2230 | else |
df7492f9 | 2231 | { |
1fa663f9 | 2232 | code |= 0x8080; |
df7492f9 KH |
2233 | EMIT_ONE_BYTE (code >> 8); |
2234 | EMIT_ONE_BYTE (code & 0xFF); | |
2235 | } | |
aa72b389 | 2236 | } |
aa72b389 | 2237 | } |
065e3595 | 2238 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2239 | coding->produced_char += produced_chars; |
2240 | coding->produced = dst - coding->destination; | |
2241 | return 0; | |
aa72b389 | 2242 | } |
b73bfc1c | 2243 | |
4ed46869 | 2244 | \f |
df7492f9 | 2245 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2246 | |
2247 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2248 | Since the intention of this note is to help understand the |
5a936b46 | 2249 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2250 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2251 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2252 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2253 | |
2254 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2255 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2256 | is encoded using bytes less than 128. This may make the encoded |
2257 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2258 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2259 | Significant Bit). |
b73bfc1c | 2260 | |
cfb43547 DL |
2261 | There are two kinds of character sets: control character sets and |
2262 | graphic character sets. The former contain control characters such | |
4ed46869 | 2263 | as `newline' and `escape' to provide control functions (control |
39787efd | 2264 | functions are also provided by escape sequences). The latter |
cfb43547 | 2265 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2266 | two control character sets and many graphic character sets. |
2267 | ||
2268 | Graphic character sets are classified into one of the following | |
39787efd KH |
2269 | four classes, according to the number of bytes (DIMENSION) and |
2270 | number of characters in one dimension (CHARS) of the set: | |
2271 | - DIMENSION1_CHARS94 | |
2272 | - DIMENSION1_CHARS96 | |
2273 | - DIMENSION2_CHARS94 | |
2274 | - DIMENSION2_CHARS96 | |
2275 | ||
2276 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2277 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2278 | hereafter). The <F> of each character set is decided by ECMA(*) |
2279 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2280 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2281 | |
2282 | Note (*): ECMA = European Computer Manufacturers Association | |
2283 | ||
cfb43547 | 2284 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2285 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2286 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2287 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2288 | o DIMENSION2_CHARS96 -- none for the moment | |
2289 | ||
39787efd | 2290 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2291 | C0 [0x00..0x1F] -- control character plane 0 |
2292 | GL [0x20..0x7F] -- graphic character plane 0 | |
2293 | C1 [0x80..0x9F] -- control character plane 1 | |
2294 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2295 | ||
2296 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2297 | C1 by an escape sequence. The most common case is that: |
2298 | - ISO646's control character set is designated/invoked to C0, and | |
2299 | - ISO6429's control character set is designated/invoked to C1, | |
2300 | and usually these designations/invocations are omitted in encoded | |
2301 | text. In a 7-bit environment, only C0 can be used, and a control | |
2302 | character for C1 is encoded by an appropriate escape sequence to | |
2303 | fit into the environment. All control characters for C1 are | |
2304 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2305 | |
2306 | A graphic character set is at first designated to one of four | |
2307 | graphic registers (G0 through G3), then these graphic registers are | |
2308 | invoked to GL or GR. These designations and invocations can be | |
2309 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2310 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2311 | these invocations and designations are omitted in encoded text. | |
2312 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2313 | |
39787efd KH |
2314 | When a graphic character set of CHARS94 is invoked to GL, codes |
2315 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2316 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2317 | be used. | |
4ed46869 KH |
2318 | |
2319 | There are two ways of invocation: locking-shift and single-shift. | |
2320 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2321 | invocation, whereas with single-shift, the invocation affects the |
2322 | following character only and doesn't affect the locking-shift | |
2323 | state. Invocations are done by the following control characters or | |
2324 | escape sequences: | |
4ed46869 KH |
2325 | |
2326 | ---------------------------------------------------------------------- | |
39787efd | 2327 | abbrev function cntrl escape seq description |
4ed46869 | 2328 | ---------------------------------------------------------------------- |
39787efd KH |
2329 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2330 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2331 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2332 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2333 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2334 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2335 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2336 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2337 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2338 | ---------------------------------------------------------------------- |
39787efd KH |
2339 | (*) These are not used by any known coding system. |
2340 | ||
2341 | Control characters for these functions are defined by macros | |
2342 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2343 | |
39787efd | 2344 | Designations are done by the following escape sequences: |
4ed46869 KH |
2345 | ---------------------------------------------------------------------- |
2346 | escape sequence description | |
2347 | ---------------------------------------------------------------------- | |
2348 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2349 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2350 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2351 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2352 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2353 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2354 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2355 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2356 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2357 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2358 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2359 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2360 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2361 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2362 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2363 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2364 | ---------------------------------------------------------------------- | |
2365 | ||
2366 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2367 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2368 | |
2369 | Note (*): Although these designations are not allowed in ISO2022, | |
2370 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2371 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2372 | 7-bit environment, non-locking-shift, and non-single-shift. |
2373 | ||
2374 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2375 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2376 | |
cfb43547 | 2377 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2378 | same multilingual text in ISO2022. Actually, there exist many |
2379 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2380 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2381 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2382 | localized platforms), and all of these are variants of ISO2022. |
2383 | ||
2384 | In addition to the above, Emacs handles two more kinds of escape | |
2385 | sequences: ISO6429's direction specification and Emacs' private | |
2386 | sequence for specifying character composition. | |
2387 | ||
39787efd | 2388 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2389 | o CSI ']' -- end of the current direction |
2390 | o CSI '0' ']' -- end of the current direction | |
2391 | o CSI '1' ']' -- start of left-to-right text | |
2392 | o CSI '2' ']' -- start of right-to-left text | |
2393 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2394 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2395 | ||
2396 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2397 | o ESC '0' -- start relative composition |
2398 | o ESC '1' -- end composition | |
2399 | o ESC '2' -- start rule-base composition (*) | |
2400 | o ESC '3' -- start relative composition with alternate chars (**) | |
2401 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2402 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2403 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2404 | |
5a936b46 DL |
2405 | (*) This form is used only in Emacs 20.7 and older versions, |
2406 | but newer versions can safely decode it. | |
cfb43547 | 2407 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2408 | and older versions can't decode it. |
ec6d2bb8 | 2409 | |
cfb43547 | 2410 | Here's a list of example usages of these composition escape |
b73bfc1c | 2411 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2412 | |
b73bfc1c | 2413 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2414 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2415 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2416 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2417 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2418 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2419 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2420 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2421 | |
2422 | enum iso_code_class_type iso_code_class[256]; | |
2423 | ||
df7492f9 KH |
2424 | #define SAFE_CHARSET_P(coding, id) \ |
2425 | ((id) <= (coding)->max_charset_id \ | |
2426 | && (coding)->safe_charsets[id] >= 0) | |
2427 | ||
2428 | ||
2429 | #define SHIFT_OUT_OK(category) \ | |
2430 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
2431 | ||
2432 | static void | |
f0064e1f DL |
2433 | setup_iso_safe_charsets (attrs) |
2434 | Lisp_Object attrs; | |
df7492f9 KH |
2435 | { |
2436 | Lisp_Object charset_list, safe_charsets; | |
2437 | Lisp_Object request; | |
2438 | Lisp_Object reg_usage; | |
2439 | Lisp_Object tail; | |
2440 | int reg94, reg96; | |
2441 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
2442 | int max_charset_id; | |
2443 | ||
2444 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2445 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2446 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2447 | { | |
2448 | CODING_ATTR_CHARSET_LIST (attrs) | |
2449 | = charset_list = Viso_2022_charset_list; | |
2450 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
2451 | } | |
2452 | ||
2453 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2454 | return; | |
2455 | ||
2456 | max_charset_id = 0; | |
2457 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2458 | { | |
2459 | int id = XINT (XCAR (tail)); | |
2460 | if (max_charset_id < id) | |
2461 | max_charset_id = id; | |
2462 | } | |
d46c5b12 | 2463 | |
df7492f9 KH |
2464 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
2465 | make_number (255)); | |
2466 | request = AREF (attrs, coding_attr_iso_request); | |
2467 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2468 | reg94 = XINT (XCAR (reg_usage)); | |
2469 | reg96 = XINT (XCDR (reg_usage)); | |
2470 | ||
2471 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2472 | { | |
2473 | Lisp_Object id; | |
2474 | Lisp_Object reg; | |
2475 | struct charset *charset; | |
2476 | ||
2477 | id = XCAR (tail); | |
2478 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2479 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2480 | if (! NILP (reg)) |
8f924df7 | 2481 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2482 | else if (charset->iso_chars_96) |
2483 | { | |
2484 | if (reg96 < 4) | |
8f924df7 | 2485 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2486 | } |
2487 | else | |
2488 | { | |
2489 | if (reg94 < 4) | |
8f924df7 | 2490 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2491 | } |
2492 | } | |
2493 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2494 | } | |
d46c5b12 | 2495 | |
b6871cc7 | 2496 | |
4ed46869 | 2497 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
2498 | Check if a text is encoded in one of ISO-2022 based codig systems. |
2499 | If it is, return 1, else return 0. */ | |
4ed46869 | 2500 | |
0a28aafb | 2501 | static int |
ff0dacd7 | 2502 | detect_coding_iso_2022 (coding, detect_info) |
df7492f9 | 2503 | struct coding_system *coding; |
ff0dacd7 | 2504 | struct coding_detection_info *detect_info; |
4ed46869 | 2505 | { |
8f924df7 KH |
2506 | const unsigned char *src = coding->source, *src_base = src; |
2507 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 2508 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 2509 | int single_shifting = 0; |
df7492f9 KH |
2510 | int id; |
2511 | int c, c1; | |
2512 | int consumed_chars = 0; | |
2513 | int i; | |
ff0dacd7 KH |
2514 | int rejected = 0; |
2515 | int found = 0; | |
2516 | ||
2517 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2518 | |
2519 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2520 | { | |
2521 | struct coding_system *this = &(coding_categories[i]); | |
2522 | Lisp_Object attrs, val; | |
2523 | ||
2524 | attrs = CODING_ID_ATTRS (this->id); | |
2525 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
2526 | && ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs), Viso_2022_charset_list)) | |
2527 | setup_iso_safe_charsets (attrs); | |
2528 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
2529 | this->max_charset_id = SCHARS (val) - 1; |
2530 | this->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
2531 | } |
2532 | ||
2533 | /* A coding system of this category is always ASCII compatible. */ | |
2534 | src += coding->head_ascii; | |
3f003981 | 2535 | |
ff0dacd7 | 2536 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 2537 | { |
065e3595 | 2538 | src_base = src; |
df7492f9 | 2539 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2540 | switch (c) |
2541 | { | |
2542 | case ISO_CODE_ESC: | |
74383408 KH |
2543 | if (inhibit_iso_escape_detection) |
2544 | break; | |
f46869e4 | 2545 | single_shifting = 0; |
df7492f9 | 2546 | ONE_MORE_BYTE (c); |
d46c5b12 | 2547 | if (c >= '(' && c <= '/') |
4ed46869 | 2548 | { |
bf9cdd4e | 2549 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 2550 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2551 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2552 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
2553 | /* Invalid designation sequence. Just ignore. */ |
2554 | break; | |
bf9cdd4e KH |
2555 | } |
2556 | else if (c == '$') | |
2557 | { | |
2558 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 2559 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
2560 | if (c >= '@' && c <= 'B') |
2561 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
ff0dacd7 | 2562 | id = iso_charset_table[1][0][c]; |
bf9cdd4e | 2563 | else if (c >= '(' && c <= '/') |
bcf26d6a | 2564 | { |
df7492f9 | 2565 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2566 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2567 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
2568 | /* Invalid designation sequence. Just ignore. */ |
2569 | break; | |
bcf26d6a | 2570 | } |
bf9cdd4e | 2571 | else |
ff0dacd7 | 2572 | /* Invalid designation sequence. Just ignore it. */ |
d46c5b12 KH |
2573 | break; |
2574 | } | |
ae9ff118 | 2575 | else if (c == 'N' || c == 'O') |
d46c5b12 | 2576 | { |
ae9ff118 | 2577 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
2578 | single_shifting = 1; |
2579 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
d46c5b12 | 2580 | break; |
4ed46869 | 2581 | } |
ec6d2bb8 KH |
2582 | else if (c >= '0' && c <= '4') |
2583 | { | |
2584 | /* ESC <Fp> for start/end composition. */ | |
ff0dacd7 | 2585 | found |= CATEGORY_MASK_ISO; |
ec6d2bb8 KH |
2586 | break; |
2587 | } | |
bf9cdd4e | 2588 | else |
df7492f9 | 2589 | { |
ff0dacd7 | 2590 | /* Invalid escape sequence. Just ignore it. */ |
df7492f9 KH |
2591 | break; |
2592 | } | |
d46c5b12 KH |
2593 | |
2594 | /* We found a valid designation sequence for CHARSET. */ | |
ff0dacd7 | 2595 | rejected |= CATEGORY_MASK_ISO_8BIT; |
df7492f9 KH |
2596 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], |
2597 | id)) | |
ff0dacd7 | 2598 | found |= CATEGORY_MASK_ISO_7; |
d46c5b12 | 2599 | else |
ff0dacd7 | 2600 | rejected |= CATEGORY_MASK_ISO_7; |
df7492f9 KH |
2601 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], |
2602 | id)) | |
ff0dacd7 | 2603 | found |= CATEGORY_MASK_ISO_7_TIGHT; |
d46c5b12 | 2604 | else |
ff0dacd7 | 2605 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; |
df7492f9 KH |
2606 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], |
2607 | id)) | |
ff0dacd7 | 2608 | found |= CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 | 2609 | else |
ff0dacd7 | 2610 | rejected |= CATEGORY_MASK_ISO_7_ELSE; |
df7492f9 KH |
2611 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], |
2612 | id)) | |
ff0dacd7 | 2613 | found |= CATEGORY_MASK_ISO_8_ELSE; |
ae9ff118 | 2614 | else |
ff0dacd7 | 2615 | rejected |= CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
2616 | break; |
2617 | ||
4ed46869 | 2618 | case ISO_CODE_SO: |
d46c5b12 | 2619 | case ISO_CODE_SI: |
ff0dacd7 | 2620 | /* Locking shift out/in. */ |
74383408 KH |
2621 | if (inhibit_iso_escape_detection) |
2622 | break; | |
f46869e4 | 2623 | single_shifting = 0; |
ff0dacd7 KH |
2624 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
2625 | found |= CATEGORY_MASK_ISO_ELSE; | |
d46c5b12 KH |
2626 | break; |
2627 | ||
4ed46869 | 2628 | case ISO_CODE_CSI: |
ff0dacd7 | 2629 | /* Control sequence introducer. */ |
f46869e4 | 2630 | single_shifting = 0; |
ff0dacd7 KH |
2631 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2632 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
2633 | goto check_extra_latin; | |
2634 | ||
4ed46869 KH |
2635 | case ISO_CODE_SS2: |
2636 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
2637 | /* Single shift. */ |
2638 | if (inhibit_iso_escape_detection) | |
2639 | break; | |
75e2a253 | 2640 | single_shifting = 0; |
ff0dacd7 KH |
2641 | rejected |= CATEGORY_MASK_ISO_7BIT; |
2642 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2643 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 | 2644 | found |= CATEGORY_MASK_ISO_8_1, single_shifting = 1; |
ff0dacd7 KH |
2645 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
2646 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 KH |
2647 | found |= CATEGORY_MASK_ISO_8_2, single_shifting = 1; |
2648 | if (single_shifting) | |
2649 | break; | |
ff0dacd7 | 2650 | goto check_extra_latin; |
4ed46869 KH |
2651 | |
2652 | default: | |
065e3595 KH |
2653 | if (c < 0) |
2654 | continue; | |
4ed46869 | 2655 | if (c < 0x80) |
f46869e4 KH |
2656 | { |
2657 | single_shifting = 0; | |
2658 | break; | |
2659 | } | |
ff0dacd7 | 2660 | if (c >= 0xA0) |
c4825358 | 2661 | { |
ff0dacd7 KH |
2662 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2663 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 2664 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
2665 | 0xA0..0FF. If the byte length is even, we include |
2666 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
2667 | only when we are not single shifting. */ | |
2668 | if (! single_shifting | |
2669 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 2670 | { |
e17de821 | 2671 | int i = 1; |
b73bfc1c KH |
2672 | while (src < src_end) |
2673 | { | |
df7492f9 | 2674 | ONE_MORE_BYTE (c); |
b73bfc1c KH |
2675 | if (c < 0xA0) |
2676 | break; | |
2677 | i++; | |
2678 | } | |
2679 | ||
2680 | if (i & 1 && src < src_end) | |
ff0dacd7 | 2681 | rejected |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2682 | else |
ff0dacd7 | 2683 | found |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2684 | } |
ff0dacd7 | 2685 | break; |
4ed46869 | 2686 | } |
ff0dacd7 KH |
2687 | check_extra_latin: |
2688 | single_shifting = 0; | |
2689 | if (! VECTORP (Vlatin_extra_code_table) | |
2690 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
2691 | { | |
2692 | rejected = CATEGORY_MASK_ISO; | |
2693 | break; | |
2694 | } | |
2695 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2696 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2697 | found |= CATEGORY_MASK_ISO_8_1; | |
2698 | else | |
2699 | rejected |= CATEGORY_MASK_ISO_8_1; | |
75e2a253 | 2700 | rejected |= CATEGORY_MASK_ISO_8_2; |
4ed46869 KH |
2701 | } |
2702 | } | |
ff0dacd7 KH |
2703 | detect_info->rejected |= CATEGORY_MASK_ISO; |
2704 | return 0; | |
4ed46869 | 2705 | |
df7492f9 | 2706 | no_more_source: |
ff0dacd7 KH |
2707 | detect_info->rejected |= rejected; |
2708 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 2709 | return 1; |
4ed46869 | 2710 | } |
ec6d2bb8 | 2711 | |
4ed46869 | 2712 | |
134b9549 KH |
2713 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
2714 | escape sequence should be kept. */ | |
df7492f9 KH |
2715 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
2716 | do { \ | |
2717 | int id, prev; \ | |
2718 | \ | |
2719 | if (final < '0' || final >= 128 \ | |
2720 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
2721 | || !SAFE_CHARSET_P (coding, id)) \ | |
2722 | { \ | |
2723 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
2724 | chars_96 = -1; \ |
2725 | break; \ | |
df7492f9 KH |
2726 | } \ |
2727 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
2728 | if (id == charset_jisx0201_roman) \ |
2729 | { \ | |
2730 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
2731 | id = charset_ascii; \ | |
2732 | } \ | |
2733 | else if (id == charset_jisx0208_1978) \ | |
2734 | { \ | |
2735 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
2736 | id = charset_jisx0208; \ | |
2737 | } \ | |
df7492f9 KH |
2738 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
2739 | /* If there was an invalid designation to REG previously, and this \ | |
2740 | designation is ASCII to REG, we should keep this designation \ | |
2741 | sequence. */ \ | |
2742 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 2743 | chars_96 = -1; \ |
4ed46869 KH |
2744 | } while (0) |
2745 | ||
d46c5b12 | 2746 | |
df7492f9 KH |
2747 | #define MAYBE_FINISH_COMPOSITION() \ |
2748 | do { \ | |
2749 | int i; \ | |
2750 | if (composition_state == COMPOSING_NO) \ | |
2751 | break; \ | |
2752 | /* It is assured that we have enough room for producing \ | |
2753 | characters stored in the table `components'. */ \ | |
2754 | if (charbuf + component_idx > charbuf_end) \ | |
2755 | goto no_more_source; \ | |
2756 | composition_state = COMPOSING_NO; \ | |
2757 | if (method == COMPOSITION_RELATIVE \ | |
2758 | || method == COMPOSITION_WITH_ALTCHARS) \ | |
2759 | { \ | |
2760 | for (i = 0; i < component_idx; i++) \ | |
2761 | *charbuf++ = components[i]; \ | |
2762 | char_offset += component_idx; \ | |
2763 | } \ | |
2764 | else \ | |
2765 | { \ | |
2766 | for (i = 0; i < component_idx; i += 2) \ | |
2767 | *charbuf++ = components[i]; \ | |
2768 | char_offset += (component_idx / 2) + 1; \ | |
2769 | } \ | |
2770 | } while (0) | |
2771 | ||
d46c5b12 | 2772 | |
aa72b389 KH |
2773 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
2774 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 | |
2775 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
2776 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
2777 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
aa72b389 | 2778 | */ |
ec6d2bb8 | 2779 | |
df7492f9 KH |
2780 | #define DECODE_COMPOSITION_START(c1) \ |
2781 | do { \ | |
2782 | if (c1 == '0' \ | |
781d7a48 | 2783 | && composition_state == COMPOSING_COMPONENT_RULE) \ |
df7492f9 KH |
2784 | { \ |
2785 | component_len = component_idx; \ | |
2786 | composition_state = COMPOSING_CHAR; \ | |
2787 | } \ | |
2788 | else \ | |
2789 | { \ | |
8f924df7 | 2790 | const unsigned char *p; \ |
df7492f9 KH |
2791 | \ |
2792 | MAYBE_FINISH_COMPOSITION (); \ | |
2793 | if (charbuf + MAX_COMPOSITION_COMPONENTS > charbuf_end) \ | |
2794 | goto no_more_source; \ | |
2795 | for (p = src; p < src_end - 1; p++) \ | |
2796 | if (*p == ISO_CODE_ESC && p[1] == '1') \ | |
2797 | break; \ | |
2798 | if (p == src_end - 1) \ | |
2799 | { \ | |
2800 | if (coding->mode & CODING_MODE_LAST_BLOCK) \ | |
2801 | goto invalid_code; \ | |
2802 | goto no_more_source; \ | |
2803 | } \ | |
2804 | \ | |
2805 | /* This is surely the start of a composition. */ \ | |
2806 | method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
2807 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
2808 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
2809 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
2810 | composition_state = (c1 <= '2' ? COMPOSING_CHAR \ | |
2811 | : COMPOSING_COMPONENT_CHAR); \ | |
2812 | component_idx = component_len = 0; \ | |
2813 | } \ | |
ec6d2bb8 KH |
2814 | } while (0) |
2815 | ||
ec6d2bb8 | 2816 | |
df7492f9 KH |
2817 | /* Handle compositoin end sequence ESC 1. */ |
2818 | ||
2819 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 2820 | do { \ |
df7492f9 KH |
2821 | int nchars = (component_len > 0 ? component_idx - component_len \ |
2822 | : method == COMPOSITION_RELATIVE ? component_idx \ | |
2823 | : (component_idx + 1) / 2); \ | |
2824 | int i; \ | |
2825 | int *saved_charbuf = charbuf; \ | |
2826 | \ | |
69a80ea3 | 2827 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ |
df7492f9 | 2828 | if (method != COMPOSITION_RELATIVE) \ |
ec6d2bb8 | 2829 | { \ |
df7492f9 KH |
2830 | if (component_len == 0) \ |
2831 | for (i = 0; i < component_idx; i++) \ | |
2832 | *charbuf++ = components[i]; \ | |
2833 | else \ | |
2834 | for (i = 0; i < component_len; i++) \ | |
2835 | *charbuf++ = components[i]; \ | |
2836 | *saved_charbuf = saved_charbuf - charbuf; \ | |
ec6d2bb8 | 2837 | } \ |
df7492f9 KH |
2838 | if (method == COMPOSITION_WITH_RULE) \ |
2839 | for (i = 0; i < component_idx; i += 2, char_offset++) \ | |
2840 | *charbuf++ = components[i]; \ | |
ec6d2bb8 | 2841 | else \ |
df7492f9 KH |
2842 | for (i = component_len; i < component_idx; i++, char_offset++) \ |
2843 | *charbuf++ = components[i]; \ | |
2844 | coding->annotated = 1; \ | |
2845 | composition_state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
2846 | } while (0) |
2847 | ||
df7492f9 | 2848 | |
ec6d2bb8 KH |
2849 | /* Decode a composition rule from the byte C1 (and maybe one more byte |
2850 | from SRC) and store one encoded composition rule in | |
2851 | coding->cmp_data. */ | |
2852 | ||
2853 | #define DECODE_COMPOSITION_RULE(c1) \ | |
2854 | do { \ | |
ec6d2bb8 KH |
2855 | (c1) -= 32; \ |
2856 | if (c1 < 81) /* old format (before ver.21) */ \ | |
2857 | { \ | |
2858 | int gref = (c1) / 9; \ | |
2859 | int nref = (c1) % 9; \ | |
2860 | if (gref == 4) gref = 10; \ | |
2861 | if (nref == 4) nref = 10; \ | |
df7492f9 | 2862 | c1 = COMPOSITION_ENCODE_RULE (gref, nref); \ |
ec6d2bb8 | 2863 | } \ |
b73bfc1c | 2864 | else if (c1 < 93) /* new format (after ver.21) */ \ |
ec6d2bb8 KH |
2865 | { \ |
2866 | ONE_MORE_BYTE (c2); \ | |
df7492f9 | 2867 | c1 = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \ |
ec6d2bb8 | 2868 | } \ |
df7492f9 KH |
2869 | else \ |
2870 | c1 = 0; \ | |
ec6d2bb8 | 2871 | } while (0) |
88993dfd | 2872 | |
d46c5b12 | 2873 | |
4ed46869 KH |
2874 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
2875 | ||
b73bfc1c | 2876 | static void |
df7492f9 | 2877 | decode_coding_iso_2022 (coding) |
4ed46869 | 2878 | struct coding_system *coding; |
4ed46869 | 2879 | { |
8f924df7 KH |
2880 | const unsigned char *src = coding->source + coding->consumed; |
2881 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2882 | const unsigned char *src_base; | |
69a80ea3 | 2883 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ff0dacd7 | 2884 | int *charbuf_end |
69a80ea3 | 2885 | = coding->charbuf + coding->charbuf_size - 4 - MAX_ANNOTATION_LENGTH; |
df7492f9 | 2886 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2887 | int multibytep = coding->src_multibyte; |
4ed46869 | 2888 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
2889 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
2890 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 2891 | int charset_id_2, charset_id_3; |
df7492f9 KH |
2892 | struct charset *charset; |
2893 | int c; | |
2894 | /* For handling composition sequence. */ | |
2895 | #define COMPOSING_NO 0 | |
2896 | #define COMPOSING_CHAR 1 | |
2897 | #define COMPOSING_RULE 2 | |
2898 | #define COMPOSING_COMPONENT_CHAR 3 | |
2899 | #define COMPOSING_COMPONENT_RULE 4 | |
2900 | ||
2901 | int composition_state = COMPOSING_NO; | |
2902 | enum composition_method method; | |
2903 | int components[MAX_COMPOSITION_COMPONENTS * 2 + 1]; | |
2904 | int component_idx; | |
2905 | int component_len; | |
24a73b0a | 2906 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2907 | int char_offset = coding->produced_char; |
2908 | int last_offset = char_offset; | |
2909 | int last_id = charset_ascii; | |
df7492f9 | 2910 | |
24a73b0a | 2911 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 2912 | setup_iso_safe_charsets (attrs); |
b73bfc1c KH |
2913 | |
2914 | while (1) | |
4ed46869 | 2915 | { |
463f5630 | 2916 | int c1, c2; |
b73bfc1c KH |
2917 | |
2918 | src_base = src; | |
df7492f9 KH |
2919 | consumed_chars_base = consumed_chars; |
2920 | ||
2921 | if (charbuf >= charbuf_end) | |
2922 | break; | |
2923 | ||
b73bfc1c | 2924 | ONE_MORE_BYTE (c1); |
065e3595 KH |
2925 | if (c1 < 0) |
2926 | goto invalid_code; | |
4ed46869 | 2927 | |
98725083 | 2928 | /* We produce at most one character. */ |
4ed46869 KH |
2929 | switch (iso_code_class [c1]) |
2930 | { | |
2931 | case ISO_0x20_or_0x7F: | |
df7492f9 | 2932 | if (composition_state != COMPOSING_NO) |
ec6d2bb8 | 2933 | { |
df7492f9 KH |
2934 | if (composition_state == COMPOSING_RULE |
2935 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2936 | { | |
2937 | DECODE_COMPOSITION_RULE (c1); | |
2938 | components[component_idx++] = c1; | |
2939 | composition_state--; | |
2940 | continue; | |
2941 | } | |
4ed46869 | 2942 | } |
df7492f9 KH |
2943 | if (charset_id_0 < 0 |
2944 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
2945 | /* This is SPACE or DEL. */ |
2946 | charset = CHARSET_FROM_ID (charset_ascii); | |
2947 | else | |
2948 | charset = CHARSET_FROM_ID (charset_id_0); | |
2949 | break; | |
4ed46869 KH |
2950 | |
2951 | case ISO_graphic_plane_0: | |
781d7a48 | 2952 | if (composition_state != COMPOSING_NO) |
b73bfc1c | 2953 | { |
781d7a48 KH |
2954 | if (composition_state == COMPOSING_RULE |
2955 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2956 | { | |
2957 | DECODE_COMPOSITION_RULE (c1); | |
2958 | components[component_idx++] = c1; | |
2959 | composition_state--; | |
2960 | continue; | |
2961 | } | |
b73bfc1c | 2962 | } |
134b9549 KH |
2963 | if (charset_id_0 < 0) |
2964 | charset = CHARSET_FROM_ID (charset_ascii); | |
2965 | else | |
2966 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
2967 | break; |
2968 | ||
2969 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
2970 | if (charset_id_1 < 0 |
2971 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
2972 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
2973 | goto invalid_code; | |
4ed46869 KH |
2974 | /* This is a graphic character, we fall down ... */ |
2975 | ||
2976 | case ISO_graphic_plane_1: | |
df7492f9 KH |
2977 | if (charset_id_1 < 0) |
2978 | goto invalid_code; | |
2979 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
2980 | break; |
2981 | ||
df7492f9 KH |
2982 | case ISO_control_0: |
2983 | MAYBE_FINISH_COMPOSITION (); | |
2984 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
2985 | break; |
2986 | ||
df7492f9 KH |
2987 | case ISO_control_1: |
2988 | MAYBE_FINISH_COMPOSITION (); | |
2989 | goto invalid_code; | |
2990 | ||
4ed46869 | 2991 | case ISO_shift_out: |
df7492f9 KH |
2992 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
2993 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
2994 | goto invalid_code; | |
2995 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
2996 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 2997 | continue; |
4ed46869 KH |
2998 | |
2999 | case ISO_shift_in: | |
df7492f9 KH |
3000 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3001 | goto invalid_code; | |
3002 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3003 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3004 | continue; |
4ed46869 KH |
3005 | |
3006 | case ISO_single_shift_2_7: | |
3007 | case ISO_single_shift_2: | |
df7492f9 KH |
3008 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3009 | goto invalid_code; | |
4ed46869 KH |
3010 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3011 | c1 = 'N'; | |
3012 | goto label_escape_sequence; | |
3013 | ||
3014 | case ISO_single_shift_3: | |
df7492f9 KH |
3015 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3016 | goto invalid_code; | |
4ed46869 KH |
3017 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3018 | c1 = 'O'; | |
3019 | goto label_escape_sequence; | |
3020 | ||
3021 | case ISO_control_sequence_introducer: | |
3022 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3023 | c1 = '['; | |
3024 | goto label_escape_sequence; | |
3025 | ||
3026 | case ISO_escape: | |
3027 | ONE_MORE_BYTE (c1); | |
3028 | label_escape_sequence: | |
df7492f9 | 3029 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3030 | designation, direction specification, and character |
3031 | composition specification. */ | |
3032 | switch (c1) | |
3033 | { | |
3034 | case '&': /* revision of following character set */ | |
3035 | ONE_MORE_BYTE (c1); | |
3036 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3037 | goto invalid_code; |
4ed46869 KH |
3038 | ONE_MORE_BYTE (c1); |
3039 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3040 | goto invalid_code; |
4ed46869 KH |
3041 | ONE_MORE_BYTE (c1); |
3042 | goto label_escape_sequence; | |
3043 | ||
3044 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3045 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3046 | goto invalid_code; | |
134b9549 KH |
3047 | { |
3048 | int reg, chars96; | |
3049 | ||
3050 | ONE_MORE_BYTE (c1); | |
3051 | if (c1 >= '@' && c1 <= 'B') | |
3052 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3053 | or JISX0208.1980 */ |
134b9549 KH |
3054 | reg = 0, chars96 = 0; |
3055 | } | |
3056 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3057 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3058 | reg = c1 - 0x28, chars96 = 0; | |
3059 | ONE_MORE_BYTE (c1); | |
3060 | } | |
3061 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3062 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3063 | reg = c1 - 0x2C, chars96 = 1; | |
3064 | ONE_MORE_BYTE (c1); | |
3065 | } | |
3066 | else | |
3067 | goto invalid_code; | |
3068 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3069 | /* We must update these variables now. */ | |
3070 | if (reg == 0) | |
3071 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3072 | else if (reg == 1) | |
3073 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3074 | if (chars96 < 0) | |
3075 | goto invalid_code; | |
3076 | } | |
b73bfc1c | 3077 | continue; |
4ed46869 KH |
3078 | |
3079 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3080 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3081 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3082 | goto invalid_code; | |
3083 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3084 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3085 | continue; |
4ed46869 KH |
3086 | |
3087 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3088 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3089 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3090 | goto invalid_code; | |
3091 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3092 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3093 | continue; |
4ed46869 KH |
3094 | |
3095 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3096 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3097 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3098 | goto invalid_code; | |
134b9549 KH |
3099 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3100 | if (charset_id_2 < 0) | |
3101 | charset = CHARSET_FROM_ID (charset_ascii); | |
3102 | else | |
3103 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3104 | ONE_MORE_BYTE (c1); |
e7046a18 | 3105 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3106 | goto invalid_code; |
4ed46869 KH |
3107 | break; |
3108 | ||
