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++; | |
1352 | dst += CHAR_STRING (c, dst); | |
1353 | produced_chars++; | |
4ed46869 KH |
1354 | } |
1355 | } | |
065e3595 | 1356 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1357 | coding->produced_char += produced_chars; |
1358 | coding->produced = dst - coding->destination; | |
1359 | return 0; | |
4ed46869 KH |
1360 | } |
1361 | ||
b73bfc1c | 1362 | |
df7492f9 | 1363 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
1364 | Check if a text is encoded in one of UTF-16 based coding systems. |
1365 | If it is, return 1, else return 0. */ | |
aa72b389 | 1366 | |
df7492f9 KH |
1367 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1368 | (((val) & 0xFC00) == 0xD800) | |
1369 | ||
1370 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1371 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1372 | |
df7492f9 KH |
1373 | #define UTF_16_INVALID_P(val) \ |
1374 | (((val) == 0xFFFE) \ | |
1375 | || ((val) == 0xFFFF) \ | |
1376 | || UTF_16_LOW_SURROGATE_P (val)) | |
aa72b389 | 1377 | |
aa72b389 | 1378 | |
df7492f9 | 1379 | static int |
ff0dacd7 | 1380 | detect_coding_utf_16 (coding, detect_info) |
aa72b389 | 1381 | struct coding_system *coding; |
ff0dacd7 | 1382 | struct coding_detection_info *detect_info; |
aa72b389 | 1383 | { |
8f924df7 KH |
1384 | const unsigned char *src = coding->source, *src_base = src; |
1385 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
1386 | int multibytep = coding->src_multibyte; |
1387 | int consumed_chars = 0; | |
1388 | int c1, c2; | |
aa72b389 | 1389 | |
ff0dacd7 | 1390 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1391 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1392 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1393 | { |
1394 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1395 | return 0; | |
1396 | } | |
24a73b0a | 1397 | |
df7492f9 KH |
1398 | ONE_MORE_BYTE (c1); |
1399 | ONE_MORE_BYTE (c2); | |
df7492f9 | 1400 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1401 | { |
b49a1807 KH |
1402 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1403 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1404 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1405 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1406 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1407 | } |
df7492f9 | 1408 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1409 | { |
b49a1807 KH |
1410 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1411 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1412 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1413 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1414 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1415 | } | |
065e3595 | 1416 | else if (c1 >= 0 && c2 >= 0) |
24a73b0a KH |
1417 | { |
1418 | unsigned char b1[256], b2[256]; | |
1419 | int b1_variants = 1, b2_variants = 1; | |
1420 | int n; | |
1421 | ||
1422 | bzero (b1, 256), bzero (b2, 256); | |
1423 | b1[c1]++, b2[c2]++; | |
1424 | for (n = 0; n < 256 && src < src_end; n++) | |
1425 | { | |
065e3595 | 1426 | src_base = src; |
24a73b0a KH |
1427 | ONE_MORE_BYTE (c1); |
1428 | ONE_MORE_BYTE (c2); | |
065e3595 KH |
1429 | if (c1 < 0 || c2 < 0) |
1430 | break; | |
24a73b0a KH |
1431 | if (! b1[c1++]) b1_variants++; |
1432 | if (! b2[c2++]) b2_variants++; | |
1433 | } | |
1434 | if (b1_variants < b2_variants) | |
1435 | detect_info->found |= CATEGORY_MASK_UTF_16_BE_NOSIG; | |
1436 | else | |
1437 | detect_info->found |= CATEGORY_MASK_UTF_16_LE_NOSIG; | |
1438 | detect_info->rejected | |
1439 | |= (CATEGORY_MASK_UTF_16_BE | CATEGORY_MASK_UTF_16_LE); | |
ff0dacd7 | 1440 | } |
df7492f9 | 1441 | no_more_source: |
ff0dacd7 | 1442 | return 1; |
df7492f9 | 1443 | } |
aa72b389 | 1444 | |
df7492f9 KH |
1445 | static void |
1446 | decode_coding_utf_16 (coding) | |
1447 | struct coding_system *coding; | |
1448 | { | |
8f924df7 KH |
1449 | const unsigned char *src = coding->source + coding->consumed; |
1450 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1451 | const unsigned char *src_base; | |
69a80ea3 KH |
1452 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1453 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
1454 | int consumed_chars = 0, consumed_chars_base; |
1455 | int multibytep = coding->src_multibyte; | |
1456 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1457 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); | |
1458 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
24a73b0a | 1459 | Lisp_Object attr, charset_list; |
df7492f9 | 1460 | |
24a73b0a | 1461 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1462 | |
b49a1807 | 1463 | if (bom == utf_16_with_bom) |
aa72b389 | 1464 | { |
df7492f9 | 1465 | int c, c1, c2; |
4af310db | 1466 | |
aa72b389 | 1467 | src_base = src; |
df7492f9 KH |
1468 | ONE_MORE_BYTE (c1); |
1469 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1470 | c = (c1 << 8) | c2; |
aa72b389 | 1471 | |
b49a1807 KH |
1472 | if (endian == utf_16_big_endian |
1473 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1474 | { |
b49a1807 KH |
1475 | /* The first two bytes are not BOM. Treat them as bytes |
1476 | for a normal character. */ | |
1477 | src = src_base; | |
1478 | coding->errors++; | |
aa72b389 | 1479 | } |
b49a1807 KH |
1480 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1481 | } | |
1482 | else if (bom == utf_16_detect_bom) | |
1483 | { | |
1484 | /* We have already tried to detect BOM and failed in | |
1485 | detect_coding. */ | |
1486 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; | |
df7492f9 | 1487 | } |
aa72b389 | 1488 | |
df7492f9 KH |
1489 | while (1) |
1490 | { | |
1491 | int c, c1, c2; | |
1492 | ||
1493 | src_base = src; | |
1494 | consumed_chars_base = consumed_chars; | |
1495 | ||
1496 | if (charbuf + 2 >= charbuf_end) | |
1497 | break; | |
1498 | ||
1499 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1500 | if (c1 < 0) |
1501 | { | |
1502 | *charbuf++ = -c1; | |
1503 | continue; | |
1504 | } | |
df7492f9 | 1505 | ONE_MORE_BYTE (c2); |
065e3595 KH |
1506 | if (c2 < 0) |
1507 | { | |
1508 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1509 | *charbuf++ = -c2; | |
1510 | continue; | |
1511 | } | |
df7492f9 | 1512 | c = (endian == utf_16_big_endian |
e19c3639 | 1513 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
df7492f9 | 1514 | if (surrogate) |
fd3ae0b9 | 1515 | { |
df7492f9 | 1516 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1517 | { |
df7492f9 KH |
1518 | if (endian == utf_16_big_endian) |
1519 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1520 | else | |
1521 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1522 | *charbuf++ = c1; | |
1523 | *charbuf++ = c2; | |
1524 | coding->errors++; | |
1525 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1526 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1527 | else |
df7492f9 | 1528 | *charbuf++ = c; |
fd3ae0b9 KH |
1529 | } |
1530 | else | |
df7492f9 KH |
1531 | { |
1532 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1533 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1534 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1535 | } |
fd3ae0b9 | 1536 | } |
aa72b389 | 1537 | else |
df7492f9 KH |
1538 | { |
1539 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1540 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1541 | else | |
1542 | *charbuf++ = c; | |
8f924df7 | 1543 | } |
aa72b389 | 1544 | } |
df7492f9 KH |
1545 | |
1546 | no_more_source: | |
1547 | coding->consumed_char += consumed_chars_base; | |
1548 | coding->consumed = src_base - coding->source; | |
1549 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1550 | } |
b73bfc1c | 1551 | |
df7492f9 KH |
1552 | static int |
1553 | encode_coding_utf_16 (coding) | |
1554 | struct coding_system *coding; | |
1555 | { | |
1556 | int multibytep = coding->dst_multibyte; | |
1557 | int *charbuf = coding->charbuf; | |
1558 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1559 | unsigned char *dst = coding->destination + coding->produced; | |
1560 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1561 | int safe_room = 8; | |
1562 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1563 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; | |
1564 | int produced_chars = 0; | |
24a73b0a | 1565 | Lisp_Object attrs, charset_list; |
df7492f9 | 1566 | int c; |
4ed46869 | 1567 | |
24a73b0a | 1568 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 1569 | |
b49a1807 | 1570 | if (bom != utf_16_without_bom) |
df7492f9 KH |
1571 | { |
1572 | ASSURE_DESTINATION (safe_room); | |
1573 | if (big_endian) | |
df7492f9 | 1574 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1575 | else |
1576 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
df7492f9 KH |
1577 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1578 | } | |
1579 | ||
1580 | while (charbuf < charbuf_end) | |
1581 | { | |
1582 | ASSURE_DESTINATION (safe_room); | |
1583 | c = *charbuf++; | |
e19c3639 KH |
1584 | if (c >= MAX_UNICODE_CHAR) |
1585 | c = coding->default_char; | |
df7492f9 KH |
1586 | |
1587 | if (c < 0x10000) | |
1588 | { | |
1589 | if (big_endian) | |
1590 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1591 | else | |
1592 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1593 | } | |
1594 | else | |
1595 | { | |
1596 | int c1, c2; | |
1597 | ||
1598 | c -= 0x10000; | |
1599 | c1 = (c >> 10) + 0xD800; | |
1600 | c2 = (c & 0x3FF) + 0xDC00; | |
1601 | if (big_endian) | |
1602 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1603 | else | |
1604 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1605 | } | |
1606 | } | |
065e3595 | 1607 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1608 | coding->produced = dst - coding->destination; |
1609 | coding->produced_char += produced_chars; | |
1610 | return 0; | |
1611 | } | |
1612 | ||
1613 | \f | |
1614 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1615 | ||
1616 | /* Emacs' internal format for representation of multiple character | |
1617 | sets is a kind of multi-byte encoding, i.e. characters are | |
1618 | represented by variable-length sequences of one-byte codes. | |
1619 | ||
1620 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1621 | represented by one-byte sequences which are their ASCII codes, in | |
1622 | the range 0x00 through 0x7F. | |
1623 | ||
1624 | 8-bit characters of the range 0x80..0x9F are represented by | |
1625 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1626 | code + 0x20). | |
1627 | ||
1628 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1629 | one-byte sequences which are their 8-bit code. | |
1630 | ||
1631 | The other characters are represented by a sequence of `base | |
1632 | leading-code', optional `extended leading-code', and one or two | |
1633 | `position-code's. The length of the sequence is determined by the | |
1634 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1635 | whereas extended leading-code and position-code take the range 0xA0 | |
1636 | through 0xFF. See `charset.h' for more details about leading-code | |
1637 | and position-code. | |
1638 | ||
1639 | --- CODE RANGE of Emacs' internal format --- | |
1640 | character set range | |
1641 | ------------- ----- | |
1642 | ascii 0x00..0x7F | |
1643 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1644 | eight-bit-graphic 0xA0..0xBF | |
1645 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1646 | --------------------------------------------- | |
1647 | ||
1648 | As this is the internal character representation, the format is | |
1649 | usually not used externally (i.e. in a file or in a data sent to a | |
1650 | process). But, it is possible to have a text externally in this | |
1651 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1652 | ||
1653 | In that case, a sequence of one-byte codes has a slightly different | |
1654 | form. | |
1655 | ||
1656 | At first, all characters in eight-bit-control are represented by | |
1657 | one-byte sequences which are their 8-bit code. | |
1658 | ||
1659 | Next, character composition data are represented by the byte | |
1660 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1661 | where, | |
1662 | METHOD is 0xF0 plus one of composition method (enum | |
1663 | composition_method), | |
1664 | ||
1665 | BYTES is 0xA0 plus a byte length of this composition data, | |
1666 | ||
1667 | CHARS is 0x20 plus a number of characters composed by this | |
1668 | data, | |
1669 | ||
1670 | COMPONENTs are characters of multibye form or composition | |
1671 | rules encoded by two-byte of ASCII codes. | |
1672 | ||
1673 | In addition, for backward compatibility, the following formats are | |
1674 | also recognized as composition data on decoding. | |
1675 | ||
1676 | 0x80 MSEQ ... | |
1677 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1678 | ||
1679 | Here, | |
1680 | MSEQ is a multibyte form but in these special format: | |
1681 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1682 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1683 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1684 | represents a composition rule. | |
1685 | */ | |
1686 | ||
1687 | char emacs_mule_bytes[256]; | |
1688 | ||
df7492f9 | 1689 | int |
ff0dacd7 | 1690 | emacs_mule_char (coding, src, nbytes, nchars, id) |
df7492f9 | 1691 | struct coding_system *coding; |
065e3595 | 1692 | const unsigned char *src; |
ff0dacd7 | 1693 | int *nbytes, *nchars, *id; |
df7492f9 | 1694 | { |
8f924df7 KH |
1695 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1696 | const unsigned char *src_base = src; | |
df7492f9 | 1697 | int multibytep = coding->src_multibyte; |
df7492f9 KH |
1698 | struct charset *charset; |
1699 | unsigned code; | |
1700 | int c; | |
1701 | int consumed_chars = 0; | |
1702 | ||
1703 | ONE_MORE_BYTE (c); | |
065e3595 | 1704 | if (c < 0) |
df7492f9 | 1705 | { |
065e3595 KH |
1706 | c = -c; |
1707 | charset = emacs_mule_charset[0]; | |
1708 | } | |
1709 | else | |
1710 | { | |
1711 | switch (emacs_mule_bytes[c]) | |