3109 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3110 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3111 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3112 | goto invalid_code; | |
134b9549 KH |
3113 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3114 | if (charset_id_3 < 0) | |
3115 | charset = CHARSET_FROM_ID (charset_ascii); | |
3116 | else | |
3117 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3118 | ONE_MORE_BYTE (c1); |
e7046a18 | 3119 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3120 | goto invalid_code; |
4ed46869 KH |
3121 | break; |
3122 | ||
ec6d2bb8 | 3123 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3124 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3125 | goto invalid_code; | |
ec6d2bb8 | 3126 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3127 | continue; |
4ed46869 | 3128 | |
ec6d2bb8 | 3129 | case '1': /* end composition */ |
df7492f9 KH |
3130 | if (composition_state == COMPOSING_NO) |
3131 | goto invalid_code; | |
3132 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3133 | continue; |
4ed46869 KH |
3134 | |
3135 | case '[': /* specification of direction */ | |
df7492f9 KH |
3136 | if (! CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION) |
3137 | goto invalid_code; | |
4ed46869 | 3138 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3139 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
df7492f9 | 3140 | left-to-right, and nozero means right-to-left. */ |
4ed46869 KH |
3141 | ONE_MORE_BYTE (c1); |
3142 | switch (c1) | |
3143 | { | |
3144 | case ']': /* end of the current direction */ | |
d46c5b12 | 3145 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3146 | |
3147 | case '0': /* end of the current direction */ | |
3148 | case '1': /* start of left-to-right direction */ | |
3149 | ONE_MORE_BYTE (c1); | |
3150 | if (c1 == ']') | |
d46c5b12 | 3151 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3152 | else |
df7492f9 | 3153 | goto invalid_code; |
4ed46869 KH |
3154 | break; |
3155 | ||
3156 | case '2': /* start of right-to-left direction */ | |
3157 | ONE_MORE_BYTE (c1); | |
3158 | if (c1 == ']') | |
d46c5b12 | 3159 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3160 | else |
df7492f9 | 3161 | goto invalid_code; |
4ed46869 KH |
3162 | break; |
3163 | ||
3164 | default: | |
df7492f9 | 3165 | goto invalid_code; |
4ed46869 | 3166 | } |
b73bfc1c | 3167 | continue; |
4ed46869 | 3168 | |
103e0180 | 3169 | case '%': |
103e0180 KH |
3170 | ONE_MORE_BYTE (c1); |
3171 | if (c1 == '/') | |
3172 | { | |
3173 | /* CTEXT extended segment: | |
3174 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3175 | We keep these bytes as is for the moment. | |
3176 | They may be decoded by post-read-conversion. */ | |
3177 | int dim, M, L; | |
4776e638 | 3178 | int size; |
8f924df7 | 3179 | |
103e0180 KH |
3180 | ONE_MORE_BYTE (dim); |
3181 | ONE_MORE_BYTE (M); | |
3182 | ONE_MORE_BYTE (L); | |
3183 | size = ((M - 128) * 128) + (L - 128); | |
4776e638 KH |
3184 | if (charbuf + 8 + size > charbuf_end) |
3185 | goto break_loop; | |
3186 | *charbuf++ = ISO_CODE_ESC; | |
3187 | *charbuf++ = '%'; | |
3188 | *charbuf++ = '/'; | |
3189 | *charbuf++ = dim; | |
3190 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3191 | *charbuf++ = BYTE8_TO_CHAR (L); | |
103e0180 KH |
3192 | while (size-- > 0) |
3193 | { | |
3194 | ONE_MORE_BYTE (c1); | |
4776e638 | 3195 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3196 | } |
103e0180 KH |
3197 | } |
3198 | else if (c1 == 'G') | |
3199 | { | |
103e0180 KH |
3200 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3201 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3202 | We keep these bytes as is for the moment. | |
3203 | They may be decoded by post-read-conversion. */ | |
4776e638 KH |
3204 | int *p = charbuf; |
3205 | ||
3206 | if (p + 6 > charbuf_end) | |
3207 | goto break_loop; | |
3208 | *p++ = ISO_CODE_ESC; | |
3209 | *p++ = '%'; | |
3210 | *p++ = 'G'; | |
3211 | while (p < charbuf_end) | |
103e0180 KH |
3212 | { |
3213 | ONE_MORE_BYTE (c1); | |
3214 | if (c1 == ISO_CODE_ESC | |
3215 | && src + 1 < src_end | |
3216 | && src[0] == '%' | |
3217 | && src[1] == '@') | |
9ffd559c KH |
3218 | { |
3219 | src += 2; | |
3220 | break; | |
3221 | } | |
4776e638 | 3222 | *p++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3223 | } |
4776e638 KH |
3224 | if (p + 3 > charbuf_end) |
3225 | goto break_loop; | |
3226 | *p++ = ISO_CODE_ESC; | |
3227 | *p++ = '%'; | |
3228 | *p++ = '@'; | |
3229 | charbuf = p; | |
103e0180 KH |
3230 | } |
3231 | else | |
4776e638 | 3232 | goto invalid_code; |
103e0180 | 3233 | continue; |
4776e638 | 3234 | break; |
103e0180 | 3235 | |
4ed46869 | 3236 | default: |
df7492f9 KH |
3237 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3238 | goto invalid_code; | |
134b9549 KH |
3239 | { |
3240 | int reg, chars96; | |
3241 | ||
3242 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3243 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3244 | reg = c1 - 0x28, chars96 = 0; | |
3245 | ONE_MORE_BYTE (c1); | |
3246 | } | |
3247 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3248 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3249 | reg = c1 - 0x2C, chars96 = 1; | |
3250 | ONE_MORE_BYTE (c1); | |
3251 | } | |
3252 | else | |
3253 | goto invalid_code; | |
3254 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3255 | /* We must update these variables now. */ | |
3256 | if (reg == 0) | |
3257 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3258 | else if (reg == 1) | |
3259 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3260 | if (chars96 < 0) | |
3261 | goto invalid_code; | |
3262 | } | |
b73bfc1c | 3263 | continue; |
4ed46869 | 3264 | } |
b73bfc1c | 3265 | } |
4ed46869 | 3266 | |
ff0dacd7 KH |
3267 | if (charset->id != charset_ascii |
3268 | && last_id != charset->id) | |
3269 | { | |
3270 | if (last_id != charset_ascii) | |
69a80ea3 | 3271 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3272 | last_id = charset->id; |
3273 | last_offset = char_offset; | |
3274 | } | |
3275 | ||
b73bfc1c | 3276 | /* Now we know CHARSET and 1st position code C1 of a character. |
df7492f9 KH |
3277 | Produce a decoded character while getting 2nd position code |
3278 | C2 if necessary. */ | |
3279 | c1 &= 0x7F; | |
3280 | if (CHARSET_DIMENSION (charset) > 1) | |
b73bfc1c KH |
3281 | { |
3282 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3283 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) |
b73bfc1c | 3284 | /* C2 is not in a valid range. */ |
df7492f9 KH |
3285 | goto invalid_code; |
3286 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3287 | if (CHARSET_DIMENSION (charset) > 2) | |
3288 | { | |
3289 | ONE_MORE_BYTE (c2); | |
3290 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) | |
3291 | /* C2 is not in a valid range. */ | |
3292 | goto invalid_code; | |
3293 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3294 | } | |
3295 | } | |
3296 | ||
3297 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); | |
3298 | if (c < 0) | |
3299 | { | |
3300 | MAYBE_FINISH_COMPOSITION (); | |
3301 | for (; src_base < src; src_base++, char_offset++) | |
3302 | { | |
3303 | if (ASCII_BYTE_P (*src_base)) | |
3304 | *charbuf++ = *src_base; | |
3305 | else | |
3306 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3307 | } | |
3308 | } | |
3309 | else if (composition_state == COMPOSING_NO) | |
3310 | { | |
3311 | *charbuf++ = c; | |
3312 | char_offset++; | |
4ed46869 | 3313 | } |
df7492f9 | 3314 | else |
781d7a48 KH |
3315 | { |
3316 | components[component_idx++] = c; | |
3317 | if (method == COMPOSITION_WITH_RULE | |
3318 | || (method == COMPOSITION_WITH_RULE_ALTCHARS | |
3319 | && composition_state == COMPOSING_COMPONENT_CHAR)) | |
3320 | composition_state++; | |
4ed46869 KH |
3321 | } |
3322 | continue; | |
3323 | ||
df7492f9 KH |
3324 | invalid_code: |
3325 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3326 | src = src_base; |
df7492f9 KH |
3327 | consumed_chars = consumed_chars_base; |
3328 | ONE_MORE_BYTE (c); | |
065e3595 | 3329 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3330 | char_offset++; |
df7492f9 | 3331 | coding->errors++; |
4776e638 KH |
3332 | continue; |
3333 | ||
3334 | break_loop: | |
3335 | break; | |
4ed46869 | 3336 | } |
fb88bf2d | 3337 | |
df7492f9 | 3338 | no_more_source: |
ff0dacd7 | 3339 | if (last_id != charset_ascii) |
69a80ea3 | 3340 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
3341 | coding->consumed_char += consumed_chars_base; |
3342 | coding->consumed = src_base - coding->source; | |
3343 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3344 | } |
3345 | ||
b73bfc1c | 3346 | |
f4dee582 | 3347 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3348 | |
3349 | /* | |
f4dee582 | 3350 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 3351 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 3352 | variant has the following specifications: |
df7492f9 | 3353 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
3354 | 2. Allows short-form designation? |
3355 | 3. ASCII should be designated to G0 before control characters? | |
3356 | 4. ASCII should be designated to G0 at end of line? | |
3357 | 5. 7-bit environment or 8-bit environment? | |
3358 | 6. Use locking-shift? | |
3359 | 7. Use Single-shift? | |
3360 | And the following two are only for Japanese: | |
3361 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
3362 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
3363 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
3364 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 3365 | details. |
4ed46869 KH |
3366 | */ |
3367 | ||
3368 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
3369 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
3370 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
3371 | designation sequence of short-form. */ | |
4ed46869 KH |
3372 | |
3373 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
3374 | do { \ | |
df7492f9 | 3375 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
4ed46869 KH |
3376 | char *intermediate_char_94 = "()*+"; \ |
3377 | char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
3378 | int revision = -1; \ |
3379 | int c; \ | |
3380 | \ | |
3381 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 3382 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
3383 | \ |
3384 | if (revision >= 0) \ | |
70c22245 | 3385 | { \ |
df7492f9 KH |
3386 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
3387 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 3388 | } \ |
df7492f9 | 3389 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
3390 | if (CHARSET_DIMENSION (charset) == 1) \ |
3391 | { \ | |
df7492f9 KH |
3392 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
3393 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 3394 | else \ |
df7492f9 KH |
3395 | c = intermediate_char_96[reg]; \ |
3396 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
3397 | } \ |
3398 | else \ | |
3399 | { \ | |
df7492f9 KH |
3400 | EMIT_ONE_ASCII_BYTE ('$'); \ |
3401 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 3402 | { \ |
df7492f9 | 3403 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
3404 | || reg != 0 \ |
3405 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 3406 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
3407 | } \ |
3408 | else \ | |
df7492f9 | 3409 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 3410 | } \ |
df7492f9 KH |
3411 | EMIT_ONE_ASCII_BYTE (final_char); \ |
3412 | \ | |
3413 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
3414 | } while (0) |
3415 | ||
df7492f9 | 3416 | |
4ed46869 KH |
3417 | /* The following two macros produce codes (control character or escape |
3418 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
3419 | single-shift-3). */ | |
3420 | ||
df7492f9 KH |
3421 | #define ENCODE_SINGLE_SHIFT_2 \ |
3422 | do { \ | |
3423 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3424 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
3425 | else \ | |
3426 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
3427 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3428 | } while (0) |
3429 | ||
df7492f9 KH |
3430 | |
3431 | #define ENCODE_SINGLE_SHIFT_3 \ | |
3432 | do { \ | |
3433 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3434 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
3435 | else \ | |
3436 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
3437 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3438 | } while (0) |
3439 | ||
df7492f9 | 3440 | |
4ed46869 KH |
3441 | /* The following four macros produce codes (control character or |
3442 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
3443 | shift-out, locking-shift-2, and locking-shift-3). */ | |
3444 | ||
df7492f9 KH |
3445 | #define ENCODE_SHIFT_IN \ |
3446 | do { \ | |
3447 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
3448 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
3449 | } while (0) |
3450 | ||
df7492f9 KH |
3451 | |
3452 | #define ENCODE_SHIFT_OUT \ | |
3453 | do { \ | |
3454 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
3455 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
3456 | } while (0) |
3457 | ||
df7492f9 KH |
3458 | |
3459 | #define ENCODE_LOCKING_SHIFT_2 \ | |
3460 | do { \ | |
3461 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3462 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
3463 | } while (0) |
3464 | ||
df7492f9 KH |
3465 | |
3466 | #define ENCODE_LOCKING_SHIFT_3 \ | |
3467 | do { \ | |
3468 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3469 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
3470 | } while (0) |
3471 | ||
df7492f9 | 3472 | |
f4dee582 RS |
3473 | /* Produce codes for a DIMENSION1 character whose character set is |
3474 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
3475 | sequences are also produced in advance if necessary. */ |
3476 | ||
6e85d753 KH |
3477 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
3478 | do { \ | |
df7492f9 | 3479 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3480 | \ |
3481 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3482 | && id == charset_ascii) \ | |
3483 | { \ | |
3484 | id = charset_jisx0201_roman; \ | |
3485 | charset = CHARSET_FROM_ID (id); \ | |
3486 | } \ | |
3487 | \ | |
df7492f9 | 3488 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3489 | { \ |
df7492f9 KH |
3490 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3491 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 3492 | else \ |
df7492f9 KH |
3493 | EMIT_ONE_BYTE (c1 | 0x80); \ |
3494 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3495 | break; \ |
3496 | } \ | |
df7492f9 | 3497 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3498 | { \ |
df7492f9 | 3499 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
3500 | break; \ |
3501 | } \ | |
df7492f9 | 3502 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3503 | { \ |
df7492f9 | 3504 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
3505 | break; \ |
3506 | } \ | |
6e85d753 KH |
3507 | else \ |
3508 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3509 | must invoke it, or, at first, designate it to some graphic \ | |
3510 | register. Then repeat the loop to actually produce the \ | |
3511 | character. */ \ | |
df7492f9 KH |
3512 | dst = encode_invocation_designation (charset, coding, dst, \ |
3513 | &produced_chars); \ | |
4ed46869 KH |
3514 | } while (1) |
3515 | ||
df7492f9 | 3516 | |
f4dee582 RS |
3517 | /* Produce codes for a DIMENSION2 character whose character set is |
3518 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
3519 | invocation codes are also produced in advance if necessary. */ |
3520 | ||
6e85d753 KH |
3521 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
3522 | do { \ | |
df7492f9 | 3523 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3524 | \ |
3525 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3526 | && id == charset_jisx0208) \ | |
3527 | { \ | |
3528 | id = charset_jisx0208_1978; \ | |
3529 | charset = CHARSET_FROM_ID (id); \ | |
3530 | } \ | |
3531 | \ | |
df7492f9 | 3532 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3533 | { \ |
df7492f9 KH |
3534 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3535 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 3536 | else \ |
df7492f9 KH |
3537 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
3538 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3539 | break; \ |
3540 | } \ | |
df7492f9 | 3541 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3542 | { \ |
df7492f9 | 3543 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
3544 | break; \ |
3545 | } \ | |
df7492f9 | 3546 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3547 | { \ |
df7492f9 | 3548 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
3549 | break; \ |
3550 | } \ | |
6e85d753 KH |
3551 | else \ |
3552 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3553 | must invoke it, or, at first, designate it to some graphic \ | |
3554 | register. Then repeat the loop to actually produce the \ | |
3555 | character. */ \ | |
df7492f9 KH |
3556 | dst = encode_invocation_designation (charset, coding, dst, \ |
3557 | &produced_chars); \ | |
4ed46869 KH |
3558 | } while (1) |
3559 | ||
05e6f5dc | 3560 | |
df7492f9 KH |
3561 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
3562 | do { \ | |
3563 | int code = ENCODE_CHAR ((charset),(c)); \ | |
3564 | \ | |
3565 | if (CHARSET_DIMENSION (charset) == 1) \ | |
3566 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
3567 | else \ | |
3568 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 3569 | } while (0) |
bdd9fb48 | 3570 | |
05e6f5dc | 3571 | |
4ed46869 | 3572 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 3573 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
3574 | Return new DST. */ |
3575 | ||
3576 | unsigned char * | |
df7492f9 KH |
3577 | encode_invocation_designation (charset, coding, dst, p_nchars) |
3578 | struct charset *charset; | |
4ed46869 KH |
3579 | struct coding_system *coding; |
3580 | unsigned char *dst; | |
df7492f9 | 3581 | int *p_nchars; |
4ed46869 | 3582 | { |
df7492f9 KH |
3583 | int multibytep = coding->dst_multibyte; |
3584 | int produced_chars = *p_nchars; | |
4ed46869 | 3585 | int reg; /* graphic register number */ |
df7492f9 | 3586 | int id = CHARSET_ID (charset); |
4ed46869 KH |
3587 | |
3588 | /* At first, check designations. */ | |
3589 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 3590 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
3591 | break; |
3592 | ||
3593 | if (reg >= 4) | |
3594 | { | |
3595 | /* CHARSET is not yet designated to any graphic registers. */ | |
3596 | /* At first check the requested designation. */ | |
df7492f9 KH |
3597 | reg = CODING_ISO_REQUEST (coding, id); |
3598 | if (reg < 0) | |
1ba9e4ab KH |
3599 | /* Since CHARSET requests no special designation, designate it |
3600 | to graphic register 0. */ | |
4ed46869 KH |
3601 | reg = 0; |
3602 | ||
3603 | ENCODE_DESIGNATION (charset, reg, coding); | |
3604 | } | |
3605 | ||
df7492f9 KH |
3606 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
3607 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
3608 | { |
3609 | /* Since the graphic register REG is not invoked to any graphic | |
3610 | planes, invoke it to graphic plane 0. */ | |
3611 | switch (reg) | |
3612 | { | |
3613 | case 0: /* graphic register 0 */ | |
3614 | ENCODE_SHIFT_IN; | |
3615 | break; | |
3616 | ||
3617 | case 1: /* graphic register 1 */ | |
3618 | ENCODE_SHIFT_OUT; | |
3619 | break; | |
3620 | ||
3621 | case 2: /* graphic register 2 */ | |
df7492f9 | 3622 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3623 | ENCODE_SINGLE_SHIFT_2; |
3624 | else | |
3625 | ENCODE_LOCKING_SHIFT_2; | |
3626 | break; | |
3627 | ||
3628 | case 3: /* graphic register 3 */ | |
df7492f9 | 3629 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3630 | ENCODE_SINGLE_SHIFT_3; |
3631 | else | |
3632 | ENCODE_LOCKING_SHIFT_3; | |
3633 | break; | |
3634 | } | |
3635 | } | |
b73bfc1c | 3636 | |
df7492f9 | 3637 | *p_nchars = produced_chars; |
4ed46869 KH |
3638 | return dst; |
3639 | } | |
3640 | ||
df7492f9 KH |
3641 | /* The following three macros produce codes for indicating direction |
3642 | of text. */ | |
3643 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 3644 | do { \ |
df7492f9 KH |
3645 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
3646 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 3647 | else \ |
df7492f9 | 3648 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
3649 | } while (0) |
3650 | ||
ec6d2bb8 | 3651 | |
df7492f9 KH |
3652 | #define ENCODE_DIRECTION_R2L() \ |
3653 | do { \ | |
3654 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
3655 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
3656 | } while (0) |
3657 | ||
ec6d2bb8 | 3658 | |
df7492f9 | 3659 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 3660 | do { \ |
df7492f9 KH |
3661 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
3662 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
ec6d2bb8 | 3663 | } while (0) |
4ed46869 | 3664 | |
4ed46869 KH |
3665 | |
3666 | /* Produce codes for designation and invocation to reset the graphic | |
3667 | planes and registers to initial state. */ | |
df7492f9 KH |
3668 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
3669 | do { \ | |
3670 | int reg; \ | |
3671 | struct charset *charset; \ | |
3672 | \ | |
3673 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
3674 | ENCODE_SHIFT_IN; \ | |
3675 | for (reg = 0; reg < 4; reg++) \ | |
3676 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
3677 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
3678 | != CODING_ISO_INITIAL (coding, reg))) \ | |
3679 | { \ | |
3680 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
3681 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
3682 | } \ | |
4ed46869 KH |
3683 | } while (0) |
3684 | ||
df7492f9 | 3685 | |
bdd9fb48 | 3686 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 3687 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
3688 | |
3689 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
3690 | find all the necessary designations. */ |
3691 | ||
b73bfc1c | 3692 | static unsigned char * |
df7492f9 | 3693 | encode_designation_at_bol (coding, charbuf, charbuf_end, dst) |
e0e989f6 | 3694 | struct coding_system *coding; |
df7492f9 KH |
3695 | int *charbuf, *charbuf_end; |
3696 | unsigned char *dst; | |
e0e989f6 | 3697 | { |
df7492f9 | 3698 | struct charset *charset; |
bdd9fb48 KH |
3699 | /* Table of charsets to be designated to each graphic register. */ |
3700 | int r[4]; | |
df7492f9 KH |
3701 | int c, found = 0, reg; |
3702 | int produced_chars = 0; | |
3703 | int multibytep = coding->dst_multibyte; | |
3704 | Lisp_Object attrs; | |
3705 | Lisp_Object charset_list; | |
3706 | ||
3707 | attrs = CODING_ID_ATTRS (coding->id); | |
3708 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
3709 | if (EQ (charset_list, Qiso_2022)) | |
3710 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
3711 | |
3712 | for (reg = 0; reg < 4; reg++) | |
3713 | r[reg] = -1; | |
3714 | ||
b73bfc1c | 3715 | while (found < 4) |
e0e989f6 | 3716 | { |
df7492f9 KH |
3717 | int id; |
3718 | ||
3719 | c = *charbuf++; | |
b73bfc1c KH |
3720 | if (c == '\n') |
3721 | break; | |
df7492f9 KH |
3722 | charset = char_charset (c, charset_list, NULL); |
3723 | id = CHARSET_ID (charset); | |
3724 | reg = CODING_ISO_REQUEST (coding, id); | |
3725 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
3726 | { |
3727 | found++; | |
df7492f9 | 3728 | r[reg] = id; |
bdd9fb48 | 3729 | } |
bdd9fb48 KH |
3730 | } |
3731 | ||
3732 | if (found) | |
3733 | { | |
3734 | for (reg = 0; reg < 4; reg++) | |
3735 | if (r[reg] >= 0 | |
df7492f9 KH |
3736 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
3737 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 3738 | } |
b73bfc1c KH |
3739 | |
3740 | return dst; | |
e0e989f6 KH |
3741 | } |
3742 | ||
4ed46869 KH |
3743 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
3744 | ||
df7492f9 KH |
3745 | static int |
3746 | encode_coding_iso_2022 (coding) | |
4ed46869 | 3747 | struct coding_system *coding; |
4ed46869 | 3748 | { |
df7492f9 KH |
3749 | int multibytep = coding->dst_multibyte; |
3750 | int *charbuf = coding->charbuf; | |
3751 | int *charbuf_end = charbuf + coding->charbuf_used; | |
3752 | unsigned char *dst = coding->destination + coding->produced; | |
3753 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
3754 | int safe_room = 16; | |
3755 | int bol_designation | |
3756 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
3757 | && CODING_ISO_BOL (coding)); | |
3758 | int produced_chars = 0; | |
3759 | Lisp_Object attrs, eol_type, charset_list; | |
3760 | int ascii_compatible; | |
b73bfc1c | 3761 | int c; |
ff0dacd7 | 3762 | int preferred_charset_id = -1; |
05e6f5dc | 3763 | |
24a73b0a KH |
3764 | CODING_GET_INFO (coding, attrs, charset_list); |
3765 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
3766 | if (VECTORP (eol_type)) | |
3767 | eol_type = Qunix; | |
3768 | ||
004068e4 | 3769 | setup_iso_safe_charsets (attrs); |
ff0dacd7 KH |
3770 | /* Charset list may have been changed. */ |
3771 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); \ | |
8f924df7 | 3772 | coding->safe_charsets = (char *) SDATA (CODING_ATTR_SAFE_CHARSETS(attrs)); |
0eecad43 | 3773 | |
df7492f9 | 3774 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
bdd9fb48 | 3775 | |
df7492f9 | 3776 | while (charbuf < charbuf_end) |
4ed46869 | 3777 | { |
df7492f9 | 3778 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 3779 | |
df7492f9 | 3780 | if (bol_designation) |
b73bfc1c | 3781 | { |
df7492f9 | 3782 | unsigned char *dst_prev = dst; |
4ed46869 | 3783 | |
bdd9fb48 | 3784 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
3785 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
3786 | bol_designation = 0; | |
3787 | /* We are sure that designation sequences are all ASCII bytes. */ | |
3788 | produced_chars += dst - dst_prev; | |
e0e989f6 KH |
3789 | } |
3790 | ||
df7492f9 | 3791 | c = *charbuf++; |
ec6d2bb8 | 3792 | |
ff0dacd7 KH |
3793 | if (c < 0) |
3794 | { | |
3795 | /* Handle an annotation. */ | |
3796 | switch (*charbuf) | |
ec6d2bb8 | 3797 | { |
ff0dacd7 KH |
3798 | case CODING_ANNOTATE_COMPOSITION_MASK: |
3799 | /* Not yet implemented. */ | |
3800 | break; | |
3801 | case CODING_ANNOTATE_CHARSET_MASK: | |
3802 | preferred_charset_id = charbuf[3]; | |
3803 | if (preferred_charset_id >= 0 | |
3804 | && NILP (Fmemq (make_number (preferred_charset_id), | |
3805 | charset_list))) | |
3806 | preferred_charset_id = -1; | |
3807 | break; | |
3808 | default: | |
3809 | abort (); | |
4ed46869 | 3810 | } |
ff0dacd7 KH |
3811 | charbuf += -c - 1; |
3812 | continue; | |
4ed46869 | 3813 | } |
ec6d2bb8 | 3814 | |
b73bfc1c KH |
3815 | /* Now encode the character C. */ |
3816 | if (c < 0x20 || c == 0x7F) | |
3817 | { | |
df7492f9 KH |
3818 | if (c == '\n' |
3819 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 3820 | { |
df7492f9 KH |
3821 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
3822 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3823 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 3824 | { |
df7492f9 KH |
3825 | int i; |
3826 | ||
3827 | for (i = 0; i < 4; i++) | |
3828 | CODING_ISO_DESIGNATION (coding, i) | |
3829 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 3830 | } |
df7492f9 KH |
3831 | bol_designation |
3832 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 3833 | } |
df7492f9 KH |
3834 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
3835 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3836 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 3837 | } |
df7492f9 | 3838 | else if (ASCII_CHAR_P (c)) |
88993dfd | 3839 | { |
df7492f9 KH |
3840 | if (ascii_compatible) |
3841 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 3842 | else |
19a8d9e0 | 3843 | { |
bf16eb23 KH |
3844 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
3845 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 3846 | } |
4ed46869 | 3847 | } |
16eafb5d | 3848 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 3849 | { |
16eafb5d KH |
3850 | c = CHAR_TO_BYTE8 (c); |
3851 | EMIT_ONE_BYTE (c); | |
88993dfd | 3852 | } |
b73bfc1c | 3853 | else |
df7492f9 | 3854 | { |
ff0dacd7 | 3855 | struct charset *charset; |
b73bfc1c | 3856 | |
ff0dacd7 KH |
3857 | if (preferred_charset_id >= 0) |
3858 | { | |
3859 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
3860 | if (! CHAR_CHARSET_P (c, charset)) | |
3861 | charset = char_charset (c, charset_list, NULL); | |
3862 | } | |
3863 | else | |
3864 | charset = char_charset (c, charset_list, NULL); | |
df7492f9 KH |
3865 | if (!charset) |
3866 | { | |
41cbe562 KH |
3867 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
3868 | { | |
3869 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
3870 | charset = CHARSET_FROM_ID (charset_ascii); | |
3871 | } | |
3872 | else | |
3873 | { | |
3874 | c = coding->default_char; | |
3875 | charset = char_charset (c, charset_list, NULL); | |
3876 | } | |
df7492f9 KH |
3877 | } |
3878 | ENCODE_ISO_CHARACTER (charset, c); | |
3879 | } | |
84fbb8a0 | 3880 | } |
b73bfc1c | 3881 | |
df7492f9 KH |
3882 | if (coding->mode & CODING_MODE_LAST_BLOCK |
3883 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
3884 | { | |
3885 | ASSURE_DESTINATION (safe_room); | |
3886 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3887 | } | |
065e3595 | 3888 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
3889 | CODING_ISO_BOL (coding) = bol_designation; |
3890 | coding->produced_char += produced_chars; | |
3891 | coding->produced = dst - coding->destination; | |
3892 | return 0; | |
4ed46869 KH |
3893 | } |
3894 | ||
3895 | \f | |
df7492f9 | 3896 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 3897 | |
df7492f9 | 3898 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
3899 | quite widely. So, for the moment, Emacs supports them in the bare |
3900 | C code. But, in the future, they may be supported only by CCL. */ | |
3901 | ||
3902 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
3903 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
3904 | as is. A character of charset katakana-jisx0201 is encoded by | |
3905 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
3906 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 3907 | so that it fit in the range below. |
4ed46869 KH |
3908 | |
3909 | --- CODE RANGE of SJIS --- | |
3910 | (character set) (range) | |
3911 | ASCII 0x00 .. 0x7F | |
df7492f9 | 3912 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 3913 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 3914 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
3915 | ------------------------------- |
3916 | ||
3917 | */ | |
3918 | ||
3919 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
3920 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 3921 | character set and is encoded in two-byte. |
4ed46869 KH |
3922 | |
3923 | --- CODE RANGE of BIG5 --- | |
3924 | (character set) (range) | |
3925 | ASCII 0x00 .. 0x7F | |
3926 | Big5 (1st byte) 0xA1 .. 0xFE | |
3927 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
3928 | -------------------------- | |
3929 | ||
df7492f9 | 3930 | */ |
4ed46869 KH |
3931 | |
3932 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3933 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 3934 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 3935 | |
0a28aafb | 3936 | static int |
ff0dacd7 | 3937 | detect_coding_sjis (coding, detect_info) |
df7492f9 | 3938 | struct coding_system *coding; |
ff0dacd7 | 3939 | struct coding_detection_info *detect_info; |
4ed46869 | 3940 | { |
065e3595 | 3941 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 3942 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
3943 | int multibytep = coding->src_multibyte; |
3944 | int consumed_chars = 0; | |
3945 | int found = 0; | |
b73bfc1c | 3946 | int c; |
df7492f9 | 3947 | |
ff0dacd7 | 3948 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3949 | /* A coding system of this category is always ASCII compatible. */ |
3950 | src += coding->head_ascii; | |
4ed46869 | 3951 | |
b73bfc1c | 3952 | while (1) |
4ed46869 | 3953 | { |
065e3595 | 3954 | src_base = src; |
df7492f9 | 3955 | ONE_MORE_BYTE (c); |
682169fe KH |
3956 | if (c < 0x80) |
3957 | continue; | |
df7492f9 | 3958 | if ((c >= 0x81 && c <= 0x9F) || (c >= 0xE0 && c <= 0xEF)) |
4ed46869 | 3959 | { |
df7492f9 | 3960 | ONE_MORE_BYTE (c); |
682169fe | 3961 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 3962 | break; |
ff0dacd7 | 3963 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 3964 | } |
df7492f9 | 3965 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 3966 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
3967 | else |
3968 | break; | |
4ed46869 | 3969 | } |
ff0dacd7 | 3970 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3971 | return 0; |
3972 | ||
3973 | no_more_source: | |
065e3595 | 3974 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 3975 | { |
ff0dacd7 | 3976 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 3977 | return 0; |
4ed46869 | 3978 | } |
ff0dacd7 KH |
3979 | detect_info->found |= found; |
3980 | return 1; | |
4ed46869 KH |
3981 | } |
3982 | ||
3983 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3984 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 3985 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 3986 | |
0a28aafb | 3987 | static int |
ff0dacd7 | 3988 | detect_coding_big5 (coding, detect_info) |
df7492f9 | 3989 | struct coding_system *coding; |
ff0dacd7 | 3990 | struct coding_detection_info *detect_info; |
4ed46869 | 3991 | { |
065e3595 | 3992 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 3993 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
3994 | int multibytep = coding->src_multibyte; |
3995 | int consumed_chars = 0; | |
3996 | int found = 0; | |
b73bfc1c | 3997 | int c; |
fa42c37f | 3998 | |
ff0dacd7 | 3999 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4000 | /* A coding system of this category is always ASCII compatible. */ |
4001 | src += coding->head_ascii; | |
fa42c37f | 4002 | |
b73bfc1c | 4003 | while (1) |
fa42c37f | 4004 | { |
065e3595 | 4005 | src_base = src; |
df7492f9 KH |
4006 | ONE_MORE_BYTE (c); |
4007 | if (c < 0x80) | |
fa42c37f | 4008 | continue; |
df7492f9 | 4009 | if (c >= 0xA1) |
fa42c37f | 4010 | { |
df7492f9 KH |
4011 | ONE_MORE_BYTE (c); |
4012 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4013 | return 0; |
ff0dacd7 | 4014 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4015 | } |
df7492f9 KH |
4016 | else |
4017 | break; | |
fa42c37f | 4018 | } |
ff0dacd7 | 4019 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4020 | return 0; |
fa42c37f | 4021 | |
df7492f9 | 4022 | no_more_source: |
065e3595 | 4023 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4024 | { |
ff0dacd7 | 4025 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4026 | return 0; |
4027 | } | |
ff0dacd7 KH |
4028 | detect_info->found |= found; |
4029 | return 1; | |
fa42c37f KH |
4030 | } |
4031 | ||
4ed46869 KH |
4032 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
4033 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
fa42c37f | 4034 | |
b73bfc1c | 4035 | static void |
df7492f9 | 4036 | decode_coding_sjis (coding) |
4ed46869 | 4037 | struct coding_system *coding; |
4ed46869 | 4038 | { |
8f924df7 KH |
4039 | const unsigned char *src = coding->source + coding->consumed; |
4040 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4041 | const unsigned char *src_base; | |
69a80ea3 KH |
4042 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4043 | int *charbuf_end | |
4044 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4045 | int consumed_chars = 0, consumed_chars_base; |
4046 | int multibytep = coding->src_multibyte; | |
4047 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4048 | struct charset *charset_kanji2; |
24a73b0a | 4049 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4050 | int char_offset = coding->produced_char; |
4051 | int last_offset = char_offset; | |
4052 | int last_id = charset_ascii; | |
a5d301df | 4053 | |
24a73b0a | 4054 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4055 | |
4056 | val = charset_list; | |
4057 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4058 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4059 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4060 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4061 | |
b73bfc1c | 4062 | while (1) |
4ed46869 | 4063 | { |
df7492f9 | 4064 | int c, c1; |
24a73b0a | 4065 | struct charset *charset; |
fa42c37f | 4066 | |
b73bfc1c | 4067 | src_base = src; |
df7492f9 | 4068 | consumed_chars_base = consumed_chars; |
fa42c37f | 4069 | |
df7492f9 KH |
4070 | if (charbuf >= charbuf_end) |
4071 | break; | |
4072 | ||
4073 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4074 | if (c < 0) |
4075 | goto invalid_code; | |
24a73b0a KH |
4076 | if (c < 0x80) |
4077 | charset = charset_roman; | |
57a47f8a | 4078 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4079 | goto invalid_code; |
57a47f8a KH |
4080 | else if (c >= 0xA1 && c <= 0xDF) |
4081 | { | |
4082 | /* SJIS -> JISX0201-Kana */ | |
4083 | c &= 0x7F; | |
4084 | charset = charset_kana; | |
4085 | } | |
4086 | else if (c <= 0xEF) | |
df7492f9 | 4087 | { |
57a47f8a KH |
4088 | /* SJIS -> JISX0208 */ |
4089 | ONE_MORE_BYTE (c1); | |
4090 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4091 | goto invalid_code; |
57a47f8a KH |
4092 | c = (c << 8) | c1; |
4093 | SJIS_TO_JIS (c); | |
4094 | charset = charset_kanji; | |
4095 | } | |
4096 | else if (c <= 0xFC && charset_kanji2) | |
4097 | { | |
c6876370 | 4098 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4099 | ONE_MORE_BYTE (c1); |
4100 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4101 | goto invalid_code; |
57a47f8a KH |
4102 | c = (c << 8) | c1; |
4103 | SJIS_TO_JIS2 (c); | |
4104 | charset = charset_kanji2; | |
df7492f9 | 4105 | } |
57a47f8a KH |
4106 | else |
4107 | goto invalid_code; | |
24a73b0a KH |
4108 | if (charset->id != charset_ascii |
4109 | && last_id != charset->id) | |
4110 | { | |
4111 | if (last_id != charset_ascii) | |
69a80ea3 | 4112 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4113 | last_id = charset->id; |
4114 | last_offset = char_offset; | |
4115 | } | |
4116 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4117 | *charbuf++ = c; |
ff0dacd7 | 4118 | char_offset++; |
df7492f9 | 4119 | continue; |
b73bfc1c | 4120 | |
df7492f9 KH |
4121 | invalid_code: |
4122 | src = src_base; | |
4123 | consumed_chars = consumed_chars_base; | |
4124 | ONE_MORE_BYTE (c); | |
065e3595 | 4125 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4126 | char_offset++; |
df7492f9 KH |
4127 | coding->errors++; |
4128 | } | |
fa42c37f | 4129 | |
df7492f9 | 4130 | no_more_source: |
ff0dacd7 | 4131 | if (last_id != charset_ascii) |
69a80ea3 | 4132 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4133 | coding->consumed_char += consumed_chars_base; |
4134 | coding->consumed = src_base - coding->source; | |
4135 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4136 | } |
4137 | ||
b73bfc1c | 4138 | static void |
df7492f9 | 4139 | decode_coding_big5 (coding) |
4ed46869 | 4140 | struct coding_system *coding; |
4ed46869 | 4141 | { |
8f924df7 KH |
4142 | const unsigned char *src = coding->source + coding->consumed; |
4143 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4144 | const unsigned char *src_base; | |
69a80ea3 KH |
4145 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4146 | int *charbuf_end | |
4147 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4148 | int consumed_chars = 0, consumed_chars_base; |
4149 | int multibytep = coding->src_multibyte; | |
4150 | struct charset *charset_roman, *charset_big5; | |
24a73b0a | 4151 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4152 | int char_offset = coding->produced_char; |
4153 | int last_offset = char_offset; | |
4154 | int last_id = charset_ascii; | |
df7492f9 | 4155 | |
24a73b0a | 4156 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4157 | val = charset_list; |
4158 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4159 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4160 | |
b73bfc1c | 4161 | while (1) |
4ed46869 | 4162 | { |
df7492f9 | 4163 | int c, c1; |
24a73b0a | 4164 | struct charset *charset; |
b73bfc1c KH |
4165 | |
4166 | src_base = src; | |
df7492f9 KH |
4167 | consumed_chars_base = consumed_chars; |
4168 | ||
4169 | if (charbuf >= charbuf_end) | |
4170 | break; | |
4171 | ||
4172 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4173 | |
065e3595 KH |
4174 | if (c < 0) |
4175 | goto invalid_code; | |
24a73b0a KH |
4176 | if (c < 0x80) |
4177 | charset = charset_roman; | |
4178 | else | |
4ed46869 | 4179 | { |
24a73b0a KH |
4180 | /* BIG5 -> Big5 */ |
4181 | if (c < 0xA1 || c > 0xFE) | |
4182 | goto invalid_code; | |
4183 | ONE_MORE_BYTE (c1); | |
4184 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4185 | goto invalid_code; | |
4186 | c = c << 8 | c1; | |
4187 | charset = charset_big5; | |
4ed46869 | 4188 | } |
24a73b0a KH |
4189 | if (charset->id != charset_ascii |
4190 | && last_id != charset->id) | |
df7492f9 | 4191 | { |
24a73b0a | 4192 | if (last_id != charset_ascii) |
69a80ea3 | 4193 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4194 | last_id = charset->id; |
4195 | last_offset = char_offset; | |
4ed46869 | 4196 | } |
24a73b0a | 4197 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4198 | *charbuf++ = c; |
ff0dacd7 | 4199 | char_offset++; |
fb88bf2d KH |
4200 | continue; |
4201 | ||
df7492f9 | 4202 | invalid_code: |
4ed46869 | 4203 | src = src_base; |
df7492f9 KH |
4204 | consumed_chars = consumed_chars_base; |
4205 | ONE_MORE_BYTE (c); | |
065e3595 | 4206 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4207 | char_offset++; |
df7492f9 | 4208 | coding->errors++; |
fb88bf2d | 4209 | } |
d46c5b12 | 4210 | |
df7492f9 | 4211 | no_more_source: |
ff0dacd7 | 4212 | if (last_id != charset_ascii) |
69a80ea3 | 4213 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4214 | coding->consumed_char += consumed_chars_base; |
4215 | coding->consumed = src_base - coding->source; | |
4216 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4217 | } |
4218 | ||
4219 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4220 | This function can encode charsets `ascii', `katakana-jisx0201', |
4221 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4222 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
4223 | (i.e. do not have extended leading-codes). Characters of other |
4224 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
4225 | SJIS text, else encode BIG5 text. */ | |
4226 | ||
df7492f9 KH |
4227 | static int |
4228 | encode_coding_sjis (coding) | |
4ed46869 | 4229 | struct coding_system *coding; |
4ed46869 | 4230 | { |
df7492f9 KH |
4231 | int multibytep = coding->dst_multibyte; |
4232 | int *charbuf = coding->charbuf; | |
4233 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4234 | unsigned char *dst = coding->destination + coding->produced; | |
4235 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4236 | int safe_room = 4; | |
4237 | int produced_chars = 0; | |
24a73b0a | 4238 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4239 | int ascii_compatible; |
4240 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4241 | struct charset *charset_kanji2; |
df7492f9 | 4242 | int c; |
a5d301df | 4243 | |
24a73b0a | 4244 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4245 | val = charset_list; |
4246 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4247 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
57a47f8a KH |
4248 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4249 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4250 | |
df7492f9 | 4251 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4252 | |
df7492f9 KH |
4253 | while (charbuf < charbuf_end) |
4254 | { | |
4255 | ASSURE_DESTINATION (safe_room); | |
4256 | c = *charbuf++; | |
b73bfc1c | 4257 | /* Now encode the character C. */ |
df7492f9 KH |
4258 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4259 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4260 | else if (CHAR_BYTE8_P (c)) |
4261 | { | |
4262 | c = CHAR_TO_BYTE8 (c); | |
4263 | EMIT_ONE_BYTE (c); | |
4264 | } | |
df7492f9 | 4265 | else |
b73bfc1c | 4266 | { |
df7492f9 KH |
4267 | unsigned code; |
4268 | struct charset *charset = char_charset (c, charset_list, &code); | |
4269 | ||
4270 | if (!charset) | |
4ed46869 | 4271 | { |
41cbe562 | 4272 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4273 | { |
41cbe562 KH |
4274 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4275 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4276 | } |
41cbe562 | 4277 | else |
b73bfc1c | 4278 | { |
41cbe562 KH |
4279 | c = coding->default_char; |
4280 | charset = char_charset (c, charset_list, &code); | |
b73bfc1c | 4281 | } |
b73bfc1c | 4282 | } |
df7492f9 KH |
4283 | if (code == CHARSET_INVALID_CODE (charset)) |
4284 | abort (); | |
4285 | if (charset == charset_kanji) | |
4286 | { | |
4287 | int c1, c2; | |
4288 | JIS_TO_SJIS (code); | |
4289 | c1 = code >> 8, c2 = code & 0xFF; | |
4290 | EMIT_TWO_BYTES (c1, c2); | |
4291 | } | |
4292 | else if (charset == charset_kana) | |
4293 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
4294 | else if (charset_kanji2 && charset == charset_kanji2) |
4295 | { | |
4296 | int c1, c2; | |
4297 | ||
4298 | c1 = code >> 8; | |
4299 | if (c1 == 0x21 || (c1 >= 0x23 && c1 < 0x25) | |
4300 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) | |
4301 | { | |
4302 | JIS_TO_SJIS2 (code); | |
4303 | c1 = code >> 8, c2 = code & 0xFF; | |
4304 | EMIT_TWO_BYTES (c1, c2); | |
4305 | } | |
4306 | else | |
4307 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4308 | } | |
df7492f9 KH |
4309 | else |
4310 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4311 | } | |
4312 | } | |
065e3595 | 4313 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4314 | coding->produced_char += produced_chars; |
4315 | coding->produced = dst - coding->destination; | |
4316 | return 0; | |
4317 | } | |
4318 | ||
4319 | static int | |
4320 | encode_coding_big5 (coding) | |
4321 | struct coding_system *coding; | |
4322 | { | |
4323 | int multibytep = coding->dst_multibyte; | |
4324 | int *charbuf = coding->charbuf; | |
4325 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4326 | unsigned char *dst = coding->destination + coding->produced; | |
4327 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4328 | int safe_room = 4; | |
4329 | int produced_chars = 0; | |
24a73b0a | 4330 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4331 | int ascii_compatible; |
4332 | struct charset *charset_roman, *charset_big5; | |
4333 | int c; | |
4334 | ||
24a73b0a | 4335 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4336 | val = charset_list; |
4337 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4338 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4339 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
4340 | ||
4341 | while (charbuf < charbuf_end) | |
4342 | { | |
4343 | ASSURE_DESTINATION (safe_room); | |
4344 | c = *charbuf++; | |
4345 | /* Now encode the character C. */ | |
4346 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
4347 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4348 | else if (CHAR_BYTE8_P (c)) |
4349 | { | |
4350 | c = CHAR_TO_BYTE8 (c); | |
4351 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
4352 | } |
4353 | else | |
4354 | { | |
df7492f9 KH |
4355 | unsigned code; |
4356 | struct charset *charset = char_charset (c, charset_list, &code); | |
4357 | ||
4358 | if (! charset) | |
b73bfc1c | 4359 | { |
41cbe562 | 4360 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4361 | { |
41cbe562 KH |
4362 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4363 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4364 | } |
41cbe562 | 4365 | else |
0eecad43 | 4366 | { |
41cbe562 KH |
4367 | c = coding->default_char; |
4368 | charset = char_charset (c, charset_list, &code); | |
0eecad43 | 4369 | } |
4ed46869 | 4370 | } |
df7492f9 KH |
4371 | if (code == CHARSET_INVALID_CODE (charset)) |
4372 | abort (); | |
4373 | if (charset == charset_big5) | |
b73bfc1c | 4374 | { |
df7492f9 KH |
4375 | int c1, c2; |
4376 | ||
4377 | c1 = code >> 8, c2 = code & 0xFF; | |
4378 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 4379 | } |
df7492f9 KH |
4380 | else |
4381 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 4382 | } |
4ed46869 | 4383 | } |
065e3595 | 4384 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4385 | coding->produced_char += produced_chars; |
4386 | coding->produced = dst - coding->destination; | |
4387 | return 0; | |
4ed46869 KH |
4388 | } |
4389 | ||
4390 | \f | |
df7492f9 | 4391 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
4392 | |
4393 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4394 | Check if a text is encoded in a coding system of which | |
4395 | encoder/decoder are written in CCL program. If it is, return | |
df7492f9 | 4396 | CATEGORY_MASK_CCL, else return 0. */ |
1397dc18 | 4397 | |
0a28aafb | 4398 | static int |
ff0dacd7 | 4399 | detect_coding_ccl (coding, detect_info) |
df7492f9 | 4400 | struct coding_system *coding; |
ff0dacd7 | 4401 | struct coding_detection_info *detect_info; |
1397dc18 | 4402 | { |
065e3595 | 4403 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4404 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4405 | int multibytep = coding->src_multibyte; |
4406 | int consumed_chars = 0; | |
4407 | int found = 0; | |
0e219d54 | 4408 | unsigned char *valids; |
df7492f9 KH |
4409 | int head_ascii = coding->head_ascii; |
4410 | Lisp_Object attrs; | |
4411 | ||
ff0dacd7 KH |
4412 | detect_info->checked |= CATEGORY_MASK_CCL; |
4413 | ||
df7492f9 | 4414 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 4415 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
4416 | attrs = CODING_ID_ATTRS (coding->id); |
4417 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4418 | src += head_ascii; | |
1397dc18 | 4419 | |
b73bfc1c | 4420 | while (1) |
1397dc18 | 4421 | { |
df7492f9 | 4422 | int c; |
065e3595 KH |
4423 | |
4424 | src_base = src; | |
df7492f9 | 4425 | ONE_MORE_BYTE (c); |
065e3595 | 4426 | if (c < 0 || ! valids[c]) |
df7492f9 | 4427 | break; |
ff0dacd7 KH |
4428 | if ((valids[c] > 1)) |
4429 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 4430 | } |
ff0dacd7 | 4431 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
4432 | return 0; |
4433 | ||
4434 | no_more_source: | |
ff0dacd7 KH |
4435 | detect_info->found |= found; |
4436 | return 1; | |
df7492f9 KH |
4437 | } |
4438 | ||
4439 | static void | |
4440 | decode_coding_ccl (coding) | |
4441 | struct coding_system *coding; | |
4442 | { | |
7c78e542 | 4443 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 4444 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
4445 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4446 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
4447 | int consumed_chars = 0; |
4448 | int multibytep = coding->src_multibyte; | |
4449 | struct ccl_program ccl; | |
4450 | int source_charbuf[1024]; | |
4451 | int source_byteidx[1024]; | |
24a73b0a | 4452 | Lisp_Object attrs, charset_list; |
df7492f9 | 4453 | |
24a73b0a | 4454 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4455 | setup_ccl_program (&ccl, CODING_CCL_DECODER (coding)); |
4456 | ||
4457 | while (src < src_end) | |
4458 | { | |
7c78e542 | 4459 | const unsigned char *p = src; |
df7492f9 KH |
4460 | int *source, *source_end; |
4461 | int i = 0; | |
4462 | ||
4463 | if (multibytep) | |
4464 | while (i < 1024 && p < src_end) | |
4465 | { | |
4466 | source_byteidx[i] = p - src; | |
4467 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
4468 | } | |
4469 | else | |
4470 | while (i < 1024 && p < src_end) | |
4471 | source_charbuf[i++] = *p++; | |
8f924df7 | 4472 | |
df7492f9 KH |
4473 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
4474 | ccl.last_block = 1; | |
4475 | ||
4476 | source = source_charbuf; | |
4477 | source_end = source + i; | |
4478 | while (source < source_end) | |
4479 | { | |
4480 | ccl_driver (&ccl, source, charbuf, | |
8dcbea82 KH |
4481 | source_end - source, charbuf_end - charbuf, |
4482 | charset_list); | |
df7492f9 KH |
4483 | source += ccl.consumed; |
4484 | charbuf += ccl.produced; | |
4485 | if (ccl.status != CCL_STAT_SUSPEND_BY_DST) | |
4486 | break; | |
4487 | } | |
4488 | if (source < source_end) | |
4489 | src += source_byteidx[source - source_charbuf]; | |
4490 | else | |
4491 | src = p; | |
4492 | consumed_chars += source - source_charbuf; | |
4493 | ||
4494 | if (ccl.status != CCL_STAT_SUSPEND_BY_SRC | |
4495 | && ccl.status != CODING_RESULT_INSUFFICIENT_SRC) | |
4496 | break; | |
4497 | } | |
4498 | ||
4499 | switch (ccl.status) | |
4500 | { | |
4501 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4502 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4503 | break; |
4504 | case CCL_STAT_SUSPEND_BY_DST: | |
4505 | break; | |
4506 | case CCL_STAT_QUIT: | |
4507 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4508 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4509 | break; |
4510 | default: | |
065e3595 | 4511 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4512 | break; |
4513 | } | |
4514 | coding->consumed_char += consumed_chars; | |
4515 | coding->consumed = src - coding->source; | |
4516 | coding->charbuf_used = charbuf - coding->charbuf; | |
4517 | } | |
4518 | ||
4519 | static int | |
4520 | encode_coding_ccl (coding) | |
4521 | struct coding_system *coding; | |
4522 | { | |
4523 | struct ccl_program ccl; | |
4524 | int multibytep = coding->dst_multibyte; | |
4525 | int *charbuf = coding->charbuf; | |
4526 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4527 | unsigned char *dst = coding->destination + coding->produced; | |
4528 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4529 | unsigned char *adjusted_dst_end = dst_end - 1; | |
4530 | int destination_charbuf[1024]; | |
4531 | int i, produced_chars = 0; | |
24a73b0a | 4532 | Lisp_Object attrs, charset_list; |
df7492f9 | 4533 | |
24a73b0a | 4534 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4535 | setup_ccl_program (&ccl, CODING_CCL_ENCODER (coding)); |
4536 | ||
4537 | ccl.last_block = coding->mode & CODING_MODE_LAST_BLOCK; | |
4538 | ccl.dst_multibyte = coding->dst_multibyte; | |
4539 | ||
4540 | while (charbuf < charbuf_end && dst < adjusted_dst_end) | |
4541 | { | |
4542 | int dst_bytes = dst_end - dst; | |
4543 | if (dst_bytes > 1024) | |
4544 | dst_bytes = 1024; | |
4545 | ||
4546 | ccl_driver (&ccl, charbuf, destination_charbuf, | |
8dcbea82 | 4547 | charbuf_end - charbuf, dst_bytes, charset_list); |
df7492f9 KH |
4548 | charbuf += ccl.consumed; |
4549 | if (multibytep) | |
4550 | for (i = 0; i < ccl.produced; i++) | |
4551 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); | |
4552 | else | |
4553 | { | |
4554 | for (i = 0; i < ccl.produced; i++) | |
4555 | *dst++ = destination_charbuf[i] & 0xFF; | |
4556 | produced_chars += ccl.produced; | |
4557 | } | |
4558 | } | |
4559 | ||
4560 | switch (ccl.status) | |
4561 | { | |
4562 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4563 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4564 | break; |
4565 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 4566 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
4567 | break; |
4568 | case CCL_STAT_QUIT: | |
4569 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4570 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4571 | break; |
4572 | default: | |
065e3595 | 4573 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 4574 | break; |
1397dc18 | 4575 | } |
df7492f9 KH |
4576 | |
4577 | coding->produced_char += produced_chars; | |
4578 | coding->produced = dst - coding->destination; | |
4579 | return 0; | |
1397dc18 KH |
4580 | } |
4581 | ||
df7492f9 | 4582 | |
1397dc18 | 4583 | \f |
df7492f9 | 4584 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 4585 | |
b73bfc1c | 4586 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 4587 | |
b73bfc1c | 4588 | static void |
df7492f9 | 4589 | decode_coding_raw_text (coding) |
4ed46869 | 4590 | struct coding_system *coding; |
4ed46869 | 4591 | { |
df7492f9 | 4592 | coding->chars_at_source = 1; |
2c78b7e1 KH |
4593 | coding->consumed_char = 0; |
4594 | coding->consumed = 0; | |
065e3595 | 4595 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 4596 | } |
4ed46869 | 4597 | |
df7492f9 KH |
4598 | static int |
4599 | encode_coding_raw_text (coding) | |
4600 | struct coding_system *coding; | |
4601 | { | |
4602 | int multibytep = coding->dst_multibyte; | |
4603 | int *charbuf = coding->charbuf; | |
4604 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
4605 | unsigned char *dst = coding->destination + coding->produced; | |
4606 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4607 | int produced_chars = 0; | |
b73bfc1c KH |
4608 | int c; |
4609 | ||
df7492f9 | 4610 | if (multibytep) |
b73bfc1c | 4611 | { |
df7492f9 | 4612 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 4613 | |
df7492f9 KH |
4614 | if (coding->src_multibyte) |
4615 | while (charbuf < charbuf_end) | |
4616 | { | |
4617 | ASSURE_DESTINATION (safe_room); | |
4618 | c = *charbuf++; | |
4619 | if (ASCII_CHAR_P (c)) | |
4620 | EMIT_ONE_ASCII_BYTE (c); | |
4621 | else if (CHAR_BYTE8_P (c)) | |
4622 | { | |
4623 | c = CHAR_TO_BYTE8 (c); | |
4624 | EMIT_ONE_BYTE (c); | |
4625 | } | |
4626 | else | |
4627 | { | |
4628 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 4629 | |
df7492f9 KH |
4630 | CHAR_STRING_ADVANCE (c, p1); |
4631 | while (p0 < p1) | |
9d123124 KH |
4632 | { |
4633 | EMIT_ONE_BYTE (*p0); | |
4634 | p0++; | |
4635 | } | |
df7492f9 KH |
4636 | } |
4637 | } | |
b73bfc1c | 4638 | else |
df7492f9 KH |
4639 | while (charbuf < charbuf_end) |
4640 | { | |
4641 | ASSURE_DESTINATION (safe_room); | |
4642 | c = *charbuf++; | |
4643 | EMIT_ONE_BYTE (c); | |
4644 | } | |
4645 | } | |
4646 | else | |
4ed46869 | 4647 | { |
df7492f9 | 4648 | if (coding->src_multibyte) |
d46c5b12 | 4649 | { |
df7492f9 KH |
4650 | int safe_room = MAX_MULTIBYTE_LENGTH; |
4651 | ||
4652 | while (charbuf < charbuf_end) | |
d46c5b12 | 4653 | { |
df7492f9 KH |
4654 | ASSURE_DESTINATION (safe_room); |
4655 | c = *charbuf++; | |
4656 | if (ASCII_CHAR_P (c)) | |
4657 | *dst++ = c; | |
4658 | else if (CHAR_BYTE8_P (c)) | |
4659 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 4660 | else |
df7492f9 KH |
4661 | CHAR_STRING_ADVANCE (c, dst); |
4662 | produced_chars++; | |
d46c5b12 KH |
4663 | } |
4664 | } | |
df7492f9 KH |
4665 | else |
4666 | { | |
4667 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
4668 | while (charbuf < charbuf_end && dst < dst_end) | |
4669 | *dst++ = *charbuf++; | |
4670 | produced_chars = dst - (coding->destination + coding->dst_bytes); | |
8f924df7 | 4671 | } |
4ed46869 | 4672 | } |
065e3595 | 4673 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4674 | coding->produced_char += produced_chars; |
4675 | coding->produced = dst - coding->destination; | |
4676 | return 0; | |
4ed46869 KH |
4677 | } |
4678 | ||
ff0dacd7 KH |
4679 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
4680 | Check if a text is encoded in a charset-based coding system. If it | |
4681 | is, return 1, else return 0. */ | |
4682 | ||
0a28aafb | 4683 | static int |
ff0dacd7 | 4684 | detect_coding_charset (coding, detect_info) |
df7492f9 | 4685 | struct coding_system *coding; |
ff0dacd7 | 4686 | struct coding_detection_info *detect_info; |
1397dc18 | 4687 | { |
065e3595 | 4688 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4689 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4690 | int multibytep = coding->src_multibyte; |
4691 | int consumed_chars = 0; | |
4692 | Lisp_Object attrs, valids; | |
584948ac | 4693 | int found = 0; |
1397dc18 | 4694 | |
ff0dacd7 KH |
4695 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
4696 | ||
df7492f9 KH |
4697 | coding = &coding_categories[coding_category_charset]; |
4698 | attrs = CODING_ID_ATTRS (coding->id); | |
4699 | valids = AREF (attrs, coding_attr_charset_valids); | |
4700 | ||
4701 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4702 | src += coding->head_ascii; | |
1397dc18 | 4703 | |
b73bfc1c | 4704 | while (1) |
1397dc18 | 4705 | { |
df7492f9 | 4706 | int c; |
1397dc18 | 4707 | |
065e3595 | 4708 | src_base = src; |
df7492f9 | 4709 | ONE_MORE_BYTE (c); |
065e3595 KH |
4710 | if (c < 0) |
4711 | continue; | |
df7492f9 KH |
4712 | if (NILP (AREF (valids, c))) |
4713 | break; | |
584948ac | 4714 | if (c >= 0x80) |
ff0dacd7 | 4715 | found = CATEGORY_MASK_CHARSET; |
df7492f9 | 4716 | } |
ff0dacd7 | 4717 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 4718 | return 0; |
4ed46869 | 4719 | |
df7492f9 | 4720 | no_more_source: |
ff0dacd7 KH |
4721 | detect_info->found |= found; |
4722 | return 1; | |
df7492f9 | 4723 | } |
b73bfc1c | 4724 | |
b73bfc1c | 4725 | static void |
df7492f9 | 4726 | decode_coding_charset (coding) |
4ed46869 | 4727 | struct coding_system *coding; |
4ed46869 | 4728 | { |
8f924df7 KH |
4729 | const unsigned char *src = coding->source + coding->consumed; |
4730 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4731 | const unsigned char *src_base; | |
69a80ea3 KH |
4732 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4733 | int *charbuf_end | |
4734 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4735 | int consumed_chars = 0, consumed_chars_base; |
4736 | int multibytep = coding->src_multibyte; | |
24a73b0a | 4737 | Lisp_Object attrs, charset_list, valids; |
ff0dacd7 KH |
4738 | int char_offset = coding->produced_char; |
4739 | int last_offset = char_offset; | |
4740 | int last_id = charset_ascii; | |
df7492f9 | 4741 | |
24a73b0a | 4742 | CODING_GET_INFO (coding, attrs, charset_list); |
4eb6d3f1 | 4743 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 4744 | |
df7492f9 | 4745 | while (1) |
4ed46869 | 4746 | { |
4eb6d3f1 | 4747 | int c; |
24a73b0a KH |
4748 | Lisp_Object val; |
4749 | struct charset *charset; | |
4750 | int dim; | |
4751 | int len = 1; | |
4752 | unsigned code; | |
df7492f9 KH |
4753 | |
4754 | src_base = src; | |
4755 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 4756 | |
df7492f9 KH |
4757 | if (charbuf >= charbuf_end) |
4758 | break; | |
4759 | ||
4eb6d3f1 | 4760 | ONE_MORE_BYTE (c); |
065e3595 KH |
4761 | if (c < 0) |
4762 | goto invalid_code; | |
24a73b0a KH |
4763 | code = c; |
4764 | ||
4765 | val = AREF (valids, c); | |
4766 | if (NILP (val)) | |
4767 | goto invalid_code; | |
4768 | if (INTEGERP (val)) | |
d46c5b12 | 4769 | { |
24a73b0a KH |
4770 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
4771 | dim = CHARSET_DIMENSION (charset); | |
4772 | while (len < dim) | |
b73bfc1c | 4773 | { |
24a73b0a KH |
4774 | ONE_MORE_BYTE (c); |
4775 | code = (code << 8) | c; | |
4776 | len++; | |
b73bfc1c | 4777 | } |
24a73b0a KH |
4778 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
4779 | charset, code, c); | |
d46c5b12 | 4780 | } |
df7492f9 | 4781 | else |
d46c5b12 | 4782 | { |
24a73b0a KH |
4783 | /* VAL is a list of charset IDs. It is assured that the |
4784 | list is sorted by charset dimensions (smaller one | |
4785 | comes first). */ | |
4786 | while (CONSP (val)) | |
4eb6d3f1 | 4787 | { |
24a73b0a | 4788 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 4789 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 4790 | while (len < dim) |
4eb6d3f1 | 4791 | { |
acb2a965 KH |
4792 | ONE_MORE_BYTE (c); |
4793 | code = (code << 8) | c; | |
f9d71dcd | 4794 | len++; |
4eb6d3f1 | 4795 | } |
24a73b0a KH |
4796 | CODING_DECODE_CHAR (coding, src, src_base, |
4797 | src_end, charset, code, c); | |
4798 | if (c >= 0) | |
4799 | break; | |
4800 | val = XCDR (val); | |
ff0dacd7 | 4801 | } |
d46c5b12 | 4802 | } |
24a73b0a KH |
4803 | if (c < 0) |
4804 | goto invalid_code; | |
4805 | if (charset->id != charset_ascii | |
4806 | && last_id != charset->id) | |
4807 | { | |
4808 | if (last_id != charset_ascii) | |
69a80ea3 | 4809 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4810 | last_id = charset->id; |
4811 | last_offset = char_offset; | |
4812 | } | |
4813 | ||
df7492f9 | 4814 | *charbuf++ = c; |
ff0dacd7 | 4815 | char_offset++; |
df7492f9 KH |
4816 | continue; |
4817 | ||
4818 | invalid_code: | |
4819 | src = src_base; | |
4820 | consumed_chars = consumed_chars_base; | |
4821 | ONE_MORE_BYTE (c); | |
065e3595 | 4822 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4823 | char_offset++; |
df7492f9 | 4824 | coding->errors++; |
4ed46869 KH |
4825 | } |
4826 | ||
df7492f9 | 4827 | no_more_source: |
ff0dacd7 | 4828 | if (last_id != charset_ascii) |
69a80ea3 | 4829 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4830 | coding->consumed_char += consumed_chars_base; |
4831 | coding->consumed = src_base - coding->source; | |
4832 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4833 | } |
4834 | ||
df7492f9 KH |
4835 | static int |
4836 | encode_coding_charset (coding) | |
4ed46869 | 4837 | struct coding_system *coding; |
4ed46869 | 4838 | { |
df7492f9 KH |
4839 | int multibytep = coding->dst_multibyte; |
4840 | int *charbuf = coding->charbuf; | |
4841 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4842 | unsigned char *dst = coding->destination + coding->produced; | |
4843 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4844 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
4845 | int produced_chars = 0; | |
24a73b0a | 4846 | Lisp_Object attrs, charset_list; |
df7492f9 | 4847 | int ascii_compatible; |
b73bfc1c | 4848 | int c; |
b73bfc1c | 4849 | |
24a73b0a | 4850 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 4851 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 4852 | |
df7492f9 | 4853 | while (charbuf < charbuf_end) |
4ed46869 | 4854 | { |
4eb6d3f1 | 4855 | struct charset *charset; |
df7492f9 | 4856 | unsigned code; |
8f924df7 | 4857 | |
df7492f9 KH |
4858 | ASSURE_DESTINATION (safe_room); |
4859 | c = *charbuf++; | |
4860 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
4861 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 4862 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 4863 | { |
16eafb5d KH |
4864 | c = CHAR_TO_BYTE8 (c); |
4865 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 4866 | } |
d46c5b12 | 4867 | else |
b73bfc1c | 4868 | { |
4eb6d3f1 KH |
4869 | charset = char_charset (c, charset_list, &code); |
4870 | if (charset) | |
4871 | { | |
4872 | if (CHARSET_DIMENSION (charset) == 1) | |
4873 | EMIT_ONE_BYTE (code); | |
4874 | else if (CHARSET_DIMENSION (charset) == 2) | |
4875 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
4876 | else if (CHARSET_DIMENSION (charset) == 3) | |
4877 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
4878 | else | |
4879 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
4880 | (code >> 8) & 0xFF, code & 0xFF); | |
4881 | } | |
4882 | else | |
41cbe562 KH |
4883 | { |
4884 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
4885 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4886 | else | |
4887 | c = coding->default_char; | |
4888 | EMIT_ONE_BYTE (c); | |
4889 | } | |
4ed46869 | 4890 | } |
4ed46869 KH |
4891 | } |
4892 | ||
065e3595 | 4893 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4894 | coding->produced_char += produced_chars; |
4895 | coding->produced = dst - coding->destination; | |
4896 | return 0; | |
4ed46869 KH |
4897 | } |
4898 | ||
4899 | \f | |
1397dc18 | 4900 | /*** 7. C library functions ***/ |
4ed46869 | 4901 | |
df7492f9 KH |
4902 | /* Setup coding context CODING from information about CODING_SYSTEM. |
4903 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
4904 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 4905 | |
ec6d2bb8 | 4906 | void |
e0e989f6 KH |
4907 | setup_coding_system (coding_system, coding) |
4908 | Lisp_Object coding_system; | |
4ed46869 KH |
4909 | struct coding_system *coding; |
4910 | { | |
df7492f9 KH |
4911 | Lisp_Object attrs; |
4912 | Lisp_Object eol_type; | |
4913 | Lisp_Object coding_type; | |
4608c386 | 4914 | Lisp_Object val; |
4ed46869 | 4915 | |
df7492f9 KH |
4916 | if (NILP (coding_system)) |
4917 | coding_system = Qno_conversion; | |
c07c8e12 | 4918 | |
df7492f9 | 4919 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 4920 | |
df7492f9 KH |
4921 | attrs = CODING_ID_ATTRS (coding->id); |
4922 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
1f5dbf34 | 4923 | |
df7492f9 KH |
4924 | coding->mode = 0; |
4925 | coding->head_ascii = -1; | |
4926 | coding->common_flags | |
4927 | = (VECTORP (eol_type) ? CODING_REQUIRE_DETECTION_MASK : 0); | |
5e5c78be KH |
4928 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
4929 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
4930 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
4931 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
4932 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
4933 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 4934 | |
df7492f9 | 4935 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 KH |
4936 | coding->max_charset_id = SCHARS (val) - 1; |
4937 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 | 4938 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
4608c386 | 4939 | |
df7492f9 KH |
4940 | coding_type = CODING_ATTR_TYPE (attrs); |
4941 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 4942 | { |
df7492f9 KH |
4943 | coding->detector = NULL; |
4944 | coding->decoder = decode_coding_raw_text; | |
4945 | coding->encoder = encode_coding_raw_text; | |
4946 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 4947 | } |
df7492f9 | 4948 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 4949 | { |
df7492f9 KH |
4950 | int i; |
4951 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
4952 | ||
4953 | /* Invoke graphic register 0 to plane 0. */ | |
4954 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
4955 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
4956 | CODING_ISO_INVOCATION (coding, 1) | |
4957 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
4958 | /* Setup the initial status of designation. */ | |
4959 | for (i = 0; i < 4; i++) | |
4960 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
4961 | /* Not single shifting initially. */ | |
4962 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
4963 | /* Beginning of buffer should also be regarded as bol. */ | |
4964 | CODING_ISO_BOL (coding) = 1; | |
4965 | coding->detector = detect_coding_iso_2022; | |
4966 | coding->decoder = decode_coding_iso_2022; | |
4967 | coding->encoder = encode_coding_iso_2022; | |
4968 | if (flags & CODING_ISO_FLAG_SAFE) | |
4969 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 4970 | coding->common_flags |
df7492f9 KH |
4971 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
4972 | | CODING_REQUIRE_FLUSHING_MASK); | |
4973 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
4974 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
4975 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
4976 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
4977 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
4978 | { | |
4979 | setup_iso_safe_charsets (attrs); | |
4980 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
4981 | coding->max_charset_id = SCHARS (val) - 1; |
4982 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
4983 | } |
4984 | CODING_ISO_FLAGS (coding) = flags; | |
d46c5b12 | 4985 | } |
df7492f9 | 4986 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 4987 | { |
df7492f9 KH |
4988 | coding->detector = detect_coding_charset; |
4989 | coding->decoder = decode_coding_charset; | |
4990 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 4991 | coding->common_flags |
df7492f9 | 4992 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 4993 | } |
df7492f9 | 4994 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 4995 | { |
df7492f9 KH |
4996 | coding->detector = detect_coding_utf_8; |
4997 | coding->decoder = decode_coding_utf_8; | |
4998 | coding->encoder = encode_coding_utf_8; | |
4999 | coding->common_flags | |
5000 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
5001 | } | |
5002 | else if (EQ (coding_type, Qutf_16)) | |
5003 | { | |
5004 | val = AREF (attrs, coding_attr_utf_16_bom); | |
5005 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_16_detect_bom | |
5006 | : EQ (val, Qt) ? utf_16_with_bom | |
5007 | : utf_16_without_bom); | |
5008 | val = AREF (attrs, coding_attr_utf_16_endian); | |
b49a1807 | 5009 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5010 | : utf_16_little_endian); |
e19c3639 | 5011 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5012 | coding->detector = detect_coding_utf_16; |
5013 | coding->decoder = decode_coding_utf_16; | |
5014 | coding->encoder = encode_coding_utf_16; | |
5015 | coding->common_flags | |
5016 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
b49a1807 KH |
5017 | if (CODING_UTF_16_BOM (coding) == utf_16_detect_bom) |
5018 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5019 | } |
df7492f9 | 5020 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5021 | { |
df7492f9 KH |
5022 | coding->detector = detect_coding_ccl; |
5023 | coding->decoder = decode_coding_ccl; | |
5024 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5025 | coding->common_flags |
df7492f9 KH |
5026 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5027 | | CODING_REQUIRE_FLUSHING_MASK); | |
5028 | } | |
5029 | else if (EQ (coding_type, Qemacs_mule)) | |
5030 | { | |
5031 | coding->detector = detect_coding_emacs_mule; | |
5032 | coding->decoder = decode_coding_emacs_mule; | |
5033 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5034 | coding->common_flags |
df7492f9 KH |
5035 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5036 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
5037 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5038 | { | |
5039 | Lisp_Object tail, safe_charsets; | |
5040 | int max_charset_id = 0; | |
5041 | ||
5042 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5043 | tail = XCDR (tail)) | |
5044 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5045 | max_charset_id = XFASTINT (XCAR (tail)); | |