b73bfc1c | 1712 | { |
065e3595 | 1713 | case 2: |
df7492f9 KH |
1714 | if (! (charset = emacs_mule_charset[c])) |
1715 | goto invalid_code; | |
1716 | ONE_MORE_BYTE (c); | |
9ffd559c | 1717 | if (c < 0xA0) |
065e3595 | 1718 | goto invalid_code; |
df7492f9 | 1719 | code = c & 0x7F; |
065e3595 KH |
1720 | break; |
1721 | ||
1722 | case 3: | |
1723 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
1724 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
1725 | { | |
1726 | ONE_MORE_BYTE (c); | |
9ffd559c | 1727 | if (c < 0xA0 || ! (charset = emacs_mule_charset[c])) |
065e3595 KH |
1728 | goto invalid_code; |
1729 | ONE_MORE_BYTE (c); | |
9ffd559c | 1730 | if (c < 0xA0) |
065e3595 KH |
1731 | goto invalid_code; |
1732 | code = c & 0x7F; | |
1733 | } | |
1734 | else | |
1735 | { | |
1736 | if (! (charset = emacs_mule_charset[c])) | |
1737 | goto invalid_code; | |
1738 | ONE_MORE_BYTE (c); | |
9ffd559c | 1739 | if (c < 0xA0) |
065e3595 KH |
1740 | goto invalid_code; |
1741 | code = (c & 0x7F) << 8; | |
1742 | ONE_MORE_BYTE (c); | |
9ffd559c | 1743 | if (c < 0xA0) |
065e3595 KH |
1744 | goto invalid_code; |
1745 | code |= c & 0x7F; | |
1746 | } | |
1747 | break; | |
1748 | ||
1749 | case 4: | |
1750 | ONE_MORE_BYTE (c); | |
1751 | if (c < 0 || ! (charset = emacs_mule_charset[c])) | |
df7492f9 KH |
1752 | goto invalid_code; |
1753 | ONE_MORE_BYTE (c); | |
9ffd559c | 1754 | if (c < 0xA0) |
065e3595 | 1755 | goto invalid_code; |
781d7a48 | 1756 | code = (c & 0x7F) << 8; |
df7492f9 | 1757 | ONE_MORE_BYTE (c); |
9ffd559c | 1758 | if (c < 0xA0) |
065e3595 | 1759 | goto invalid_code; |
df7492f9 | 1760 | code |= c & 0x7F; |
065e3595 | 1761 | break; |
df7492f9 | 1762 | |
065e3595 KH |
1763 | case 1: |
1764 | code = c; | |
1765 | charset = CHARSET_FROM_ID (ASCII_BYTE_P (code) | |
1766 | ? charset_ascii : charset_eight_bit); | |
1767 | break; | |
df7492f9 | 1768 | |
065e3595 KH |
1769 | default: |
1770 | abort (); | |
1771 | } | |
1772 | c = DECODE_CHAR (charset, code); | |
1773 | if (c < 0) | |
1774 | goto invalid_code; | |
df7492f9 | 1775 | } |
df7492f9 KH |
1776 | *nbytes = src - src_base; |
1777 | *nchars = consumed_chars; | |
ff0dacd7 KH |
1778 | if (id) |
1779 | *id = charset->id; | |
df7492f9 KH |
1780 | return c; |
1781 | ||
1782 | no_more_source: | |
1783 | return -2; | |
1784 | ||
1785 | invalid_code: | |
1786 | return -1; | |
1787 | } | |
1788 | ||
1789 | ||
1790 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1791 | Check if a text is encoded in `emacs-mule'. If it is, return 1, |
1792 | else return 0. */ | |
df7492f9 KH |
1793 | |
1794 | static int | |
ff0dacd7 | 1795 | detect_coding_emacs_mule (coding, detect_info) |
df7492f9 | 1796 | struct coding_system *coding; |
ff0dacd7 | 1797 | struct coding_detection_info *detect_info; |
df7492f9 | 1798 | { |
065e3595 | 1799 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1800 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1801 | int multibytep = coding->src_multibyte; |
1802 | int consumed_chars = 0; | |
1803 | int c; | |
1804 | int found = 0; | |
1805 | ||
ff0dacd7 | 1806 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1807 | /* A coding system of this category is always ASCII compatible. */ |
1808 | src += coding->head_ascii; | |
1809 | ||
1810 | while (1) | |
1811 | { | |
065e3595 | 1812 | src_base = src; |
df7492f9 | 1813 | ONE_MORE_BYTE (c); |
065e3595 KH |
1814 | if (c < 0) |
1815 | continue; | |
df7492f9 KH |
1816 | if (c == 0x80) |
1817 | { | |
1818 | /* Perhaps the start of composite character. We simple skip | |
1819 | it because analyzing it is too heavy for detecting. But, | |
1820 | at least, we check that the composite character | |
1821 | constitues of more than 4 bytes. */ | |
8f924df7 | 1822 | const unsigned char *src_base; |
df7492f9 KH |
1823 | |
1824 | repeat: | |
1825 | src_base = src; | |
1826 | do | |
1827 | { | |
1828 | ONE_MORE_BYTE (c); | |
1829 | } | |
1830 | while (c >= 0xA0); | |
1831 | ||
1832 | if (src - src_base <= 4) | |
1833 | break; | |
ff0dacd7 | 1834 | found = CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1835 | if (c == 0x80) |
1836 | goto repeat; | |
b73bfc1c | 1837 | } |
df7492f9 KH |
1838 | |
1839 | if (c < 0x80) | |
b73bfc1c | 1840 | { |
df7492f9 KH |
1841 | if (c < 0x20 |
1842 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1843 | break; | |
1844 | } | |
1845 | else | |
1846 | { | |
0e219d54 | 1847 | int more_bytes = emacs_mule_bytes[*src_base] - 1; |
df7492f9 | 1848 | |
0e219d54 | 1849 | while (more_bytes > 0) |
df7492f9 KH |
1850 | { |
1851 | ONE_MORE_BYTE (c); | |
0e219d54 KH |
1852 | if (c < 0xA0) |
1853 | { | |
1854 | src--; /* Unread the last byte. */ | |
1855 | break; | |
1856 | } | |
1857 | more_bytes--; | |
df7492f9 | 1858 | } |
0e219d54 | 1859 | if (more_bytes != 0) |
df7492f9 | 1860 | break; |
ff0dacd7 | 1861 | found = CATEGORY_MASK_EMACS_MULE; |
4ed46869 KH |
1862 | } |
1863 | } | |
ff0dacd7 | 1864 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1865 | return 0; |
1866 | ||
1867 | no_more_source: | |
065e3595 | 1868 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 1869 | { |
ff0dacd7 | 1870 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
89528eb3 KH |
1871 | return 0; |
1872 | } | |
ff0dacd7 KH |
1873 | detect_info->found |= found; |
1874 | return 1; | |
4ed46869 KH |
1875 | } |
1876 | ||
b73bfc1c | 1877 | |
df7492f9 KH |
1878 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
1879 | ||
1880 | /* Decode a character represented as a component of composition | |
1881 | sequence of Emacs 20/21 style at SRC. Set C to that character and | |
1882 | update SRC to the head of next character (or an encoded composition | |
1883 | rule). If SRC doesn't points a composition component, set C to -1. | |
1884 | If SRC points an invalid byte sequence, global exit by a return | |
1885 | value 0. */ | |
1886 | ||
1887 | #define DECODE_EMACS_MULE_COMPOSITION_CHAR(buf) \ | |
1888 | if (1) \ | |
1889 | { \ | |
1890 | int c; \ | |
1891 | int nbytes, nchars; \ | |
1892 | \ | |
1893 | if (src == src_end) \ | |
1894 | break; \ | |
ff0dacd7 | 1895 | c = emacs_mule_char (coding, src, &nbytes, &nchars, NULL);\ |
df7492f9 KH |
1896 | if (c < 0) \ |
1897 | { \ | |
1898 | if (c == -2) \ | |
1899 | break; \ | |
1900 | goto invalid_code; \ | |
1901 | } \ | |
1902 | *buf++ = c; \ | |
1903 | src += nbytes; \ | |
1904 | consumed_chars += nchars; \ | |
1905 | } \ | |
1906 | else | |
1907 | ||
1908 | ||
1909 | /* Decode a composition rule represented as a component of composition | |
781d7a48 KH |
1910 | sequence of Emacs 20 style at SRC. Store the decoded rule in *BUF, |
1911 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1912 | to -1. */ | |
df7492f9 | 1913 | |
781d7a48 | 1914 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(buf) \ |
df7492f9 KH |
1915 | do { \ |
1916 | int c, gref, nref; \ | |
1917 | \ | |
781d7a48 | 1918 | if (src >= src_end) \ |
df7492f9 KH |
1919 | goto invalid_code; \ |
1920 | ONE_MORE_BYTE_NO_CHECK (c); \ | |
781d7a48 | 1921 | c -= 0x20; \ |
df7492f9 KH |
1922 | if (c < 0 || c >= 81) \ |
1923 | goto invalid_code; \ | |
1924 | \ | |
1925 | gref = c / 9, nref = c % 9; \ | |
1926 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1927 | } while (0) | |
1928 | ||
1929 | ||
781d7a48 KH |
1930 | /* Decode a composition rule represented as a component of composition |
1931 | sequence of Emacs 21 style at SRC. Store the decoded rule in *BUF, | |
1932 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1933 | to -1. */ | |
1934 | ||
1935 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(buf) \ | |
1936 | do { \ | |
1937 | int gref, nref; \ | |
1938 | \ | |
1939 | if (src + 1>= src_end) \ | |
1940 | goto invalid_code; \ | |
1941 | ONE_MORE_BYTE_NO_CHECK (gref); \ | |
1942 | gref -= 0x20; \ | |
1943 | ONE_MORE_BYTE_NO_CHECK (nref); \ | |
1944 | nref -= 0x20; \ | |
1945 | if (gref < 0 || gref >= 81 \ | |
1946 | || nref < 0 || nref >= 81) \ | |
1947 | goto invalid_code; \ | |
1948 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1949 | } while (0) | |
1950 | ||
1951 | ||
df7492f9 | 1952 | #define DECODE_EMACS_MULE_21_COMPOSITION(c) \ |
aa72b389 | 1953 | do { \ |
df7492f9 | 1954 | /* Emacs 21 style format. The first three bytes at SRC are \ |
781d7a48 | 1955 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is \ |
df7492f9 KH |
1956 | the byte length of this composition information, CHARS is the \ |
1957 | number of characters composed by this composition. */ \ | |
781d7a48 KH |
1958 | enum composition_method method = c - 0xF2; \ |
1959 | int *charbuf_base = charbuf; \ | |
df7492f9 KH |
1960 | int consumed_chars_limit; \ |
1961 | int nbytes, nchars; \ | |
1962 | \ | |
1963 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
1964 | if (c < 0) \ |
1965 | goto invalid_code; \ | |
df7492f9 KH |
1966 | nbytes = c - 0xA0; \ |
1967 | if (nbytes < 3) \ | |
1968 | goto invalid_code; \ | |
1969 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
1970 | if (c < 0) \ |
1971 | goto invalid_code; \ | |
df7492f9 | 1972 | nchars = c - 0xA0; \ |
69a80ea3 | 1973 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ |
df7492f9 KH |
1974 | consumed_chars_limit = consumed_chars_base + nbytes; \ |
1975 | if (method != COMPOSITION_RELATIVE) \ | |
aa72b389 | 1976 | { \ |
df7492f9 KH |
1977 | int i = 0; \ |
1978 | while (consumed_chars < consumed_chars_limit) \ | |
aa72b389 | 1979 | { \ |
df7492f9 | 1980 | if (i % 2 && method != COMPOSITION_WITH_ALTCHARS) \ |
781d7a48 | 1981 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (charbuf); \ |
df7492f9 KH |
1982 | else \ |
1983 | DECODE_EMACS_MULE_COMPOSITION_CHAR (charbuf); \ | |
781d7a48 | 1984 | i++; \ |
aa72b389 | 1985 | } \ |
df7492f9 KH |
1986 | if (consumed_chars < consumed_chars_limit) \ |
1987 | goto invalid_code; \ | |
781d7a48 | 1988 | charbuf_base[0] -= i; \ |
aa72b389 KH |
1989 | } \ |
1990 | } while (0) | |
93dec019 | 1991 | |
aa72b389 | 1992 | |
df7492f9 KH |
1993 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION(c) \ |
1994 | do { \ | |
1995 | /* Emacs 20 style format for relative composition. */ \ | |
1996 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 1997 | enum composition_method method = COMPOSITION_RELATIVE; \ |
df7492f9 KH |
1998 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
1999 | int *buf = components; \ | |
2000 | int i, j; \ | |
2001 | \ | |
2002 | src = src_base; \ | |
2003 | ONE_MORE_BYTE (c); /* skip 0x80 */ \ | |
2004 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
2005 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
2006 | if (i < 2) \ | |
2007 | goto invalid_code; \ | |
69a80ea3 | 2008 | ADD_COMPOSITION_DATA (charbuf, i, method); \ |
df7492f9 KH |
2009 | for (j = 0; j < i; j++) \ |
2010 | *charbuf++ = components[j]; \ | |
2011 | } while (0) | |
2012 | ||
2013 | ||
2014 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION(c) \ | |
2015 | do { \ | |
2016 | /* Emacs 20 style format for rule-base composition. */ \ | |
2017 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 2018 | enum composition_method method = COMPOSITION_WITH_RULE; \ |
df7492f9 KH |
2019 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
2020 | int *buf = components; \ | |
2021 | int i, j; \ | |
2022 | \ | |
2023 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
2024 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
2025 | { \ | |
781d7a48 | 2026 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (buf); \ |
df7492f9 KH |
2027 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ |
2028 | } \ | |
2029 | if (i < 1 || (buf - components) % 2 == 0) \ | |
2030 | goto invalid_code; \ | |
2031 | if (charbuf + i + (i / 2) + 1 < charbuf_end) \ | |
2032 | goto no_more_source; \ | |
69a80ea3 | 2033 | ADD_COMPOSITION_DATA (buf, i, method); \ |
df7492f9 KH |
2034 | for (j = 0; j < i; j++) \ |
2035 | *charbuf++ = components[j]; \ | |
2036 | for (j = 0; j < i; j += 2) \ | |
2037 | *charbuf++ = components[j]; \ | |
2038 | } while (0) | |
2039 | ||
aa72b389 KH |
2040 | |
2041 | static void | |
df7492f9 | 2042 | decode_coding_emacs_mule (coding) |
aa72b389 | 2043 | struct coding_system *coding; |
aa72b389 | 2044 | { |
8f924df7 KH |
2045 | const unsigned char *src = coding->source + coding->consumed; |
2046 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2047 | const unsigned char *src_base; | |
69a80ea3 KH |
2048 | int *charbuf = coding->charbuf + coding->charbuf_used; |
2049 | int *charbuf_end | |
2050 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 | 2051 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2052 | int multibytep = coding->src_multibyte; |
24a73b0a | 2053 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2054 | int char_offset = coding->produced_char; |
2055 | int last_offset = char_offset; | |
2056 | int last_id = charset_ascii; | |
aa72b389 | 2057 | |
24a73b0a | 2058 | CODING_GET_INFO (coding, attrs, charset_list); |
aa72b389 | 2059 | |
aa72b389 KH |
2060 | while (1) |
2061 | { | |
df7492f9 KH |
2062 | int c; |
2063 | ||
aa72b389 | 2064 | src_base = src; |
df7492f9 KH |
2065 | consumed_chars_base = consumed_chars; |
2066 | ||
2067 | if (charbuf >= charbuf_end) | |
2068 | break; | |
aa72b389 | 2069 | |
df7492f9 | 2070 | ONE_MORE_BYTE (c); |
065e3595 KH |
2071 | if (c < 0) |
2072 | { | |
2073 | *charbuf++ = -c; | |
2074 | char_offset++; | |
2075 | } | |
2076 | else if (c < 0x80) | |
aa72b389 | 2077 | { |
df7492f9 KH |
2078 | *charbuf++ = c; |
2079 | char_offset++; | |
aa72b389 | 2080 | } |
df7492f9 KH |
2081 | else if (c == 0x80) |
2082 | { | |
df7492f9 | 2083 | ONE_MORE_BYTE (c); |
065e3595 KH |
2084 | if (c < 0) |
2085 | goto invalid_code; | |
781d7a48 KH |
2086 | if (c - 0xF2 >= COMPOSITION_RELATIVE |
2087 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) | |
df7492f9 KH |
2088 | DECODE_EMACS_MULE_21_COMPOSITION (c); |
2089 | else if (c < 0xC0) | |
2090 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (c); | |
2091 | else if (c == 0xFF) | |
2092 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (c); | |
2093 | else | |
2094 | goto invalid_code; | |