5046 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), | |
5047 | make_number (255)); | |
5048 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5049 | tail = XCDR (tail)) | |
8f924df7 | 5050 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5051 | coding->max_charset_id = max_charset_id; |
8f924df7 | 5052 | coding->safe_charsets = (char *) SDATA (safe_charsets); |
df7492f9 KH |
5053 | } |
5054 | } | |
5055 | else if (EQ (coding_type, Qshift_jis)) | |
5056 | { | |
5057 | coding->detector = detect_coding_sjis; | |
5058 | coding->decoder = decode_coding_sjis; | |
5059 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5060 | coding->common_flags |
df7492f9 KH |
5061 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5062 | } | |
5063 | else if (EQ (coding_type, Qbig5)) | |
5064 | { | |
5065 | coding->detector = detect_coding_big5; | |
5066 | coding->decoder = decode_coding_big5; | |
5067 | coding->encoder = encode_coding_big5; | |
c952af22 | 5068 | coding->common_flags |
df7492f9 KH |
5069 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5070 | } | |
5071 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5072 | { |
df7492f9 KH |
5073 | coding->detector = NULL; |
5074 | coding->decoder = decode_coding_raw_text; | |
5075 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5076 | if (! EQ (eol_type, Qunix)) |
5077 | { | |
5078 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5079 | if (! VECTORP (eol_type)) | |
5080 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5081 | } | |
5082 | ||
4ed46869 | 5083 | } |
4ed46869 | 5084 | |
df7492f9 | 5085 | return; |
4ed46869 KH |
5086 | } |
5087 | ||
df7492f9 KH |
5088 | /* Return raw-text or one of its subsidiaries that has the same |
5089 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5090 | |
df7492f9 KH |
5091 | Lisp_Object |
5092 | raw_text_coding_system (coding_system) | |
5093 | Lisp_Object coding_system; | |
ec6d2bb8 | 5094 | { |
0be8721c | 5095 | Lisp_Object spec, attrs; |
df7492f9 | 5096 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5097 | |
d3e4cb56 KH |
5098 | if (NILP (coding_system)) |
5099 | return Qraw_text; | |
df7492f9 KH |
5100 | spec = CODING_SYSTEM_SPEC (coding_system); |
5101 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5102 | |
df7492f9 KH |
5103 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5104 | return coding_system; | |
ec6d2bb8 | 5105 | |
df7492f9 KH |
5106 | eol_type = AREF (spec, 2); |
5107 | if (VECTORP (eol_type)) | |
5108 | return Qraw_text; | |
5109 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5110 | raw_text_eol_type = AREF (spec, 2); | |
5111 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5112 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5113 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5114 | } |
5115 | ||
54f78171 | 5116 | |
df7492f9 KH |
5117 | /* If CODING_SYSTEM doesn't specify end-of-line format but PARENT |
5118 | does, return one of the subsidiary that has the same eol-spec as | |
5119 | PARENT. Otherwise, return CODING_SYSTEM. */ | |
5120 | ||
5121 | Lisp_Object | |
5122 | coding_inherit_eol_type (coding_system, parent) | |
b74e4686 | 5123 | Lisp_Object coding_system, parent; |
54f78171 | 5124 | { |
3e139625 | 5125 | Lisp_Object spec, eol_type; |
54f78171 | 5126 | |
d3e4cb56 KH |
5127 | if (NILP (coding_system)) |
5128 | coding_system = Qraw_text; | |
df7492f9 | 5129 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5130 | eol_type = AREF (spec, 2); |
d3e4cb56 KH |
5131 | if (VECTORP (eol_type) |
5132 | && ! NILP (parent)) | |
df7492f9 KH |
5133 | { |
5134 | Lisp_Object parent_spec; | |
df7492f9 KH |
5135 | Lisp_Object parent_eol_type; |
5136 | ||
5137 | parent_spec | |
5138 | = CODING_SYSTEM_SPEC (buffer_defaults.buffer_file_coding_system); | |
5139 | parent_eol_type = AREF (parent_spec, 2); | |
5140 | if (EQ (parent_eol_type, Qunix)) | |
5141 | coding_system = AREF (eol_type, 0); | |
5142 | else if (EQ (parent_eol_type, Qdos)) | |
5143 | coding_system = AREF (eol_type, 1); | |
5144 | else if (EQ (parent_eol_type, Qmac)) | |
5145 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5146 | } |
df7492f9 | 5147 | return coding_system; |
54f78171 KH |
5148 | } |
5149 | ||
4ed46869 KH |
5150 | /* Emacs has a mechanism to automatically detect a coding system if it |
5151 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
5152 | it's impossible to distinguish some coding systems accurately | |
5153 | because they use the same range of codes. So, at first, coding | |
5154 | systems are categorized into 7, those are: | |
5155 | ||
0ef69138 | 5156 | o coding-category-emacs-mule |
4ed46869 KH |
5157 | |
5158 | The category for a coding system which has the same code range | |
5159 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 5160 | symbol) `emacs-mule' by default. |
4ed46869 KH |
5161 | |
5162 | o coding-category-sjis | |
5163 | ||
5164 | The category for a coding system which has the same code range | |
5165 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 5166 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
5167 | |
5168 | o coding-category-iso-7 | |
5169 | ||
5170 | The category for a coding system which has the same code range | |
7717c392 | 5171 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
5172 | shift and single shift functions. This can encode/decode all |
5173 | charsets. Assigned the coding-system (Lisp symbol) | |
5174 | `iso-2022-7bit' by default. | |
5175 | ||
5176 | o coding-category-iso-7-tight | |
5177 | ||
5178 | Same as coding-category-iso-7 except that this can | |
5179 | encode/decode only the specified charsets. | |
4ed46869 KH |
5180 | |
5181 | o coding-category-iso-8-1 | |
5182 | ||
5183 | The category for a coding system which has the same code range | |
5184 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5185 | for DIMENSION1 charset. This doesn't use any locking shift |
5186 | and single shift functions. Assigned the coding-system (Lisp | |
5187 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
5188 | |
5189 | o coding-category-iso-8-2 | |
5190 | ||
5191 | The category for a coding system which has the same code range | |
5192 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5193 | for DIMENSION2 charset. This doesn't use any locking shift |
5194 | and single shift functions. Assigned the coding-system (Lisp | |
5195 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 5196 | |
7717c392 | 5197 | o coding-category-iso-7-else |
4ed46869 KH |
5198 | |
5199 | The category for a coding system which has the same code range | |
df7492f9 | 5200 | as ISO2022 of 7-bit environemnt but uses locking shift or |
7717c392 KH |
5201 | single shift functions. Assigned the coding-system (Lisp |
5202 | symbol) `iso-2022-7bit-lock' by default. | |
5203 | ||
5204 | o coding-category-iso-8-else | |
5205 | ||
5206 | The category for a coding system which has the same code range | |
df7492f9 | 5207 | as ISO2022 of 8-bit environemnt but uses locking shift or |
7717c392 KH |
5208 | single shift functions. Assigned the coding-system (Lisp |
5209 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
5210 | |
5211 | o coding-category-big5 | |
5212 | ||
5213 | The category for a coding system which has the same code range | |
5214 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5215 | `cn-big5' by default. |
4ed46869 | 5216 | |
fa42c37f KH |
5217 | o coding-category-utf-8 |
5218 | ||
5219 | The category for a coding system which has the same code range | |
6e76ae91 | 5220 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
5221 | symbol) `utf-8' by default. |
5222 | ||
5223 | o coding-category-utf-16-be | |
5224 | ||
5225 | The category for a coding system in which a text has an | |
5226 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
5227 | endian at the head. Assigned the coding-system (Lisp symbol) | |
5228 | `utf-16-be' by default. | |
5229 | ||
5230 | o coding-category-utf-16-le | |
5231 | ||
5232 | The category for a coding system in which a text has an | |
5233 | Unicode signature (cf. Unicode Standard) in the order of | |
5234 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
5235 | symbol) `utf-16-le' by default. | |
5236 | ||
1397dc18 KH |
5237 | o coding-category-ccl |
5238 | ||
5239 | The category for a coding system of which encoder/decoder is | |
5240 | written in CCL programs. The default value is nil, i.e., no | |
5241 | coding system is assigned. | |
5242 | ||
4ed46869 KH |
5243 | o coding-category-binary |
5244 | ||
5245 | The category for a coding system not categorized in any of the | |
5246 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5247 | `no-conversion' by default. |
4ed46869 KH |
5248 | |
5249 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 5250 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
5251 | What Emacs does actually is to detect a category of coding system. |
5252 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 5253 | decide only one possible category, it selects a category of the |
4ed46869 KH |
5254 | highest priority. Priorities of categories are also specified by a |
5255 | user in a Lisp variable `coding-category-list'. | |
5256 | ||
5257 | */ | |
5258 | ||
df7492f9 KH |
5259 | #define EOL_SEEN_NONE 0 |
5260 | #define EOL_SEEN_LF 1 | |
5261 | #define EOL_SEEN_CR 2 | |
5262 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 5263 | |
ff0dacd7 KH |
5264 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
5265 | SOURCE is encoded. If CATEGORY is one of | |
5266 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
5267 | two-byte, else they are encoded by one-byte. | |
5268 | ||
5269 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 5270 | |
bc4bc72a | 5271 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
5272 | |
5273 | static int | |
89528eb3 | 5274 | detect_eol (source, src_bytes, category) |
f6cbaf43 | 5275 | const unsigned char *source; |
df7492f9 | 5276 | EMACS_INT src_bytes; |
89528eb3 | 5277 | enum coding_category category; |
4ed46869 | 5278 | { |
f6cbaf43 | 5279 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 5280 | unsigned char c; |
df7492f9 KH |
5281 | int total = 0; |
5282 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 5283 | |
89528eb3 | 5284 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 5285 | { |
df7492f9 | 5286 | int msb, lsb; |
fa42c37f | 5287 | |
89528eb3 KH |
5288 | msb = category == (coding_category_utf_16_le |
5289 | | coding_category_utf_16_le_nosig); | |
df7492f9 | 5290 | lsb = 1 - msb; |
fa42c37f | 5291 | |
df7492f9 | 5292 | while (src + 1 < src_end) |
fa42c37f | 5293 | { |
df7492f9 KH |
5294 | c = src[lsb]; |
5295 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 5296 | { |
df7492f9 KH |
5297 | int this_eol; |
5298 | ||
5299 | if (c == '\n') | |
5300 | this_eol = EOL_SEEN_LF; | |
5301 | else if (src + 3 >= src_end | |
5302 | || src[msb + 2] != 0 | |
5303 | || src[lsb + 2] != '\n') | |
5304 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 5305 | else |
8f924df7 | 5306 | this_eol = EOL_SEEN_CRLF; |
df7492f9 KH |
5307 | |
5308 | if (eol_seen == EOL_SEEN_NONE) | |
5309 | /* This is the first end-of-line. */ | |
5310 | eol_seen = this_eol; | |
5311 | else if (eol_seen != this_eol) | |
fa42c37f | 5312 | { |
df7492f9 KH |
5313 | /* The found type is different from what found before. */ |
5314 | eol_seen = EOL_SEEN_LF; | |
5315 | break; | |
fa42c37f | 5316 | } |
df7492f9 KH |
5317 | if (++total == MAX_EOL_CHECK_COUNT) |
5318 | break; | |
fa42c37f | 5319 | } |
df7492f9 | 5320 | src += 2; |
fa42c37f | 5321 | } |
bcf26d6a | 5322 | } |
d46c5b12 | 5323 | else |
c4825358 | 5324 | { |
df7492f9 | 5325 | while (src < src_end) |
27901516 | 5326 | { |
df7492f9 KH |
5327 | c = *src++; |
5328 | if (c == '\n' || c == '\r') | |
5329 | { | |
5330 | int this_eol; | |
d46c5b12 | 5331 | |
df7492f9 KH |
5332 | if (c == '\n') |
5333 | this_eol = EOL_SEEN_LF; | |
5334 | else if (src >= src_end || *src != '\n') | |
5335 | this_eol = EOL_SEEN_CR; | |
5336 | else | |
5337 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 5338 | |
df7492f9 KH |
5339 | if (eol_seen == EOL_SEEN_NONE) |
5340 | /* This is the first end-of-line. */ | |
5341 | eol_seen = this_eol; | |
5342 | else if (eol_seen != this_eol) | |
5343 | { | |
5344 | /* The found type is different from what found before. */ | |
5345 | eol_seen = EOL_SEEN_LF; | |
5346 | break; | |
5347 | } | |
5348 | if (++total == MAX_EOL_CHECK_COUNT) | |
5349 | break; | |
5350 | } | |
5351 | } | |
73be902c | 5352 | } |
df7492f9 | 5353 | return eol_seen; |
73be902c KH |
5354 | } |
5355 | ||
df7492f9 | 5356 | |
24a73b0a | 5357 | static Lisp_Object |
df7492f9 KH |
5358 | adjust_coding_eol_type (coding, eol_seen) |
5359 | struct coding_system *coding; | |
5360 | int eol_seen; | |
73be902c | 5361 | { |
0be8721c | 5362 | Lisp_Object eol_type; |
8f924df7 | 5363 | |
df7492f9 KH |
5364 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
5365 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
5366 | { |
5367 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
5368 | eol_type = Qunix; | |
5369 | } | |
6f197c07 | 5370 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
5371 | { |
5372 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
5373 | eol_type = Qdos; | |
5374 | } | |
6f197c07 | 5375 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
5376 | { |
5377 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
5378 | eol_type = Qmac; | |
5379 | } | |
5380 | return eol_type; | |
d46c5b12 | 5381 | } |
4ed46869 | 5382 | |
df7492f9 KH |
5383 | /* Detect how a text specified in CODING is encoded. If a coding |
5384 | system is detected, update fields of CODING by the detected coding | |
5385 | system. */ | |
0a28aafb | 5386 | |
df7492f9 KH |
5387 | void |
5388 | detect_coding (coding) | |
d46c5b12 | 5389 | struct coding_system *coding; |
d46c5b12 | 5390 | { |
8f924df7 | 5391 | const unsigned char *src, *src_end; |
d46c5b12 | 5392 | |
df7492f9 KH |
5393 | coding->consumed = coding->consumed_char = 0; |
5394 | coding->produced = coding->produced_char = 0; | |
5395 | coding_set_source (coding); | |
1c3478b0 | 5396 | |
df7492f9 | 5397 | src_end = coding->source + coding->src_bytes; |
1c3478b0 | 5398 | |
df7492f9 KH |
5399 | /* If we have not yet decided the text encoding type, detect it |
5400 | now. */ | |
5401 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 5402 | { |
df7492f9 | 5403 | int c, i; |
6cb21a4f | 5404 | struct coding_detection_info detect_info; |
df7492f9 | 5405 | |
6cb21a4f | 5406 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
24a73b0a | 5407 | for (i = 0, src = coding->source; src < src_end; i++, src++) |
d46c5b12 | 5408 | { |
df7492f9 | 5409 | c = *src; |
6cb21a4f | 5410 | if (c & 0x80) |
df7492f9 | 5411 | break; |
6cb21a4f KH |
5412 | if (c < 0x20 |
5413 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
5414 | && ! inhibit_iso_escape_detection | |
5415 | && ! detect_info.checked) | |
5416 | { | |
5417 | coding->head_ascii = src - (coding->source + coding->consumed); | |
5418 | if (detect_coding_iso_2022 (coding, &detect_info)) | |
5419 | { | |
5420 | /* We have scanned the whole data. */ | |
5421 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
5422 | /* We didn't find an 8-bit code. */ | |
5423 | src = src_end; | |
5424 | break; | |
5425 | } | |
5426 | } | |
d46c5b12 | 5427 | } |
df7492f9 KH |
5428 | coding->head_ascii = src - (coding->source + coding->consumed); |
5429 | ||
3aef54f3 | 5430 | if (coding->head_ascii < coding->src_bytes |
6cb21a4f | 5431 | || detect_info.found) |
d46c5b12 | 5432 | { |
ff0dacd7 KH |
5433 | enum coding_category category; |
5434 | struct coding_system *this; | |
df7492f9 | 5435 | |
6cb21a4f KH |
5436 | if (coding->head_ascii == coding->src_bytes) |
5437 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
5438 | for (i = 0; i < coding_category_raw_text; i++) | |
5439 | { | |
5440 | category = coding_priorities[i]; | |
5441 | this = coding_categories + category; | |
5442 | if (detect_info.found & (1 << category)) | |
24a73b0a | 5443 | break; |
6cb21a4f KH |
5444 | } |
5445 | else | |
5446 | for (i = 0; i < coding_category_raw_text; i++) | |
5447 | { | |
5448 | category = coding_priorities[i]; | |
5449 | this = coding_categories + category; | |
5450 | if (this->id < 0) | |
5451 | { | |
5452 | /* No coding system of this category is defined. */ | |
5453 | detect_info.rejected |= (1 << category); | |
5454 | } | |
5455 | else if (category >= coding_category_raw_text) | |
5456 | continue; | |
5457 | else if (detect_info.checked & (1 << category)) | |
5458 | { | |
5459 | if (detect_info.found & (1 << category)) | |
5460 | break; | |
5461 | } | |
5462 | else if ((*(this->detector)) (coding, &detect_info) | |
5463 | && detect_info.found & (1 << category)) | |
5464 | { | |
5465 | if (category == coding_category_utf_16_auto) | |
5466 | { | |
5467 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
5468 | category = coding_category_utf_16_le; | |
5469 | else | |
5470 | category = coding_category_utf_16_be; | |
5471 | } | |
5472 | break; | |
5473 | } | |
5474 | } | |
5475 | ||
ff0dacd7 KH |
5476 | if (i < coding_category_raw_text) |
5477 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5478 | else if (detect_info.rejected == CATEGORY_MASK_ANY) | |
df7492f9 | 5479 | setup_coding_system (Qraw_text, coding); |
ff0dacd7 | 5480 | else if (detect_info.rejected) |
df7492f9 | 5481 | for (i = 0; i < coding_category_raw_text; i++) |
ff0dacd7 KH |
5482 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) |
5483 | { | |
5484 | this = coding_categories + coding_priorities[i]; | |
5485 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5486 | break; | |
5487 | } | |
d46c5b12 | 5488 | } |
b73bfc1c | 5489 | } |
24a73b0a KH |
5490 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
5491 | == coding_category_utf_16_auto) | |
b49a1807 KH |
5492 | { |
5493 | Lisp_Object coding_systems; | |
5494 | struct coding_detection_info detect_info; | |
5495 | ||
5496 | coding_systems | |
5497 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_16_bom); | |
5498 | detect_info.found = detect_info.rejected = 0; | |
5499 | if (CONSP (coding_systems) | |
24a73b0a | 5500 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
5501 | { |
5502 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
5503 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 5504 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
5505 | setup_coding_system (XCDR (coding_systems), coding); |
5506 | } | |
5507 | } | |
4ed46869 | 5508 | } |
4ed46869 | 5509 | |
d46c5b12 | 5510 | |
aaaf0b1e | 5511 | static void |
df7492f9 | 5512 | decode_eol (coding) |
aaaf0b1e | 5513 | struct coding_system *coding; |
aaaf0b1e | 5514 | { |
24a73b0a KH |
5515 | Lisp_Object eol_type; |
5516 | unsigned char *p, *pbeg, *pend; | |
5517 | ||
5518 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
5519 | if (EQ (eol_type, Qunix)) | |
5520 | return; | |
5521 | ||
5522 | if (NILP (coding->dst_object)) | |
5523 | pbeg = coding->destination; | |
5524 | else | |
5525 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
5526 | pend = pbeg + coding->produced; | |
5527 | ||
5528 | if (VECTORP (eol_type)) | |
aaaf0b1e | 5529 | { |
df7492f9 | 5530 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 5531 | |
24a73b0a | 5532 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 5533 | { |
df7492f9 KH |
5534 | if (*p == '\n') |
5535 | eol_seen |= EOL_SEEN_LF; | |
5536 | else if (*p == '\r') | |
aaaf0b1e | 5537 | { |
df7492f9 | 5538 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 5539 | { |
df7492f9 KH |
5540 | eol_seen |= EOL_SEEN_CRLF; |
5541 | p++; | |
aaaf0b1e | 5542 | } |
aaaf0b1e | 5543 | else |
df7492f9 | 5544 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 5545 | } |
aaaf0b1e | 5546 | } |
24a73b0a KH |
5547 | if (eol_seen != EOL_SEEN_NONE |
5548 | && eol_seen != EOL_SEEN_LF | |
5549 | && eol_seen != EOL_SEEN_CRLF | |
5550 | && eol_seen != EOL_SEEN_CR) | |
5551 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 5552 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 5553 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 5554 | } |
d46c5b12 | 5555 | |
24a73b0a | 5556 | if (EQ (eol_type, Qmac)) |
27901516 | 5557 | { |
24a73b0a | 5558 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
5559 | if (*p == '\r') |
5560 | *p = '\n'; | |
4ed46869 | 5561 | } |
24a73b0a | 5562 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 5563 | { |
24a73b0a | 5564 | int n = 0; |
b73bfc1c | 5565 | |
24a73b0a KH |
5566 | if (NILP (coding->dst_object)) |
5567 | { | |
5568 | for (p = pend - 2; p >= pbeg; p--) | |
5569 | if (*p == '\r') | |
5570 | { | |
5571 | safe_bcopy ((char *) (p + 1), (char *) p, pend-- - p - 1); | |
5572 | n++; | |
5573 | } | |
5574 | } | |
5575 | else | |
5576 | { | |
5577 | for (p = pend - 2; p >= pbeg; p--) | |
5578 | if (*p == '\r') | |
5579 | { | |
5580 | int pos_byte = coding->dst_pos_byte + (p - pbeg); | |
5581 | int pos = BYTE_TO_CHAR (pos_byte); | |
5582 | ||
5583 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
5584 | n++; | |
5585 | } | |
5586 | } | |
5587 | coding->produced -= n; | |
5588 | coding->produced_char -= n; | |
aaaf0b1e | 5589 | } |
4ed46869 KH |
5590 | } |
5591 | ||
7d64c6ad | 5592 | |
a6f87d34 KH |
5593 | /* Return a translation table (or list of them) from coding system |
5594 | attribute vector ATTRS for encoding (ENCODEP is nonzero) or | |
5595 | decoding (ENCODEP is zero). */ | |
7d64c6ad | 5596 | |
e6a54062 | 5597 | static Lisp_Object |
09ee6fdd KH |
5598 | get_translation_table (attrs, encodep, max_lookup) |
5599 | Lisp_Object attrs; | |
5600 | int encodep, *max_lookup; | |
7d64c6ad KH |
5601 | { |
5602 | Lisp_Object standard, translation_table; | |
09ee6fdd | 5603 | Lisp_Object val; |
7d64c6ad KH |
5604 | |
5605 | if (encodep) | |
5606 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
5607 | standard = Vstandard_translation_table_for_encode; | |
5608 | else | |
5609 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
5610 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 5611 | if (NILP (translation_table)) |
09ee6fdd KH |
5612 | translation_table = standard; |
5613 | else | |
a6f87d34 | 5614 | { |
09ee6fdd KH |
5615 | if (SYMBOLP (translation_table)) |
5616 | translation_table = Fget (translation_table, Qtranslation_table); | |
5617 | else if (CONSP (translation_table)) | |
5618 | { | |
5619 | translation_table = Fcopy_sequence (translation_table); | |
5620 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
5621 | if (SYMBOLP (XCAR (val))) | |
5622 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
5623 | } | |
5624 | if (CHAR_TABLE_P (standard)) | |
5625 | { | |
5626 | if (CONSP (translation_table)) | |
5627 | translation_table = nconc2 (translation_table, | |
5628 | Fcons (standard, Qnil)); | |
5629 | else | |
5630 | translation_table = Fcons (translation_table, | |
5631 | Fcons (standard, Qnil)); | |
5632 | } | |
a6f87d34 | 5633 | } |
2170c8f0 KH |
5634 | |
5635 | if (max_lookup) | |
09ee6fdd | 5636 | { |
2170c8f0 KH |
5637 | *max_lookup = 1; |
5638 | if (CHAR_TABLE_P (translation_table) | |
5639 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
5640 | { | |
5641 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
5642 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
5643 | *max_lookup = XFASTINT (val); | |
5644 | } | |
5645 | else if (CONSP (translation_table)) | |
5646 | { | |
5647 | Lisp_Object tail, val; | |
09ee6fdd | 5648 | |
2170c8f0 KH |
5649 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
5650 | if (CHAR_TABLE_P (XCAR (tail)) | |
5651 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
5652 | { | |
5653 | val = XCHAR_TABLE (XCAR (tail))->extras[1]; | |
5654 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
5655 | *max_lookup = XFASTINT (val); | |
5656 | } | |
5657 | } | |
a6f87d34 | 5658 | } |
7d64c6ad KH |
5659 | return translation_table; |
5660 | } | |
5661 | ||
09ee6fdd KH |
5662 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
5663 | do { \ | |
5664 | trans = Qnil; \ | |
5665 | if (CHAR_TABLE_P (table)) \ | |
5666 | { \ | |
5667 | trans = CHAR_TABLE_REF (table, c); \ | |
5668 | if (CHARACTERP (trans)) \ | |
5669 | c = XFASTINT (trans), trans = Qnil; \ | |
5670 | } \ | |
5671 | else if (CONSP (table)) \ | |
5672 | { \ | |
5673 | Lisp_Object tail; \ | |
5674 | \ | |
5675 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
5676 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
5677 | { \ | |
5678 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
5679 | if (CHARACTERP (trans)) \ | |
5680 | c = XFASTINT (trans), trans = Qnil; \ | |
5681 | else if (! NILP (trans)) \ | |
5682 | break; \ | |
5683 | } \ | |
5684 | } \ | |
e6a54062 KH |
5685 | } while (0) |
5686 | ||
7d64c6ad | 5687 | |
69a80ea3 KH |
5688 | static Lisp_Object |
5689 | get_translation (val, buf, buf_end, last_block, from_nchars, to_nchars) | |
5690 | Lisp_Object val; | |
5691 | int *buf, *buf_end; | |
5692 | int last_block; | |
5693 | int *from_nchars, *to_nchars; | |
5694 | { | |
433f7f87 KH |
5695 | /* VAL is TO or (([FROM-CHAR ...] . TO) ...) where TO is TO-CHAR or |
5696 | [TO-CHAR ...]. */ | |
69a80ea3 KH |
5697 | if (CONSP (val)) |
5698 | { | |
433f7f87 | 5699 | Lisp_Object from, tail; |
69a80ea3 KH |
5700 | int i, len; |
5701 | ||
433f7f87 | 5702 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
69a80ea3 | 5703 | { |
433f7f87 KH |
5704 | val = XCAR (tail); |
5705 | from = XCAR (val); | |
5706 | len = ASIZE (from); | |
5707 | for (i = 0; i < len; i++) | |
5708 | { | |
5709 | if (buf + i == buf_end) | |
5710 | { | |
5711 | if (! last_block) | |
5712 | return Qt; | |
5713 | break; | |
5714 | } | |
5715 | if (XINT (AREF (from, i)) != buf[i]) | |
5716 | break; | |
5717 | } | |
5718 | if (i == len) | |
5719 | { | |
5720 | val = XCDR (val); | |
5721 | *from_nchars = len; | |
5722 | break; | |
5723 | } | |
69a80ea3 | 5724 | } |
433f7f87 KH |
5725 | if (! CONSP (tail)) |
5726 | return Qnil; | |
69a80ea3 KH |
5727 | } |
5728 | if (VECTORP (val)) | |
5729 | *buf = XINT (AREF (val, 0)), *to_nchars = ASIZE (val); | |
5730 | else | |
5731 | *buf = XINT (val); | |
5732 | return val; | |
5733 | } | |
5734 | ||
5735 | ||
d46c5b12 | 5736 | static int |
69a80ea3 | 5737 | produce_chars (coding, translation_table, last_block) |
df7492f9 | 5738 | struct coding_system *coding; |
69a80ea3 KH |
5739 | Lisp_Object translation_table; |
5740 | int last_block; | |
4ed46869 | 5741 | { |
df7492f9 KH |
5742 | unsigned char *dst = coding->destination + coding->produced; |
5743 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5744 | int produced; | |
5745 | int produced_chars = 0; | |
69a80ea3 | 5746 | int carryover = 0; |
4ed46869 | 5747 | |
df7492f9 | 5748 | if (! coding->chars_at_source) |
4ed46869 | 5749 | { |
df7492f9 | 5750 | /* Characters are in coding->charbuf. */ |
fba4576f AS |
5751 | int *buf = coding->charbuf; |
5752 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 5753 | |
df7492f9 KH |
5754 | if (BUFFERP (coding->src_object) |
5755 | && EQ (coding->src_object, coding->dst_object)) | |
8f924df7 | 5756 | dst_end = ((unsigned char *) coding->source) + coding->consumed; |
4ed46869 | 5757 | |
df7492f9 | 5758 | while (buf < buf_end) |
4ed46869 | 5759 | { |
69a80ea3 | 5760 | int c = *buf, i; |
bc4bc72a | 5761 | |
df7492f9 KH |
5762 | if (c >= 0) |
5763 | { | |
69a80ea3 KH |
5764 | int from_nchars = 1, to_nchars = 1; |
5765 | Lisp_Object trans = Qnil; | |
5766 | ||
09ee6fdd | 5767 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 5768 | if (! NILP (trans)) |
69a80ea3 KH |
5769 | { |
5770 | trans = get_translation (trans, buf, buf_end, last_block, | |
5771 | &from_nchars, &to_nchars); | |
5772 | if (EQ (trans, Qt)) | |
5773 | break; | |
5774 | c = *buf; | |
5775 | } | |
5776 | ||
5777 | if (dst + MAX_MULTIBYTE_LENGTH * to_nchars > dst_end) | |
5778 | { | |
5779 | dst = alloc_destination (coding, | |
5780 | buf_end - buf | |
5781 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
5782 | dst); | |
5783 | dst_end = coding->destination + coding->dst_bytes; | |
5784 | } | |
5785 | ||
433f7f87 | 5786 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 5787 | { |
433f7f87 KH |
5788 | if (i > 0) |
5789 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
5790 | if (coding->dst_multibyte |
5791 | || ! CHAR_BYTE8_P (c)) | |
5792 | CHAR_STRING_ADVANCE (c, dst); | |
5793 | else | |
5794 | *dst++ = CHAR_TO_BYTE8 (c); | |
5795 | } | |
5796 | produced_chars += to_nchars; | |
5797 | *buf++ = to_nchars; | |
5798 | while (--from_nchars > 0) | |
5799 | *buf++ = 0; | |
d46c5b12 | 5800 | } |
df7492f9 | 5801 | else |
69a80ea3 KH |
5802 | /* This is an annotation datum. (-C) is the length. */ |
5803 | buf += -c; | |
4ed46869 | 5804 | } |
69a80ea3 | 5805 | carryover = buf_end - buf; |
4ed46869 | 5806 | } |
fa42c37f | 5807 | else |
fa42c37f | 5808 | { |
8f924df7 KH |
5809 | const unsigned char *src = coding->source; |
5810 | const unsigned char *src_end = src + coding->src_bytes; | |
df7492f9 | 5811 | Lisp_Object eol_type; |
fa42c37f | 5812 | |
df7492f9 | 5813 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
4ed46869 | 5814 | |
df7492f9 | 5815 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 5816 | { |
df7492f9 | 5817 | if (coding->src_multibyte) |
fa42c37f | 5818 | { |
71c81426 | 5819 | int multibytep = 1; |
df7492f9 | 5820 | int consumed_chars; |
d46c5b12 | 5821 | |
df7492f9 KH |
5822 | while (1) |
5823 | { | |
8f924df7 | 5824 | const unsigned char *src_base = src; |
df7492f9 | 5825 | int c; |
b73bfc1c | 5826 | |
df7492f9 KH |
5827 | ONE_MORE_BYTE (c); |
5828 | if (c == '\r') | |
5829 | { | |
5830 | if (EQ (eol_type, Qdos)) | |
5831 | { | |
98725083 KH |
5832 | if (src == src_end) |
5833 | { | |
065e3595 KH |
5834 | record_conversion_result |
5835 | (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
98725083 KH |
5836 | goto no_more_source; |
5837 | } | |
5838 | if (*src == '\n') | |
df7492f9 KH |
5839 | c = *src++; |
5840 | } | |
5841 | else if (EQ (eol_type, Qmac)) | |
5842 | c = '\n'; | |
5843 | } | |
5844 | if (dst == dst_end) | |
5845 | { | |
2c78b7e1 | 5846 | coding->consumed = src - coding->source; |
b73bfc1c | 5847 | |
2c78b7e1 | 5848 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5849 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5850 | if (dst == dst_end) |
5851 | { | |
5852 | dst = alloc_destination (coding, src_end - src + 1, | |
5853 | dst); | |
5854 | dst_end = coding->destination + coding->dst_bytes; | |
5855 | coding_set_source (coding); | |
5856 | src = coding->source + coding->consumed; | |
5857 | src_end = coding->source + coding->src_bytes; | |
5858 | } | |
df7492f9 KH |
5859 | } |
5860 | *dst++ = c; | |
5861 | produced_chars++; | |
5862 | } | |
5863 | no_more_source: | |
5864 | ; | |
fa42c37f KH |
5865 | } |
5866 | else | |
df7492f9 KH |
5867 | while (src < src_end) |
5868 | { | |
71c81426 | 5869 | int multibytep = 1; |
df7492f9 | 5870 | int c = *src++; |
b73bfc1c | 5871 | |
df7492f9 KH |
5872 | if (c == '\r') |
5873 | { | |
5874 | if (EQ (eol_type, Qdos)) | |
5875 | { | |
5876 | if (src < src_end | |
5877 | && *src == '\n') | |
5878 | c = *src++; | |
5879 | } | |
5880 | else if (EQ (eol_type, Qmac)) | |
5881 | c = '\n'; | |
5882 | } | |
5883 | if (dst >= dst_end - 1) | |
5884 | { | |
2c78b7e1 | 5885 | coding->consumed = src - coding->source; |
df7492f9 | 5886 | |
2c78b7e1 | 5887 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5888 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5889 | if (dst >= dst_end - 1) |
5890 | { | |
5891 | dst = alloc_destination (coding, src_end - src + 2, | |
5892 | dst); | |
5893 | dst_end = coding->destination + coding->dst_bytes; | |
5894 | coding_set_source (coding); | |
5895 | src = coding->source + coding->consumed; | |
5896 | src_end = coding->source + coding->src_bytes; | |
5897 | } | |
df7492f9 KH |
5898 | } |
5899 | EMIT_ONE_BYTE (c); | |
5900 | } | |
d46c5b12 | 5901 | } |
df7492f9 KH |
5902 | else |
5903 | { | |
5904 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 5905 | { |
df7492f9 | 5906 | int require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 5907 | |
df7492f9 | 5908 | if (require > 0) |
fa42c37f | 5909 | { |
df7492f9 KH |
5910 | EMACS_INT offset = src - coding->source; |
5911 | ||
5912 | dst = alloc_destination (coding, require, dst); | |
5913 | coding_set_source (coding); | |
5914 | src = coding->source + offset; | |
5915 | src_end = coding->source + coding->src_bytes; | |
fa42c37f KH |
5916 | } |
5917 | } | |
df7492f9 KH |
5918 | produced_chars = coding->src_chars; |
5919 | while (src < src_end) | |
fa42c37f | 5920 | { |
df7492f9 KH |
5921 | int c = *src++; |
5922 | ||
5923 | if (c == '\r') | |
5924 | { | |
5925 | if (EQ (eol_type, Qdos)) | |
5926 | { | |
5927 | if (src < src_end | |
5928 | && *src == '\n') | |
5929 | c = *src++; | |
5930 | produced_chars--; | |
5931 | } | |
5932 | else if (EQ (eol_type, Qmac)) | |
5933 | c = '\n'; | |
5934 | } | |
5935 | *dst++ = c; | |
fa42c37f KH |
5936 | } |
5937 | } | |
2c78b7e1 KH |
5938 | coding->consumed = coding->src_bytes; |
5939 | coding->consumed_char = coding->src_chars; | |
fa42c37f KH |
5940 | } |
5941 | ||
df7492f9 KH |
5942 | produced = dst - (coding->destination + coding->produced); |
5943 | if (BUFFERP (coding->dst_object)) | |
5944 | insert_from_gap (produced_chars, produced); | |
5945 | coding->produced += produced; | |
5946 | coding->produced_char += produced_chars; | |
69a80ea3 | 5947 | return carryover; |
fa42c37f KH |
5948 | } |
5949 | ||
ff0dacd7 KH |
5950 | /* Compose text in CODING->object according to the annotation data at |
5951 | CHARBUF. CHARBUF is an array: | |
5952 | [ -LENGTH ANNOTATION_MASK FROM TO METHOD COMP_LEN [ COMPONENTS... ] ] | |
df7492f9 | 5953 | */ |
4ed46869 | 5954 | |
df7492f9 | 5955 | static INLINE void |
69a80ea3 | 5956 | produce_composition (coding, charbuf, pos) |
4ed46869 | 5957 | struct coding_system *coding; |
df7492f9 | 5958 | int *charbuf; |
69a80ea3 | 5959 | EMACS_INT pos; |
4ed46869 | 5960 | { |
df7492f9 | 5961 | int len; |
69a80ea3 | 5962 | EMACS_INT to; |
df7492f9 | 5963 | enum composition_method method; |
df7492f9 | 5964 | Lisp_Object components; |
fa42c37f | 5965 | |
df7492f9 | 5966 | len = -charbuf[0]; |
69a80ea3 | 5967 | to = pos + charbuf[2]; |
9ffd559c KH |
5968 | if (to <= pos) |
5969 | return; | |
69a80ea3 | 5970 | method = (enum composition_method) (charbuf[3]); |
d46c5b12 | 5971 | |
df7492f9 KH |
5972 | if (method == COMPOSITION_RELATIVE) |
5973 | components = Qnil; | |
9ffd559c KH |
5974 | else if (method >= COMPOSITION_WITH_RULE |
5975 | && method <= COMPOSITION_WITH_RULE_ALTCHARS) | |
d46c5b12 | 5976 | { |
df7492f9 KH |
5977 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
5978 | int i; | |
b73bfc1c | 5979 | |
69a80ea3 KH |
5980 | len -= 4; |
5981 | charbuf += 4; | |
df7492f9 | 5982 | for (i = 0; i < len; i++) |
9ffd559c KH |
5983 | { |
5984 | args[i] = make_number (charbuf[i]); | |
5985 | if (args[i] < 0) | |
5986 | return; | |
5987 | } | |
df7492f9 KH |
5988 | components = (method == COMPOSITION_WITH_ALTCHARS |
5989 | ? Fstring (len, args) : Fvector (len, args)); | |
d46c5b12 | 5990 | } |
9ffd559c KH |
5991 | else |
5992 | return; | |
69a80ea3 | 5993 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
5994 | } |
5995 | ||
d46c5b12 | 5996 | |
ff0dacd7 KH |
5997 | /* Put `charset' property on text in CODING->object according to |
5998 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 5999 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 6000 | */ |
d46c5b12 | 6001 | |
ff0dacd7 | 6002 | static INLINE void |
69a80ea3 | 6003 | produce_charset (coding, charbuf, pos) |
d46c5b12 | 6004 | struct coding_system *coding; |
ff0dacd7 | 6005 | int *charbuf; |
69a80ea3 | 6006 | EMACS_INT pos; |
d46c5b12 | 6007 | { |
69a80ea3 KH |
6008 | EMACS_INT from = pos - charbuf[2]; |
6009 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); | |
b73bfc1c | 6010 | |
69a80ea3 | 6011 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
6012 | Qcharset, CHARSET_NAME (charset), |
6013 | coding->dst_object); | |
d46c5b12 KH |
6014 | } |
6015 | ||
d46c5b12 | 6016 | |
df7492f9 KH |
6017 | #define CHARBUF_SIZE 0x4000 |
6018 | ||
6019 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
6020 | do { \ | |
6021 | int size = CHARBUF_SIZE;; \ | |
6022 | \ | |
6023 | coding->charbuf = NULL; \ | |
6024 | while (size > 1024) \ | |
6025 | { \ | |
6026 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
6027 | if (coding->charbuf) \ | |
6028 | break; \ | |
6029 | size >>= 1; \ | |
6030 | } \ | |
6031 | if (! coding->charbuf) \ | |
6032 | { \ | |
065e3595 | 6033 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
df7492f9 KH |
6034 | return coding->result; \ |
6035 | } \ | |
6036 | coding->charbuf_size = size; \ | |
6037 | } while (0) | |
4ed46869 | 6038 | |
d46c5b12 KH |
6039 | |
6040 | static void | |
69a80ea3 | 6041 | produce_annotation (coding, pos) |
d46c5b12 | 6042 | struct coding_system *coding; |
69a80ea3 | 6043 | EMACS_INT pos; |
d46c5b12 | 6044 | { |
df7492f9 KH |
6045 | int *charbuf = coding->charbuf; |
6046 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 6047 | |
ff0dacd7 KH |
6048 | if (NILP (coding->dst_object)) |
6049 | return; | |
d46c5b12 | 6050 | |
df7492f9 | 6051 | while (charbuf < charbuf_end) |
a84f1519 | 6052 | { |
df7492f9 | 6053 | if (*charbuf >= 0) |
69a80ea3 | 6054 | pos += *charbuf++; |
d46c5b12 | 6055 | else |
d46c5b12 | 6056 | { |
df7492f9 | 6057 | int len = -*charbuf; |
ff0dacd7 | 6058 | switch (charbuf[1]) |
df7492f9 KH |
6059 | { |
6060 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
69a80ea3 | 6061 | produce_composition (coding, charbuf, pos); |
df7492f9 | 6062 | break; |
ff0dacd7 | 6063 | case CODING_ANNOTATE_CHARSET_MASK: |
69a80ea3 | 6064 | produce_charset (coding, charbuf, pos); |
ff0dacd7 | 6065 | break; |
df7492f9 KH |
6066 | default: |
6067 | abort (); | |
6068 | } | |
6069 | charbuf += len; | |
d46c5b12 | 6070 | } |
a84f1519 | 6071 | } |
d46c5b12 KH |
6072 | } |
6073 | ||
df7492f9 KH |
6074 | /* Decode the data at CODING->src_object into CODING->dst_object. |
6075 | CODING->src_object is a buffer, a string, or nil. | |
6076 | CODING->dst_object is a buffer. | |
d46c5b12 | 6077 | |
df7492f9 KH |
6078 | If CODING->src_object is a buffer, it must be the current buffer. |
6079 | In this case, if CODING->src_pos is positive, it is a position of | |
6080 | the source text in the buffer, otherwise, the source text is in the | |
6081 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
6082 | the text from GPT (which must be the same as PT). If this is the | |
6083 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6084 | negative. | |
d46c5b12 | 6085 | |
df7492f9 KH |
6086 | If CODING->src_object is a string, CODING->src_pos in an index to |
6087 | that string. | |
d46c5b12 | 6088 | |
df7492f9 KH |
6089 | If CODING->src_object is nil, CODING->source must already point to |
6090 | the non-relocatable memory area. In this case, CODING->src_pos is | |
6091 | an offset from CODING->source. | |
73be902c | 6092 | |
df7492f9 KH |
6093 | The decoded data is inserted at the current point of the buffer |
6094 | CODING->dst_object. | |
6095 | */ | |
d46c5b12 | 6096 | |
df7492f9 KH |
6097 | static int |
6098 | decode_coding (coding) | |
d46c5b12 | 6099 | struct coding_system *coding; |
d46c5b12 | 6100 | { |
df7492f9 | 6101 | Lisp_Object attrs; |
24a73b0a | 6102 | Lisp_Object undo_list; |
7d64c6ad | 6103 | Lisp_Object translation_table; |
69a80ea3 KH |
6104 | int carryover; |
6105 | int i; | |
d46c5b12 | 6106 | |
df7492f9 KH |
6107 | if (BUFFERP (coding->src_object) |
6108 | && coding->src_pos > 0 | |
6109 | && coding->src_pos < GPT | |
6110 | && coding->src_pos + coding->src_chars > GPT) | |
6111 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 6112 | |
24a73b0a | 6113 | undo_list = Qt; |
df7492f9 | 6114 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 6115 | { |
df7492f9 KH |
6116 | if (current_buffer != XBUFFER (coding->dst_object)) |
6117 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6118 | if (GPT != PT) | |
6119 | move_gap_both (PT, PT_BYTE); | |
24a73b0a KH |
6120 | undo_list = current_buffer->undo_list; |
6121 | current_buffer->undo_list = Qt; | |
1c3478b0 KH |
6122 | } |
6123 | ||
df7492f9 KH |
6124 | coding->consumed = coding->consumed_char = 0; |
6125 | coding->produced = coding->produced_char = 0; | |
6126 | coding->chars_at_source = 0; | |
065e3595 | 6127 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 6128 | coding->errors = 0; |
1c3478b0 | 6129 | |
df7492f9 KH |
6130 | ALLOC_CONVERSION_WORK_AREA (coding); |
6131 | ||
6132 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 6133 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 6134 | |
69a80ea3 | 6135 | carryover = 0; |
df7492f9 | 6136 | do |
b73bfc1c | 6137 | { |
69a80ea3 KH |
6138 | EMACS_INT pos = coding->dst_pos + coding->produced_char; |
6139 | ||
df7492f9 KH |
6140 | coding_set_source (coding); |
6141 | coding->annotated = 0; | |
69a80ea3 | 6142 | coding->charbuf_used = carryover; |
df7492f9 | 6143 | (*(coding->decoder)) (coding); |
df7492f9 | 6144 | coding_set_destination (coding); |
69a80ea3 | 6145 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 6146 | if (coding->annotated) |
69a80ea3 KH |
6147 | produce_annotation (coding, pos); |
6148 | for (i = 0; i < carryover; i++) | |
6149 | coding->charbuf[i] | |
6150 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 6151 | } |
df7492f9 KH |
6152 | while (coding->consumed < coding->src_bytes |
6153 | && ! coding->result); | |
d46c5b12 | 6154 | |
69a80ea3 KH |
6155 | if (carryover > 0) |
6156 | { | |
6157 | coding_set_destination (coding); | |
6158 | coding->charbuf_used = carryover; | |
6159 | produce_chars (coding, translation_table, 1); | |
6160 | } | |
6161 | ||
df7492f9 KH |
6162 | coding->carryover_bytes = 0; |
6163 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 6164 | { |
df7492f9 | 6165 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 6166 | const unsigned char *src; |
df7492f9 KH |
6167 | |
6168 | coding_set_source (coding); | |
6169 | coding_set_destination (coding); | |
6170 | src = coding->source + coding->consumed; | |
6171 | ||
6172 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 6173 | { |
df7492f9 KH |
6174 | /* Flush out unprocessed data as binary chars. We are sure |
6175 | that the number of data is less than the size of | |
6176 | coding->charbuf. */ | |
065e3595 | 6177 | coding->charbuf_used = 0; |
df7492f9 | 6178 | while (nbytes-- > 0) |
1c3478b0 | 6179 | { |
df7492f9 | 6180 | int c = *src++; |
98725083 KH |
6181 | |
6182 | coding->charbuf[coding->charbuf_used++] = (c & 0x80 ? - c : c); | |
1c3478b0 | 6183 | } |
f6cbaf43 | 6184 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 6185 | } |
d46c5b12 | 6186 | else |
df7492f9 KH |
6187 | { |
6188 | /* Record unprocessed bytes in coding->carryover. We are | |
6189 | sure that the number of data is less than the size of | |
6190 | coding->carryover. */ | |
6191 | unsigned char *p = coding->carryover; | |
6192 | ||
6193 | coding->carryover_bytes = nbytes; | |
6194 | while (nbytes-- > 0) | |
6195 | *p++ = *src++; | |
1c3478b0 | 6196 | } |
df7492f9 | 6197 | coding->consumed = coding->src_bytes; |
b73bfc1c | 6198 | } |
69f76525 | 6199 | |
24a73b0a KH |
6200 | if (BUFFERP (coding->dst_object)) |
6201 | { | |
6202 | current_buffer->undo_list = undo_list; | |
6203 | record_insert (coding->dst_pos, coding->produced_char); | |
6204 | } | |
6205 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix)) | |
6206 | decode_eol (coding); | |
73be902c | 6207 | return coding->result; |
4ed46869 KH |
6208 | } |
6209 | ||
aaaf0b1e | 6210 | |
e1c23804 | 6211 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
6212 | ending before LIMIT of CODING->src_object (buffer or string), store |
6213 | the data in BUF, set *STOP to a starting position of the next | |
6214 | composition (if any) or to LIMIT, and return the address of the | |
6215 | next element of BUF. | |
6216 | ||
6217 | If such an annotation is not found, set *STOP to a starting | |
6218 | position of a composition after POS (if any) or to LIMIT, and | |
6219 | return BUF. */ | |
6220 | ||
6221 | static INLINE int * | |
6222 | handle_composition_annotation (pos, limit, coding, buf, stop) | |
6223 | EMACS_INT pos, limit; | |
aaaf0b1e | 6224 | struct coding_system *coding; |
ff0dacd7 KH |
6225 | int *buf; |
6226 | EMACS_INT *stop; | |
aaaf0b1e | 6227 | { |
ff0dacd7 KH |
6228 | EMACS_INT start, end; |
6229 | Lisp_Object prop; | |
aaaf0b1e | 6230 | |
ff0dacd7 KH |
6231 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
6232 | || end > limit) | |
6233 | *stop = limit; | |
6234 | else if (start > pos) | |
6235 | *stop = start; | |
6236 | else | |
aaaf0b1e | 6237 | { |
ff0dacd7 | 6238 | if (start == pos) |
aaaf0b1e | 6239 | { |
ff0dacd7 KH |
6240 | /* We found a composition. Store the corresponding |
6241 | annotation data in BUF. */ | |
6242 | int *head = buf; | |
6243 | enum composition_method method = COMPOSITION_METHOD (prop); | |
6244 | int nchars = COMPOSITION_LENGTH (prop); | |
6245 | ||
69a80ea3 | 6246 | ADD_COMPOSITION_DATA (buf, nchars, method); |
ff0dacd7 | 6247 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 6248 | { |
ff0dacd7 KH |
6249 | Lisp_Object components; |
6250 | int len, i, i_byte; | |
6251 | ||
6252 | components = COMPOSITION_COMPONENTS (prop); | |
6253 | if (VECTORP (components)) | |
aaaf0b1e | 6254 | { |
ff0dacd7 KH |
6255 | len = XVECTOR (components)->size; |
6256 | for (i = 0; i < len; i++) | |
6257 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 6258 | } |
ff0dacd7 | 6259 | else if (STRINGP (components)) |
aaaf0b1e | 6260 | { |
8f924df7 | 6261 | len = SCHARS (components); |
ff0dacd7 KH |
6262 | i = i_byte = 0; |
6263 | while (i < len) | |
6264 | { | |
6265 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
6266 | buf++; | |
6267 | } | |
6268 | } | |
6269 | else if (INTEGERP (components)) | |
6270 | { | |
6271 | len = 1; | |
6272 | *buf++ = XINT (components); | |
6273 | } | |
6274 | else if (CONSP (components)) | |
6275 | { | |
6276 | for (len = 0; CONSP (components); | |
6277 | len++, components = XCDR (components)) | |
6278 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 6279 | } |
aaaf0b1e | 6280 | else |
ff0dacd7 KH |
6281 | abort (); |
6282 | *head -= len; | |
aaaf0b1e | 6283 | } |
aaaf0b1e | 6284 | } |
ff0dacd7 KH |
6285 | |
6286 | if (find_composition (end, limit, &start, &end, &prop, | |
6287 | coding->src_object) | |
6288 | && end <= limit) | |
6289 | *stop = start; | |
6290 | else | |
6291 | *stop = limit; | |
aaaf0b1e | 6292 | } |
ff0dacd7 KH |
6293 | return buf; |
6294 | } | |
6295 | ||
6296 | ||
e1c23804 | 6297 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
6298 | CODING->src_object (buffer of string), store the data in BUF, set |
6299 | *STOP to the position where the value of `charset' property changes | |
6300 | (limiting by LIMIT), and return the address of the next element of | |
6301 | BUF. | |
6302 | ||
6303 | If the property value is nil, set *STOP to the position where the | |
6304 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
6305 | ||
6306 | static INLINE int * | |
6307 | handle_charset_annotation (pos, limit, coding, buf, stop) | |
6308 | EMACS_INT pos, limit; | |
6309 | struct coding_system *coding; | |
6310 | int *buf; | |
6311 | EMACS_INT *stop; | |
6312 | { | |
6313 | Lisp_Object val, next; | |
6314 | int id; | |
6315 | ||
6316 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
6317 | if (! NILP (val) && CHARSETP (val)) | |
6318 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
6319 | else | |
6320 | id = -1; | |
69a80ea3 | 6321 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
6322 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
6323 | coding->src_object, | |
6324 | make_number (limit)); | |
6325 | *stop = XINT (next); | |
6326 | return buf; | |
6327 | } | |
6328 | ||
6329 | ||
df7492f9 | 6330 | static void |
09ee6fdd | 6331 | consume_chars (coding, translation_table, max_lookup) |
df7492f9 | 6332 | struct coding_system *coding; |
433f7f87 | 6333 | Lisp_Object translation_table; |
09ee6fdd | 6334 | int max_lookup; |
df7492f9 KH |
6335 | { |
6336 | int *buf = coding->charbuf; | |
ff0dacd7 | 6337 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 6338 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 6339 | const unsigned char *src_end = coding->source + coding->src_bytes; |
ff0dacd7 KH |
6340 | EMACS_INT pos = coding->src_pos + coding->consumed_char; |
6341 | EMACS_INT end_pos = coding->src_pos + coding->src_chars; | |
df7492f9 KH |
6342 | int multibytep = coding->src_multibyte; |
6343 | Lisp_Object eol_type; | |
6344 | int c; | |
ff0dacd7 | 6345 | EMACS_INT stop, stop_composition, stop_charset; |
09ee6fdd | 6346 | int *lookup_buf = NULL; |
433f7f87 KH |
6347 | |
6348 | if (! NILP (translation_table)) | |
09ee6fdd | 6349 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 6350 | |
df7492f9 KH |
6351 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6352 | if (VECTORP (eol_type)) | |
6353 | eol_type = Qunix; | |
88993dfd | 6354 | |
df7492f9 KH |
6355 | /* Note: composition handling is not yet implemented. */ |
6356 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 6357 | |
0b5670c9 KH |
6358 | if (NILP (coding->src_object)) |
6359 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 6360 | else |
0b5670c9 KH |
6361 | { |
6362 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
6363 | stop = stop_composition = pos; | |
6364 | else | |
6365 | stop = stop_composition = end_pos; | |
6366 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
6367 | stop = stop_charset = pos; | |
6368 | else | |
6369 | stop_charset = end_pos; | |
6370 | } | |
ec6d2bb8 | 6371 | |
24a73b0a | 6372 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 6373 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 6374 | while (buf < buf_end) |
aaaf0b1e | 6375 | { |
433f7f87 KH |
6376 | Lisp_Object trans; |
6377 | ||
df7492f9 | 6378 | if (pos == stop) |
ec6d2bb8 | 6379 | { |
df7492f9 KH |
6380 | if (pos == end_pos) |
6381 | break; | |
ff0dacd7 KH |
6382 | if (pos == stop_composition) |
6383 | buf = handle_composition_annotation (pos, end_pos, coding, | |
6384 | buf, &stop_composition); | |
6385 | if (pos == stop_charset) | |
6386 | buf = handle_charset_annotation (pos, end_pos, coding, | |
6387 | buf, &stop_charset); | |
6388 | stop = (stop_composition < stop_charset | |
6389 | ? stop_composition : stop_charset); | |
df7492f9 KH |
6390 | } |
6391 | ||
6392 | if (! multibytep) | |
4776e638 | 6393 | { |
d3e4cb56 | 6394 | EMACS_INT bytes; |
aaaf0b1e | 6395 | |
ea29edf2 KH |
6396 | if (coding->encoder == encode_coding_raw_text) |
6397 | c = *src++, pos++; | |
6398 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
4776e638 KH |
6399 | c = STRING_CHAR_ADVANCE (src), pos += bytes; |
6400 | else | |
f03caae0 | 6401 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 6402 | } |
df7492f9 | 6403 | else |
4776e638 | 6404 | c = STRING_CHAR_ADVANCE (src), pos++; |
df7492f9 KH |
6405 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
6406 | c = '\n'; | |
6407 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 6408 | { |
df7492f9 | 6409 | if (c == '\n') |
aaaf0b1e | 6410 | { |
df7492f9 KH |
6411 | if (EQ (eol_type, Qdos)) |
6412 | *buf++ = '\r'; | |
6413 | else | |
6414 | c = '\r'; | |
aaaf0b1e KH |
6415 | } |
6416 | } | |
433f7f87 | 6417 | |
e6a54062 | 6418 | trans = Qnil; |
09ee6fdd | 6419 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6420 | if (NILP (trans)) |
433f7f87 KH |
6421 | *buf++ = c; |
6422 | else | |
6423 | { | |
6424 | int from_nchars = 1, to_nchars = 1; | |
6425 | int *lookup_buf_end; | |
6426 | const unsigned char *p = src; | |
6427 | int i; | |
6428 | ||
6429 | lookup_buf[0] = c; | |
6430 | for (i = 1; i < max_lookup && p < src_end; i++) | |
6431 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
6432 | lookup_buf_end = lookup_buf + i; | |
6433 | trans = get_translation (trans, lookup_buf, lookup_buf_end, 1, | |
6434 | &from_nchars, &to_nchars); | |
6435 | if (EQ (trans, Qt) | |
6436 | || buf + to_nchars > buf_end) | |
6437 | break; | |
6438 | *buf++ = *lookup_buf; | |
6439 | for (i = 1; i < to_nchars; i++) | |
6440 | *buf++ = XINT (AREF (trans, i)); | |
6441 | for (i = 1; i < from_nchars; i++, pos++) | |
6442 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
6443 | } | |
aaaf0b1e | 6444 | } |
ec6d2bb8 | 6445 | |
df7492f9 KH |
6446 | coding->consumed = src - coding->source; |
6447 | coding->consumed_char = pos - coding->src_pos; | |
6448 | coding->charbuf_used = buf - coding->charbuf; | |
6449 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
6450 | } |
6451 | ||
4ed46869 | 6452 | |
df7492f9 KH |
6453 | /* Encode the text at CODING->src_object into CODING->dst_object. |
6454 | CODING->src_object is a buffer or a string. | |
6455 | CODING->dst_object is a buffer or nil. | |
6456 | ||
6457 | If CODING->src_object is a buffer, it must be the current buffer. | |
6458 | In this case, if CODING->src_pos is positive, it is a position of | |
6459 | the source text in the buffer, otherwise. the source text is in the | |
6460 | gap area of the buffer, and coding->src_pos specifies the offset of | |
6461 | the text from GPT (which must be the same as PT). If this is the | |
6462 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6463 | negative and CODING should not have `pre-write-conversion'. | |
6464 | ||
6465 | If CODING->src_object is a string, CODING should not have | |
6466 | `pre-write-conversion'. | |
6467 | ||
6468 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
6469 | the current point of that buffer. | |
6470 | ||
6471 | If CODING->dst_object is nil, the encoded data is placed at the | |
6472 | memory area specified by CODING->destination. */ | |
6473 | ||
6474 | static int | |
6475 | encode_coding (coding) | |
4ed46869 | 6476 | struct coding_system *coding; |
4ed46869 | 6477 | { |
df7492f9 | 6478 | Lisp_Object attrs; |
7d64c6ad | 6479 | Lisp_Object translation_table; |
09ee6fdd | 6480 | int max_lookup; |
9861e777 | 6481 | |
df7492f9 | 6482 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
6483 | if (coding->encoder == encode_coding_raw_text) |
6484 | translation_table = Qnil, max_lookup = 0; | |
6485 | else | |
6486 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 6487 | |
df7492f9 | 6488 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 6489 | { |
df7492f9 KH |
6490 | set_buffer_internal (XBUFFER (coding->dst_object)); |
6491 | coding->dst_multibyte | |
6492 | = ! NILP (current_buffer->enable_multibyte_characters); | |
8844fa83 | 6493 | } |
4ed46869 | 6494 | |
b73bfc1c | 6495 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 6496 | coding->produced = coding->produced_char = 0; |
065e3595 | 6497 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 6498 | coding->errors = 0; |
b73bfc1c | 6499 | |
df7492f9 | 6500 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 6501 | |
df7492f9 KH |
6502 | do { |
6503 | coding_set_source (coding); | |
09ee6fdd | 6504 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
6505 | coding_set_destination (coding); |
6506 | (*(coding->encoder)) (coding); | |
6507 | } while (coding->consumed_char < coding->src_chars); | |
6508 | ||
6509 | if (BUFFERP (coding->dst_object)) | |
6510 | insert_from_gap (coding->produced_char, coding->produced); | |
6511 | ||
6512 | return (coding->result); | |
ec6d2bb8 KH |
6513 | } |
6514 | ||
fb88bf2d | 6515 | |
24a73b0a KH |
6516 | /* Name (or base name) of work buffer for code conversion. */ |
6517 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 6518 | |
24a73b0a KH |
6519 | /* A working buffer used by the top level conversion. Once it is |
6520 | created, it is never destroyed. It has the name | |
6521 | Vcode_conversion_workbuf_name. The other working buffers are | |
6522 | destroyed after the use is finished, and their names are modified | |
6523 | versions of Vcode_conversion_workbuf_name. */ | |
6524 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 6525 | |
24a73b0a KH |
6526 | /* 1 iff Vcode_conversion_reused_workbuf is already in use. */ |
6527 | static int reused_workbuf_in_use; | |
4ed46869 | 6528 | |
24a73b0a KH |
6529 | |
6530 | /* Return a working buffer of code convesion. MULTIBYTE specifies the | |
6531 | multibyteness of returning buffer. */ | |
b73bfc1c | 6532 | |
f6cbaf43 | 6533 | static Lisp_Object |
24a73b0a | 6534 | make_conversion_work_buffer (multibyte) |
f6cbaf43 | 6535 | int multibyte; |
df7492f9 | 6536 | { |
24a73b0a KH |
6537 | Lisp_Object name, workbuf; |
6538 | struct buffer *current; | |
4ed46869 | 6539 | |
24a73b0a | 6540 | if (reused_workbuf_in_use++) |
065e3595 KH |
6541 | { |
6542 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
6543 | workbuf = Fget_buffer_create (name); | |
6544 | } | |
df7492f9 | 6545 | else |
065e3595 KH |
6546 | { |
6547 | name = Vcode_conversion_workbuf_name; | |
6548 | workbuf = Fget_buffer_create (name); | |
6549 | if (NILP (Vcode_conversion_reused_workbuf)) | |
6550 | Vcode_conversion_reused_workbuf = workbuf; | |
6551 | } | |
24a73b0a KH |
6552 | current = current_buffer; |
6553 | set_buffer_internal (XBUFFER (workbuf)); | |
6554 | Ferase_buffer (); | |
df7492f9 | 6555 | current_buffer->undo_list = Qt; |
24a73b0a | 6556 | current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil; |
df7492f9 | 6557 | set_buffer_internal (current); |
24a73b0a | 6558 | return workbuf; |
df7492f9 | 6559 | } |
d46c5b12 | 6560 | |
24a73b0a | 6561 | |
4776e638 | 6562 | static Lisp_Object |
24a73b0a KH |
6563 | code_conversion_restore (arg) |
6564 | Lisp_Object arg; | |
4776e638 | 6565 | { |
24a73b0a KH |
6566 | Lisp_Object current, workbuf; |
6567 | ||
6568 | current = XCAR (arg); | |
6569 | workbuf = XCDR (arg); | |
6570 | if (! NILP (workbuf)) | |
6571 | { | |
6572 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
6573 | reused_workbuf_in_use = 0; | |
6574 | else if (! NILP (Fbuffer_live_p (workbuf))) | |
6575 | Fkill_buffer (workbuf); | |
6576 | } | |
6577 | set_buffer_internal (XBUFFER (current)); | |
4776e638 KH |
6578 | return Qnil; |
6579 | } | |
b73bfc1c | 6580 | |
24a73b0a KH |
6581 | Lisp_Object |
6582 | code_conversion_save (with_work_buf, multibyte) | |
4776e638 | 6583 | int with_work_buf, multibyte; |
df7492f9 | 6584 | { |
24a73b0a | 6585 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 6586 | |
4776e638 | 6587 | if (with_work_buf) |
24a73b0a KH |
6588 | workbuf = make_conversion_work_buffer (multibyte); |
6589 | record_unwind_protect (code_conversion_restore, | |
6590 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 6591 | return workbuf; |
df7492f9 | 6592 | } |
d46c5b12 | 6593 | |
df7492f9 KH |
6594 | int |
6595 | decode_coding_gap (coding, chars, bytes) | |
6596 | struct coding_system *coding; | |
6597 | EMACS_INT chars, bytes; | |
6598 | { | |
6599 | int count = specpdl_ptr - specpdl; | |
5e5c78be | 6600 | Lisp_Object attrs; |
fb88bf2d | 6601 | |
24a73b0a | 6602 | code_conversion_save (0, 0); |
ec6d2bb8 | 6603 | |
24a73b0a | 6604 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6605 | coding->src_chars = chars; |
6606 | coding->src_bytes = bytes; | |
6607 | coding->src_pos = -chars; | |
6608 | coding->src_pos_byte = -bytes; | |
6609 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 6610 | coding->dst_object = coding->src_object; |
df7492f9 KH |
6611 | coding->dst_pos = PT; |
6612 | coding->dst_pos_byte = PT_BYTE; | |
71c81426 | 6613 | coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters); |
98725083 | 6614 | coding->mode |= CODING_MODE_LAST_BLOCK; |
4ed46869 | 6615 | |
df7492f9 KH |
6616 | if (CODING_REQUIRE_DETECTION (coding)) |
6617 | detect_coding (coding); | |
8f924df7 | 6618 | |
df7492f9 | 6619 | decode_coding (coding); |
d46c5b12 | 6620 | |
5e5c78be KH |
6621 | attrs = CODING_ID_ATTRS (coding->id); |
6622 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 6623 | { |
5e5c78be KH |
6624 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
6625 | Lisp_Object val; | |
6626 | ||
6627 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
6628 | val = call1 (CODING_ATTR_POST_READ (attrs), |
6629 | make_number (coding->produced_char)); | |
5e5c78be KH |
6630 | CHECK_NATNUM (val); |
6631 | coding->produced_char += Z - prev_Z; | |
6632 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 6633 | } |
4ed46869 | 6634 | |
df7492f9 | 6635 | unbind_to (count, Qnil); |
b73bfc1c KH |
6636 | return coding->result; |
6637 | } | |
52d41803 | 6638 | |
4ed46869 | 6639 | int |
df7492f9 | 6640 | encode_coding_gap (coding, chars, bytes) |
4ed46869 | 6641 | struct coding_system *coding; |
df7492f9 | 6642 | EMACS_INT chars, bytes; |
4ed46869 | 6643 | { |
df7492f9 | 6644 | int count = specpdl_ptr - specpdl; |
4ed46869 | 6645 | |
24a73b0a | 6646 | code_conversion_save (0, 0); |
4ed46869 | 6647 | |
24a73b0a | 6648 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6649 | coding->src_chars = chars; |
6650 | coding->src_bytes = bytes; | |
6651 | coding->src_pos = -chars; | |
6652 | coding->src_pos_byte = -bytes; | |
6653 | coding->src_multibyte = chars < bytes; | |
6654 | coding->dst_object = coding->src_object; | |
6655 | coding->dst_pos = PT; | |
6656 | coding->dst_pos_byte = PT_BYTE; | |
4ed46869 | 6657 | |
df7492f9 | 6658 | encode_coding (coding); |
b73bfc1c | 6659 | |
df7492f9 KH |
6660 | unbind_to (count, Qnil); |
6661 | return coding->result; | |
6662 | } | |
4ed46869 | 6663 | |
d46c5b12 | 6664 | |
df7492f9 KH |
6665 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
6666 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 6667 | |
df7492f9 | 6668 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 6669 | |
df7492f9 KH |
6670 | If it is a buffer, the text is at point of the buffer. FROM and TO |
6671 | are positions in the buffer. | |
b73bfc1c | 6672 | |
df7492f9 KH |
6673 | If it is a string, the text is at the beginning of the string. |
6674 | FROM and TO are indices to the string. | |
4ed46869 | 6675 | |
df7492f9 KH |
6676 | If it is nil, the text is at coding->source. FROM and TO are |
6677 | indices to coding->source. | |
bb10be8b | 6678 | |
df7492f9 | 6679 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 6680 | |
df7492f9 KH |
6681 | If it is a buffer, the decoded text is inserted at point of the |
6682 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
6683 | is deleted. | |
4ed46869 | 6684 | |
df7492f9 KH |
6685 | If it is Qt, a string is made from the decoded text, and |
6686 | set in CODING->dst_object. | |
d46c5b12 | 6687 | |
df7492f9 | 6688 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 6689 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
6690 | CODING->destination by xmalloc. If the decoded text is longer than |
6691 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
6692 | */ | |
d46c5b12 | 6693 | |
df7492f9 KH |
6694 | void |
6695 | decode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6696 | dst_object) | |
d46c5b12 | 6697 | struct coding_system *coding; |
df7492f9 KH |
6698 | Lisp_Object src_object; |
6699 | EMACS_INT from, from_byte, to, to_byte; | |
6700 | Lisp_Object dst_object; | |
d46c5b12 | 6701 | { |
df7492f9 KH |
6702 | int count = specpdl_ptr - specpdl; |
6703 | unsigned char *destination; | |
6704 | EMACS_INT dst_bytes; | |
6705 | EMACS_INT chars = to - from; | |
6706 | EMACS_INT bytes = to_byte - from_byte; | |
6707 | Lisp_Object attrs; | |
4776e638 KH |
6708 | Lisp_Object buffer; |
6709 | int saved_pt = -1, saved_pt_byte; | |
d46c5b12 | 6710 | |
4776e638 | 6711 | buffer = Fcurrent_buffer (); |
93dec019 | 6712 | |
df7492f9 | 6713 | if (NILP (dst_object)) |
d46c5b12 | 6714 | { |
df7492f9 KH |
6715 | destination = coding->destination; |
6716 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 6717 | } |
93dec019 | 6718 | |
df7492f9 KH |
6719 | coding->src_object = src_object; |
6720 | coding->src_chars = chars; | |
6721 | coding->src_bytes = bytes; | |
6722 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 6723 | |
df7492f9 | 6724 | if (STRINGP (src_object)) |
d46c5b12 | 6725 | { |
df7492f9 KH |
6726 | coding->src_pos = from; |
6727 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6728 | } |
df7492f9 | 6729 | else if (BUFFERP (src_object)) |
88993dfd | 6730 | { |
df7492f9 KH |
6731 | set_buffer_internal (XBUFFER (src_object)); |
6732 | if (from != GPT) | |
6733 | move_gap_both (from, from_byte); | |
6734 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 6735 | { |
4776e638 | 6736 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6737 | TEMP_SET_PT_BOTH (from, from_byte); |
6738 | del_range_both (from, from_byte, to, to_byte, 1); | |
6739 | coding->src_pos = -chars; | |
6740 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 6741 | } |
df7492f9 | 6742 | else |
fb88bf2d | 6743 | { |
df7492f9 KH |
6744 | coding->src_pos = from; |
6745 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 6746 | } |
88993dfd KH |
6747 | } |
6748 | ||
df7492f9 KH |
6749 | if (CODING_REQUIRE_DETECTION (coding)) |
6750 | detect_coding (coding); | |
6751 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 6752 | |
2cb26057 KH |
6753 | if (EQ (dst_object, Qt) |
6754 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
6755 | && NILP (dst_object))) | |
b73bfc1c | 6756 | { |
24a73b0a | 6757 | coding->dst_object = code_conversion_save (1, 1); |
df7492f9 KH |
6758 | coding->dst_pos = BEG; |
6759 | coding->dst_pos_byte = BEG_BYTE; | |
6760 | coding->dst_multibyte = 1; | |
b73bfc1c | 6761 | } |
df7492f9 | 6762 | else if (BUFFERP (dst_object)) |
d46c5b12 | 6763 | { |
24a73b0a | 6764 | code_conversion_save (0, 0); |
df7492f9 KH |
6765 | coding->dst_object = dst_object; |
6766 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6767 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6768 | coding->dst_multibyte | |
6769 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
d46c5b12 KH |
6770 | } |
6771 | else | |
6772 | { | |
24a73b0a | 6773 | code_conversion_save (0, 0); |
df7492f9 KH |
6774 | coding->dst_object = Qnil; |
6775 | coding->dst_multibyte = 1; | |
d46c5b12 KH |
6776 | } |
6777 | ||
df7492f9 | 6778 | decode_coding (coding); |
fa46990e | 6779 | |
df7492f9 KH |
6780 | if (BUFFERP (coding->dst_object)) |
6781 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 6782 | |
df7492f9 | 6783 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 6784 | { |
df7492f9 KH |
6785 | struct gcpro gcpro1, gcpro2; |
6786 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; | |
2b4f9037 | 6787 | Lisp_Object val; |
d46c5b12 | 6788 | |
c0cc7f7f | 6789 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
df7492f9 KH |
6790 | GCPRO2 (coding->src_object, coding->dst_object); |
6791 | val = call1 (CODING_ATTR_POST_READ (attrs), | |
6792 | make_number (coding->produced_char)); | |
6793 | UNGCPRO; | |
6794 | CHECK_NATNUM (val); | |
6795 | coding->produced_char += Z - prev_Z; | |
6796 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 6797 | } |
de79a6a5 | 6798 | |
df7492f9 | 6799 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 6800 | { |
df7492f9 KH |
6801 | coding->dst_object = Fbuffer_string (); |
6802 | } | |
6803 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
6804 | { | |
6805 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6806 | if (dst_bytes < coding->produced) | |
6807 | { | |
6808 | destination | |
6809 | = (unsigned char *) xrealloc (destination, coding->produced); | |
6810 | if (! destination) | |
6811 | { | |
065e3595 KH |
6812 | record_conversion_result (coding, |
6813 | CODING_RESULT_INSUFFICIENT_DST); | |
df7492f9 KH |
6814 | unbind_to (count, Qnil); |
6815 | return; | |
6816 | } | |
6817 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
6818 | move_gap_both (BEGV, BEGV_BYTE); | |
6819 | bcopy (BEGV_ADDR, destination, coding->produced); | |
6820 | coding->destination = destination; | |
d46c5b12 | 6821 | } |
ec6d2bb8 | 6822 | } |
b73bfc1c | 6823 | |
4776e638 KH |
6824 | if (saved_pt >= 0) |
6825 | { | |
6826 | /* This is the case of: | |
6827 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
6828 | As we have moved PT while replacing the original buffer | |
6829 | contents, we must recover it now. */ | |
6830 | set_buffer_internal (XBUFFER (src_object)); | |
6831 | if (saved_pt < from) | |
6832 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
6833 | else if (saved_pt < from + chars) | |
6834 | TEMP_SET_PT_BOTH (from, from_byte); | |
6835 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
6836 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
6837 | saved_pt_byte + (coding->produced - bytes)); | |
6838 | else | |
6839 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
6840 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 6841 | } |
4776e638 | 6842 | |
065e3595 | 6843 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
6844 | } |
6845 | ||
d46c5b12 | 6846 | |
df7492f9 KH |
6847 | void |
6848 | encode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6849 | dst_object) | |
d46c5b12 | 6850 | struct coding_system *coding; |
df7492f9 KH |
6851 | Lisp_Object src_object; |
6852 | EMACS_INT from, from_byte, to, to_byte; | |
6853 | Lisp_Object dst_object; | |
d46c5b12 | 6854 | { |
b73bfc1c | 6855 | int count = specpdl_ptr - specpdl; |
df7492f9 KH |
6856 | EMACS_INT chars = to - from; |
6857 | EMACS_INT bytes = to_byte - from_byte; | |
6858 | Lisp_Object attrs; | |
4776e638 KH |
6859 | Lisp_Object buffer; |
6860 | int saved_pt = -1, saved_pt_byte; | |
df7492f9 | 6861 | |
4776e638 | 6862 | buffer = Fcurrent_buffer (); |
df7492f9 KH |
6863 | |
6864 | coding->src_object = src_object; | |
6865 | coding->src_chars = chars; | |
6866 | coding->src_bytes = bytes; | |
6867 | coding->src_multibyte = chars < bytes; | |
6868 | ||
6869 | attrs = CODING_ID_ATTRS (coding->id); | |
6870 | ||
6871 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
6bac5b12 | 6872 | { |
24a73b0a | 6873 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
6874 | set_buffer_internal (XBUFFER (coding->src_object)); |
6875 | if (STRINGP (src_object)) | |
6876 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
6877 | else if (BUFFERP (src_object)) | |
6878 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
6879 | else | |
6880 | insert_1_both (coding->source + from, chars, bytes, 0, 0, 0); | |
d46c5b12 | 6881 | |
df7492f9 KH |
6882 | if (EQ (src_object, dst_object)) |
6883 | { | |
6884 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 6885 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6886 | del_range_both (from, from_byte, to, to_byte, 1); |
6887 | set_buffer_internal (XBUFFER (coding->src_object)); | |
6888 | } | |
6889 | ||
ac87bbef KH |
6890 | call2 (CODING_ATTR_PRE_WRITE (attrs), |
6891 | make_number (BEG), make_number (Z)); | |
6892 | coding->src_object = Fcurrent_buffer (); | |
df7492f9 KH |
6893 | if (BEG != GPT) |
6894 | move_gap_both (BEG, BEG_BYTE); | |
6895 | coding->src_chars = Z - BEG; | |
6896 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
6897 | coding->src_pos = BEG; | |
6898 | coding->src_pos_byte = BEG_BYTE; | |
6899 | coding->src_multibyte = Z < Z_BYTE; | |
6900 | } | |
6901 | else if (STRINGP (src_object)) | |
d46c5b12 | 6902 | { |
24a73b0a | 6903 | code_conversion_save (0, 0); |
df7492f9 KH |
6904 | coding->src_pos = from; |
6905 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 6906 | } |
df7492f9 | 6907 | else if (BUFFERP (src_object)) |
b73bfc1c | 6908 | { |
24a73b0a | 6909 | code_conversion_save (0, 0); |
df7492f9 | 6910 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 6911 | if (EQ (src_object, dst_object)) |
d46c5b12 | 6912 | { |
4776e638 | 6913 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
6914 | coding->src_object = del_range_1 (from, to, 1, 1); |
6915 | coding->src_pos = 0; | |
6916 | coding->src_pos_byte = 0; | |
d46c5b12 | 6917 | } |
df7492f9 | 6918 | else |
d46c5b12 | 6919 | { |
ff0dacd7 KH |
6920 | if (from < GPT && to >= GPT) |
6921 | move_gap_both (from, from_byte); | |
df7492f9 KH |
6922 | coding->src_pos = from; |
6923 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6924 | } |
d46c5b12 | 6925 | } |
4776e638 | 6926 | else |
24a73b0a | 6927 | code_conversion_save (0, 0); |
d46c5b12 | 6928 | |
df7492f9 | 6929 | if (BUFFERP (dst_object)) |
88993dfd | 6930 | { |
df7492f9 | 6931 | coding->dst_object = dst_object; |
28f67a95 KH |
6932 | if (EQ (src_object, dst_object)) |
6933 | { | |
6934 | coding->dst_pos = from; | |
6935 | coding->dst_pos_byte = from_byte; | |
6936 | } | |
6937 | else | |
6938 | { | |
6939 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6940 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6941 | } | |
df7492f9 KH |
6942 | coding->dst_multibyte |
6943 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
88993dfd | 6944 | } |
df7492f9 | 6945 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 6946 | { |
df7492f9 | 6947 | coding->dst_object = Qnil; |
df7492f9 | 6948 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
6949 | if (coding->dst_bytes == 0) |
6950 | coding->dst_bytes = 1; | |
6951 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 6952 | coding->dst_multibyte = 0; |
d46c5b12 KH |
6953 | } |
6954 | else | |
6955 | { | |
df7492f9 KH |
6956 | coding->dst_object = Qnil; |
6957 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
6958 | } |
6959 | ||
df7492f9 | 6960 | encode_coding (coding); |
d46c5b12 | 6961 | |
df7492f9 | 6962 | if (EQ (dst_object, Qt)) |
d46c5b12 | 6963 | { |
df7492f9 KH |
6964 | if (BUFFERP (coding->dst_object)) |
6965 | coding->dst_object = Fbuffer_string (); | |
6966 | else | |
d46c5b12 | 6967 | { |
df7492f9 KH |
6968 | coding->dst_object |
6969 | = make_unibyte_string ((char *) coding->destination, | |
6970 | coding->produced); | |
6971 | xfree (coding->destination); | |
d46c5b12 | 6972 | } |
4ed46869 | 6973 | } |
d46c5b12 | 6974 | |
4776e638 KH |
6975 | if (saved_pt >= 0) |
6976 | { | |
6977 | /* This is the case of: | |
6978 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
6979 | As we have moved PT while replacing the original buffer | |
6980 | contents, we must recover it now. */ | |
6981 | set_buffer_internal (XBUFFER (src_object)); | |
6982 | if (saved_pt < from) | |
6983 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
6984 | else if (saved_pt < from + chars) | |
6985 | TEMP_SET_PT_BOTH (from, from_byte); | |
6986 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
6987 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
6988 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 6989 | else |