2095 | } | |
2096 | else if (c < 0xA0 && emacs_mule_bytes[c] > 1) | |
2097 | { | |
2098 | int nbytes, nchars; | |
ff0dacd7 KH |
2099 | int id; |
2100 | ||
781d7a48 KH |
2101 | src = src_base; |
2102 | consumed_chars = consumed_chars_base; | |
ff0dacd7 | 2103 | c = emacs_mule_char (coding, src, &nbytes, &nchars, &id); |
df7492f9 KH |
2104 | if (c < 0) |
2105 | { | |
2106 | if (c == -2) | |
2107 | break; | |
2108 | goto invalid_code; | |
2109 | } | |
ff0dacd7 KH |
2110 | if (last_id != id) |
2111 | { | |
2112 | if (last_id != charset_ascii) | |
69a80ea3 | 2113 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
2114 | last_id = id; |
2115 | last_offset = char_offset; | |
2116 | } | |
df7492f9 | 2117 | *charbuf++ = c; |
781d7a48 KH |
2118 | src += nbytes; |
2119 | consumed_chars += nchars; | |
df7492f9 KH |
2120 | char_offset++; |
2121 | } | |
2122 | continue; | |
2123 | ||
2124 | invalid_code: | |
2125 | src = src_base; | |
2126 | consumed_chars = consumed_chars_base; | |
2127 | ONE_MORE_BYTE (c); | |
2128 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2129 | char_offset++; |
df7492f9 KH |
2130 | coding->errors++; |
2131 | } | |
2132 | ||
2133 | no_more_source: | |
ff0dacd7 | 2134 | if (last_id != charset_ascii) |
69a80ea3 | 2135 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2136 | coding->consumed_char += consumed_chars_base; |
2137 | coding->consumed = src_base - coding->source; | |
2138 | coding->charbuf_used = charbuf - coding->charbuf; | |
2139 | } | |
2140 | ||
2141 | ||
2142 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2143 | do { \ | |
2144 | if (id < 0xA0) \ | |
2145 | codes[0] = id, codes[1] = 0; \ | |
2146 | else if (id < 0xE0) \ | |
2147 | codes[0] = 0x9A, codes[1] = id; \ | |
2148 | else if (id < 0xF0) \ | |
2149 | codes[0] = 0x9B, codes[1] = id; \ | |
2150 | else if (id < 0xF5) \ | |
2151 | codes[0] = 0x9C, codes[1] = id; \ | |
2152 | else \ | |
2153 | codes[0] = 0x9D, codes[1] = id; \ | |
2154 | } while (0); | |
2155 | ||
aa72b389 | 2156 | |
df7492f9 KH |
2157 | static int |
2158 | encode_coding_emacs_mule (coding) | |
2159 | struct coding_system *coding; | |
2160 | { | |
2161 | int multibytep = coding->dst_multibyte; | |
2162 | int *charbuf = coding->charbuf; | |
2163 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2164 | unsigned char *dst = coding->destination + coding->produced; | |
2165 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2166 | int safe_room = 8; | |
df7492f9 | 2167 | int produced_chars = 0; |
24a73b0a | 2168 | Lisp_Object attrs, charset_list; |
df7492f9 | 2169 | int c; |
ff0dacd7 | 2170 | int preferred_charset_id = -1; |
df7492f9 | 2171 | |
24a73b0a | 2172 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2173 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2174 | { | |
2175 | CODING_ATTR_CHARSET_LIST (attrs) | |
2176 | = charset_list = Vemacs_mule_charset_list; | |
2177 | } | |
df7492f9 KH |
2178 | |
2179 | while (charbuf < charbuf_end) | |
2180 | { | |
2181 | ASSURE_DESTINATION (safe_room); | |
2182 | c = *charbuf++; | |
ff0dacd7 KH |
2183 | |
2184 | if (c < 0) | |
2185 | { | |
2186 | /* Handle an annotation. */ | |
2187 | switch (*charbuf) | |
2188 | { | |
2189 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2190 | /* Not yet implemented. */ | |
2191 | break; | |
2192 | case CODING_ANNOTATE_CHARSET_MASK: | |
2193 | preferred_charset_id = charbuf[3]; | |
2194 | if (preferred_charset_id >= 0 | |
2195 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2196 | charset_list))) | |
2197 | preferred_charset_id = -1; | |
2198 | break; | |
2199 | default: | |
2200 | abort (); | |
2201 | } | |
2202 | charbuf += -c - 1; | |
2203 | continue; | |
2204 | } | |
2205 | ||
df7492f9 KH |
2206 | if (ASCII_CHAR_P (c)) |
2207 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2208 | else if (CHAR_BYTE8_P (c)) |
2209 | { | |
2210 | c = CHAR_TO_BYTE8 (c); | |
2211 | EMIT_ONE_BYTE (c); | |
2212 | } | |
df7492f9 | 2213 | else |
aa72b389 | 2214 | { |
df7492f9 KH |
2215 | struct charset *charset; |
2216 | unsigned code; | |
2217 | int dimension; | |
2218 | int emacs_mule_id; | |
2219 | unsigned char leading_codes[2]; | |
2220 | ||
ff0dacd7 KH |
2221 | if (preferred_charset_id >= 0) |
2222 | { | |
2223 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
2224 | if (! CHAR_CHARSET_P (c, charset)) | |
2225 | charset = char_charset (c, charset_list, NULL); | |
2226 | } | |
2227 | else | |
2228 | charset = char_charset (c, charset_list, &code); | |
df7492f9 KH |
2229 | if (! charset) |
2230 | { | |
2231 | c = coding->default_char; | |
2232 | if (ASCII_CHAR_P (c)) | |
2233 | { | |
2234 | EMIT_ONE_ASCII_BYTE (c); | |
2235 | continue; | |
2236 | } | |
2237 | charset = char_charset (c, charset_list, &code); | |
2238 | } | |
2239 | dimension = CHARSET_DIMENSION (charset); | |
2240 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2241 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2242 | EMIT_ONE_BYTE (leading_codes[0]); | |
2243 | if (leading_codes[1]) | |
2244 | EMIT_ONE_BYTE (leading_codes[1]); | |
2245 | if (dimension == 1) | |
1fa663f9 | 2246 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2247 | else |
df7492f9 | 2248 | { |
1fa663f9 | 2249 | code |= 0x8080; |
df7492f9 KH |
2250 | EMIT_ONE_BYTE (code >> 8); |
2251 | EMIT_ONE_BYTE (code & 0xFF); | |
2252 | } | |
aa72b389 | 2253 | } |
aa72b389 | 2254 | } |
065e3595 | 2255 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2256 | coding->produced_char += produced_chars; |
2257 | coding->produced = dst - coding->destination; | |
2258 | return 0; | |
aa72b389 | 2259 | } |
b73bfc1c | 2260 | |
4ed46869 | 2261 | \f |
df7492f9 | 2262 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2263 | |
2264 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2265 | Since the intention of this note is to help understand the |
5a936b46 | 2266 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2267 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2268 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2269 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2270 | |
2271 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2272 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2273 | is encoded using bytes less than 128. This may make the encoded |
2274 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2275 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2276 | Significant Bit). |
b73bfc1c | 2277 | |
cfb43547 DL |
2278 | There are two kinds of character sets: control character sets and |
2279 | graphic character sets. The former contain control characters such | |
4ed46869 | 2280 | as `newline' and `escape' to provide control functions (control |
39787efd | 2281 | functions are also provided by escape sequences). The latter |
cfb43547 | 2282 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2283 | two control character sets and many graphic character sets. |
2284 | ||
2285 | Graphic character sets are classified into one of the following | |
39787efd KH |
2286 | four classes, according to the number of bytes (DIMENSION) and |
2287 | number of characters in one dimension (CHARS) of the set: | |
2288 | - DIMENSION1_CHARS94 | |
2289 | - DIMENSION1_CHARS96 | |
2290 | - DIMENSION2_CHARS94 | |
2291 | - DIMENSION2_CHARS96 | |
2292 | ||
2293 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2294 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2295 | hereafter). The <F> of each character set is decided by ECMA(*) |
2296 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2297 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2298 | |
2299 | Note (*): ECMA = European Computer Manufacturers Association | |
2300 | ||
cfb43547 | 2301 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2302 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2303 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2304 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2305 | o DIMENSION2_CHARS96 -- none for the moment | |
2306 | ||
39787efd | 2307 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2308 | C0 [0x00..0x1F] -- control character plane 0 |
2309 | GL [0x20..0x7F] -- graphic character plane 0 | |
2310 | C1 [0x80..0x9F] -- control character plane 1 | |
2311 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2312 | ||
2313 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2314 | C1 by an escape sequence. The most common case is that: |
2315 | - ISO646's control character set is designated/invoked to C0, and | |
2316 | - ISO6429's control character set is designated/invoked to C1, | |
2317 | and usually these designations/invocations are omitted in encoded | |
2318 | text. In a 7-bit environment, only C0 can be used, and a control | |
2319 | character for C1 is encoded by an appropriate escape sequence to | |
2320 | fit into the environment. All control characters for C1 are | |
2321 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2322 | |
2323 | A graphic character set is at first designated to one of four | |
2324 | graphic registers (G0 through G3), then these graphic registers are | |
2325 | invoked to GL or GR. These designations and invocations can be | |
2326 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2327 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2328 | these invocations and designations are omitted in encoded text. | |
2329 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2330 | |
39787efd KH |
2331 | When a graphic character set of CHARS94 is invoked to GL, codes |
2332 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2333 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2334 | be used. | |
4ed46869 KH |
2335 | |
2336 | There are two ways of invocation: locking-shift and single-shift. | |
2337 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2338 | invocation, whereas with single-shift, the invocation affects the |
2339 | following character only and doesn't affect the locking-shift | |
2340 | state. Invocations are done by the following control characters or | |
2341 | escape sequences: | |
4ed46869 KH |
2342 | |
2343 | ---------------------------------------------------------------------- | |
39787efd | 2344 | abbrev function cntrl escape seq description |
4ed46869 | 2345 | ---------------------------------------------------------------------- |
39787efd KH |
2346 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2347 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2348 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2349 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2350 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2351 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2352 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2353 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2354 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2355 | ---------------------------------------------------------------------- |
39787efd KH |
2356 | (*) These are not used by any known coding system. |
2357 | ||
2358 | Control characters for these functions are defined by macros | |
2359 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2360 | |
39787efd | 2361 | Designations are done by the following escape sequences: |
4ed46869 KH |
2362 | ---------------------------------------------------------------------- |
2363 | escape sequence description | |
2364 | ---------------------------------------------------------------------- | |
2365 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2366 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2367 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2368 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2369 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2370 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2371 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2372 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2373 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2374 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2375 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2376 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2377 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2378 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2379 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2380 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2381 | ---------------------------------------------------------------------- | |
2382 | ||
2383 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2384 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2385 | |
2386 | Note (*): Although these designations are not allowed in ISO2022, | |
2387 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2388 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2389 | 7-bit environment, non-locking-shift, and non-single-shift. |
2390 | ||
2391 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2392 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2393 | |
cfb43547 | 2394 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2395 | same multilingual text in ISO2022. Actually, there exist many |
2396 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2397 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2398 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2399 | localized platforms), and all of these are variants of ISO2022. |
2400 | ||
2401 | In addition to the above, Emacs handles two more kinds of escape | |
2402 | sequences: ISO6429's direction specification and Emacs' private | |
2403 | sequence for specifying character composition. | |
2404 | ||
39787efd | 2405 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2406 | o CSI ']' -- end of the current direction |
2407 | o CSI '0' ']' -- end of the current direction | |
2408 | o CSI '1' ']' -- start of left-to-right text | |
2409 | o CSI '2' ']' -- start of right-to-left text | |
2410 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2411 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2412 | ||
2413 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2414 | o ESC '0' -- start relative composition |
2415 | o ESC '1' -- end composition | |
2416 | o ESC '2' -- start rule-base composition (*) | |
2417 | o ESC '3' -- start relative composition with alternate chars (**) | |
2418 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2419 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2420 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2421 | |
5a936b46 DL |
2422 | (*) This form is used only in Emacs 20.7 and older versions, |
2423 | but newer versions can safely decode it. | |
cfb43547 | 2424 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2425 | and older versions can't decode it. |
ec6d2bb8 | 2426 | |
cfb43547 | 2427 | Here's a list of example usages of these composition escape |
b73bfc1c | 2428 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2429 | |
b73bfc1c | 2430 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2431 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2432 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2433 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2434 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2435 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2436 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2437 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2438 | |
2439 | enum iso_code_class_type iso_code_class[256]; | |
2440 | ||
df7492f9 KH |
2441 | #define SAFE_CHARSET_P(coding, id) \ |
2442 | ((id) <= (coding)->max_charset_id \ | |
2443 | && (coding)->safe_charsets[id] >= 0) | |
2444 | ||
2445 | ||
2446 | #define SHIFT_OUT_OK(category) \ | |
2447 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
2448 | ||
2449 | static void | |
f0064e1f DL |
2450 | setup_iso_safe_charsets (attrs) |
2451 | Lisp_Object attrs; | |
df7492f9 KH |
2452 | { |
2453 | Lisp_Object charset_list, safe_charsets; | |
2454 | Lisp_Object request; | |
2455 | Lisp_Object reg_usage; | |
2456 | Lisp_Object tail; | |
2457 | int reg94, reg96; | |
2458 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
2459 | int max_charset_id; | |
2460 | ||
2461 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2462 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2463 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2464 | { | |
2465 | CODING_ATTR_CHARSET_LIST (attrs) | |
2466 | = charset_list = Viso_2022_charset_list; | |
2467 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
2468 | } | |
2469 | ||
2470 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2471 | return; | |
2472 | ||
2473 | max_charset_id = 0; | |
2474 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2475 | { | |
2476 | int id = XINT (XCAR (tail)); | |
2477 | if (max_charset_id < id) | |
2478 | max_charset_id = id; | |
2479 | } | |
d46c5b12 | 2480 | |
df7492f9 KH |
2481 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
2482 | make_number (255)); | |
2483 | request = AREF (attrs, coding_attr_iso_request); | |
2484 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2485 | reg94 = XINT (XCAR (reg_usage)); | |
2486 | reg96 = XINT (XCDR (reg_usage)); | |
2487 | ||
2488 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2489 | { | |
2490 | Lisp_Object id; | |
2491 | Lisp_Object reg; | |
2492 | struct charset *charset; | |
2493 | ||
2494 | id = XCAR (tail); | |
2495 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2496 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2497 | if (! NILP (reg)) |
8f924df7 | 2498 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2499 | else if (charset->iso_chars_96) |
2500 | { | |
2501 | if (reg96 < 4) | |
8f924df7 | 2502 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2503 | } |
2504 | else | |
2505 | { | |
2506 | if (reg94 < 4) | |
8f924df7 | 2507 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2508 | } |
2509 | } | |
2510 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2511 | } | |
d46c5b12 | 2512 | |
b6871cc7 | 2513 | |
4ed46869 | 2514 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
2515 | Check if a text is encoded in one of ISO-2022 based codig systems. |
2516 | If it is, return 1, else return 0. */ | |
4ed46869 | 2517 | |
0a28aafb | 2518 | static int |
ff0dacd7 | 2519 | detect_coding_iso_2022 (coding, detect_info) |
df7492f9 | 2520 | struct coding_system *coding; |
ff0dacd7 | 2521 | struct coding_detection_info *detect_info; |
4ed46869 | 2522 | { |
8f924df7 KH |
2523 | const unsigned char *src = coding->source, *src_base = src; |
2524 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 2525 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 2526 | int single_shifting = 0; |
df7492f9 KH |
2527 | int id; |
2528 | int c, c1; | |
2529 | int consumed_chars = 0; | |
2530 | int i; | |
ff0dacd7 KH |
2531 | int rejected = 0; |
2532 | int found = 0; | |
2533 | ||
2534 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2535 | |
2536 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2537 | { | |
2538 | struct coding_system *this = &(coding_categories[i]); | |
2539 | Lisp_Object attrs, val; | |
2540 | ||
2541 | attrs = CODING_ID_ATTRS (this->id); | |
2542 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
2543 | && ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs), Viso_2022_charset_list)) | |
2544 | setup_iso_safe_charsets (attrs); | |
2545 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
2546 | this->max_charset_id = SCHARS (val) - 1; |
2547 | this->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
2548 | } |
2549 | ||
2550 | /* A coding system of this category is always ASCII compatible. */ | |
2551 | src += coding->head_ascii; | |
3f003981 | 2552 | |
ff0dacd7 | 2553 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 2554 | { |
065e3595 | 2555 | src_base = src; |
df7492f9 | 2556 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2557 | switch (c) |
2558 | { | |
2559 | case ISO_CODE_ESC: | |
74383408 KH |
2560 | if (inhibit_iso_escape_detection) |
2561 | break; | |
f46869e4 | 2562 | single_shifting = 0; |
df7492f9 | 2563 | ONE_MORE_BYTE (c); |
d46c5b12 | 2564 | if (c >= '(' && c <= '/') |
4ed46869 | 2565 | { |
bf9cdd4e | 2566 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 2567 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2568 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2569 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
2570 | /* Invalid designation sequence. Just ignore. */ |
2571 | break; | |
bf9cdd4e KH |
2572 | } |
2573 | else if (c == '$') | |
2574 | { | |
2575 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 2576 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
2577 | if (c >= '@' && c <= 'B') |
2578 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
ff0dacd7 | 2579 | id = iso_charset_table[1][0][c]; |
bf9cdd4e | 2580 | else if (c >= '(' && c <= '/') |
bcf26d6a | 2581 | { |
df7492f9 | 2582 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2583 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2584 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
2585 | /* Invalid designation sequence. Just ignore. */ |
2586 | break; | |
bcf26d6a | 2587 | } |
bf9cdd4e | 2588 | else |
ff0dacd7 | 2589 | /* Invalid designation sequence. Just ignore it. */ |
d46c5b12 KH |
2590 | break; |
2591 | } | |
ae9ff118 | 2592 | else if (c == 'N' || c == 'O') |
d46c5b12 | 2593 | { |
ae9ff118 | 2594 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
2595 | single_shifting = 1; |
2596 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
d46c5b12 | 2597 | break; |
4ed46869 | 2598 | } |
ec6d2bb8 KH |
2599 | else if (c >= '0' && c <= '4') |
2600 | { | |
2601 | /* ESC <Fp> for start/end composition. */ | |
ff0dacd7 | 2602 | found |= CATEGORY_MASK_ISO; |
ec6d2bb8 KH |
2603 | break; |
2604 | } | |
bf9cdd4e | 2605 | else |
df7492f9 | 2606 | { |
ff0dacd7 | 2607 | /* Invalid escape sequence. Just ignore it. */ |
df7492f9 KH |
2608 | break; |
2609 | } | |
d46c5b12 KH |
2610 | |
2611 | /* We found a valid designation sequence for CHARSET. */ | |
ff0dacd7 | 2612 | rejected |= CATEGORY_MASK_ISO_8BIT; |
df7492f9 KH |
2613 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], |
2614 | id)) | |
ff0dacd7 | 2615 | found |= CATEGORY_MASK_ISO_7; |
d46c5b12 | 2616 | else |
ff0dacd7 | 2617 | rejected |= CATEGORY_MASK_ISO_7; |
df7492f9 KH |
2618 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], |
2619 | id)) | |
ff0dacd7 | 2620 | found |= CATEGORY_MASK_ISO_7_TIGHT; |
d46c5b12 | 2621 | else |
ff0dacd7 | 2622 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; |
df7492f9 KH |
2623 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], |
2624 | id)) | |
ff0dacd7 | 2625 | found |= CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 | 2626 | else |
ff0dacd7 | 2627 | rejected |= CATEGORY_MASK_ISO_7_ELSE; |
df7492f9 KH |
2628 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], |
2629 | id)) | |
ff0dacd7 | 2630 | found |= CATEGORY_MASK_ISO_8_ELSE; |
ae9ff118 | 2631 | else |
ff0dacd7 | 2632 | rejected |= CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
2633 | break; |
2634 | ||
4ed46869 | 2635 | case ISO_CODE_SO: |
d46c5b12 | 2636 | case ISO_CODE_SI: |
ff0dacd7 | 2637 | /* Locking shift out/in. */ |
74383408 KH |
2638 | if (inhibit_iso_escape_detection) |
2639 | break; | |
f46869e4 | 2640 | single_shifting = 0; |
ff0dacd7 KH |
2641 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
2642 | found |= CATEGORY_MASK_ISO_ELSE; | |
d46c5b12 KH |
2643 | break; |
2644 | ||
4ed46869 | 2645 | case ISO_CODE_CSI: |
ff0dacd7 | 2646 | /* Control sequence introducer. */ |
f46869e4 | 2647 | single_shifting = 0; |
ff0dacd7 KH |
2648 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2649 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
2650 | goto check_extra_latin; | |
2651 | ||
4ed46869 KH |
2652 | case ISO_CODE_SS2: |
2653 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
2654 | /* Single shift. */ |
2655 | if (inhibit_iso_escape_detection) | |
2656 | break; | |
75e2a253 | 2657 | single_shifting = 0; |
ff0dacd7 KH |
2658 | rejected |= CATEGORY_MASK_ISO_7BIT; |
2659 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2660 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 | 2661 | found |= CATEGORY_MASK_ISO_8_1, single_shifting = 1; |
ff0dacd7 KH |
2662 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
2663 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 KH |
2664 | found |= CATEGORY_MASK_ISO_8_2, single_shifting = 1; |
2665 | if (single_shifting) | |
2666 | break; | |
ff0dacd7 | 2667 | goto check_extra_latin; |
4ed46869 KH |
2668 | |
2669 | default: | |
065e3595 KH |
2670 | if (c < 0) |
2671 | continue; | |
4ed46869 | 2672 | if (c < 0x80) |
f46869e4 KH |
2673 | { |
2674 | single_shifting = 0; | |
2675 | break; | |
2676 | } | |
ff0dacd7 | 2677 | if (c >= 0xA0) |
c4825358 | 2678 | { |
ff0dacd7 KH |
2679 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2680 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 2681 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
2682 | 0xA0..0FF. If the byte length is even, we include |
2683 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
2684 | only when we are not single shifting. */ | |
2685 | if (! single_shifting | |
2686 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 2687 | { |
e17de821 | 2688 | int i = 1; |
b73bfc1c KH |
2689 | while (src < src_end) |
2690 | { | |
df7492f9 | 2691 | ONE_MORE_BYTE (c); |
b73bfc1c KH |
2692 | if (c < 0xA0) |
2693 | break; | |
2694 | i++; | |
2695 | } | |
2696 | ||
2697 | if (i & 1 && src < src_end) | |
ff0dacd7 | 2698 | rejected |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2699 | else |
ff0dacd7 | 2700 | found |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2701 | } |
ff0dacd7 | 2702 | break; |
4ed46869 | 2703 | } |
ff0dacd7 KH |
2704 | check_extra_latin: |
2705 | single_shifting = 0; | |
2706 | if (! VECTORP (Vlatin_extra_code_table) | |
2707 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
2708 | { | |
2709 | rejected = CATEGORY_MASK_ISO; | |
2710 | break; | |
2711 | } | |
2712 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2713 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2714 | found |= CATEGORY_MASK_ISO_8_1; | |
2715 | else | |
2716 | rejected |= CATEGORY_MASK_ISO_8_1; | |
75e2a253 | 2717 | rejected |= CATEGORY_MASK_ISO_8_2; |
4ed46869 KH |
2718 | } |
2719 | } | |
ff0dacd7 KH |
2720 | detect_info->rejected |= CATEGORY_MASK_ISO; |
2721 | return 0; | |
4ed46869 | 2722 | |
df7492f9 | 2723 | no_more_source: |
ff0dacd7 KH |
2724 | detect_info->rejected |= rejected; |
2725 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 2726 | return 1; |
4ed46869 | 2727 | } |
ec6d2bb8 | 2728 | |
4ed46869 | 2729 | |
134b9549 KH |
2730 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
2731 | escape sequence should be kept. */ | |
df7492f9 KH |
2732 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
2733 | do { \ | |
2734 | int id, prev; \ | |
2735 | \ | |
2736 | if (final < '0' || final >= 128 \ | |
2737 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
2738 | || !SAFE_CHARSET_P (coding, id)) \ | |
2739 | { \ | |
2740 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
2741 | chars_96 = -1; \ |
2742 | break; \ | |
df7492f9 KH |
2743 | } \ |
2744 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
2745 | if (id == charset_jisx0201_roman) \ |
2746 | { \ | |
2747 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
2748 | id = charset_ascii; \ | |
2749 | } \ | |
2750 | else if (id == charset_jisx0208_1978) \ | |
2751 | { \ | |
2752 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
2753 | id = charset_jisx0208; \ | |
2754 | } \ | |
df7492f9 KH |
2755 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
2756 | /* If there was an invalid designation to REG previously, and this \ | |
2757 | designation is ASCII to REG, we should keep this designation \ | |
2758 | sequence. */ \ | |
2759 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 2760 | chars_96 = -1; \ |
4ed46869 KH |
2761 | } while (0) |
2762 | ||
d46c5b12 | 2763 | |
df7492f9 KH |
2764 | #define MAYBE_FINISH_COMPOSITION() \ |