4776e638 KH |
6990 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
6991 | saved_pt_byte + (coding->produced - bytes)); | |
6992 | } | |
6993 | ||
df7492f9 | 6994 | unbind_to (count, Qnil); |
b73bfc1c KH |
6995 | } |
6996 | ||
df7492f9 | 6997 | |
b73bfc1c | 6998 | Lisp_Object |
df7492f9 | 6999 | preferred_coding_system () |
b73bfc1c | 7000 | { |
df7492f9 | 7001 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 7002 | |
df7492f9 | 7003 | return CODING_ID_NAME (id); |
4ed46869 KH |
7004 | } |
7005 | ||
7006 | \f | |
7007 | #ifdef emacs | |
1397dc18 | 7008 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 7009 | |
4ed46869 | 7010 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 7011 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 7012 | See the documentation of `define-coding-system' for information |
48b0f3ae PJ |
7013 | about coding-system objects. */) |
7014 | (obj) | |
4ed46869 KH |
7015 | Lisp_Object obj; |
7016 | { | |
df7492f9 | 7017 | return ((NILP (obj) || CODING_SYSTEM_P (obj)) ? Qt : Qnil); |
4ed46869 KH |
7018 | } |
7019 | ||
9d991de8 RS |
7020 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
7021 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae PJ |
7022 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
7023 | (prompt) | |
4ed46869 KH |
7024 | Lisp_Object prompt; |
7025 | { | |
e0e989f6 | 7026 | Lisp_Object val; |
9d991de8 RS |
7027 | do |
7028 | { | |
4608c386 KH |
7029 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
7030 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 7031 | } |
8f924df7 | 7032 | while (SCHARS (val) == 0); |
e0e989f6 | 7033 | return (Fintern (val, Qnil)); |
4ed46869 KH |
7034 | } |
7035 | ||
9b787f3e | 7036 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae PJ |
7037 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
7038 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. */) | |
7039 | (prompt, default_coding_system) | |
9b787f3e | 7040 | Lisp_Object prompt, default_coding_system; |
4ed46869 | 7041 | { |
f44d27ce | 7042 | Lisp_Object val; |
9b787f3e | 7043 | if (SYMBOLP (default_coding_system)) |
a3181084 | 7044 | XSETSTRING (default_coding_system, XPNTR (SYMBOL_NAME (default_coding_system))); |
4608c386 | 7045 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
7046 | Qt, Qnil, Qcoding_system_history, |
7047 | default_coding_system, Qnil); | |
8f924df7 | 7048 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
7049 | } |
7050 | ||
7051 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
7052 | 1, 1, 0, | |
48b0f3ae | 7053 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
7054 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
7055 | It is valid if it is nil or a symbol defined as a coding system by the | |
7056 | function `define-coding-system'. */) | |
df7492f9 | 7057 | (coding_system) |
4ed46869 KH |
7058 | Lisp_Object coding_system; |
7059 | { | |
b7826503 | 7060 | CHECK_SYMBOL (coding_system); |
4ed46869 KH |
7061 | if (!NILP (Fcoding_system_p (coding_system))) |
7062 | return coding_system; | |
7063 | while (1) | |
02ba4723 | 7064 | Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil)); |
4ed46869 | 7065 | } |
df7492f9 | 7066 | |
3a73fa5d | 7067 | \f |
89528eb3 KH |
7068 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
7069 | HIGHEST is nonzero, return the coding system of the highest | |
7070 | priority among the detected coding systems. Otherwize return a | |
7071 | list of detected coding systems sorted by their priorities. If | |
7072 | MULTIBYTEP is nonzero, it is assumed that the bytes are in correct | |
7073 | multibyte form but contains only ASCII and eight-bit chars. | |
7074 | Otherwise, the bytes are raw bytes. | |
7075 | ||
7076 | CODING-SYSTEM controls the detection as below: | |
7077 | ||
7078 | If it is nil, detect both text-format and eol-format. If the | |
7079 | text-format part of CODING-SYSTEM is already specified | |
7080 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
7081 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
7082 | detect only text-format. */ | |
7083 | ||
d46c5b12 | 7084 | Lisp_Object |
24a73b0a KH |
7085 | detect_coding_system (src, src_chars, src_bytes, highest, multibytep, |
7086 | coding_system) | |
8f924df7 | 7087 | const unsigned char *src; |
24a73b0a | 7088 | int src_chars, src_bytes, highest; |
0a28aafb | 7089 | int multibytep; |
df7492f9 | 7090 | Lisp_Object coding_system; |
4ed46869 | 7091 | { |
8f924df7 | 7092 | const unsigned char *src_end = src + src_bytes; |
df7492f9 KH |
7093 | Lisp_Object attrs, eol_type; |
7094 | Lisp_Object val; | |
7095 | struct coding_system coding; | |
89528eb3 | 7096 | int id; |
ff0dacd7 | 7097 | struct coding_detection_info detect_info; |
24a73b0a | 7098 | enum coding_category base_category; |
b73bfc1c | 7099 | |
df7492f9 KH |
7100 | if (NILP (coding_system)) |
7101 | coding_system = Qundecided; | |
7102 | setup_coding_system (coding_system, &coding); | |
7103 | attrs = CODING_ID_ATTRS (coding.id); | |
7104 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 7105 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 7106 | |
df7492f9 | 7107 | coding.source = src; |
24a73b0a | 7108 | coding.src_chars = src_chars; |
df7492f9 KH |
7109 | coding.src_bytes = src_bytes; |
7110 | coding.src_multibyte = multibytep; | |
7111 | coding.consumed = 0; | |
89528eb3 | 7112 | coding.mode |= CODING_MODE_LAST_BLOCK; |
d46c5b12 | 7113 | |
ff0dacd7 | 7114 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 7115 | |
89528eb3 | 7116 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
7117 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
7118 | if (base_category == coding_category_undecided) | |
4ed46869 | 7119 | { |
ff0dacd7 KH |
7120 | enum coding_category category; |
7121 | struct coding_system *this; | |
7122 | int c, i; | |
88993dfd | 7123 | |
24a73b0a KH |
7124 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
7125 | for (i = 0; src < src_end; i++, src++) | |
4ed46869 | 7126 | { |
df7492f9 | 7127 | c = *src; |
6cb21a4f | 7128 | if (c & 0x80) |
d46c5b12 | 7129 | break; |
6cb21a4f KH |
7130 | if (c < 0x20 |
7131 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
7132 | && inhibit_iso_escape_detection) | |
7133 | { | |
7134 | coding.head_ascii = src - coding.source; | |
7135 | if (detect_coding_iso_2022 (&coding, &detect_info)) | |
7136 | { | |
7137 | /* We have scanned the whole data. */ | |
7138 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
7139 | /* We didn't find an 8-bit code. */ | |
7140 | src = src_end; | |
7141 | break; | |
7142 | } | |
7143 | } | |
4ed46869 | 7144 | } |
df7492f9 | 7145 | coding.head_ascii = src - coding.source; |
88993dfd | 7146 | |
6cb21a4f KH |
7147 | if (src < src_end |
7148 | || detect_info.found) | |
7149 | { | |
7150 | if (src == src_end) | |
7151 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
7152 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 7153 | { |
6cb21a4f KH |
7154 | category = coding_priorities[i]; |
7155 | if (detect_info.found & (1 << category)) | |
ff0dacd7 KH |
7156 | break; |
7157 | } | |
6cb21a4f KH |
7158 | else |
7159 | for (i = 0; i < coding_category_raw_text; i++) | |
df7492f9 | 7160 | { |
6cb21a4f KH |
7161 | category = coding_priorities[i]; |
7162 | this = coding_categories + category; | |
7163 | ||
7164 | if (this->id < 0) | |
24a73b0a | 7165 | { |
6cb21a4f KH |
7166 | /* No coding system of this category is defined. */ |
7167 | detect_info.rejected |= (1 << category); | |
7168 | } | |
7169 | else if (category >= coding_category_raw_text) | |
7170 | continue; | |
7171 | else if (detect_info.checked & (1 << category)) | |
7172 | { | |
7173 | if (highest | |
7174 | && (detect_info.found & (1 << category))) | |
7175 | break; | |
7176 | } | |
7177 | else | |
7178 | { | |
7179 | if ((*(this->detector)) (&coding, &detect_info) | |
7180 | && highest | |
7181 | && (detect_info.found & (1 << category))) | |
24a73b0a | 7182 | { |
6cb21a4f KH |
7183 | if (category == coding_category_utf_16_auto) |
7184 | { | |
7185 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
7186 | category = coding_category_utf_16_le; | |
7187 | else | |
7188 | category = coding_category_utf_16_be; | |
7189 | } | |
7190 | break; | |
24a73b0a | 7191 | } |
24a73b0a | 7192 | } |
df7492f9 | 7193 | } |
6cb21a4f | 7194 | } |
ec6d2bb8 | 7195 | |
ff0dacd7 | 7196 | if (detect_info.rejected == CATEGORY_MASK_ANY) |
ec6d2bb8 | 7197 | { |
ff0dacd7 | 7198 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
89528eb3 KH |
7199 | id = coding_categories[coding_category_raw_text].id; |
7200 | val = Fcons (make_number (id), Qnil); | |
7201 | } | |
ff0dacd7 | 7202 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 7203 | { |
ff0dacd7 | 7204 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
7205 | id = coding_categories[coding_category_undecided].id; |
7206 | val = Fcons (make_number (id), Qnil); | |
7207 | } | |
7208 | else if (highest) | |
7209 | { | |
ff0dacd7 | 7210 | if (detect_info.found) |
ec6d2bb8 | 7211 | { |
ff0dacd7 KH |
7212 | detect_info.found = 1 << category; |
7213 | val = Fcons (make_number (this->id), Qnil); | |
7214 | } | |
7215 | else | |
7216 | for (i = 0; i < coding_category_raw_text; i++) | |
7217 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
7218 | { | |
7219 | detect_info.found = 1 << coding_priorities[i]; | |
7220 | id = coding_categories[coding_priorities[i]].id; | |
7221 | val = Fcons (make_number (id), Qnil); | |
7222 | break; | |
7223 | } | |
7224 | } | |
89528eb3 KH |
7225 | else |
7226 | { | |
ff0dacd7 KH |
7227 | int mask = detect_info.rejected | detect_info.found; |
7228 | int found = 0; | |
89528eb3 | 7229 | val = Qnil; |
ec6d2bb8 | 7230 | |
89528eb3 | 7231 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
7232 | { |
7233 | category = coding_priorities[i]; | |
7234 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 7235 | { |
ff0dacd7 KH |
7236 | found |= 1 << category; |
7237 | id = coding_categories[category].id; | |
7238 | val = Fcons (make_number (id), val); | |
7239 | } | |
7240 | } | |
7241 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
7242 | { | |
7243 | category = coding_priorities[i]; | |
7244 | if (detect_info.found & (1 << category)) | |
7245 | { | |
7246 | id = coding_categories[category].id; | |
7247 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 7248 | } |
ec6d2bb8 | 7249 | } |
ff0dacd7 | 7250 | detect_info.found |= found; |
ec6d2bb8 | 7251 | } |
ec6d2bb8 | 7252 | } |
24a73b0a KH |
7253 | else if (base_category == coding_category_utf_16_auto) |
7254 | { | |
7255 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
7256 | { | |
24a73b0a KH |
7257 | struct coding_system *this; |
7258 | ||
7259 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
7260 | this = coding_categories + coding_category_utf_16_le; | |
7261 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
7262 | this = coding_categories + coding_category_utf_16_be; | |
7263 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
7264 | this = coding_categories + coding_category_utf_16_be_nosig; | |
7265 | else | |
7266 | this = coding_categories + coding_category_utf_16_le_nosig; | |
7267 | val = Fcons (make_number (this->id), Qnil); | |
7268 | } | |
7269 | } | |
df7492f9 KH |
7270 | else |
7271 | { | |
ff0dacd7 | 7272 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 7273 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 7274 | } |
df7492f9 | 7275 | |
89528eb3 | 7276 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 7277 | { |
89528eb3 | 7278 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol; |
df7492f9 KH |
7279 | Lisp_Object tail; |
7280 | ||
89528eb3 KH |
7281 | if (VECTORP (eol_type)) |
7282 | { | |
ff0dacd7 | 7283 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
89528eb3 KH |
7284 | normal_eol = detect_eol (coding.source, src_bytes, |
7285 | coding_category_raw_text); | |
ff0dacd7 KH |
7286 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
7287 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
7288 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
7289 | coding_category_utf_16_be); | |
ff0dacd7 KH |
7290 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
7291 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
7292 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
7293 | coding_category_utf_16_le); | |
7294 | } | |
7295 | else | |
7296 | { | |
7297 | if (EQ (eol_type, Qunix)) | |
7298 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
7299 | else if (EQ (eol_type, Qdos)) | |
7300 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
7301 | else | |
7302 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
7303 | } | |
7304 | ||
df7492f9 KH |
7305 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
7306 | { | |
89528eb3 | 7307 | enum coding_category category; |
df7492f9 | 7308 | int this_eol; |
89528eb3 KH |
7309 | |
7310 | id = XINT (XCAR (tail)); | |
7311 | attrs = CODING_ID_ATTRS (id); | |
7312 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
7313 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
7314 | if (VECTORP (eol_type)) |
7315 | { | |
89528eb3 KH |
7316 | if (category == coding_category_utf_16_be |
7317 | || category == coding_category_utf_16_be_nosig) | |
7318 | this_eol = utf_16_be_eol; | |
7319 | else if (category == coding_category_utf_16_le | |
7320 | || category == coding_category_utf_16_le_nosig) | |
7321 | this_eol = utf_16_le_eol; | |
df7492f9 | 7322 | else |
89528eb3 KH |
7323 | this_eol = normal_eol; |
7324 | ||
df7492f9 KH |
7325 | if (this_eol == EOL_SEEN_LF) |
7326 | XSETCAR (tail, AREF (eol_type, 0)); | |
7327 | else if (this_eol == EOL_SEEN_CRLF) | |
7328 | XSETCAR (tail, AREF (eol_type, 1)); | |
7329 | else if (this_eol == EOL_SEEN_CR) | |
7330 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
7331 | else |
7332 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 7333 | } |
89528eb3 KH |
7334 | else |
7335 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
7336 | } |
7337 | } | |
ec6d2bb8 | 7338 | |
03699b14 | 7339 | return (highest ? XCAR (val) : val); |
ec6d2bb8 KH |
7340 | } |
7341 | ||
ec6d2bb8 | 7342 | |
d46c5b12 KH |
7343 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
7344 | 2, 3, 0, | |
48b0f3ae PJ |
7345 | doc: /* Detect coding system of the text in the region between START and END. |
7346 | Return a list of possible coding systems ordered by priority. | |
ec6d2bb8 | 7347 | |
48b0f3ae PJ |
7348 | If only ASCII characters are found, it returns a list of single element |
7349 | `undecided' or its subsidiary coding system according to a detected | |
7350 | end-of-line format. | |
ec6d2bb8 | 7351 | |
48b0f3ae PJ |
7352 | If optional argument HIGHEST is non-nil, return the coding system of |
7353 | highest priority. */) | |
7354 | (start, end, highest) | |
d46c5b12 KH |
7355 | Lisp_Object start, end, highest; |
7356 | { | |
7357 | int from, to; | |
7358 | int from_byte, to_byte; | |
ec6d2bb8 | 7359 | |
b7826503 PJ |
7360 | CHECK_NUMBER_COERCE_MARKER (start); |
7361 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 7362 | |
d46c5b12 KH |
7363 | validate_region (&start, &end); |
7364 | from = XINT (start), to = XINT (end); | |
7365 | from_byte = CHAR_TO_BYTE (from); | |
7366 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 7367 | |
d46c5b12 KH |
7368 | if (from < GPT && to >= GPT) |
7369 | move_gap_both (to, to_byte); | |
c210f766 | 7370 | |
d46c5b12 | 7371 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 7372 | to - from, to_byte - from_byte, |
0a28aafb KH |
7373 | !NILP (highest), |
7374 | !NILP (current_buffer | |
df7492f9 KH |
7375 | ->enable_multibyte_characters), |
7376 | Qnil); | |
ec6d2bb8 KH |
7377 | } |
7378 | ||
d46c5b12 KH |
7379 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
7380 | 1, 2, 0, | |
48b0f3ae PJ |
7381 | doc: /* Detect coding system of the text in STRING. |
7382 | Return a list of possible coding systems ordered by priority. | |
fb88bf2d | 7383 | |
48b0f3ae PJ |
7384 | If only ASCII characters are found, it returns a list of single element |
7385 | `undecided' or its subsidiary coding system according to a detected | |
7386 | end-of-line format. | |
d46c5b12 | 7387 | |
48b0f3ae PJ |
7388 | If optional argument HIGHEST is non-nil, return the coding system of |
7389 | highest priority. */) | |
7390 | (string, highest) | |
d46c5b12 KH |
7391 | Lisp_Object string, highest; |
7392 | { | |
b7826503 | 7393 | CHECK_STRING (string); |
b73bfc1c | 7394 | |
24a73b0a KH |
7395 | return detect_coding_system (SDATA (string), |
7396 | SCHARS (string), SBYTES (string), | |
8f924df7 | 7397 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 7398 | Qnil); |
4ed46869 | 7399 | } |
4ed46869 | 7400 | |
b73bfc1c | 7401 | |
df7492f9 KH |
7402 | static INLINE int |
7403 | char_encodable_p (c, attrs) | |
7404 | int c; | |
7405 | Lisp_Object attrs; | |
05e6f5dc | 7406 | { |
df7492f9 | 7407 | Lisp_Object tail; |
df7492f9 | 7408 | struct charset *charset; |
7d64c6ad | 7409 | Lisp_Object translation_table; |
d46c5b12 | 7410 | |
7d64c6ad | 7411 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 7412 | if (! NILP (translation_table)) |
7d64c6ad | 7413 | c = translate_char (translation_table, c); |
df7492f9 KH |
7414 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
7415 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 7416 | { |
df7492f9 KH |
7417 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
7418 | if (CHAR_CHARSET_P (c, charset)) | |
7419 | break; | |
e133c8fa | 7420 | } |
df7492f9 | 7421 | return (! NILP (tail)); |
05e6f5dc | 7422 | } |
83fa074f | 7423 | |
fb88bf2d | 7424 | |
df7492f9 KH |
7425 | /* Return a list of coding systems that safely encode the text between |
7426 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
7427 | systems not to check. The returned list doesn't contain any such | |
48468dac | 7428 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 7429 | unibyte, return t. */ |
e077cc80 | 7430 | |
df7492f9 KH |
7431 | DEFUN ("find-coding-systems-region-internal", |
7432 | Ffind_coding_systems_region_internal, | |
7433 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
7434 | doc: /* Internal use only. */) | |
7435 | (start, end, exclude) | |
7436 | Lisp_Object start, end, exclude; | |
7437 | { | |
7438 | Lisp_Object coding_attrs_list, safe_codings; | |
7439 | EMACS_INT start_byte, end_byte; | |
7c78e542 | 7440 | const unsigned char *p, *pbeg, *pend; |
df7492f9 KH |
7441 | int c; |
7442 | Lisp_Object tail, elt; | |
d46c5b12 | 7443 | |
df7492f9 KH |
7444 | if (STRINGP (start)) |
7445 | { | |
7446 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 7447 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
7448 | return Qt; |
7449 | start_byte = 0; | |
8f924df7 | 7450 | end_byte = SBYTES (start); |
df7492f9 KH |
7451 | } |
7452 | else | |
d46c5b12 | 7453 | { |
df7492f9 KH |
7454 | CHECK_NUMBER_COERCE_MARKER (start); |
7455 | CHECK_NUMBER_COERCE_MARKER (end); | |
7456 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
7457 | args_out_of_range (start, end); | |
7458 | if (NILP (current_buffer->enable_multibyte_characters)) | |
7459 | return Qt; | |
7460 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7461 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7462 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
7463 | return Qt; | |
d46c5b12 | 7464 | |
e1c23804 | 7465 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 7466 | { |
e1c23804 DL |
7467 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7468 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7469 | else |
e1c23804 | 7470 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
7471 | } |
7472 | } | |
7473 | ||
df7492f9 KH |
7474 | coding_attrs_list = Qnil; |
7475 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
7476 | if (NILP (exclude) | |
7477 | || NILP (Fmemq (XCAR (tail), exclude))) | |
7478 | { | |
7479 | Lisp_Object attrs; | |
d46c5b12 | 7480 | |
df7492f9 KH |
7481 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
7482 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
7483 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
7484 | { |
7485 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 7486 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
7487 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
7488 | } | |
df7492f9 | 7489 | } |
d46c5b12 | 7490 | |
df7492f9 | 7491 | if (STRINGP (start)) |
8f924df7 | 7492 | p = pbeg = SDATA (start); |
df7492f9 KH |
7493 | else |
7494 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
7495 | pend = p + (end_byte - start_byte); | |
b843d1ae | 7496 | |
df7492f9 KH |
7497 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
7498 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 7499 | |
05e6f5dc | 7500 | while (p < pend) |
72d1a715 | 7501 | { |
df7492f9 KH |
7502 | if (ASCII_BYTE_P (*p)) |
7503 | p++; | |
72d1a715 RS |
7504 | else |
7505 | { | |
df7492f9 | 7506 | c = STRING_CHAR_ADVANCE (p); |
12410ef1 | 7507 | |
df7492f9 KH |
7508 | charset_map_loaded = 0; |
7509 | for (tail = coding_attrs_list; CONSP (tail);) | |
7510 | { | |
7511 | elt = XCAR (tail); | |
7512 | if (NILP (elt)) | |
7513 | tail = XCDR (tail); | |
7514 | else if (char_encodable_p (c, elt)) | |
7515 | tail = XCDR (tail); | |
7516 | else if (CONSP (XCDR (tail))) | |
7517 | { | |
7518 | XSETCAR (tail, XCAR (XCDR (tail))); | |
7519 | XSETCDR (tail, XCDR (XCDR (tail))); | |
7520 | } | |
7521 | else | |
7522 | { | |
7523 | XSETCAR (tail, Qnil); | |
7524 | tail = XCDR (tail); | |
7525 | } | |
7526 | } | |
7527 | if (charset_map_loaded) | |
7528 | { | |
7529 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 7530 | |
df7492f9 | 7531 | if (STRINGP (start)) |
8f924df7 | 7532 | pbeg = SDATA (start); |
df7492f9 KH |
7533 | else |
7534 | pbeg = BYTE_POS_ADDR (start_byte); | |
7535 | p = pbeg + p_offset; | |
7536 | pend = pbeg + pend_offset; | |
7537 | } | |
7538 | } | |
ec6d2bb8 | 7539 | } |
fb88bf2d | 7540 | |
988b3759 | 7541 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
7542 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
7543 | if (! NILP (XCAR (tail))) | |
7544 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 7545 | |
05e6f5dc KH |
7546 | return safe_codings; |
7547 | } | |
4956c225 | 7548 | |
d46c5b12 | 7549 | |
8f924df7 KH |
7550 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
7551 | Sunencodable_char_position, 3, 5, 0, | |
7552 | doc: /* | |
7553 | Return position of first un-encodable character in a region. | |
7554 | START and END specfiy the region and CODING-SYSTEM specifies the | |
7555 | encoding to check. Return nil if CODING-SYSTEM does encode the region. | |
d46c5b12 | 7556 | |
8f924df7 KH |
7557 | If optional 4th argument COUNT is non-nil, it specifies at most how |
7558 | many un-encodable characters to search. In this case, the value is a | |
7559 | list of positions. | |
d46c5b12 | 7560 | |
8f924df7 KH |
7561 | If optional 5th argument STRING is non-nil, it is a string to search |
7562 | for un-encodable characters. In that case, START and END are indexes | |
7563 | to the string. */) | |
7564 | (start, end, coding_system, count, string) | |
7565 | Lisp_Object start, end, coding_system, count, string; | |
7566 | { | |
7567 | int n; | |
7568 | struct coding_system coding; | |
7d64c6ad | 7569 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 KH |
7570 | Lisp_Object positions; |
7571 | int from, to; | |
7572 | const unsigned char *p, *stop, *pend; | |
7573 | int ascii_compatible; | |
fb88bf2d | 7574 | |
8f924df7 KH |
7575 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
7576 | attrs = CODING_ID_ATTRS (coding.id); | |
7577 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
7578 | return Qnil; | |
7579 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
7580 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 7581 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 7582 | |
8f924df7 KH |
7583 | if (NILP (string)) |
7584 | { | |
7585 | validate_region (&start, &end); | |
7586 | from = XINT (start); | |
7587 | to = XINT (end); | |
7588 | if (NILP (current_buffer->enable_multibyte_characters) | |
7589 | || (ascii_compatible | |
7590 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
7591 | return Qnil; | |
7592 | p = CHAR_POS_ADDR (from); | |
7593 | pend = CHAR_POS_ADDR (to); | |
7594 | if (from < GPT && to >= GPT) | |
7595 | stop = GPT_ADDR; | |
7596 | else | |
7597 | stop = pend; | |
7598 | } | |
7599 | else | |
7600 | { | |
7601 | CHECK_STRING (string); | |
7602 | CHECK_NATNUM (start); | |
7603 | CHECK_NATNUM (end); | |
7604 | from = XINT (start); | |
7605 | to = XINT (end); | |
7606 | if (from > to | |
7607 | || to > SCHARS (string)) | |
7608 | args_out_of_range_3 (string, start, end); | |
7609 | if (! STRING_MULTIBYTE (string)) | |
7610 | return Qnil; | |
7611 | p = SDATA (string) + string_char_to_byte (string, from); | |
7612 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
7613 | if (ascii_compatible && (to - from) == (pend - p)) | |
7614 | return Qnil; | |
7615 | } | |
f2558efd | 7616 | |
8f924df7 KH |
7617 | if (NILP (count)) |
7618 | n = 1; | |
7619 | else | |
b73bfc1c | 7620 | { |
8f924df7 KH |
7621 | CHECK_NATNUM (count); |
7622 | n = XINT (count); | |
b73bfc1c KH |
7623 | } |
7624 | ||
8f924df7 KH |
7625 | positions = Qnil; |
7626 | while (1) | |
d46c5b12 | 7627 | { |
8f924df7 | 7628 | int c; |
ec6d2bb8 | 7629 | |
8f924df7 KH |
7630 | if (ascii_compatible) |
7631 | while (p < stop && ASCII_BYTE_P (*p)) | |
7632 | p++, from++; | |
7633 | if (p >= stop) | |
0e79d667 | 7634 | { |
8f924df7 KH |
7635 | if (p >= pend) |
7636 | break; | |
7637 | stop = pend; | |
7638 | p = GAP_END_ADDR; | |
0e79d667 | 7639 | } |
ec6d2bb8 | 7640 | |
8f924df7 KH |
7641 | c = STRING_CHAR_ADVANCE (p); |
7642 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
7643 | && ! char_charset (translate_char (translation_table, c), |
7644 | charset_list, NULL)) | |
ec6d2bb8 | 7645 | { |
8f924df7 KH |
7646 | positions = Fcons (make_number (from), positions); |
7647 | n--; | |
7648 | if (n == 0) | |
7649 | break; | |
ec6d2bb8 KH |
7650 | } |
7651 | ||
8f924df7 KH |
7652 | from++; |
7653 | } | |
d46c5b12 | 7654 | |
8f924df7 KH |
7655 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
7656 | } | |
d46c5b12 | 7657 | |
d46c5b12 | 7658 | |
df7492f9 KH |
7659 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
7660 | Scheck_coding_systems_region, 3, 3, 0, | |
7661 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 7662 | |
df7492f9 KH |
7663 | START and END are buffer positions specifying the region. |
7664 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 7665 | |
df7492f9 KH |
7666 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
7667 | CODING-SYSTEM is a member of CODING-SYSTEM-LIst and can't encode the | |
7668 | whole region, POS0, POS1, ... are buffer positions where non-encodable | |
7669 | characters are found. | |
93dec019 | 7670 | |
df7492f9 KH |
7671 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
7672 | value is nil. | |
93dec019 | 7673 | |
df7492f9 KH |
7674 | START may be a string. In that case, check if the string is |
7675 | encodable, and the value contains indices to the string instead of | |
7676 | buffer positions. END is ignored. */) | |
7677 | (start, end, coding_system_list) | |
7678 | Lisp_Object start, end, coding_system_list; | |
05e6f5dc | 7679 | { |
df7492f9 KH |
7680 | Lisp_Object list; |
7681 | EMACS_INT start_byte, end_byte; | |
7682 | int pos; | |
7c78e542 | 7683 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 7684 | int c; |
7d64c6ad | 7685 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 7686 | |
05e6f5dc KH |
7687 | if (STRINGP (start)) |
7688 | { | |
df7492f9 | 7689 | if (!STRING_MULTIBYTE (start) |
8f924df7 | 7690 | && SCHARS (start) != SBYTES (start)) |
df7492f9 KH |
7691 | return Qnil; |
7692 | start_byte = 0; | |
8f924df7 | 7693 | end_byte = SBYTES (start); |
df7492f9 | 7694 | pos = 0; |
d46c5b12 | 7695 | } |
05e6f5dc | 7696 | else |
b73bfc1c | 7697 | { |
b7826503 PJ |
7698 | CHECK_NUMBER_COERCE_MARKER (start); |
7699 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
7700 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
7701 | args_out_of_range (start, end); | |
7702 | if (NILP (current_buffer->enable_multibyte_characters)) | |
df7492f9 KH |
7703 | return Qnil; |
7704 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7705 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7706 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
05e6f5dc | 7707 | return Qt; |
df7492f9 | 7708 | |
e1c23804 | 7709 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 7710 | { |
e1c23804 DL |
7711 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7712 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7713 | else |
e1c23804 | 7714 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 7715 | } |
e1c23804 | 7716 | pos = XINT (start); |
b73bfc1c | 7717 | } |
7553d0e1 | 7718 | |
df7492f9 KH |
7719 | list = Qnil; |
7720 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 7721 | { |
df7492f9 | 7722 | elt = XCAR (tail); |
7d64c6ad | 7723 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
7724 | ASET (attrs, coding_attr_trans_tbl, |
7725 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 7726 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
7727 | } |
7728 | ||
df7492f9 | 7729 | if (STRINGP (start)) |
8f924df7 | 7730 | p = pbeg = SDATA (start); |
72d1a715 | 7731 | else |
df7492f9 KH |
7732 | p = pbeg = BYTE_POS_ADDR (start_byte); |
7733 | pend = p + (end_byte - start_byte); | |
4ed46869 | 7734 | |
df7492f9 KH |
7735 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
7736 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 7737 | |
df7492f9 | 7738 | while (p < pend) |
d46c5b12 | 7739 | { |
df7492f9 KH |
7740 | if (ASCII_BYTE_P (*p)) |
7741 | p++; | |
e133c8fa | 7742 | else |
05e6f5dc | 7743 | { |
df7492f9 KH |
7744 | c = STRING_CHAR_ADVANCE (p); |
7745 | ||
7746 | charset_map_loaded = 0; | |
7747 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
7748 | { | |
7749 | elt = XCDR (XCAR (tail)); | |
7750 | if (! char_encodable_p (c, XCAR (elt))) | |
7751 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
7752 | } | |
7753 | if (charset_map_loaded) | |
7754 | { | |
7755 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
7756 | ||
7757 | if (STRINGP (start)) | |
8f924df7 | 7758 | pbeg = SDATA (start); |
df7492f9 KH |
7759 | else |
7760 | pbeg = BYTE_POS_ADDR (start_byte); | |
7761 | p = pbeg + p_offset; | |
7762 | pend = pbeg + pend_offset; | |
7763 | } | |
05e6f5dc | 7764 | } |
df7492f9 | 7765 | pos++; |
d46c5b12 | 7766 | } |
4ed46869 | 7767 | |
df7492f9 KH |
7768 | tail = list; |
7769 | list = Qnil; | |
7770 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 7771 | { |
df7492f9 KH |
7772 | elt = XCAR (tail); |
7773 | if (CONSP (XCDR (XCDR (elt)))) | |
7774 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
7775 | list); | |
ec6d2bb8 | 7776 | } |
2b4f9037 | 7777 | |
df7492f9 | 7778 | return list; |
d46c5b12 KH |
7779 | } |
7780 | ||
3fd9494b | 7781 | |
b73bfc1c | 7782 | Lisp_Object |
df7492f9 KH |
7783 | code_convert_region (start, end, coding_system, dst_object, encodep, norecord) |
7784 | Lisp_Object start, end, coding_system, dst_object; | |
7785 | int encodep, norecord; | |
4ed46869 | 7786 | { |
3a73fa5d | 7787 | struct coding_system coding; |
df7492f9 KH |
7788 | EMACS_INT from, from_byte, to, to_byte; |
7789 | Lisp_Object src_object; | |
4ed46869 | 7790 | |
b7826503 PJ |
7791 | CHECK_NUMBER_COERCE_MARKER (start); |
7792 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
7793 | if (NILP (coding_system)) |
7794 | coding_system = Qno_conversion; | |
7795 | else | |
7796 | CHECK_CODING_SYSTEM (coding_system); | |
7797 | src_object = Fcurrent_buffer (); | |
7798 | if (NILP (dst_object)) | |
7799 | dst_object = src_object; | |
7800 | else if (! EQ (dst_object, Qt)) | |
7801 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 7802 | |
d46c5b12 KH |
7803 | validate_region (&start, &end); |
7804 | from = XFASTINT (start); | |
df7492f9 | 7805 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 7806 | to = XFASTINT (end); |
df7492f9 | 7807 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 7808 | |
df7492f9 KH |
7809 | setup_coding_system (coding_system, &coding); |
7810 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 7811 | |
df7492f9 KH |
7812 | if (encodep) |
7813 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7814 | dst_object); | |
7815 | else | |
7816 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7817 | dst_object); | |
7818 | if (! norecord) | |
7819 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 7820 | |
df7492f9 KH |
7821 | return (BUFFERP (dst_object) |
7822 | ? make_number (coding.produced_char) | |
7823 | : coding.dst_object); | |
4031e2bf | 7824 | } |
78108bcd | 7825 | |
4ed46869 | 7826 | |
4031e2bf | 7827 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 7828 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 7829 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
7830 | When called from a program, takes four arguments: |
7831 | START, END, CODING-SYSTEM, and DESTINATION. | |
7832 | START and END are buffer positions. | |
8844fa83 | 7833 | |
df7492f9 KH |
7834 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
7835 | If nil, the region between START and END is replace by the decoded text. | |
7836 | If buffer, the decoded text is inserted in the buffer. | |
7837 | If t, the decoded text is returned. | |
8844fa83 | 7838 | |
48b0f3ae PJ |
7839 | This function sets `last-coding-system-used' to the precise coding system |
7840 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7841 | not fully specified.) | |
7842 | It returns the length of the decoded text. */) | |
df7492f9 KH |
7843 | (start, end, coding_system, destination) |
7844 | Lisp_Object start, end, coding_system, destination; | |
4031e2bf | 7845 | { |
df7492f9 | 7846 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 7847 | } |
8844fa83 | 7848 | |
3a73fa5d | 7849 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
7850 | 3, 4, "r\nzCoding system: ", |
7851 | doc: /* Encode the current region by specified coding system. | |
48b0f3ae PJ |
7852 | When called from a program, takes three arguments: |
7853 | START, END, and CODING-SYSTEM. START and END are buffer positions. | |
d46c5b12 | 7854 | |
df7492f9 KH |
7855 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
7856 | If nil, the region between START and END is replace by the encoded text. | |
7857 | If buffer, the encoded text is inserted in the buffer. | |
7858 | If t, the encoded text is returned. | |
2391eaa4 | 7859 | |
48b0f3ae PJ |
7860 | This function sets `last-coding-system-used' to the precise coding system |
7861 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7862 | not fully specified.) | |
7863 | It returns the length of the encoded text. */) | |
df7492f9 KH |
7864 | (start, end, coding_system, destination) |
7865 | Lisp_Object start, end, coding_system, destination; | |
3a73fa5d | 7866 | { |
df7492f9 | 7867 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
7868 | } |
7869 | ||
7870 | Lisp_Object | |
df7492f9 KH |
7871 | code_convert_string (string, coding_system, dst_object, |
7872 | encodep, nocopy, norecord) | |
7873 | Lisp_Object string, coding_system, dst_object; | |
7874 | int encodep, nocopy, norecord; | |
b73bfc1c | 7875 | { |
4031e2bf | 7876 | struct coding_system coding; |
df7492f9 | 7877 | EMACS_INT chars, bytes; |
ec6d2bb8 | 7878 | |
b7826503 | 7879 | CHECK_STRING (string); |
d46c5b12 | 7880 | if (NILP (coding_system)) |
4956c225 | 7881 | { |
df7492f9 KH |
7882 | if (! norecord) |
7883 | Vlast_coding_system_used = Qno_conversion; | |
7884 | if (NILP (dst_object)) | |
7885 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 7886 | } |
b73bfc1c | 7887 | |
df7492f9 KH |
7888 | if (NILP (coding_system)) |
7889 | coding_system = Qno_conversion; | |
7890 | else | |
7891 | CHECK_CODING_SYSTEM (coding_system); | |
7892 | if (NILP (dst_object)) | |
7893 | dst_object = Qt; | |
7894 | else if (! EQ (dst_object, Qt)) | |
7895 | CHECK_BUFFER (dst_object); | |
73be902c | 7896 | |
df7492f9 | 7897 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 7898 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
7899 | chars = SCHARS (string); |
7900 | bytes = SBYTES (string); | |
df7492f9 KH |
7901 | if (encodep) |
7902 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7903 | else | |
7904 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7905 | if (! norecord) | |
7906 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 7907 | |
df7492f9 KH |
7908 | return (BUFFERP (dst_object) |
7909 | ? make_number (coding.produced_char) | |
7910 | : coding.dst_object); | |
4ed46869 | 7911 | } |
73be902c | 7912 | |
b73bfc1c | 7913 | |
ecec61c1 | 7914 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 7915 | Do not set Vlast_coding_system_used. |
4ed46869 | 7916 | |
ec6d2bb8 KH |
7917 | This function is called only from macros DECODE_FILE and |
7918 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 7919 | |
ecec61c1 KH |
7920 | Lisp_Object |
7921 | code_convert_string_norecord (string, coding_system, encodep) | |
7922 | Lisp_Object string, coding_system; | |