2765 | do { \ | |
2766 | int i; \ | |
2767 | if (composition_state == COMPOSING_NO) \ | |
2768 | break; \ | |
2769 | /* It is assured that we have enough room for producing \ | |
2770 | characters stored in the table `components'. */ \ | |
2771 | if (charbuf + component_idx > charbuf_end) \ | |
2772 | goto no_more_source; \ | |
2773 | composition_state = COMPOSING_NO; \ | |
2774 | if (method == COMPOSITION_RELATIVE \ | |
2775 | || method == COMPOSITION_WITH_ALTCHARS) \ | |
2776 | { \ | |
2777 | for (i = 0; i < component_idx; i++) \ | |
2778 | *charbuf++ = components[i]; \ | |
2779 | char_offset += component_idx; \ | |
2780 | } \ | |
2781 | else \ | |
2782 | { \ | |
2783 | for (i = 0; i < component_idx; i += 2) \ | |
2784 | *charbuf++ = components[i]; \ | |
2785 | char_offset += (component_idx / 2) + 1; \ | |
2786 | } \ | |
2787 | } while (0) | |
2788 | ||
d46c5b12 | 2789 | |
aa72b389 KH |
2790 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
2791 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 | |
2792 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
2793 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
2794 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
aa72b389 | 2795 | */ |
ec6d2bb8 | 2796 | |
df7492f9 KH |
2797 | #define DECODE_COMPOSITION_START(c1) \ |
2798 | do { \ | |
2799 | if (c1 == '0' \ | |
781d7a48 | 2800 | && composition_state == COMPOSING_COMPONENT_RULE) \ |
df7492f9 KH |
2801 | { \ |
2802 | component_len = component_idx; \ | |
2803 | composition_state = COMPOSING_CHAR; \ | |
2804 | } \ | |
2805 | else \ | |
2806 | { \ | |
8f924df7 | 2807 | const unsigned char *p; \ |
df7492f9 KH |
2808 | \ |
2809 | MAYBE_FINISH_COMPOSITION (); \ | |
2810 | if (charbuf + MAX_COMPOSITION_COMPONENTS > charbuf_end) \ | |
2811 | goto no_more_source; \ | |
2812 | for (p = src; p < src_end - 1; p++) \ | |
2813 | if (*p == ISO_CODE_ESC && p[1] == '1') \ | |
2814 | break; \ | |
2815 | if (p == src_end - 1) \ | |
2816 | { \ | |
2817 | if (coding->mode & CODING_MODE_LAST_BLOCK) \ | |
2818 | goto invalid_code; \ | |
2819 | goto no_more_source; \ | |
2820 | } \ | |
2821 | \ | |
2822 | /* This is surely the start of a composition. */ \ | |
2823 | method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
2824 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
2825 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
2826 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
2827 | composition_state = (c1 <= '2' ? COMPOSING_CHAR \ | |
2828 | : COMPOSING_COMPONENT_CHAR); \ | |
2829 | component_idx = component_len = 0; \ | |
2830 | } \ | |
ec6d2bb8 KH |
2831 | } while (0) |
2832 | ||
ec6d2bb8 | 2833 | |
df7492f9 KH |
2834 | /* Handle compositoin end sequence ESC 1. */ |
2835 | ||
2836 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 2837 | do { \ |
df7492f9 KH |
2838 | int nchars = (component_len > 0 ? component_idx - component_len \ |
2839 | : method == COMPOSITION_RELATIVE ? component_idx \ | |
2840 | : (component_idx + 1) / 2); \ | |
2841 | int i; \ | |
2842 | int *saved_charbuf = charbuf; \ | |
2843 | \ | |
69a80ea3 | 2844 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ |
df7492f9 | 2845 | if (method != COMPOSITION_RELATIVE) \ |
ec6d2bb8 | 2846 | { \ |
df7492f9 KH |
2847 | if (component_len == 0) \ |
2848 | for (i = 0; i < component_idx; i++) \ | |
2849 | *charbuf++ = components[i]; \ | |
2850 | else \ | |
2851 | for (i = 0; i < component_len; i++) \ | |
2852 | *charbuf++ = components[i]; \ | |
2853 | *saved_charbuf = saved_charbuf - charbuf; \ | |
ec6d2bb8 | 2854 | } \ |
df7492f9 KH |
2855 | if (method == COMPOSITION_WITH_RULE) \ |
2856 | for (i = 0; i < component_idx; i += 2, char_offset++) \ | |
2857 | *charbuf++ = components[i]; \ | |
ec6d2bb8 | 2858 | else \ |
df7492f9 KH |
2859 | for (i = component_len; i < component_idx; i++, char_offset++) \ |
2860 | *charbuf++ = components[i]; \ | |
2861 | coding->annotated = 1; \ | |
2862 | composition_state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
2863 | } while (0) |
2864 | ||
df7492f9 | 2865 | |
ec6d2bb8 KH |
2866 | /* Decode a composition rule from the byte C1 (and maybe one more byte |
2867 | from SRC) and store one encoded composition rule in | |
2868 | coding->cmp_data. */ | |
2869 | ||
2870 | #define DECODE_COMPOSITION_RULE(c1) \ | |
2871 | do { \ | |
ec6d2bb8 KH |
2872 | (c1) -= 32; \ |
2873 | if (c1 < 81) /* old format (before ver.21) */ \ | |
2874 | { \ | |
2875 | int gref = (c1) / 9; \ | |
2876 | int nref = (c1) % 9; \ | |
2877 | if (gref == 4) gref = 10; \ | |
2878 | if (nref == 4) nref = 10; \ | |
df7492f9 | 2879 | c1 = COMPOSITION_ENCODE_RULE (gref, nref); \ |
ec6d2bb8 | 2880 | } \ |
b73bfc1c | 2881 | else if (c1 < 93) /* new format (after ver.21) */ \ |
ec6d2bb8 KH |
2882 | { \ |
2883 | ONE_MORE_BYTE (c2); \ | |
df7492f9 | 2884 | c1 = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \ |
ec6d2bb8 | 2885 | } \ |
df7492f9 KH |
2886 | else \ |
2887 | c1 = 0; \ | |
ec6d2bb8 | 2888 | } while (0) |
88993dfd | 2889 | |
d46c5b12 | 2890 | |
4ed46869 KH |
2891 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
2892 | ||
b73bfc1c | 2893 | static void |
df7492f9 | 2894 | decode_coding_iso_2022 (coding) |
4ed46869 | 2895 | struct coding_system *coding; |
4ed46869 | 2896 | { |
8f924df7 KH |
2897 | const unsigned char *src = coding->source + coding->consumed; |
2898 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2899 | const unsigned char *src_base; | |
69a80ea3 | 2900 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ff0dacd7 | 2901 | int *charbuf_end |
69a80ea3 | 2902 | = coding->charbuf + coding->charbuf_size - 4 - MAX_ANNOTATION_LENGTH; |
df7492f9 | 2903 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2904 | int multibytep = coding->src_multibyte; |
4ed46869 | 2905 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
2906 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
2907 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 2908 | int charset_id_2, charset_id_3; |
df7492f9 KH |
2909 | struct charset *charset; |
2910 | int c; | |
2911 | /* For handling composition sequence. */ | |
2912 | #define COMPOSING_NO 0 | |
2913 | #define COMPOSING_CHAR 1 | |
2914 | #define COMPOSING_RULE 2 | |
2915 | #define COMPOSING_COMPONENT_CHAR 3 | |
2916 | #define COMPOSING_COMPONENT_RULE 4 | |
2917 | ||
2918 | int composition_state = COMPOSING_NO; | |
2919 | enum composition_method method; | |
2920 | int components[MAX_COMPOSITION_COMPONENTS * 2 + 1]; | |
2921 | int component_idx; | |
2922 | int component_len; | |
24a73b0a | 2923 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2924 | int char_offset = coding->produced_char; |
2925 | int last_offset = char_offset; | |
2926 | int last_id = charset_ascii; | |
df7492f9 | 2927 | |
24a73b0a | 2928 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 2929 | setup_iso_safe_charsets (attrs); |
b73bfc1c KH |
2930 | |
2931 | while (1) | |
4ed46869 | 2932 | { |
463f5630 | 2933 | int c1, c2; |
b73bfc1c KH |
2934 | |
2935 | src_base = src; | |
df7492f9 KH |
2936 | consumed_chars_base = consumed_chars; |
2937 | ||
2938 | if (charbuf >= charbuf_end) | |
2939 | break; | |
2940 | ||
b73bfc1c | 2941 | ONE_MORE_BYTE (c1); |
065e3595 KH |
2942 | if (c1 < 0) |
2943 | goto invalid_code; | |
4ed46869 | 2944 | |
98725083 | 2945 | /* We produce at most one character. */ |
4ed46869 KH |
2946 | switch (iso_code_class [c1]) |
2947 | { | |
2948 | case ISO_0x20_or_0x7F: | |
df7492f9 | 2949 | if (composition_state != COMPOSING_NO) |
ec6d2bb8 | 2950 | { |
df7492f9 KH |
2951 | if (composition_state == COMPOSING_RULE |
2952 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2953 | { | |
2954 | DECODE_COMPOSITION_RULE (c1); | |
2955 | components[component_idx++] = c1; | |
2956 | composition_state--; | |
2957 | continue; | |
2958 | } | |
4ed46869 | 2959 | } |
df7492f9 KH |
2960 | if (charset_id_0 < 0 |
2961 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
2962 | /* This is SPACE or DEL. */ |
2963 | charset = CHARSET_FROM_ID (charset_ascii); | |
2964 | else | |
2965 | charset = CHARSET_FROM_ID (charset_id_0); | |
2966 | break; | |
4ed46869 KH |
2967 | |
2968 | case ISO_graphic_plane_0: | |
781d7a48 | 2969 | if (composition_state != COMPOSING_NO) |
b73bfc1c | 2970 | { |
781d7a48 KH |
2971 | if (composition_state == COMPOSING_RULE |
2972 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2973 | { | |
2974 | DECODE_COMPOSITION_RULE (c1); | |
2975 | components[component_idx++] = c1; | |
2976 | composition_state--; | |
2977 | continue; | |
2978 | } | |
b73bfc1c | 2979 | } |
134b9549 KH |
2980 | if (charset_id_0 < 0) |
2981 | charset = CHARSET_FROM_ID (charset_ascii); | |
2982 | else | |
2983 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
2984 | break; |
2985 | ||
2986 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
2987 | if (charset_id_1 < 0 |
2988 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
2989 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
2990 | goto invalid_code; | |
4ed46869 KH |
2991 | /* This is a graphic character, we fall down ... */ |
2992 | ||
2993 | case ISO_graphic_plane_1: | |
df7492f9 KH |
2994 | if (charset_id_1 < 0) |
2995 | goto invalid_code; | |
2996 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
2997 | break; |
2998 | ||
df7492f9 KH |
2999 | case ISO_control_0: |
3000 | MAYBE_FINISH_COMPOSITION (); | |
3001 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
3002 | break; |
3003 | ||
df7492f9 KH |
3004 | case ISO_control_1: |
3005 | MAYBE_FINISH_COMPOSITION (); | |
3006 | goto invalid_code; | |
3007 | ||
4ed46869 | 3008 | case ISO_shift_out: |
df7492f9 KH |
3009 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3010 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3011 | goto invalid_code; | |
3012 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3013 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3014 | continue; |
4ed46869 KH |
3015 | |
3016 | case ISO_shift_in: | |
df7492f9 KH |
3017 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3018 | goto invalid_code; | |
3019 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3020 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3021 | continue; |
4ed46869 KH |
3022 | |
3023 | case ISO_single_shift_2_7: | |
3024 | case ISO_single_shift_2: | |
df7492f9 KH |
3025 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3026 | goto invalid_code; | |
4ed46869 KH |
3027 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3028 | c1 = 'N'; | |
3029 | goto label_escape_sequence; | |
3030 | ||
3031 | case ISO_single_shift_3: | |
df7492f9 KH |
3032 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3033 | goto invalid_code; | |
4ed46869 KH |
3034 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3035 | c1 = 'O'; | |
3036 | goto label_escape_sequence; | |
3037 | ||
3038 | case ISO_control_sequence_introducer: | |
3039 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3040 | c1 = '['; | |
3041 | goto label_escape_sequence; | |
3042 | ||
3043 | case ISO_escape: | |
3044 | ONE_MORE_BYTE (c1); | |
3045 | label_escape_sequence: | |
df7492f9 | 3046 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3047 | designation, direction specification, and character |
3048 | composition specification. */ | |
3049 | switch (c1) | |
3050 | { | |
3051 | case '&': /* revision of following character set */ | |
3052 | ONE_MORE_BYTE (c1); | |
3053 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3054 | goto invalid_code; |
4ed46869 KH |
3055 | ONE_MORE_BYTE (c1); |
3056 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3057 | goto invalid_code; |
4ed46869 KH |
3058 | ONE_MORE_BYTE (c1); |
3059 | goto label_escape_sequence; | |
3060 | ||
3061 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3062 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3063 | goto invalid_code; | |
134b9549 KH |
3064 | { |
3065 | int reg, chars96; | |
3066 | ||
3067 | ONE_MORE_BYTE (c1); | |
3068 | if (c1 >= '@' && c1 <= 'B') | |
3069 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3070 | or JISX0208.1980 */ |
134b9549 KH |
3071 | reg = 0, chars96 = 0; |
3072 | } | |
3073 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3074 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3075 | reg = c1 - 0x28, chars96 = 0; | |
3076 | ONE_MORE_BYTE (c1); | |
3077 | } | |
3078 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3079 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3080 | reg = c1 - 0x2C, chars96 = 1; | |
3081 | ONE_MORE_BYTE (c1); | |
3082 | } | |
3083 | else | |
3084 | goto invalid_code; | |
3085 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3086 | /* We must update these variables now. */ | |
3087 | if (reg == 0) | |
3088 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3089 | else if (reg == 1) | |
3090 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3091 | if (chars96 < 0) | |
3092 | goto invalid_code; | |
3093 | } | |
b73bfc1c | 3094 | continue; |
4ed46869 KH |
3095 | |
3096 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3097 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3098 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3099 | goto invalid_code; | |
3100 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3101 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3102 | continue; |
4ed46869 KH |
3103 | |
3104 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3105 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3106 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3107 | goto invalid_code; | |
3108 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3109 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3110 | continue; |
4ed46869 KH |
3111 | |
3112 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3113 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3114 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3115 | goto invalid_code; | |
134b9549 KH |
3116 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3117 | if (charset_id_2 < 0) | |
3118 | charset = CHARSET_FROM_ID (charset_ascii); | |