7923 | int encodep; | |
4ed46869 | 7924 | { |
0be8721c | 7925 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
7926 | } |
7927 | ||
4ed46869 | 7928 | |
df7492f9 KH |
7929 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
7930 | 2, 4, 0, | |
7931 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
7932 | ||
7933 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
7934 | if the decoding operation is trivial. | |
ecec61c1 | 7935 | |
df7492f9 | 7936 | Optional fourth arg BUFFER non-nil meant that the decoded text is |
a3f6ee6d | 7937 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 | 7938 | the return value is BUFFER. |
ecec61c1 | 7939 | |
df7492f9 KH |
7940 | This function sets `last-coding-system-used' to the precise coding system |
7941 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7942 | not fully specified. */) | |
7943 | (string, coding_system, nocopy, buffer) | |
7944 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 7945 | { |
df7492f9 KH |
7946 | return code_convert_string (string, coding_system, buffer, |
7947 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
7948 | } |
7949 | ||
df7492f9 KH |
7950 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
7951 | 2, 4, 0, | |
7952 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
7953 | ||
7954 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
7955 | itself if the encoding operation is trivial. | |
7956 | ||
7957 | Optional fourth arg BUFFER non-nil meant that the encoded text is | |
a3f6ee6d | 7958 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 KH |
7959 | the return value is BUFFER. |
7960 | ||
7961 | This function sets `last-coding-system-used' to the precise coding system | |
7962 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7963 | not fully specified.) */) | |
7964 | (string, coding_system, nocopy, buffer) | |
7965 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 7966 | { |
df7492f9 | 7967 | return code_convert_string (string, coding_system, buffer, |
c197f191 | 7968 | 1, ! NILP (nocopy), 1); |
4ed46869 | 7969 | } |
df7492f9 | 7970 | |
3a73fa5d | 7971 | \f |
4ed46869 | 7972 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
7973 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
7974 | Return the corresponding character. */) | |
7975 | (code) | |
4ed46869 | 7976 | Lisp_Object code; |
4ed46869 | 7977 | { |
df7492f9 KH |
7978 | Lisp_Object spec, attrs, val; |
7979 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
7980 | int c; | |
4ed46869 | 7981 | |
df7492f9 KH |
7982 | CHECK_NATNUM (code); |
7983 | c = XFASTINT (code); | |
7984 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
7985 | attrs = AREF (spec, 0); | |
4ed46869 | 7986 | |
df7492f9 KH |
7987 | if (ASCII_BYTE_P (c) |
7988 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7989 | return code; | |
4ed46869 | 7990 | |
df7492f9 KH |
7991 | val = CODING_ATTR_CHARSET_LIST (attrs); |
7992 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
7993 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
7994 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 7995 | |
df7492f9 KH |
7996 | if (c <= 0x7F) |
7997 | charset = charset_roman; | |
7998 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 7999 | { |
df7492f9 KH |
8000 | charset = charset_kana; |
8001 | c -= 0x80; | |
4ed46869 | 8002 | } |
55ab7be3 | 8003 | else |
4ed46869 | 8004 | { |
004068e4 | 8005 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
8006 | |
8007 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
8008 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
8009 | error ("Invalid code: %d", code); | |
8010 | SJIS_TO_JIS (c); | |
8011 | charset = charset_kanji; | |
4ed46869 | 8012 | } |
df7492f9 KH |
8013 | c = DECODE_CHAR (charset, c); |
8014 | if (c < 0) | |
8015 | error ("Invalid code: %d", code); | |
8016 | return make_number (c); | |
93dec019 | 8017 | } |
4ed46869 | 8018 | |
48b0f3ae | 8019 | |
4ed46869 | 8020 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
8021 | doc: /* Encode a Japanese character CHAR to shift_jis encoding. |
8022 | Return the corresponding code in SJIS. */) | |
8023 | (ch) | |
df7492f9 | 8024 | Lisp_Object ch; |
4ed46869 | 8025 | { |
df7492f9 KH |
8026 | Lisp_Object spec, attrs, charset_list; |
8027 | int c; | |
8028 | struct charset *charset; | |
8029 | unsigned code; | |
48b0f3ae | 8030 | |
df7492f9 KH |
8031 | CHECK_CHARACTER (ch); |
8032 | c = XFASTINT (ch); | |
8033 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
8034 | attrs = AREF (spec, 0); | |
8035 | ||
8036 | if (ASCII_CHAR_P (c) | |
8037 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8038 | return ch; | |
8039 | ||
8040 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
8041 | charset = char_charset (c, charset_list, &code); | |
8042 | if (code == CHARSET_INVALID_CODE (charset)) | |
8043 | error ("Can't encode by shift_jis encoding: %d", c); | |
8044 | JIS_TO_SJIS (code); | |
8045 | ||
8046 | return make_number (code); | |
4ed46869 KH |
8047 | } |
8048 | ||
8049 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
8050 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
8051 | Return the corresponding character. */) | |
8052 | (code) | |
4ed46869 | 8053 | Lisp_Object code; |
d46c5b12 | 8054 | { |
df7492f9 KH |
8055 | Lisp_Object spec, attrs, val; |
8056 | struct charset *charset_roman, *charset_big5, *charset; | |
8057 | int c; | |
6289dd10 | 8058 | |
df7492f9 KH |
8059 | CHECK_NATNUM (code); |
8060 | c = XFASTINT (code); | |
8061 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
8062 | attrs = AREF (spec, 0); | |
4ed46869 | 8063 | |
df7492f9 KH |
8064 | if (ASCII_BYTE_P (c) |
8065 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8066 | return code; | |
6289dd10 | 8067 | |
df7492f9 KH |
8068 | val = CODING_ATTR_CHARSET_LIST (attrs); |
8069 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
8070 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 8071 | |
df7492f9 KH |
8072 | if (c <= 0x7F) |
8073 | charset = charset_roman; | |
c28a9453 KH |
8074 | else |
8075 | { | |
df7492f9 KH |
8076 | int b1 = c >> 8, b2 = c & 0x7F; |
8077 | if (b1 < 0xA1 || b1 > 0xFE | |
8078 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
8079 | error ("Invalid code: %d", code); | |
8080 | charset = charset_big5; | |
c28a9453 | 8081 | } |
df7492f9 KH |
8082 | c = DECODE_CHAR (charset, (unsigned )c); |
8083 | if (c < 0) | |
8084 | error ("Invalid code: %d", code); | |
8085 | return make_number (c); | |
d46c5b12 | 8086 | } |
6289dd10 | 8087 | |
4ed46869 | 8088 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
48b0f3ae PJ |
8089 | doc: /* Encode the Big5 character CHAR to BIG5 coding system. |
8090 | Return the corresponding character code in Big5. */) | |
8091 | (ch) | |
4ed46869 KH |
8092 | Lisp_Object ch; |
8093 | { | |
df7492f9 KH |
8094 | Lisp_Object spec, attrs, charset_list; |
8095 | struct charset *charset; | |
8096 | int c; | |
8097 | unsigned code; | |
8098 | ||
8099 | CHECK_CHARACTER (ch); | |
8100 | c = XFASTINT (ch); | |
8101 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
8102 | attrs = AREF (spec, 0); | |
8103 | if (ASCII_CHAR_P (c) | |
8104 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8105 | return ch; | |
8106 | ||
8107 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
8108 | charset = char_charset (c, charset_list, &code); | |
8109 | if (code == CHARSET_INVALID_CODE (charset)) | |
8110 | error ("Can't encode by Big5 encoding: %d", c); | |
8111 | ||
8112 | return make_number (code); | |
4ed46869 | 8113 | } |
48b0f3ae | 8114 | |
3a73fa5d | 8115 | \f |
1ba9e4ab KH |
8116 | DEFUN ("set-terminal-coding-system-internal", |
8117 | Fset_terminal_coding_system_internal, | |
48b0f3ae PJ |
8118 | Sset_terminal_coding_system_internal, 1, 1, 0, |
8119 | doc: /* Internal use only. */) | |
8120 | (coding_system) | |
b74e4686 | 8121 | Lisp_Object coding_system; |
4ed46869 | 8122 | { |
b7826503 | 8123 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
8124 | setup_coding_system (Fcheck_coding_system (coding_system), |
8125 | &terminal_coding); | |
48b0f3ae | 8126 | |
70c22245 | 8127 | /* We had better not send unsafe characters to terminal. */ |
df7492f9 KH |
8128 | terminal_coding.mode |= CODING_MODE_SAFE_ENCODING; |
8129 | /* Characer composition should be disabled. */ | |
8130 | terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
8131 | terminal_coding.src_multibyte = 1; |
8132 | terminal_coding.dst_multibyte = 0; | |
4ed46869 KH |
8133 | return Qnil; |
8134 | } | |
8135 | ||
c4825358 KH |
8136 | DEFUN ("set-safe-terminal-coding-system-internal", |
8137 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 8138 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 8139 | doc: /* Internal use only. */) |
48b0f3ae | 8140 | (coding_system) |
b74e4686 | 8141 | Lisp_Object coding_system; |
d46c5b12 | 8142 | { |
b7826503 | 8143 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
8144 | setup_coding_system (Fcheck_coding_system (coding_system), |
8145 | &safe_terminal_coding); | |
df7492f9 KH |
8146 | /* Characer composition should be disabled. */ |
8147 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
8148 | safe_terminal_coding.src_multibyte = 1; |
8149 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
8150 | return Qnil; |
8151 | } | |
4ed46869 | 8152 | |
4ed46869 KH |
8153 | DEFUN ("terminal-coding-system", |
8154 | Fterminal_coding_system, Sterminal_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
8155 | doc: /* Return coding system specified for terminal output. */) |
8156 | () | |
4ed46869 | 8157 | { |
df7492f9 | 8158 | return CODING_ID_NAME (terminal_coding.id); |
4ed46869 KH |
8159 | } |
8160 | ||
1ba9e4ab KH |
8161 | DEFUN ("set-keyboard-coding-system-internal", |
8162 | Fset_keyboard_coding_system_internal, | |
48b0f3ae PJ |
8163 | Sset_keyboard_coding_system_internal, 1, 1, 0, |
8164 | doc: /* Internal use only. */) | |
8165 | (coding_system) | |
4ed46869 KH |
8166 | Lisp_Object coding_system; |
8167 | { | |
b7826503 | 8168 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
8169 | setup_coding_system (Fcheck_coding_system (coding_system), |
8170 | &keyboard_coding); | |
8171 | /* Characer composition should be disabled. */ | |
8172 | keyboard_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
8173 | return Qnil; |
8174 | } | |
8175 | ||
8176 | DEFUN ("keyboard-coding-system", | |
8177 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
8178 | doc: /* Return coding system specified for decoding keyboard input. */) |
8179 | () | |
4ed46869 | 8180 | { |
df7492f9 | 8181 | return CODING_ID_NAME (keyboard_coding.id); |
4ed46869 KH |
8182 | } |
8183 | ||
4ed46869 | 8184 | \f |
a5d301df KH |
8185 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
8186 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
8187 | doc: /* Choose a coding system for an operation based on the target name. |
8188 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
8189 | DECODING-SYSTEM is the coding system to use for decoding | |
8190 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
8191 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 8192 | |
48b0f3ae PJ |
8193 | The first argument OPERATION specifies an I/O primitive: |
8194 | For file I/O, `insert-file-contents' or `write-region'. | |
8195 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
8196 | For network I/O, `open-network-stream'. | |
05e6f5dc | 8197 | |
48b0f3ae PJ |
8198 | The remaining arguments should be the same arguments that were passed |
8199 | to the primitive. Depending on which primitive, one of those arguments | |
8200 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
8201 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 8202 | |
48b0f3ae PJ |
8203 | TARGET has a meaning which depends on OPERATION: |
8204 | For file I/O, TARGET is a file name. | |
8205 | For process I/O, TARGET is a process name. | |
8206 | For network I/O, TARGET is a service name or a port number | |
05e6f5dc | 8207 | |
48b0f3ae PJ |
8208 | This function looks up what specified for TARGET in, |
8209 | `file-coding-system-alist', `process-coding-system-alist', | |
8210 | or `network-coding-system-alist' depending on OPERATION. | |
8211 | They may specify a coding system, a cons of coding systems, | |
8212 | or a function symbol to call. | |
8213 | In the last case, we call the function with one argument, | |
8214 | which is a list of all the arguments given to this function. | |
8215 | ||
8216 | usage: (find-operation-coding-system OPERATION ARGUMENTS ...) */) | |
8217 | (nargs, args) | |
4ed46869 KH |
8218 | int nargs; |
8219 | Lisp_Object *args; | |
6b89e3aa | 8220 | { |
4ed46869 KH |
8221 | Lisp_Object operation, target_idx, target, val; |
8222 | register Lisp_Object chain; | |
177c0ea7 | 8223 | |
4ed46869 KH |
8224 | if (nargs < 2) |
8225 | error ("Too few arguments"); | |
8226 | operation = args[0]; | |
8227 | if (!SYMBOLP (operation) | |
8228 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
df7492f9 | 8229 | error ("Invalid first arguement"); |
4ed46869 KH |
8230 | if (nargs < 1 + XINT (target_idx)) |
8231 | error ("Too few arguments for operation: %s", | |
8f924df7 | 8232 | SDATA (SYMBOL_NAME (operation))); |
4ed46869 KH |
8233 | target = args[XINT (target_idx) + 1]; |
8234 | if (!(STRINGP (target) | |
8235 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) | |
df7492f9 | 8236 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
4ed46869 | 8237 | |
2e34157c RS |
8238 | chain = ((EQ (operation, Qinsert_file_contents) |
8239 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 8240 | ? Vfile_coding_system_alist |
2e34157c | 8241 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
8242 | ? Vnetwork_coding_system_alist |
8243 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
8244 | if (NILP (chain)) |
8245 | return Qnil; | |
8246 | ||
03699b14 | 8247 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 8248 | { |
f44d27ce | 8249 | Lisp_Object elt; |
6b89e3aa | 8250 | |
df7492f9 | 8251 | elt = XCAR (chain); |
4ed46869 KH |
8252 | if (CONSP (elt) |
8253 | && ((STRINGP (target) | |
03699b14 KR |
8254 | && STRINGP (XCAR (elt)) |
8255 | && fast_string_match (XCAR (elt), target) >= 0) | |
8256 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 8257 | { |
03699b14 | 8258 | val = XCDR (elt); |
b19fd4c5 KH |
8259 | /* Here, if VAL is both a valid coding system and a valid |
8260 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
8261 | if (CONSP (val)) |
8262 | return val; | |
8263 | if (! SYMBOLP (val)) | |
8264 | return Qnil; | |
8265 | if (! NILP (Fcoding_system_p (val))) | |
8266 | return Fcons (val, val); | |
b19fd4c5 | 8267 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 8268 | { |
b19fd4c5 KH |
8269 | val = call1 (val, Flist (nargs, args)); |
8270 | if (CONSP (val)) | |
8271 | return val; | |
8272 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
8273 | return Fcons (val, val); | |
6b89e3aa | 8274 | } |
02ba4723 | 8275 | return Qnil; |
6b89e3aa KH |
8276 | } |
8277 | } | |
4ed46869 | 8278 | return Qnil; |
6b89e3aa KH |
8279 | } |
8280 | ||
df7492f9 | 8281 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 8282 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 8283 | doc: /* Assign higher priority to the coding systems given as arguments. |
ff563fce | 8284 | If multiple coding systems belongs to the same category, |
a3181084 DL |
8285 | all but the first one are ignored. |
8286 | ||
8287 | usage: (set-coding-system-priority ...) */) | |
df7492f9 KH |
8288 | (nargs, args) |
8289 | int nargs; | |
8290 | Lisp_Object *args; | |
8291 | { | |
8292 | int i, j; | |
8293 | int changed[coding_category_max]; | |
8294 | enum coding_category priorities[coding_category_max]; | |
8295 | ||
8296 | bzero (changed, sizeof changed); | |
6b89e3aa | 8297 | |
df7492f9 | 8298 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 8299 | { |
df7492f9 KH |
8300 | enum coding_category category; |
8301 | Lisp_Object spec, attrs; | |
6b89e3aa | 8302 | |
df7492f9 KH |
8303 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
8304 | attrs = AREF (spec, 0); | |
8305 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8306 | if (changed[category]) | |
8307 | /* Ignore this coding system because a coding system of the | |
8308 | same category already had a higher priority. */ | |
8309 | continue; | |
8310 | changed[category] = 1; | |
8311 | priorities[j++] = category; | |
8312 | if (coding_categories[category].id >= 0 | |
8313 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
8314 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 8315 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 8316 | } |
6b89e3aa | 8317 | |
df7492f9 KH |
8318 | /* Now we have decided top J priorities. Reflect the order of the |
8319 | original priorities to the remaining priorities. */ | |
6b89e3aa | 8320 | |
df7492f9 | 8321 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 8322 | { |
df7492f9 KH |
8323 | while (j < coding_category_max |
8324 | && changed[coding_priorities[j]]) | |
8325 | j++; | |
8326 | if (j == coding_category_max) | |
8327 | abort (); | |
8328 | priorities[i] = coding_priorities[j]; | |
8329 | } | |
6b89e3aa | 8330 | |
df7492f9 | 8331 | bcopy (priorities, coding_priorities, sizeof priorities); |
177c0ea7 | 8332 | |
ff563fce KH |
8333 | /* Update `coding-category-list'. */ |
8334 | Vcoding_category_list = Qnil; | |
8335 | for (i = coding_category_max - 1; i >= 0; i--) | |
8336 | Vcoding_category_list | |
8337 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
8338 | Vcoding_category_list); | |
6b89e3aa | 8339 | |
df7492f9 | 8340 | return Qnil; |
6b89e3aa KH |
8341 | } |
8342 | ||
df7492f9 KH |
8343 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
8344 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 DL |
8345 | doc: /* Return a list of coding systems ordered by their priorities. |
8346 | HIGHESTP non-nil means just return the highest priority one. */) | |
df7492f9 KH |
8347 | (highestp) |
8348 | Lisp_Object highestp; | |
d46c5b12 KH |
8349 | { |
8350 | int i; | |
df7492f9 | 8351 | Lisp_Object val; |
6b89e3aa | 8352 | |
df7492f9 | 8353 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 8354 | { |
df7492f9 KH |
8355 | enum coding_category category = coding_priorities[i]; |
8356 | int id = coding_categories[category].id; | |
8357 | Lisp_Object attrs; | |
068a9dbd | 8358 | |
df7492f9 KH |
8359 | if (id < 0) |
8360 | continue; | |
8361 | attrs = CODING_ID_ATTRS (id); | |
8362 | if (! NILP (highestp)) | |
8363 | return CODING_ATTR_BASE_NAME (attrs); | |
8364 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
8365 | } | |
8366 | return Fnreverse (val); | |
8367 | } | |
068a9dbd | 8368 | |
f0064e1f | 8369 | static char *suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
8370 | |
8371 | static Lisp_Object | |
df7492f9 KH |
8372 | make_subsidiaries (base) |
8373 | Lisp_Object base; | |
068a9dbd | 8374 | { |
df7492f9 | 8375 | Lisp_Object subsidiaries; |
8f924df7 | 8376 | int base_name_len = SBYTES (SYMBOL_NAME (base)); |
df7492f9 KH |
8377 | char *buf = (char *) alloca (base_name_len + 6); |
8378 | int i; | |
068a9dbd | 8379 | |
8f924df7 | 8380 | bcopy (SDATA (SYMBOL_NAME (base)), buf, base_name_len); |
df7492f9 KH |
8381 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
8382 | for (i = 0; i < 3; i++) | |
068a9dbd | 8383 | { |
df7492f9 KH |
8384 | bcopy (suffixes[i], buf + base_name_len, strlen (suffixes[i]) + 1); |
8385 | ASET (subsidiaries, i, intern (buf)); | |
068a9dbd | 8386 | } |
df7492f9 | 8387 | return subsidiaries; |
068a9dbd KH |
8388 | } |
8389 | ||
8390 | ||
df7492f9 KH |
8391 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
8392 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
8393 | doc: /* For internal use only. |
8394 | usage: (define-coding-system-internal ...) */) | |
df7492f9 KH |
8395 | (nargs, args) |
8396 | int nargs; | |
8397 | Lisp_Object *args; | |
068a9dbd | 8398 | { |
df7492f9 KH |
8399 | Lisp_Object name; |
8400 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
8401 | Lisp_Object attrs; /* Vector of attributes. */ | |
8402 | Lisp_Object eol_type; | |
8403 | Lisp_Object aliases; | |
8404 | Lisp_Object coding_type, charset_list, safe_charsets; | |
8405 | enum coding_category category; | |
8406 | Lisp_Object tail, val; | |
8407 | int max_charset_id = 0; | |
8408 | int i; | |
068a9dbd | 8409 | |
df7492f9 KH |
8410 | if (nargs < coding_arg_max) |
8411 | goto short_args; | |
068a9dbd | 8412 | |
df7492f9 | 8413 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 8414 | |
df7492f9 KH |
8415 | name = args[coding_arg_name]; |
8416 | CHECK_SYMBOL (name); | |
8417 | CODING_ATTR_BASE_NAME (attrs) = name; | |
068a9dbd | 8418 | |
df7492f9 KH |
8419 | val = args[coding_arg_mnemonic]; |
8420 | if (! STRINGP (val)) | |
8421 | CHECK_CHARACTER (val); | |
8422 | CODING_ATTR_MNEMONIC (attrs) = val; | |
068a9dbd | 8423 | |
df7492f9 KH |
8424 | coding_type = args[coding_arg_coding_type]; |
8425 | CHECK_SYMBOL (coding_type); | |
8426 | CODING_ATTR_TYPE (attrs) = coding_type; | |
068a9dbd | 8427 | |
df7492f9 KH |
8428 | charset_list = args[coding_arg_charset_list]; |
8429 | if (SYMBOLP (charset_list)) | |
8430 | { | |
8431 | if (EQ (charset_list, Qiso_2022)) | |
8432 | { | |
8433 | if (! EQ (coding_type, Qiso_2022)) | |
8434 | error ("Invalid charset-list"); | |
8435 | charset_list = Viso_2022_charset_list; | |
8436 | } | |
8437 | else if (EQ (charset_list, Qemacs_mule)) | |
8438 | { | |
8439 | if (! EQ (coding_type, Qemacs_mule)) | |
8440 | error ("Invalid charset-list"); | |
8441 | charset_list = Vemacs_mule_charset_list; | |
8442 | } | |
8443 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8444 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
8445 | max_charset_id = XFASTINT (XCAR (tail)); | |
8446 | } | |
068a9dbd KH |
8447 | else |
8448 | { | |
df7492f9 KH |
8449 | charset_list = Fcopy_sequence (charset_list); |
8450 | for (tail = charset_list; !NILP (tail); tail = Fcdr (tail)) | |
068a9dbd | 8451 | { |
df7492f9 KH |
8452 | struct charset *charset; |
8453 | ||
8454 | val = Fcar (tail); | |
8455 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8456 | if (EQ (coding_type, Qiso_2022) | |
8457 | ? CHARSET_ISO_FINAL (charset) < 0 | |
8458 | : EQ (coding_type, Qemacs_mule) | |
8459 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
8460 | : 0) | |
8461 | error ("Can't handle charset `%s'", | |
8f924df7 | 8462 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 8463 | |
8f924df7 | 8464 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
8465 | if (max_charset_id < charset->id) |
8466 | max_charset_id = charset->id; | |
068a9dbd KH |
8467 | } |
8468 | } | |
df7492f9 | 8469 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; |
068a9dbd | 8470 | |
df7492f9 KH |
8471 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
8472 | make_number (255)); | |
8473 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8f924df7 | 8474 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 8475 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; |
068a9dbd | 8476 | |
584948ac | 8477 | CODING_ATTR_ASCII_COMPAT (attrs) = args[coding_arg_ascii_compatible_p]; |
3a73fa5d | 8478 | |
df7492f9 | 8479 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 8480 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 8481 | CHECK_SYMBOL (val); |
df7492f9 | 8482 | CODING_ATTR_DECODE_TBL (attrs) = val; |
3a73fa5d | 8483 | |
df7492f9 | 8484 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 8485 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 8486 | CHECK_SYMBOL (val); |
df7492f9 | 8487 | CODING_ATTR_ENCODE_TBL (attrs) = val; |
d46c5b12 | 8488 | |
df7492f9 KH |
8489 | val = args[coding_arg_post_read_conversion]; |
8490 | CHECK_SYMBOL (val); | |
8491 | CODING_ATTR_POST_READ (attrs) = val; | |
d46c5b12 | 8492 | |
df7492f9 KH |
8493 | val = args[coding_arg_pre_write_conversion]; |
8494 | CHECK_SYMBOL (val); | |
8495 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
3a73fa5d | 8496 | |
df7492f9 KH |
8497 | val = args[coding_arg_default_char]; |
8498 | if (NILP (val)) | |
8499 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
8500 | else | |
8501 | { | |
8f924df7 | 8502 | CHECK_CHARACTER (val); |
df7492f9 KH |
8503 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; |
8504 | } | |
4031e2bf | 8505 | |
8f924df7 KH |
8506 | val = args[coding_arg_for_unibyte]; |
8507 | CODING_ATTR_FOR_UNIBYTE (attrs) = NILP (val) ? Qnil : Qt; | |
3a73fa5d | 8508 | |
df7492f9 KH |
8509 | val = args[coding_arg_plist]; |
8510 | CHECK_LIST (val); | |
8511 | CODING_ATTR_PLIST (attrs) = val; | |
3a73fa5d | 8512 | |
df7492f9 KH |
8513 | if (EQ (coding_type, Qcharset)) |
8514 | { | |
c7c66a95 KH |
8515 | /* Generate a lisp vector of 256 elements. Each element is nil, |
8516 | integer, or a list of charset IDs. | |
3a73fa5d | 8517 | |
c7c66a95 KH |
8518 | If Nth element is nil, the byte code N is invalid in this |
8519 | coding system. | |
4ed46869 | 8520 | |
c7c66a95 KH |
8521 | If Nth element is a number NUM, N is the first byte of a |
8522 | charset whose ID is NUM. | |
4ed46869 | 8523 | |
c7c66a95 KH |
8524 | If Nth element is a list of charset IDs, N is the first byte |
8525 | of one of them. The list is sorted by dimensions of the | |
2bc515e4 | 8526 | charsets. A charset of smaller dimension comes firtst. */ |
df7492f9 | 8527 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 8528 | |
5c99c2e6 | 8529 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 8530 | { |
c7c66a95 KH |
8531 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
8532 | int dim = CHARSET_DIMENSION (charset); | |
8533 | int idx = (dim - 1) * 4; | |
4ed46869 | 8534 | |
5c99c2e6 | 8535 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
584948ac | 8536 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
4031e2bf | 8537 | |
15d143f7 KH |
8538 | for (i = charset->code_space[idx]; |
8539 | i <= charset->code_space[idx + 1]; i++) | |
8540 | { | |
c7c66a95 KH |
8541 | Lisp_Object tmp, tmp2; |
8542 | int dim2; | |
ec6d2bb8 | 8543 | |
c7c66a95 KH |
8544 | tmp = AREF (val, i); |
8545 | if (NILP (tmp)) | |
8546 | tmp = XCAR (tail); | |
8547 | else if (NUMBERP (tmp)) | |
8548 | { | |
8549 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
8550 | if (dim < dim2) | |
c7c66a95 | 8551 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
8552 | else |
8553 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 8554 | } |
15d143f7 | 8555 | else |
c7c66a95 KH |
8556 | { |
8557 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
8558 | { | |
8559 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
8560 | if (dim < dim2) | |
8561 | break; | |
8562 | } | |
8563 | if (NILP (tmp2)) | |
8564 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
8565 | else | |
8566 | { | |
8567 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
8568 | XSETCAR (tmp2, XCAR (tail)); | |
8569 | } | |
8570 | } | |
8571 | ASET (val, i, tmp); | |
15d143f7 | 8572 | } |
df7492f9 KH |
8573 | } |
8574 | ASET (attrs, coding_attr_charset_valids, val); | |
8575 | category = coding_category_charset; | |
8576 | } | |
8577 | else if (EQ (coding_type, Qccl)) | |
8578 | { | |
8579 | Lisp_Object valids; | |
ecec61c1 | 8580 | |
df7492f9 KH |
8581 | if (nargs < coding_arg_ccl_max) |
8582 | goto short_args; | |
ecec61c1 | 8583 | |
df7492f9 KH |
8584 | val = args[coding_arg_ccl_decoder]; |
8585 | CHECK_CCL_PROGRAM (val); | |
8586 | if (VECTORP (val)) | |
8587 | val = Fcopy_sequence (val); | |
8588 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 8589 | |
df7492f9 KH |
8590 | val = args[coding_arg_ccl_encoder]; |
8591 | CHECK_CCL_PROGRAM (val); | |
8592 | if (VECTORP (val)) | |
8593 | val = Fcopy_sequence (val); | |
8594 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 8595 | |
df7492f9 KH |
8596 | val = args[coding_arg_ccl_valids]; |
8597 | valids = Fmake_string (make_number (256), make_number (0)); | |
8598 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
8599 | { | |
8dcbea82 | 8600 | int from, to; |
ecec61c1 | 8601 | |
df7492f9 KH |
8602 | val = Fcar (tail); |
8603 | if (INTEGERP (val)) | |
8dcbea82 KH |
8604 | { |
8605 | from = to = XINT (val); | |
8606 | if (from < 0 || from > 255) | |
8607 | args_out_of_range_3 (val, make_number (0), make_number (255)); | |
8608 | } | |
df7492f9 KH |
8609 | else |
8610 | { | |
df7492f9 | 8611 | CHECK_CONS (val); |
8f924df7 KH |
8612 | CHECK_NATNUM_CAR (val); |
8613 | CHECK_NATNUM_CDR (val); | |
df7492f9 | 8614 | from = XINT (XCAR (val)); |
8f924df7 | 8615 | if (from > 255) |
8dcbea82 KH |
8616 | args_out_of_range_3 (XCAR (val), |
8617 | make_number (0), make_number (255)); | |
df7492f9 | 8618 | to = XINT (XCDR (val)); |
8dcbea82 KH |
8619 | if (to < from || to > 255) |
8620 | args_out_of_range_3 (XCDR (val), | |
8621 | XCAR (val), make_number (255)); | |
df7492f9 | 8622 | } |
8dcbea82 | 8623 | for (i = from; i <= to; i++) |
8f924df7 | 8624 | SSET (valids, i, 1); |
df7492f9 KH |
8625 | } |
8626 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 8627 | |
df7492f9 | 8628 | category = coding_category_ccl; |
55ab7be3 | 8629 | } |
df7492f9 | 8630 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 8631 | { |
df7492f9 | 8632 | Lisp_Object bom, endian; |
4ed46869 | 8633 | |
584948ac | 8634 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; |
4ed46869 | 8635 | |
df7492f9 KH |
8636 | if (nargs < coding_arg_utf16_max) |
8637 | goto short_args; | |
4ed46869 | 8638 | |
df7492f9 KH |
8639 | bom = args[coding_arg_utf16_bom]; |
8640 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
8641 | { | |
8642 | CHECK_CONS (bom); | |
8f924df7 KH |
8643 | val = XCAR (bom); |
8644 | CHECK_CODING_SYSTEM (val); | |
8645 | val = XCDR (bom); | |
8646 | CHECK_CODING_SYSTEM (val); | |
df7492f9 KH |
8647 | } |
8648 | ASET (attrs, coding_attr_utf_16_bom, bom); | |
8649 | ||
8650 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
8651 | CHECK_SYMBOL (endian); |
8652 | if (NILP (endian)) | |
8653 | endian = Qbig; | |
8654 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 8655 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
8656 | ASET (attrs, coding_attr_utf_16_endian, endian); |
8657 | ||
8658 | category = (CONSP (bom) | |
8659 | ? coding_category_utf_16_auto | |
8660 | : NILP (bom) | |
b49a1807 | 8661 | ? (EQ (endian, Qbig) |
df7492f9 KH |
8662 | ? coding_category_utf_16_be_nosig |
8663 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 8664 | : (EQ (endian, Qbig) |
df7492f9 KH |
8665 | ? coding_category_utf_16_be |
8666 | : coding_category_utf_16_le)); | |
8667 | } | |
8668 | else if (EQ (coding_type, Qiso_2022)) | |
8669 | { | |
8670 | Lisp_Object initial, reg_usage, request, flags; | |
4776e638 | 8671 | int i; |
1397dc18 | 8672 | |
df7492f9 KH |
8673 | if (nargs < coding_arg_iso2022_max) |
8674 | goto short_args; | |
8675 | ||
8676 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
8677 | CHECK_VECTOR (initial); | |
8678 | for (i = 0; i < 4; i++) | |
8679 | { | |
8680 | val = Faref (initial, make_number (i)); | |
8681 | if (! NILP (val)) | |
8682 | { | |
584948ac KH |
8683 | struct charset *charset; |
8684 | ||
8685 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8686 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
8687 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
8688 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8689 | } |
8690 | else | |
8691 | ASET (initial, i, make_number (-1)); | |
8692 | } | |
8693 | ||
8694 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
8695 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
8696 | CHECK_NUMBER_CAR (reg_usage); |
8697 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
8698 | |
8699 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
8700 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 8701 | { |
df7492f9 | 8702 | int id; |
8f924df7 | 8703 | Lisp_Object tmp; |
df7492f9 KH |
8704 | |
8705 | val = Fcar (tail); | |
8706 | CHECK_CONS (val); | |
8f924df7 KH |
8707 | tmp = XCAR (val); |
8708 | CHECK_CHARSET_GET_ID (tmp, id); | |
8709 | CHECK_NATNUM_CDR (val); | |
df7492f9 KH |
8710 | if (XINT (XCDR (val)) >= 4) |
8711 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
8f924df7 | 8712 | XSETCAR (val, make_number (id)); |
1397dc18 | 8713 | } |
4ed46869 | 8714 | |
df7492f9 KH |
8715 | flags = args[coding_arg_iso2022_flags]; |
8716 | CHECK_NATNUM (flags); | |
8717 | i = XINT (flags); | |
8718 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
8719 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
8720 | ||
8721 | ASET (attrs, coding_attr_iso_initial, initial); | |
8722 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
8723 | ASET (attrs, coding_attr_iso_request, request); | |
8724 | ASET (attrs, coding_attr_iso_flags, flags); | |
8725 | setup_iso_safe_charsets (attrs); | |
8726 | ||
8727 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
8728 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
8729 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
8730 | ? coding_category_iso_7_else | |
8731 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
8732 | ? coding_category_iso_7 | |
8733 | : coding_category_iso_7_tight); | |
8734 | else | |
8735 | { | |
8736 | int id = XINT (AREF (initial, 1)); | |
8737 | ||
c6fb6e98 | 8738 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
8739 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
8740 | || id < 0) | |
8741 | ? coding_category_iso_8_else | |
8742 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
8743 | ? coding_category_iso_8_1 | |
8744 | : coding_category_iso_8_2); | |
8745 | } | |
0ce7886f KH |
8746 | if (category != coding_category_iso_8_1 |
8747 | && category != coding_category_iso_8_2) | |
8748 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; | |
df7492f9 KH |
8749 | } |
8750 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 8751 | { |
df7492f9 KH |
8752 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
8753 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
584948ac | 8754 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
df7492f9 | 8755 | category = coding_category_emacs_mule; |
c28a9453 | 8756 | } |
df7492f9 | 8757 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 8758 | { |
df7492f9 KH |
8759 | |
8760 | struct charset *charset; | |
8761 | ||
7d64c6ad | 8762 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 8763 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 8764 | error ("There should be three or four charsets"); |
df7492f9 KH |
8765 | |
8766 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8767 | if (CHARSET_DIMENSION (charset) != 1) | |
8768 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8769 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8770 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8771 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8772 | |
8773 | charset_list = XCDR (charset_list); | |
8774 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8775 | if (CHARSET_DIMENSION (charset) != 1) | |
8776 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8777 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
8778 | |
8779 | charset_list = XCDR (charset_list); | |
8780 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8781 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
8782 | error ("Dimension of charset %s is not two", |
8783 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
8784 | ||
8785 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
8786 | if (! NILP (charset_list)) |
8787 | { | |
8788 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8789 | if (CHARSET_DIMENSION (charset) != 2) | |
8790 | error ("Dimension of charset %s is not two", | |
8791 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
8792 | } | |
df7492f9 KH |
8793 | |
8794 | category = coding_category_sjis; | |
8795 | Vsjis_coding_system = name; | |
c28a9453 | 8796 | } |
df7492f9 KH |
8797 | else if (EQ (coding_type, Qbig5)) |
8798 | { | |
8799 | struct charset *charset; | |
4ed46869 | 8800 | |
df7492f9 KH |
8801 | if (XINT (Flength (charset_list)) != 2) |
8802 | error ("There should be just two charsets"); | |
8803 | ||
8804 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8805 | if (CHARSET_DIMENSION (charset) != 1) | |
8806 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8807 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8808 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8809 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8810 | |
8811 | charset_list = XCDR (charset_list); | |
8812 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8813 | if (CHARSET_DIMENSION (charset) != 2) | |
8814 | error ("Dimension of charset %s is not two", | |
8f924df7 | 8815 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 8816 | |
df7492f9 KH |
8817 | category = coding_category_big5; |
8818 | Vbig5_coding_system = name; | |
8819 | } | |
8820 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 8821 | { |
584948ac KH |
8822 | category = coding_category_raw_text; |
8823 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
c28a9453 | 8824 | } |
df7492f9 | 8825 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 8826 | { |
584948ac KH |
8827 | category = coding_category_utf_8; |