3119 | else | |
3120 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3121 | ONE_MORE_BYTE (c1); |
e7046a18 | 3122 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3123 | goto invalid_code; |
4ed46869 KH |
3124 | break; |
3125 | ||
3126 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3127 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3128 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3129 | goto invalid_code; | |
134b9549 KH |
3130 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3131 | if (charset_id_3 < 0) | |
3132 | charset = CHARSET_FROM_ID (charset_ascii); | |
3133 | else | |
3134 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3135 | ONE_MORE_BYTE (c1); |
e7046a18 | 3136 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3137 | goto invalid_code; |
4ed46869 KH |
3138 | break; |
3139 | ||
ec6d2bb8 | 3140 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3141 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3142 | goto invalid_code; | |
ec6d2bb8 | 3143 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3144 | continue; |
4ed46869 | 3145 | |
ec6d2bb8 | 3146 | case '1': /* end composition */ |
df7492f9 KH |
3147 | if (composition_state == COMPOSING_NO) |
3148 | goto invalid_code; | |
3149 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3150 | continue; |
4ed46869 KH |
3151 | |
3152 | case '[': /* specification of direction */ | |
df7492f9 KH |
3153 | if (! CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION) |
3154 | goto invalid_code; | |
4ed46869 | 3155 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3156 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
df7492f9 | 3157 | left-to-right, and nozero means right-to-left. */ |
4ed46869 KH |
3158 | ONE_MORE_BYTE (c1); |
3159 | switch (c1) | |
3160 | { | |
3161 | case ']': /* end of the current direction */ | |
d46c5b12 | 3162 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3163 | |
3164 | case '0': /* end of the current direction */ | |
3165 | case '1': /* start of left-to-right direction */ | |
3166 | ONE_MORE_BYTE (c1); | |
3167 | if (c1 == ']') | |
d46c5b12 | 3168 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3169 | else |
df7492f9 | 3170 | goto invalid_code; |
4ed46869 KH |
3171 | break; |
3172 | ||
3173 | case '2': /* start of right-to-left direction */ | |
3174 | ONE_MORE_BYTE (c1); | |
3175 | if (c1 == ']') | |
d46c5b12 | 3176 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3177 | else |
df7492f9 | 3178 | goto invalid_code; |
4ed46869 KH |
3179 | break; |
3180 | ||
3181 | default: | |
df7492f9 | 3182 | goto invalid_code; |
4ed46869 | 3183 | } |
b73bfc1c | 3184 | continue; |
4ed46869 | 3185 | |
103e0180 | 3186 | case '%': |
103e0180 KH |
3187 | ONE_MORE_BYTE (c1); |
3188 | if (c1 == '/') | |
3189 | { | |
3190 | /* CTEXT extended segment: | |
3191 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3192 | We keep these bytes as is for the moment. | |
3193 | They may be decoded by post-read-conversion. */ | |
3194 | int dim, M, L; | |
4776e638 | 3195 | int size; |
8f924df7 | 3196 | |
103e0180 KH |
3197 | ONE_MORE_BYTE (dim); |
3198 | ONE_MORE_BYTE (M); | |
3199 | ONE_MORE_BYTE (L); | |
3200 | size = ((M - 128) * 128) + (L - 128); | |
4776e638 KH |
3201 | if (charbuf + 8 + size > charbuf_end) |
3202 | goto break_loop; | |
3203 | *charbuf++ = ISO_CODE_ESC; | |
3204 | *charbuf++ = '%'; | |
3205 | *charbuf++ = '/'; | |
3206 | *charbuf++ = dim; | |
3207 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3208 | *charbuf++ = BYTE8_TO_CHAR (L); | |
103e0180 KH |
3209 | while (size-- > 0) |
3210 | { | |
3211 | ONE_MORE_BYTE (c1); | |
4776e638 | 3212 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3213 | } |
103e0180 KH |
3214 | } |
3215 | else if (c1 == 'G') | |
3216 | { | |
103e0180 KH |
3217 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3218 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3219 | We keep these bytes as is for the moment. | |
3220 | They may be decoded by post-read-conversion. */ | |
4776e638 KH |
3221 | int *p = charbuf; |
3222 | ||
3223 | if (p + 6 > charbuf_end) | |
3224 | goto break_loop; | |
3225 | *p++ = ISO_CODE_ESC; | |
3226 | *p++ = '%'; | |
3227 | *p++ = 'G'; | |
3228 | while (p < charbuf_end) | |
103e0180 KH |
3229 | { |
3230 | ONE_MORE_BYTE (c1); | |
3231 | if (c1 == ISO_CODE_ESC | |
3232 | && src + 1 < src_end | |
3233 | && src[0] == '%' | |
3234 | && src[1] == '@') | |
9ffd559c KH |
3235 | { |
3236 | src += 2; | |
3237 | break; | |
3238 | } | |
4776e638 | 3239 | *p++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3240 | } |
4776e638 KH |
3241 | if (p + 3 > charbuf_end) |
3242 | goto break_loop; | |
3243 | *p++ = ISO_CODE_ESC; | |
3244 | *p++ = '%'; | |
3245 | *p++ = '@'; | |
3246 | charbuf = p; | |
103e0180 KH |
3247 | } |
3248 | else | |
4776e638 | 3249 | goto invalid_code; |
103e0180 | 3250 | continue; |
4776e638 | 3251 | break; |
103e0180 | 3252 | |
4ed46869 | 3253 | default: |
df7492f9 KH |
3254 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3255 | goto invalid_code; | |
134b9549 KH |
3256 | { |
3257 | int reg, chars96; | |
3258 | ||
3259 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3260 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3261 | reg = c1 - 0x28, chars96 = 0; | |
3262 | ONE_MORE_BYTE (c1); | |
3263 | } | |
3264 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3265 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3266 | reg = c1 - 0x2C, chars96 = 1; | |
3267 | ONE_MORE_BYTE (c1); | |
3268 | } | |
3269 | else | |
3270 | goto invalid_code; | |
3271 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3272 | /* We must update these variables now. */ | |
3273 | if (reg == 0) | |
3274 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3275 | else if (reg == 1) | |
3276 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3277 | if (chars96 < 0) | |
3278 | goto invalid_code; | |
3279 | } | |
b73bfc1c | 3280 | continue; |
4ed46869 | 3281 | } |
b73bfc1c | 3282 | } |
4ed46869 | 3283 | |
ff0dacd7 KH |
3284 | if (charset->id != charset_ascii |
3285 | && last_id != charset->id) | |
3286 | { | |
3287 | if (last_id != charset_ascii) | |
69a80ea3 | 3288 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3289 | last_id = charset->id; |
3290 | last_offset = char_offset; | |
3291 | } | |
3292 | ||
b73bfc1c | 3293 | /* Now we know CHARSET and 1st position code C1 of a character. |
df7492f9 KH |
3294 | Produce a decoded character while getting 2nd position code |
3295 | C2 if necessary. */ | |
3296 | c1 &= 0x7F; | |
3297 | if (CHARSET_DIMENSION (charset) > 1) | |
b73bfc1c KH |
3298 | { |
3299 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3300 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) |
b73bfc1c | 3301 | /* C2 is not in a valid range. */ |
df7492f9 KH |
3302 | goto invalid_code; |
3303 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3304 | if (CHARSET_DIMENSION (charset) > 2) | |
3305 | { | |
3306 | ONE_MORE_BYTE (c2); | |
3307 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) | |
3308 | /* C2 is not in a valid range. */ | |
3309 | goto invalid_code; | |
3310 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3311 | } | |
3312 | } | |
3313 | ||
3314 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); | |
3315 | if (c < 0) | |
3316 | { | |
3317 | MAYBE_FINISH_COMPOSITION (); | |
3318 | for (; src_base < src; src_base++, char_offset++) | |
3319 | { | |
3320 | if (ASCII_BYTE_P (*src_base)) | |
3321 | *charbuf++ = *src_base; | |
3322 | else | |
3323 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3324 | } | |
3325 | } | |
3326 | else if (composition_state == COMPOSING_NO) | |
3327 | { | |
3328 | *charbuf++ = c; | |
3329 | char_offset++; | |
4ed46869 | 3330 | } |
df7492f9 | 3331 | else |
781d7a48 KH |
3332 | { |
3333 | components[component_idx++] = c; | |
3334 | if (method == COMPOSITION_WITH_RULE | |
3335 | || (method == COMPOSITION_WITH_RULE_ALTCHARS | |
3336 | && composition_state == COMPOSING_COMPONENT_CHAR)) | |
3337 | composition_state++; | |
4ed46869 KH |
3338 | } |
3339 | continue; | |
3340 | ||
df7492f9 KH |
3341 | invalid_code: |
3342 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3343 | src = src_base; |
df7492f9 KH |
3344 | consumed_chars = consumed_chars_base; |
3345 | ONE_MORE_BYTE (c); | |
065e3595 | 3346 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3347 | char_offset++; |
df7492f9 | 3348 | coding->errors++; |
4776e638 KH |
3349 | continue; |
3350 | ||
3351 | break_loop: | |
3352 | break; | |
4ed46869 | 3353 | } |
fb88bf2d | 3354 | |
df7492f9 | 3355 | no_more_source: |
ff0dacd7 | 3356 | if (last_id != charset_ascii) |
69a80ea3 | 3357 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
3358 | coding->consumed_char += consumed_chars_base; |
3359 | coding->consumed = src_base - coding->source; | |
3360 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3361 | } |
3362 | ||
b73bfc1c | 3363 | |
f4dee582 | 3364 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3365 | |
3366 | /* | |
f4dee582 | 3367 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 3368 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 3369 | variant has the following specifications: |
df7492f9 | 3370 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
3371 | 2. Allows short-form designation? |
3372 | 3. ASCII should be designated to G0 before control characters? | |
3373 | 4. ASCII should be designated to G0 at end of line? | |
3374 | 5. 7-bit environment or 8-bit environment? | |
3375 | 6. Use locking-shift? | |
3376 | 7. Use Single-shift? | |
3377 | And the following two are only for Japanese: | |
3378 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
3379 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
3380 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
3381 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 3382 | details. |
4ed46869 KH |
3383 | */ |
3384 | ||
3385 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
3386 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
3387 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
3388 | designation sequence of short-form. */ | |
4ed46869 KH |
3389 | |
3390 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
3391 | do { \ | |
df7492f9 | 3392 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
4ed46869 KH |
3393 | char *intermediate_char_94 = "()*+"; \ |
3394 | char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
3395 | int revision = -1; \ |
3396 | int c; \ | |
3397 | \ | |
3398 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 3399 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
3400 | \ |
3401 | if (revision >= 0) \ | |
70c22245 | 3402 | { \ |
df7492f9 KH |
3403 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
3404 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 3405 | } \ |
df7492f9 | 3406 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
3407 | if (CHARSET_DIMENSION (charset) == 1) \ |
3408 | { \ | |
df7492f9 KH |
3409 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
3410 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 3411 | else \ |
df7492f9 KH |
3412 | c = intermediate_char_96[reg]; \ |
3413 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
3414 | } \ |
3415 | else \ | |
3416 | { \ | |
df7492f9 KH |
3417 | EMIT_ONE_ASCII_BYTE ('$'); \ |
3418 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 3419 | { \ |
df7492f9 | 3420 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
3421 | || reg != 0 \ |
3422 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 3423 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
3424 | } \ |
3425 | else \ | |
df7492f9 | 3426 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 3427 | } \ |
df7492f9 KH |
3428 | EMIT_ONE_ASCII_BYTE (final_char); \ |
3429 | \ | |
3430 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
3431 | } while (0) |
3432 | ||
df7492f9 | 3433 | |
4ed46869 KH |
3434 | /* The following two macros produce codes (control character or escape |
3435 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
3436 | single-shift-3). */ | |
3437 | ||
df7492f9 KH |
3438 | #define ENCODE_SINGLE_SHIFT_2 \ |
3439 | do { \ | |
3440 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3441 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
3442 | else \ | |
3443 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
3444 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3445 | } while (0) |
3446 | ||
df7492f9 KH |
3447 | |
3448 | #define ENCODE_SINGLE_SHIFT_3 \ | |
3449 | do { \ | |
3450 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3451 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
3452 | else \ | |
3453 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
3454 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3455 | } while (0) |
3456 | ||
df7492f9 | 3457 | |
4ed46869 KH |
3458 | /* The following four macros produce codes (control character or |
3459 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
3460 | shift-out, locking-shift-2, and locking-shift-3). */ | |
3461 | ||
df7492f9 KH |
3462 | #define ENCODE_SHIFT_IN \ |
3463 | do { \ | |
3464 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
3465 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
3466 | } while (0) |
3467 | ||
df7492f9 KH |
3468 | |
3469 | #define ENCODE_SHIFT_OUT \ | |
3470 | do { \ | |
3471 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
3472 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
3473 | } while (0) |
3474 | ||
df7492f9 KH |
3475 | |
3476 | #define ENCODE_LOCKING_SHIFT_2 \ | |
3477 | do { \ | |
3478 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3479 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
3480 | } while (0) |
3481 | ||
df7492f9 KH |
3482 | |
3483 | #define ENCODE_LOCKING_SHIFT_3 \ | |
3484 | do { \ | |
3485 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3486 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
3487 | } while (0) |
3488 | ||
df7492f9 | 3489 | |
f4dee582 RS |
3490 | /* Produce codes for a DIMENSION1 character whose character set is |
3491 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
3492 | sequences are also produced in advance if necessary. */ |
3493 | ||
6e85d753 KH |
3494 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
3495 | do { \ | |
df7492f9 | 3496 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3497 | \ |
3498 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3499 | && id == charset_ascii) \ | |
3500 | { \ | |
3501 | id = charset_jisx0201_roman; \ | |
3502 | charset = CHARSET_FROM_ID (id); \ | |
3503 | } \ | |
3504 | \ | |
df7492f9 | 3505 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3506 | { \ |
df7492f9 KH |
3507 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3508 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 3509 | else \ |
df7492f9 KH |
3510 | EMIT_ONE_BYTE (c1 | 0x80); \ |
3511 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3512 | break; \ |
3513 | } \ | |
df7492f9 | 3514 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3515 | { \ |
df7492f9 | 3516 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
3517 | break; \ |
3518 | } \ | |
df7492f9 | 3519 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3520 | { \ |
df7492f9 | 3521 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
3522 | break; \ |
3523 | } \ | |
6e85d753 KH |
3524 | else \ |
3525 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3526 | must invoke it, or, at first, designate it to some graphic \ | |
3527 | register. Then repeat the loop to actually produce the \ | |
3528 | character. */ \ | |
df7492f9 KH |
3529 | dst = encode_invocation_designation (charset, coding, dst, \ |
3530 | &produced_chars); \ | |
4ed46869 KH |
3531 | } while (1) |
3532 | ||
df7492f9 | 3533 | |
f4dee582 RS |
3534 | /* Produce codes for a DIMENSION2 character whose character set is |
3535 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
3536 | invocation codes are also produced in advance if necessary. */ |
3537 | ||
6e85d753 KH |
3538 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
3539 | do { \ | |
df7492f9 | 3540 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3541 | \ |
3542 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3543 | && id == charset_jisx0208) \ | |
3544 | { \ | |
3545 | id = charset_jisx0208_1978; \ | |
3546 | charset = CHARSET_FROM_ID (id); \ | |
3547 | } \ | |
3548 | \ | |
df7492f9 | 3549 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3550 | { \ |
df7492f9 KH |
3551 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3552 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 3553 | else \ |
df7492f9 KH |
3554 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
3555 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3556 | break; \ |
3557 | } \ | |
df7492f9 | 3558 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3559 | { \ |
df7492f9 | 3560 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
3561 | break; \ |
3562 | } \ | |
df7492f9 | 3563 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3564 | { \ |
df7492f9 | 3565 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
3566 | break; \ |
3567 | } \ | |
6e85d753 KH |
3568 | else \ |
3569 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3570 | must invoke it, or, at first, designate it to some graphic \ | |
3571 | register. Then repeat the loop to actually produce the \ | |
3572 | character. */ \ | |
df7492f9 KH |
3573 | dst = encode_invocation_designation (charset, coding, dst, \ |
3574 | &produced_chars); \ | |
4ed46869 KH |
3575 | } while (1) |
3576 | ||
05e6f5dc | 3577 | |
df7492f9 KH |
3578 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
3579 | do { \ | |
3580 | int code = ENCODE_CHAR ((charset),(c)); \ | |
3581 | \ | |
3582 | if (CHARSET_DIMENSION (charset) == 1) \ | |
3583 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
3584 | else \ | |
3585 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 3586 | } while (0) |
bdd9fb48 | 3587 | |
05e6f5dc | 3588 | |
4ed46869 | 3589 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 3590 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
3591 | Return new DST. */ |
3592 | ||
3593 | unsigned char * | |
df7492f9 KH |
3594 | encode_invocation_designation (charset, coding, dst, p_nchars) |
3595 | struct charset *charset; | |
4ed46869 KH |
3596 | struct coding_system *coding; |
3597 | unsigned char *dst; | |
df7492f9 | 3598 | int *p_nchars; |
4ed46869 | 3599 | { |
df7492f9 KH |
3600 | int multibytep = coding->dst_multibyte; |
3601 | int produced_chars = *p_nchars; | |
4ed46869 | 3602 | int reg; /* graphic register number */ |
df7492f9 | 3603 | int id = CHARSET_ID (charset); |
4ed46869 KH |
3604 | |
3605 | /* At first, check designations. */ | |
3606 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 3607 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
3608 | break; |
3609 | ||
3610 | if (reg >= 4) | |
3611 | { | |
3612 | /* CHARSET is not yet designated to any graphic registers. */ | |
3613 | /* At first check the requested designation. */ | |
df7492f9 KH |
3614 | reg = CODING_ISO_REQUEST (coding, id); |
3615 | if (reg < 0) | |
1ba9e4ab KH |
3616 | /* Since CHARSET requests no special designation, designate it |
3617 | to graphic register 0. */ | |
4ed46869 KH |
3618 | reg = 0; |
3619 | ||
3620 | ENCODE_DESIGNATION (charset, reg, coding); | |
3621 | } | |
3622 | ||
df7492f9 KH |
3623 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
3624 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
3625 | { |
3626 | /* Since the graphic register REG is not invoked to any graphic | |
3627 | planes, invoke it to graphic plane 0. */ | |
3628 | switch (reg) | |
3629 | { | |
3630 | case 0: /* graphic register 0 */ | |
3631 | ENCODE_SHIFT_IN; | |
3632 | break; | |
3633 | ||
3634 | case 1: /* graphic register 1 */ | |
3635 | ENCODE_SHIFT_OUT; | |
3636 | break; | |
3637 | ||
3638 | case 2: /* graphic register 2 */ | |
df7492f9 | 3639 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3640 | ENCODE_SINGLE_SHIFT_2; |
3641 | else | |
3642 | ENCODE_LOCKING_SHIFT_2; | |
3643 | break; | |
3644 | ||
3645 | case 3: /* graphic register 3 */ | |
df7492f9 | 3646 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3647 | ENCODE_SINGLE_SHIFT_3; |
3648 | else | |
3649 | ENCODE_LOCKING_SHIFT_3; | |
3650 | break; | |
3651 | } | |
3652 | } | |
b73bfc1c | 3653 | |
df7492f9 | 3654 | *p_nchars = produced_chars; |
4ed46869 KH |
3655 | return dst; |
3656 | } | |
3657 | ||
df7492f9 KH |
3658 | /* The following three macros produce codes for indicating direction |
3659 | of text. */ | |
3660 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 3661 | do { \ |
df7492f9 KH |
3662 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
3663 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 3664 | else \ |
df7492f9 | 3665 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
3666 | } while (0) |
3667 | ||
ec6d2bb8 | 3668 | |
df7492f9 KH |
3669 | #define ENCODE_DIRECTION_R2L() \ |
3670 | do { \ | |
3671 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
3672 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
3673 | } while (0) |
3674 | ||
ec6d2bb8 | 3675 | |
df7492f9 | 3676 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 3677 | do { \ |
df7492f9 KH |
3678 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
3679 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
ec6d2bb8 | 3680 | } while (0) |
4ed46869 | 3681 | |
4ed46869 KH |
3682 | |
3683 | /* Produce codes for designation and invocation to reset the graphic | |
3684 | planes and registers to initial state. */ | |
df7492f9 KH |
3685 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
3686 | do { \ | |
3687 | int reg; \ | |
3688 | struct charset *charset; \ | |
3689 | \ | |
3690 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
3691 | ENCODE_SHIFT_IN; \ | |
3692 | for (reg = 0; reg < 4; reg++) \ | |
3693 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
3694 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
3695 | != CODING_ISO_INITIAL (coding, reg))) \ | |
3696 | { \ | |
3697 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
3698 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
3699 | } \ | |
4ed46869 KH |
3700 | } while (0) |
3701 | ||
df7492f9 | 3702 | |
bdd9fb48 | 3703 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 3704 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
3705 | |
3706 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
3707 | find all the necessary designations. */ |
3708 | ||
b73bfc1c | 3709 | static unsigned char * |
df7492f9 | 3710 | encode_designation_at_bol (coding, charbuf, charbuf_end, dst) |
e0e989f6 | 3711 | struct coding_system *coding; |
df7492f9 KH |
3712 | int *charbuf, *charbuf_end; |
3713 | unsigned char *dst; | |
e0e989f6 | 3714 | { |
df7492f9 | 3715 | struct charset *charset; |
bdd9fb48 KH |
3716 | /* Table of charsets to be designated to each graphic register. */ |
3717 | int r[4]; | |
df7492f9 KH |
3718 | int c, found = 0, reg; |
3719 | int produced_chars = 0; | |
3720 | int multibytep = coding->dst_multibyte; | |
3721 | Lisp_Object attrs; | |
3722 | Lisp_Object charset_list; | |
3723 | ||
3724 | attrs = CODING_ID_ATTRS (coding->id); | |
3725 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
3726 | if (EQ (charset_list, Qiso_2022)) | |
3727 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
3728 | |
3729 | for (reg = 0; reg < 4; reg++) | |
3730 | r[reg] = -1; | |
3731 | ||
b73bfc1c | 3732 | while (found < 4) |
e0e989f6 | 3733 | { |
df7492f9 KH |
3734 | int id; |
3735 | ||
3736 | c = *charbuf++; | |
b73bfc1c KH |
3737 | if (c == '\n') |
3738 | break; | |
df7492f9 KH |
3739 | charset = char_charset (c, charset_list, NULL); |
3740 | id = CHARSET_ID (charset); | |
3741 | reg = CODING_ISO_REQUEST (coding, id); | |
3742 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
3743 | { |
3744 | found++; | |
df7492f9 | 3745 | r[reg] = id; |
bdd9fb48 | 3746 | } |
bdd9fb48 KH |
3747 | } |
3748 | ||
3749 | if (found) | |
3750 | { | |
3751 | for (reg = 0; reg < 4; reg++) | |
3752 | if (r[reg] >= 0 | |
df7492f9 KH |
3753 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
3754 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 3755 | } |
b73bfc1c KH |
3756 | |
3757 | return dst; | |
e0e989f6 KH |
3758 | } |
3759 | ||
4ed46869 KH |
3760 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
3761 | ||
df7492f9 KH |
3762 | static int |
3763 | encode_coding_iso_2022 (coding) | |
4ed46869 | 3764 | struct coding_system *coding; |
4ed46869 | 3765 | { |
df7492f9 KH |
3766 | int multibytep = coding->dst_multibyte; |
3767 | int *charbuf = coding->charbuf; | |
3768 | int *charbuf_end = charbuf + coding->charbuf_used; | |
3769 | unsigned char *dst = coding->destination + coding->produced; | |
3770 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
3771 | int safe_room = 16; | |
3772 | int bol_designation | |
3773 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
3774 | && CODING_ISO_BOL (coding)); | |
3775 | int produced_chars = 0; | |
3776 | Lisp_Object attrs, eol_type, charset_list; | |
3777 | int ascii_compatible; | |
b73bfc1c | 3778 | int c; |
ff0dacd7 | 3779 | int preferred_charset_id = -1; |
05e6f5dc | 3780 | |
24a73b0a KH |
3781 | CODING_GET_INFO (coding, attrs, charset_list); |
3782 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
3783 | if (VECTORP (eol_type)) | |
3784 | eol_type = Qunix; | |
3785 | ||
004068e4 | 3786 | setup_iso_safe_charsets (attrs); |
ff0dacd7 KH |
3787 | /* Charset list may have been changed. */ |
3788 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); \ | |
8f924df7 | 3789 | coding->safe_charsets = (char *) SDATA (CODING_ATTR_SAFE_CHARSETS(attrs)); |
0eecad43 | 3790 | |
df7492f9 | 3791 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
bdd9fb48 | 3792 | |
df7492f9 | 3793 | while (charbuf < charbuf_end) |
4ed46869 | 3794 | { |
df7492f9 | 3795 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 3796 | |
df7492f9 | 3797 | if (bol_designation) |
b73bfc1c | 3798 | { |
df7492f9 | 3799 | unsigned char *dst_prev = dst; |
4ed46869 | 3800 | |
bdd9fb48 | 3801 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
3802 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
3803 | bol_designation = 0; | |
3804 | /* We are sure that designation sequences are all ASCII bytes. */ | |
3805 | produced_chars += dst - dst_prev; | |
e0e989f6 KH |
3806 | } |
3807 | ||
df7492f9 | 3808 | c = *charbuf++; |
ec6d2bb8 | 3809 | |
ff0dacd7 KH |
3810 | if (c < 0) |
3811 | { | |
3812 | /* Handle an annotation. */ | |
3813 | switch (*charbuf) | |
ec6d2bb8 | 3814 | { |
ff0dacd7 KH |
3815 | case CODING_ANNOTATE_COMPOSITION_MASK: |
3816 | /* Not yet implemented. */ | |
3817 | break; | |
3818 | case CODING_ANNOTATE_CHARSET_MASK: | |
3819 | preferred_charset_id = charbuf[3]; | |
3820 | if (preferred_charset_id >= 0 | |
3821 | && NILP (Fmemq (make_number (preferred_charset_id), | |
3822 | charset_list))) | |
3823 | preferred_charset_id = -1; | |
3824 | break; | |
3825 | default: | |
3826 | abort (); | |
4ed46869 | 3827 | } |
ff0dacd7 KH |
3828 | charbuf += -c - 1; |
3829 | continue; | |
4ed46869 | 3830 | } |
ec6d2bb8 | 3831 | |
b73bfc1c KH |
3832 | /* Now encode the character C. */ |
3833 | if (c < 0x20 || c == 0x7F) | |
3834 | { | |
df7492f9 KH |
3835 | if (c == '\n' |
3836 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 3837 | { |
df7492f9 KH |
3838 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
3839 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3840 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 3841 | { |
df7492f9 KH |
3842 | int i; |
3843 | ||
3844 | for (i = 0; i < 4; i++) | |
3845 | CODING_ISO_DESIGNATION (coding, i) | |
3846 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 3847 | } |
df7492f9 KH |
3848 | bol_designation |
3849 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 3850 | } |
df7492f9 KH |
3851 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
3852 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3853 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 3854 | } |