8828 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
4ed46869 | 8829 | } |
df7492f9 KH |
8830 | else if (EQ (coding_type, Qundecided)) |
8831 | category = coding_category_undecided; | |
4ed46869 | 8832 | else |
df7492f9 | 8833 | error ("Invalid coding system type: %s", |
8f924df7 | 8834 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 8835 | |
df7492f9 | 8836 | CODING_ATTR_CATEGORY (attrs) = make_number (category); |
01378f49 KH |
8837 | CODING_ATTR_PLIST (attrs) |
8838 | = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category), | |
8839 | CODING_ATTR_PLIST (attrs))); | |
c4825358 | 8840 | |
df7492f9 KH |
8841 | eol_type = args[coding_arg_eol_type]; |
8842 | if (! NILP (eol_type) | |
8843 | && ! EQ (eol_type, Qunix) | |
8844 | && ! EQ (eol_type, Qdos) | |
8845 | && ! EQ (eol_type, Qmac)) | |
8846 | error ("Invalid eol-type"); | |
4ed46869 | 8847 | |
df7492f9 | 8848 | aliases = Fcons (name, Qnil); |
4ed46869 | 8849 | |
df7492f9 KH |
8850 | if (NILP (eol_type)) |
8851 | { | |
8852 | eol_type = make_subsidiaries (name); | |
8853 | for (i = 0; i < 3; i++) | |
1397dc18 | 8854 | { |
df7492f9 KH |
8855 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
8856 | ||
8857 | this_name = AREF (eol_type, i); | |
8858 | this_aliases = Fcons (this_name, Qnil); | |
8859 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
8860 | this_spec = Fmake_vector (make_number (3), attrs); | |
8861 | ASET (this_spec, 1, this_aliases); | |
8862 | ASET (this_spec, 2, this_eol_type); | |
8863 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
8864 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
8865 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
8866 | Vcoding_system_alist); | |
1397dc18 | 8867 | } |
d46c5b12 | 8868 | } |
4ed46869 | 8869 | |
df7492f9 KH |
8870 | spec_vec = Fmake_vector (make_number (3), attrs); |
8871 | ASET (spec_vec, 1, aliases); | |
8872 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 8873 | |
df7492f9 KH |
8874 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
8875 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
8876 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
8877 | Vcoding_system_alist); | |
48b0f3ae | 8878 | |
df7492f9 KH |
8879 | { |
8880 | int id = coding_categories[category].id; | |
48b0f3ae | 8881 | |
df7492f9 KH |
8882 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
8883 | setup_coding_system (name, &coding_categories[category]); | |
8884 | } | |
48b0f3ae | 8885 | |
d46c5b12 | 8886 | return Qnil; |
48b0f3ae | 8887 | |
df7492f9 KH |
8888 | short_args: |
8889 | return Fsignal (Qwrong_number_of_arguments, | |
8890 | Fcons (intern ("define-coding-system-internal"), | |
8891 | make_number (nargs))); | |
d46c5b12 | 8892 | } |
4ed46869 | 8893 | |
d6925f38 | 8894 | |
a6f87d34 KH |
8895 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
8896 | 3, 3, 0, | |
8897 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
8898 | (coding_system, prop, val) | |
8899 | Lisp_Object coding_system, prop, val; | |
8900 | { | |
3dbe7859 | 8901 | Lisp_Object spec, attrs; |
a6f87d34 KH |
8902 | |
8903 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8904 | attrs = AREF (spec, 0); | |
8905 | if (EQ (prop, QCmnemonic)) | |
8906 | { | |
8907 | if (! STRINGP (val)) | |
8908 | CHECK_CHARACTER (val); | |
8909 | CODING_ATTR_MNEMONIC (attrs) = val; | |
8910 | } | |
8911 | else if (EQ (prop, QCdefalut_char)) | |
8912 | { | |
8913 | if (NILP (val)) | |
8914 | val = make_number (' '); | |
8915 | else | |
8916 | CHECK_CHARACTER (val); | |
8917 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; | |
8918 | } | |
8919 | else if (EQ (prop, QCdecode_translation_table)) | |
8920 | { | |
8921 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
8922 | CHECK_SYMBOL (val); | |
8923 | CODING_ATTR_DECODE_TBL (attrs) = val; | |
8924 | } | |
8925 | else if (EQ (prop, QCencode_translation_table)) | |
8926 | { | |
8927 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
8928 | CHECK_SYMBOL (val); | |
8929 | CODING_ATTR_ENCODE_TBL (attrs) = val; | |
8930 | } | |
8931 | else if (EQ (prop, QCpost_read_conversion)) | |
8932 | { | |
8933 | CHECK_SYMBOL (val); | |
8934 | CODING_ATTR_POST_READ (attrs) = val; | |
8935 | } | |
8936 | else if (EQ (prop, QCpre_write_conversion)) | |
8937 | { | |
8938 | CHECK_SYMBOL (val); | |
8939 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
8940 | } | |
8941 | ||
8942 | CODING_ATTR_PLIST (attrs) | |
8943 | = Fplist_put (CODING_ATTR_PLIST (attrs), prop, val); | |
8944 | return val; | |
8945 | } | |
8946 | ||
8947 | ||
df7492f9 KH |
8948 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
8949 | Sdefine_coding_system_alias, 2, 2, 0, | |
8950 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
8951 | (alias, coding_system) | |
8952 | Lisp_Object alias, coding_system; | |
66cfb530 | 8953 | { |
df7492f9 | 8954 | Lisp_Object spec, aliases, eol_type; |
4ed46869 | 8955 | |
df7492f9 KH |
8956 | CHECK_SYMBOL (alias); |
8957 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8958 | aliases = AREF (spec, 1); | |
d6925f38 KH |
8959 | /* ALISES should be a list of length more than zero, and the first |
8960 | element is a base coding system. Append ALIAS at the tail of the | |
8961 | list. */ | |
df7492f9 KH |
8962 | while (!NILP (XCDR (aliases))) |
8963 | aliases = XCDR (aliases); | |
8f924df7 | 8964 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 8965 | |
df7492f9 KH |
8966 | eol_type = AREF (spec, 2); |
8967 | if (VECTORP (eol_type)) | |
4ed46869 | 8968 | { |
df7492f9 KH |
8969 | Lisp_Object subsidiaries; |
8970 | int i; | |
4ed46869 | 8971 | |
df7492f9 KH |
8972 | subsidiaries = make_subsidiaries (alias); |
8973 | for (i = 0; i < 3; i++) | |
8974 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
8975 | AREF (eol_type, i)); | |
4ed46869 | 8976 | } |
df7492f9 KH |
8977 | |
8978 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 8979 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
5bad0796 DL |
8980 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), |
8981 | Vcoding_system_alist); | |
66cfb530 | 8982 | |
4ed46869 KH |
8983 | return Qnil; |
8984 | } | |
8985 | ||
df7492f9 KH |
8986 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
8987 | 1, 1, 0, | |
8988 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 8989 | Any alias or subsidiary coding system is not a base coding system. */) |
df7492f9 KH |
8990 | (coding_system) |
8991 | Lisp_Object coding_system; | |
d46c5b12 | 8992 | { |
df7492f9 | 8993 | Lisp_Object spec, attrs; |
d46c5b12 | 8994 | |
df7492f9 KH |
8995 | if (NILP (coding_system)) |
8996 | return (Qno_conversion); | |
8997 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8998 | attrs = AREF (spec, 0); | |
8999 | return CODING_ATTR_BASE_NAME (attrs); | |
9000 | } | |
1397dc18 | 9001 | |
df7492f9 KH |
9002 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
9003 | 1, 1, 0, | |
9004 | doc: "Return the property list of CODING-SYSTEM.") | |
9005 | (coding_system) | |
9006 | Lisp_Object coding_system; | |
9007 | { | |
9008 | Lisp_Object spec, attrs; | |
1397dc18 | 9009 | |
df7492f9 KH |
9010 | if (NILP (coding_system)) |
9011 | coding_system = Qno_conversion; | |
9012 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9013 | attrs = AREF (spec, 0); | |
9014 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
9015 | } |
9016 | ||
df7492f9 KH |
9017 | |
9018 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
9019 | 1, 1, 0, | |
da7db224 | 9020 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
df7492f9 KH |
9021 | (coding_system) |
9022 | Lisp_Object coding_system; | |
66cfb530 | 9023 | { |
df7492f9 | 9024 | Lisp_Object spec; |
84d60297 | 9025 | |
df7492f9 KH |
9026 | if (NILP (coding_system)) |
9027 | coding_system = Qno_conversion; | |
9028 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 9029 | return AREF (spec, 1); |
df7492f9 | 9030 | } |
66cfb530 | 9031 | |
df7492f9 KH |
9032 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
9033 | Scoding_system_eol_type, 1, 1, 0, | |
9034 | doc: /* Return eol-type of CODING-SYSTEM. | |
9035 | An eol-type is integer 0, 1, 2, or a vector of coding systems. | |
66cfb530 | 9036 | |
df7492f9 KH |
9037 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
9038 | and CR respectively. | |
66cfb530 | 9039 | |
df7492f9 KH |
9040 | A vector value indicates that a format of end-of-line should be |
9041 | detected automatically. Nth element of the vector is the subsidiary | |
9042 | coding system whose eol-type is N. */) | |
6b89e3aa KH |
9043 | (coding_system) |
9044 | Lisp_Object coding_system; | |
9045 | { | |
df7492f9 KH |
9046 | Lisp_Object spec, eol_type; |
9047 | int n; | |
6b89e3aa | 9048 | |
df7492f9 KH |
9049 | if (NILP (coding_system)) |
9050 | coding_system = Qno_conversion; | |
9051 | if (! CODING_SYSTEM_P (coding_system)) | |
9052 | return Qnil; | |
9053 | spec = CODING_SYSTEM_SPEC (coding_system); | |
9054 | eol_type = AREF (spec, 2); | |
9055 | if (VECTORP (eol_type)) | |
9056 | return Fcopy_sequence (eol_type); | |
9057 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
9058 | return make_number (n); | |
6b89e3aa KH |
9059 | } |
9060 | ||
4ed46869 KH |
9061 | #endif /* emacs */ |
9062 | ||
9063 | \f | |
1397dc18 | 9064 | /*** 9. Post-amble ***/ |
4ed46869 | 9065 | |
dfcf069d | 9066 | void |
4ed46869 KH |
9067 | init_coding_once () |
9068 | { | |
9069 | int i; | |
9070 | ||
df7492f9 KH |
9071 | for (i = 0; i < coding_category_max; i++) |
9072 | { | |
9073 | coding_categories[i].id = -1; | |
9074 | coding_priorities[i] = i; | |
9075 | } | |
4ed46869 KH |
9076 | |
9077 | /* ISO2022 specific initialize routine. */ | |
9078 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 9079 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
9080 | for (i = 0x21; i < 0x7F; i++) |
9081 | iso_code_class[i] = ISO_graphic_plane_0; | |
9082 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 9083 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
9084 | for (i = 0xA1; i < 0xFF; i++) |
9085 | iso_code_class[i] = ISO_graphic_plane_1; | |
9086 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
9087 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
9088 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
9089 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
9090 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
9091 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
9092 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
9093 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
9094 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
9095 | ||
df7492f9 KH |
9096 | for (i = 0; i < 256; i++) |
9097 | { | |
9098 | emacs_mule_bytes[i] = 1; | |
9099 | } | |
7c78e542 KH |
9100 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
9101 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
9102 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
9103 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
9104 | } |
9105 | ||
9106 | #ifdef emacs | |
9107 | ||
dfcf069d | 9108 | void |
e0e989f6 KH |
9109 | syms_of_coding () |
9110 | { | |
df7492f9 | 9111 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
9112 | { |
9113 | Lisp_Object args[2]; | |
9114 | args[0] = QCtest; | |
9115 | args[1] = Qeq; | |
9116 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
9117 | } | |
df7492f9 KH |
9118 | |
9119 | staticpro (&Vsjis_coding_system); | |
9120 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 9121 | |
df7492f9 KH |
9122 | staticpro (&Vbig5_coding_system); |
9123 | Vbig5_coding_system = Qnil; | |
9124 | ||
24a73b0a KH |
9125 | staticpro (&Vcode_conversion_reused_workbuf); |
9126 | Vcode_conversion_reused_workbuf = Qnil; | |
9127 | ||
9128 | staticpro (&Vcode_conversion_workbuf_name); | |
9129 | Vcode_conversion_workbuf_name = build_string (" *code-conversion-work*"); | |
e0e989f6 | 9130 | |
24a73b0a | 9131 | reused_workbuf_in_use = 0; |
df7492f9 KH |
9132 | |
9133 | DEFSYM (Qcharset, "charset"); | |
9134 | DEFSYM (Qtarget_idx, "target-idx"); | |
9135 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
9136 | Fset (Qcoding_system_history, Qnil); |
9137 | ||
9ce27fde | 9138 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 9139 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 9140 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
9141 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
9142 | ||
df7492f9 | 9143 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 9144 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
9145 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
9146 | ||
df7492f9 | 9147 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 9148 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
9149 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
9150 | ||
df7492f9 | 9151 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 9152 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
9153 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
9154 | ||
df7492f9 | 9155 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 9156 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
9157 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
9158 | ||
df7492f9 KH |
9159 | DEFSYM (Qcoding_system, "coding-system"); |
9160 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 9161 | |
df7492f9 KH |
9162 | DEFSYM (Qeol_type, "eol-type"); |
9163 | DEFSYM (Qunix, "unix"); | |
9164 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 9165 | |
df7492f9 KH |
9166 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
9167 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
9168 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
9169 | DEFSYM (Qdefault_char, "default-char"); | |
9170 | DEFSYM (Qundecided, "undecided"); | |
9171 | DEFSYM (Qno_conversion, "no-conversion"); | |
9172 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 9173 | |
df7492f9 | 9174 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 9175 | |
df7492f9 | 9176 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 9177 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 9178 | |
df7492f9 | 9179 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
9180 | DEFSYM (Qbig, "big"); |
9181 | DEFSYM (Qlittle, "little"); | |
27901516 | 9182 | |
df7492f9 KH |
9183 | DEFSYM (Qshift_jis, "shift-jis"); |
9184 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 9185 | |
df7492f9 | 9186 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 9187 | |
df7492f9 | 9188 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 KH |
9189 | Fput (Qcoding_system_error, Qerror_conditions, |
9190 | Fcons (Qcoding_system_error, Fcons (Qerror, Qnil))); | |
9191 | Fput (Qcoding_system_error, Qerror_message, | |
9ce27fde | 9192 | build_string ("Invalid coding system")); |
4ed46869 | 9193 | |
05e6f5dc KH |
9194 | /* Intern this now in case it isn't already done. |
9195 | Setting this variable twice is harmless. | |
9196 | But don't staticpro it here--that is done in alloc.c. */ | |
9197 | Qchar_table_extra_slots = intern ("char-table-extra-slots"); | |
70c22245 | 9198 | |
df7492f9 | 9199 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 9200 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
9201 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
9202 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
9203 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 9204 | |
df7492f9 | 9205 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 9206 | |
df7492f9 | 9207 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 9208 | |
01378f49 | 9209 | DEFSYM (QCcategory, ":category"); |
a6f87d34 KH |
9210 | DEFSYM (QCmnemonic, ":mnemonic"); |
9211 | DEFSYM (QCdefalut_char, ":default-char"); | |
9212 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); | |
9213 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
9214 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
9215 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
01378f49 | 9216 | |
df7492f9 KH |
9217 | Vcoding_category_table |
9218 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
9219 | staticpro (&Vcoding_category_table); | |
9220 | /* Followings are target of code detection. */ | |
9221 | ASET (Vcoding_category_table, coding_category_iso_7, | |
9222 | intern ("coding-category-iso-7")); | |
9223 | ASET (Vcoding_category_table, coding_category_iso_7_tight, | |
9224 | intern ("coding-category-iso-7-tight")); | |
9225 | ASET (Vcoding_category_table, coding_category_iso_8_1, | |
9226 | intern ("coding-category-iso-8-1")); | |
9227 | ASET (Vcoding_category_table, coding_category_iso_8_2, | |
9228 | intern ("coding-category-iso-8-2")); | |
9229 | ASET (Vcoding_category_table, coding_category_iso_7_else, | |
9230 | intern ("coding-category-iso-7-else")); | |
9231 | ASET (Vcoding_category_table, coding_category_iso_8_else, | |
9232 | intern ("coding-category-iso-8-else")); | |
9233 | ASET (Vcoding_category_table, coding_category_utf_8, | |
9234 | intern ("coding-category-utf-8")); | |
9235 | ASET (Vcoding_category_table, coding_category_utf_16_be, | |
9236 | intern ("coding-category-utf-16-be")); | |
ff563fce KH |
9237 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
9238 | intern ("coding-category-utf-16-auto")); | |
df7492f9 KH |
9239 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
9240 | intern ("coding-category-utf-16-le")); | |
9241 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, | |
9242 | intern ("coding-category-utf-16-be-nosig")); | |
9243 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, | |
9244 | intern ("coding-category-utf-16-le-nosig")); | |
9245 | ASET (Vcoding_category_table, coding_category_charset, | |
9246 | intern ("coding-category-charset")); | |
9247 | ASET (Vcoding_category_table, coding_category_sjis, | |
9248 | intern ("coding-category-sjis")); | |
9249 | ASET (Vcoding_category_table, coding_category_big5, | |
9250 | intern ("coding-category-big5")); | |
9251 | ASET (Vcoding_category_table, coding_category_ccl, | |
9252 | intern ("coding-category-ccl")); | |
9253 | ASET (Vcoding_category_table, coding_category_emacs_mule, | |
9254 | intern ("coding-category-emacs-mule")); | |
9255 | /* Followings are NOT target of code detection. */ | |
9256 | ASET (Vcoding_category_table, coding_category_raw_text, | |
9257 | intern ("coding-category-raw-text")); | |
9258 | ASET (Vcoding_category_table, coding_category_undecided, | |
9259 | intern ("coding-category-undecided")); | |
ecf488bc | 9260 | |
065e3595 KH |
9261 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
9262 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
9263 | DEFSYM (Qinvalid_source, "invalid-source"); | |
9264 | DEFSYM (Qinterrupted, "interrupted"); | |
9265 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
9266 | ||
4ed46869 KH |
9267 | defsubr (&Scoding_system_p); |
9268 | defsubr (&Sread_coding_system); | |
9269 | defsubr (&Sread_non_nil_coding_system); | |
9270 | defsubr (&Scheck_coding_system); | |
9271 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 9272 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 9273 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 9274 | defsubr (&Sunencodable_char_position); |
df7492f9 | 9275 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
9276 | defsubr (&Sdecode_coding_region); |
9277 | defsubr (&Sencode_coding_region); | |
9278 | defsubr (&Sdecode_coding_string); | |
9279 | defsubr (&Sencode_coding_string); | |
9280 | defsubr (&Sdecode_sjis_char); | |
9281 | defsubr (&Sencode_sjis_char); | |
9282 | defsubr (&Sdecode_big5_char); | |
9283 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 9284 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 9285 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 9286 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 9287 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 9288 | defsubr (&Skeyboard_coding_system); |
a5d301df | 9289 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 9290 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 9291 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 9292 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 9293 | defsubr (&Scoding_system_put); |
df7492f9 KH |
9294 | defsubr (&Scoding_system_base); |
9295 | defsubr (&Scoding_system_plist); | |
9296 | defsubr (&Scoding_system_aliases); | |
9297 | defsubr (&Scoding_system_eol_type); | |
9298 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 9299 | |
4608c386 | 9300 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
48b0f3ae PJ |
9301 | doc: /* List of coding systems. |
9302 | ||
9303 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 9304 | updated by the functions `define-coding-system' and |
48b0f3ae | 9305 | `define-coding-system-alias'. */); |
4608c386 KH |
9306 | Vcoding_system_list = Qnil; |
9307 | ||
9308 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, | |
48b0f3ae PJ |
9309 | doc: /* Alist of coding system names. |
9310 | Each element is one element list of coding system name. | |
9311 | This variable is given to `completing-read' as TABLE argument. | |
9312 | ||
9313 | Do not alter the value of this variable manually. This variable should be | |
9314 | updated by the functions `make-coding-system' and | |
9315 | `define-coding-system-alias'. */); | |
4608c386 KH |
9316 | Vcoding_system_alist = Qnil; |
9317 | ||
4ed46869 | 9318 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
48b0f3ae PJ |
9319 | doc: /* List of coding-categories (symbols) ordered by priority. |
9320 | ||
9321 | On detecting a coding system, Emacs tries code detection algorithms | |
9322 | associated with each coding-category one by one in this order. When | |
9323 | one algorithm agrees with a byte sequence of source text, the coding | |
9324 | system bound to the corresponding coding-category is selected. */); | |
4ed46869 KH |
9325 | { |
9326 | int i; | |
9327 | ||
9328 | Vcoding_category_list = Qnil; | |
df7492f9 | 9329 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 9330 | Vcoding_category_list |
d46c5b12 KH |
9331 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
9332 | Vcoding_category_list); | |
4ed46869 KH |
9333 | } |
9334 | ||
9335 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, | |
48b0f3ae PJ |
9336 | doc: /* Specify the coding system for read operations. |
9337 | It is useful to bind this variable with `let', but do not set it globally. | |
9338 | If the value is a coding system, it is used for decoding on read operation. | |
9339 | If not, an appropriate element is used from one of the coding system alists: | |
9340 | There are three such tables, `file-coding-system-alist', | |
9341 | `process-coding-system-alist', and `network-coding-system-alist'. */); | |
4ed46869 KH |
9342 | Vcoding_system_for_read = Qnil; |
9343 | ||
9344 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, | |
48b0f3ae PJ |
9345 | doc: /* Specify the coding system for write operations. |
9346 | Programs bind this variable with `let', but you should not set it globally. | |
9347 | If the value is a coding system, it is used for encoding of output, | |
9348 | when writing it to a file and when sending it to a file or subprocess. | |
9349 | ||
9350 | If this does not specify a coding system, an appropriate element | |
9351 | is used from one of the coding system alists: | |
9352 | There are three such tables, `file-coding-system-alist', | |
9353 | `process-coding-system-alist', and `network-coding-system-alist'. | |
9354 | For output to files, if the above procedure does not specify a coding system, | |
9355 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
9356 | Vcoding_system_for_write = Qnil; |
9357 | ||
9358 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, | |
df7492f9 KH |
9359 | doc: /* |
9360 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
9361 | Vlast_coding_system_used = Qnil; |
9362 | ||
065e3595 KH |
9363 | DEFVAR_LISP ("last-code-conversion-error", &Vlast_code_conversion_error, |
9364 | doc: /* | |
9365 | Error status of the last code conversion. | |
9366 | ||
9367 | When an error was detected in the last code conversion, this variable | |
9368 | is set to one of the following symbols. | |
9369 | `insufficient-source' | |
9370 | `inconsistent-eol' | |
9371 | `invalid-source' | |
9372 | `interrupted' | |
9373 | `insufficient-memory' | |
9374 | When no error was detected, the value doesn't change. So, to check | |
9375 | the error status of a code conversion by this variable, you must | |
9376 | explicitly set this variable to nil before performing code | |
9377 | conversion. */); | |
9378 | Vlast_code_conversion_error = Qnil; | |
9379 | ||
9ce27fde | 9380 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
df7492f9 KH |
9381 | doc: /* |
9382 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
9383 | See info node `Coding Systems' and info node `Text and Binary' concerning |
9384 | such conversion. */); | |
9ce27fde KH |
9385 | inhibit_eol_conversion = 0; |
9386 | ||
ed29121d | 9387 | DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
df7492f9 KH |
9388 | doc: /* |
9389 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
9390 | Bind it to t if the process output is to be treated as if it were a file |
9391 | read from some filesystem. */); | |
ed29121d EZ |
9392 | inherit_process_coding_system = 0; |
9393 | ||
02ba4723 | 9394 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
df7492f9 KH |
9395 | doc: /* |
9396 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
9397 | The format is ((PATTERN . VAL) ...), |
9398 | where PATTERN is a regular expression matching a file name, | |
9399 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9400 | If VAL is a coding system, it is used for both decoding and encoding | |
9401 | the file contents. | |
9402 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9403 | and the cdr part is used for encoding. | |
9404 | If VAL is a function symbol, the function must return a coding system | |
0192762c DL |
9405 | or a cons of coding systems which are used as above. The function gets |
9406 | the arguments with which `find-operation-coding-systems' was called. | |
48b0f3ae PJ |
9407 | |
9408 | See also the function `find-operation-coding-system' | |
9409 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
9410 | Vfile_coding_system_alist = Qnil; |
9411 | ||
9412 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, | |
df7492f9 KH |
9413 | doc: /* |
9414 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
9415 | The format is ((PATTERN . VAL) ...), |
9416 | where PATTERN is a regular expression matching a program name, | |
9417 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9418 | If VAL is a coding system, it is used for both decoding what received | |
9419 | from the program and encoding what sent to the program. | |
9420 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9421 | and the cdr part is used for encoding. | |
9422 | If VAL is a function symbol, the function must return a coding system | |
9423 | or a cons of coding systems which are used as above. | |
9424 | ||
9425 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
9426 | Vprocess_coding_system_alist = Qnil; |
9427 | ||
9428 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, | |
df7492f9 KH |
9429 | doc: /* |
9430 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
9431 | The format is ((PATTERN . VAL) ...), |
9432 | where PATTERN is a regular expression matching a network service name | |
9433 | or is a port number to connect to, | |
9434 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9435 | If VAL is a coding system, it is used for both decoding what received | |
9436 | from the network stream and encoding what sent to the network stream. | |
9437 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9438 | and the cdr part is used for encoding. | |
9439 | If VAL is a function symbol, the function must return a coding system | |
9440 | or a cons of coding systems which are used as above. | |
9441 | ||
9442 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 9443 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 9444 | |
68c45bf0 | 9445 | DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
75205970 RS |
9446 | doc: /* Coding system to use with system messages. |
9447 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
9448 | Vlocale_coding_system = Qnil; |
9449 | ||
005f0d35 | 9450 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
7722baf9 | 9451 | DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
df7492f9 KH |
9452 | doc: /* |
9453 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
7722baf9 | 9454 | eol_mnemonic_unix = build_string (":"); |
4ed46869 | 9455 | |
7722baf9 | 9456 | DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
df7492f9 KH |
9457 | doc: /* |
9458 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
7722baf9 | 9459 | eol_mnemonic_dos = build_string ("\\"); |
4ed46869 | 9460 | |
7722baf9 | 9461 | DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
df7492f9 KH |
9462 | doc: /* |
9463 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
7722baf9 | 9464 | eol_mnemonic_mac = build_string ("/"); |
4ed46869 | 9465 | |
7722baf9 | 9466 | DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
df7492f9 KH |
9467 | doc: /* |
9468 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
7722baf9 | 9469 | eol_mnemonic_undecided = build_string (":"); |
4ed46869 | 9470 | |
84fbb8a0 | 9471 | DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
df7492f9 KH |
9472 | doc: /* |
9473 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 9474 | Venable_character_translation = Qt; |
bdd9fb48 | 9475 | |
f967223b | 9476 | DEFVAR_LISP ("standard-translation-table-for-decode", |
48b0f3ae PJ |
9477 | &Vstandard_translation_table_for_decode, |
9478 | doc: /* Table for translating characters while decoding. */); | |
f967223b | 9479 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 9480 | |
f967223b | 9481 | DEFVAR_LISP ("standard-translation-table-for-encode", |
48b0f3ae PJ |
9482 | &Vstandard_translation_table_for_encode, |
9483 | doc: /* Table for translating characters while encoding. */); | |
f967223b | 9484 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 9485 | |
df7492f9 | 9486 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table, |
48b0f3ae PJ |
9487 | doc: /* Alist of charsets vs revision numbers. |
9488 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
9489 | designate it with the escape sequence identifying revision (cdr part |
9490 | of the element). */); | |
9491 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
9492 | |
9493 | DEFVAR_LISP ("default-process-coding-system", | |
9494 | &Vdefault_process_coding_system, | |
48b0f3ae PJ |
9495 | doc: /* Cons of coding systems used for process I/O by default. |
9496 | The car part is used for decoding a process output, | |
9497 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 9498 | Vdefault_process_coding_system = Qnil; |
c4825358 | 9499 | |
3f003981 | 9500 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
df7492f9 KH |
9501 | doc: /* |
9502 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
9503 | This is a vector of length 256. |
9504 | If Nth element is non-nil, the existence of code N in a file | |
9505 | \(or output of subprocess) doesn't prevent it to be detected as | |
9506 | a coding system of ISO 2022 variant which has a flag | |
9507 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
9508 | or reading output of a subprocess. | |
9509 | Only 128th through 159th elements has a meaning. */); | |
3f003981 | 9510 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
9511 | |
9512 | DEFVAR_LISP ("select-safe-coding-system-function", | |
9513 | &Vselect_safe_coding_system_function, | |
df7492f9 KH |
9514 | doc: /* |
9515 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
9516 | |
9517 | If set, this function is called to force a user to select a proper | |
9518 | coding system which can encode the text in the case that a default | |
9519 | coding system used in each operation can't encode the text. | |
9520 | ||
9521 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
9522 | Vselect_safe_coding_system_function = Qnil; |
9523 | ||
5d5bf4d8 KH |
9524 | DEFVAR_BOOL ("coding-system-require-warning", |
9525 | &coding_system_require_warning, | |
9526 | doc: /* Internal use only. | |
6b89e3aa KH |
9527 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
9528 | called even if `coding-system-for-write' is non-nil. The command | |
9529 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
9530 | coding_system_require_warning = 0; |
9531 | ||
9532 | ||
22ab2303 | 9533 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
74383408 | 9534 | &inhibit_iso_escape_detection, |
df7492f9 KH |
9535 | doc: /* |
9536 | If non-nil, Emacs ignores ISO2022's escape sequence on code detection. | |
48b0f3ae PJ |
9537 | |
9538 | By default, on reading a file, Emacs tries to detect how the text is | |
9539 | encoded. This code detection is sensitive to escape sequences. If | |
9540 | the sequence is valid as ISO2022, the code is determined as one of | |
9541 | the ISO2022 encodings, and the file is decoded by the corresponding | |
9542 | coding system (e.g. `iso-2022-7bit'). | |
9543 | ||
9544 | However, there may be a case that you want to read escape sequences in | |
9545 | a file as is. In such a case, you can set this variable to non-nil. | |
9546 | Then, as the code detection ignores any escape sequences, no file is | |
9547 | detected as encoded in some ISO2022 encoding. The result is that all | |
9548 | escape sequences become visible in a buffer. | |
9549 | ||
9550 | The default value is nil, and it is strongly recommended not to change | |
9551 | it. That is because many Emacs Lisp source files that contain | |
9552 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
9553 | in Emacs's distribution, and they won't be decoded correctly on | |
9554 | reading if you suppress escape sequence detection. | |
9555 | ||
9556 | The other way to read escape sequences in a file without decoding is | |
9557 | to explicitly specify some coding system that doesn't use ISO2022's | |
9558 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); | |
74383408 | 9559 | inhibit_iso_escape_detection = 0; |
002fdb44 DL |
9560 | |
9561 | DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input, | |
15c8f9d1 DL |
9562 | doc: /* Char table for translating self-inserting characters. |
9563 | This is applied to the result of input methods, not their input. See also | |
9564 | `keyboard-translate-table'. */); | |
002fdb44 | 9565 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 9566 | |
2c78b7e1 KH |
9567 | { |
9568 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 9569 | Lisp_Object plist[16]; |
2c78b7e1 KH |
9570 | int i; |
9571 | ||
9572 | for (i = 0; i < coding_arg_max; i++) | |
9573 | args[i] = Qnil; | |
9574 | ||
9575 | plist[0] = intern (":name"); | |
9576 | plist[1] = args[coding_arg_name] = Qno_conversion; | |
9577 | plist[2] = intern (":mnemonic"); | |
9578 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); | |
9579 | plist[4] = intern (":coding-type"); | |
9580 | plist[5] = args[coding_arg_coding_type] = Qraw_text; | |
9581 | plist[6] = intern (":ascii-compatible-p"); | |
9582 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; | |
9583 | plist[8] = intern (":default-char"); | |
9584 | plist[9] = args[coding_arg_default_char] = make_number (0); | |
8f924df7 KH |
9585 | plist[10] = intern (":for-unibyte"); |
9586 | plist[11] = args[coding_arg_for_unibyte] = Qt; | |
9587 | plist[12] = intern (":docstring"); | |
9588 | plist[13] = build_string ("Do no conversion.\n\ | |
2c78b7e1 KH |
9589 | \n\ |
9590 | When you visit a file with this coding, the file is read into a\n\ | |
9591 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
9592 | character."); | |
8f924df7 KH |
9593 | plist[14] = intern (":eol-type"); |
9594 | plist[15] = args[coding_arg_eol_type] = Qunix; | |
9595 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 KH |
9596 | Fdefine_coding_system_internal (coding_arg_max, args); |
9597 | } | |
9598 | ||
9599 | setup_coding_system (Qno_conversion, &keyboard_coding); | |
9600 | setup_coding_system (Qno_conversion, &terminal_coding); | |
9601 | setup_coding_system (Qno_conversion, &safe_terminal_coding); | |
ff563fce KH |
9602 | |
9603 | { | |
9604 | int i; | |
9605 | ||
9606 | for (i = 0; i < coding_category_max; i++) | |
9607 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
9608 | } | |
4ed46869 KH |
9609 | } |
9610 | ||
68c45bf0 PE |
9611 | char * |
9612 | emacs_strerror (error_number) | |
9613 | int error_number; | |
9614 | { | |
9615 | char *str; | |
9616 | ||
ca9c0567 | 9617 | synchronize_system_messages_locale (); |
68c45bf0 PE |
9618 | str = strerror (error_number); |
9619 | ||
9620 | if (! NILP (Vlocale_coding_system)) | |
9621 | { | |
9622 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
9623 | Vlocale_coding_system, | |
9624 | 0); | |
d5db4077 | 9625 | str = (char *) SDATA (dec); |
68c45bf0 PE |
9626 | } |
9627 | ||
9628 | return str; | |
9629 | } | |
9630 | ||
4ed46869 | 9631 | #endif /* emacs */ |
9ffd559c KH |
9632 | |
9633 | /* arch-tag: 3a3a2b01-5ff6-4071-9afe-f5b808d9229d | |
9634 | (do not change this comment) */ |