df7492f9 | 3855 | else if (ASCII_CHAR_P (c)) |
88993dfd | 3856 | { |
df7492f9 KH |
3857 | if (ascii_compatible) |
3858 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 3859 | else |
19a8d9e0 | 3860 | { |
bf16eb23 KH |
3861 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
3862 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 3863 | } |
4ed46869 | 3864 | } |
16eafb5d | 3865 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 3866 | { |
16eafb5d KH |
3867 | c = CHAR_TO_BYTE8 (c); |
3868 | EMIT_ONE_BYTE (c); | |
88993dfd | 3869 | } |
b73bfc1c | 3870 | else |
df7492f9 | 3871 | { |
ff0dacd7 | 3872 | struct charset *charset; |
b73bfc1c | 3873 | |
ff0dacd7 KH |
3874 | if (preferred_charset_id >= 0) |
3875 | { | |
3876 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
3877 | if (! CHAR_CHARSET_P (c, charset)) | |
3878 | charset = char_charset (c, charset_list, NULL); | |
3879 | } | |
3880 | else | |
3881 | charset = char_charset (c, charset_list, NULL); | |
df7492f9 KH |
3882 | if (!charset) |
3883 | { | |
41cbe562 KH |
3884 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
3885 | { | |
3886 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
3887 | charset = CHARSET_FROM_ID (charset_ascii); | |
3888 | } | |
3889 | else | |
3890 | { | |
3891 | c = coding->default_char; | |
3892 | charset = char_charset (c, charset_list, NULL); | |
3893 | } | |
df7492f9 KH |
3894 | } |
3895 | ENCODE_ISO_CHARACTER (charset, c); | |
3896 | } | |
84fbb8a0 | 3897 | } |
b73bfc1c | 3898 | |
df7492f9 KH |
3899 | if (coding->mode & CODING_MODE_LAST_BLOCK |
3900 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
3901 | { | |
3902 | ASSURE_DESTINATION (safe_room); | |
3903 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3904 | } | |
065e3595 | 3905 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
3906 | CODING_ISO_BOL (coding) = bol_designation; |
3907 | coding->produced_char += produced_chars; | |
3908 | coding->produced = dst - coding->destination; | |
3909 | return 0; | |
4ed46869 KH |
3910 | } |
3911 | ||
3912 | \f | |
df7492f9 | 3913 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 3914 | |
df7492f9 | 3915 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
3916 | quite widely. So, for the moment, Emacs supports them in the bare |
3917 | C code. But, in the future, they may be supported only by CCL. */ | |
3918 | ||
3919 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
3920 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
3921 | as is. A character of charset katakana-jisx0201 is encoded by | |
3922 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
3923 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 3924 | so that it fit in the range below. |
4ed46869 KH |
3925 | |
3926 | --- CODE RANGE of SJIS --- | |
3927 | (character set) (range) | |
3928 | ASCII 0x00 .. 0x7F | |
df7492f9 | 3929 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 3930 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 3931 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
3932 | ------------------------------- |
3933 | ||
3934 | */ | |
3935 | ||
3936 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
3937 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 3938 | character set and is encoded in two-byte. |
4ed46869 KH |
3939 | |
3940 | --- CODE RANGE of BIG5 --- | |
3941 | (character set) (range) | |
3942 | ASCII 0x00 .. 0x7F | |
3943 | Big5 (1st byte) 0xA1 .. 0xFE | |
3944 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
3945 | -------------------------- | |
3946 | ||
df7492f9 | 3947 | */ |
4ed46869 KH |
3948 | |
3949 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3950 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 3951 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 3952 | |
0a28aafb | 3953 | static int |
ff0dacd7 | 3954 | detect_coding_sjis (coding, detect_info) |
df7492f9 | 3955 | struct coding_system *coding; |
ff0dacd7 | 3956 | struct coding_detection_info *detect_info; |
4ed46869 | 3957 | { |
065e3595 | 3958 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 3959 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
3960 | int multibytep = coding->src_multibyte; |
3961 | int consumed_chars = 0; | |
3962 | int found = 0; | |
b73bfc1c | 3963 | int c; |
df7492f9 | 3964 | |
ff0dacd7 | 3965 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3966 | /* A coding system of this category is always ASCII compatible. */ |
3967 | src += coding->head_ascii; | |
4ed46869 | 3968 | |
b73bfc1c | 3969 | while (1) |
4ed46869 | 3970 | { |
065e3595 | 3971 | src_base = src; |
df7492f9 | 3972 | ONE_MORE_BYTE (c); |
682169fe KH |
3973 | if (c < 0x80) |
3974 | continue; | |
df7492f9 | 3975 | if ((c >= 0x81 && c <= 0x9F) || (c >= 0xE0 && c <= 0xEF)) |
4ed46869 | 3976 | { |
df7492f9 | 3977 | ONE_MORE_BYTE (c); |
682169fe | 3978 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 3979 | break; |
ff0dacd7 | 3980 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 3981 | } |
df7492f9 | 3982 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 3983 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
3984 | else |
3985 | break; | |
4ed46869 | 3986 | } |
ff0dacd7 | 3987 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3988 | return 0; |
3989 | ||
3990 | no_more_source: | |
065e3595 | 3991 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 3992 | { |
ff0dacd7 | 3993 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 3994 | return 0; |
4ed46869 | 3995 | } |
ff0dacd7 KH |
3996 | detect_info->found |= found; |
3997 | return 1; | |
4ed46869 KH |
3998 | } |
3999 | ||
4000 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4001 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 4002 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 4003 | |
0a28aafb | 4004 | static int |
ff0dacd7 | 4005 | detect_coding_big5 (coding, detect_info) |
df7492f9 | 4006 | struct coding_system *coding; |
ff0dacd7 | 4007 | struct coding_detection_info *detect_info; |
4ed46869 | 4008 | { |
065e3595 | 4009 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4010 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4011 | int multibytep = coding->src_multibyte; |
4012 | int consumed_chars = 0; | |
4013 | int found = 0; | |
b73bfc1c | 4014 | int c; |
fa42c37f | 4015 | |
ff0dacd7 | 4016 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4017 | /* A coding system of this category is always ASCII compatible. */ |
4018 | src += coding->head_ascii; | |
fa42c37f | 4019 | |
b73bfc1c | 4020 | while (1) |
fa42c37f | 4021 | { |
065e3595 | 4022 | src_base = src; |
df7492f9 KH |
4023 | ONE_MORE_BYTE (c); |
4024 | if (c < 0x80) | |
fa42c37f | 4025 | continue; |
df7492f9 | 4026 | if (c >= 0xA1) |
fa42c37f | 4027 | { |
df7492f9 KH |
4028 | ONE_MORE_BYTE (c); |
4029 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4030 | return 0; |
ff0dacd7 | 4031 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4032 | } |
df7492f9 KH |
4033 | else |
4034 | break; | |
fa42c37f | 4035 | } |
ff0dacd7 | 4036 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4037 | return 0; |
fa42c37f | 4038 | |
df7492f9 | 4039 | no_more_source: |
065e3595 | 4040 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4041 | { |
ff0dacd7 | 4042 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4043 | return 0; |
4044 | } | |
ff0dacd7 KH |
4045 | detect_info->found |= found; |
4046 | return 1; | |
fa42c37f KH |
4047 | } |
4048 | ||
4ed46869 KH |
4049 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
4050 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
fa42c37f | 4051 | |
b73bfc1c | 4052 | static void |
df7492f9 | 4053 | decode_coding_sjis (coding) |
4ed46869 | 4054 | struct coding_system *coding; |
4ed46869 | 4055 | { |
8f924df7 KH |
4056 | const unsigned char *src = coding->source + coding->consumed; |
4057 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4058 | const unsigned char *src_base; | |
69a80ea3 KH |
4059 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4060 | int *charbuf_end | |
4061 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4062 | int consumed_chars = 0, consumed_chars_base; |
4063 | int multibytep = coding->src_multibyte; | |
4064 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4065 | struct charset *charset_kanji2; |
24a73b0a | 4066 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4067 | int char_offset = coding->produced_char; |
4068 | int last_offset = char_offset; | |
4069 | int last_id = charset_ascii; | |
a5d301df | 4070 | |
24a73b0a | 4071 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4072 | |
4073 | val = charset_list; | |
4074 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4075 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4076 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4077 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4078 | |
b73bfc1c | 4079 | while (1) |
4ed46869 | 4080 | { |
df7492f9 | 4081 | int c, c1; |
24a73b0a | 4082 | struct charset *charset; |
fa42c37f | 4083 | |
b73bfc1c | 4084 | src_base = src; |
df7492f9 | 4085 | consumed_chars_base = consumed_chars; |
fa42c37f | 4086 | |
df7492f9 KH |
4087 | if (charbuf >= charbuf_end) |
4088 | break; | |
4089 | ||
4090 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4091 | if (c < 0) |
4092 | goto invalid_code; | |
24a73b0a KH |
4093 | if (c < 0x80) |
4094 | charset = charset_roman; | |
57a47f8a | 4095 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4096 | goto invalid_code; |
57a47f8a KH |
4097 | else if (c >= 0xA1 && c <= 0xDF) |
4098 | { | |
4099 | /* SJIS -> JISX0201-Kana */ | |
4100 | c &= 0x7F; | |
4101 | charset = charset_kana; | |
4102 | } | |
4103 | else if (c <= 0xEF) | |
df7492f9 | 4104 | { |
57a47f8a KH |
4105 | /* SJIS -> JISX0208 */ |
4106 | ONE_MORE_BYTE (c1); | |
4107 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4108 | goto invalid_code; |
57a47f8a KH |
4109 | c = (c << 8) | c1; |
4110 | SJIS_TO_JIS (c); | |
4111 | charset = charset_kanji; | |
4112 | } | |
4113 | else if (c <= 0xFC && charset_kanji2) | |
4114 | { | |
c6876370 | 4115 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4116 | ONE_MORE_BYTE (c1); |
4117 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4118 | goto invalid_code; |
57a47f8a KH |
4119 | c = (c << 8) | c1; |
4120 | SJIS_TO_JIS2 (c); | |
4121 | charset = charset_kanji2; | |
df7492f9 | 4122 | } |
57a47f8a KH |
4123 | else |
4124 | goto invalid_code; | |
24a73b0a KH |
4125 | if (charset->id != charset_ascii |
4126 | && last_id != charset->id) | |
4127 | { | |
4128 | if (last_id != charset_ascii) | |
69a80ea3 | 4129 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4130 | last_id = charset->id; |
4131 | last_offset = char_offset; | |
4132 | } | |
4133 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4134 | *charbuf++ = c; |
ff0dacd7 | 4135 | char_offset++; |
df7492f9 | 4136 | continue; |
b73bfc1c | 4137 | |
df7492f9 KH |
4138 | invalid_code: |
4139 | src = src_base; | |
4140 | consumed_chars = consumed_chars_base; | |
4141 | ONE_MORE_BYTE (c); | |
065e3595 | 4142 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4143 | char_offset++; |
df7492f9 KH |
4144 | coding->errors++; |
4145 | } | |
fa42c37f | 4146 | |
df7492f9 | 4147 | no_more_source: |
ff0dacd7 | 4148 | if (last_id != charset_ascii) |
69a80ea3 | 4149 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4150 | coding->consumed_char += consumed_chars_base; |
4151 | coding->consumed = src_base - coding->source; | |
4152 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4153 | } |
4154 | ||
b73bfc1c | 4155 | static void |
df7492f9 | 4156 | decode_coding_big5 (coding) |
4ed46869 | 4157 | struct coding_system *coding; |
4ed46869 | 4158 | { |
8f924df7 KH |
4159 | const unsigned char *src = coding->source + coding->consumed; |
4160 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4161 | const unsigned char *src_base; | |
69a80ea3 KH |
4162 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4163 | int *charbuf_end | |
4164 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4165 | int consumed_chars = 0, consumed_chars_base; |
4166 | int multibytep = coding->src_multibyte; | |
4167 | struct charset *charset_roman, *charset_big5; | |
24a73b0a | 4168 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4169 | int char_offset = coding->produced_char; |
4170 | int last_offset = char_offset; | |
4171 | int last_id = charset_ascii; | |
df7492f9 | 4172 | |
24a73b0a | 4173 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4174 | val = charset_list; |
4175 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4176 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4177 | |
b73bfc1c | 4178 | while (1) |
4ed46869 | 4179 | { |
df7492f9 | 4180 | int c, c1; |
24a73b0a | 4181 | struct charset *charset; |
b73bfc1c KH |
4182 | |
4183 | src_base = src; | |
df7492f9 KH |
4184 | consumed_chars_base = consumed_chars; |
4185 | ||
4186 | if (charbuf >= charbuf_end) | |
4187 | break; | |
4188 | ||
4189 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4190 | |
065e3595 KH |
4191 | if (c < 0) |
4192 | goto invalid_code; | |
24a73b0a KH |
4193 | if (c < 0x80) |
4194 | charset = charset_roman; | |
4195 | else | |
4ed46869 | 4196 | { |
24a73b0a KH |
4197 | /* BIG5 -> Big5 */ |
4198 | if (c < 0xA1 || c > 0xFE) | |
4199 | goto invalid_code; | |
4200 | ONE_MORE_BYTE (c1); | |
4201 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4202 | goto invalid_code; | |
4203 | c = c << 8 | c1; | |
4204 | charset = charset_big5; | |
4ed46869 | 4205 | } |
24a73b0a KH |
4206 | if (charset->id != charset_ascii |
4207 | && last_id != charset->id) | |
df7492f9 | 4208 | { |
24a73b0a | 4209 | if (last_id != charset_ascii) |
69a80ea3 | 4210 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4211 | last_id = charset->id; |
4212 | last_offset = char_offset; | |
4ed46869 | 4213 | } |
24a73b0a | 4214 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4215 | *charbuf++ = c; |
ff0dacd7 | 4216 | char_offset++; |
fb88bf2d KH |
4217 | continue; |
4218 | ||
df7492f9 | 4219 | invalid_code: |
4ed46869 | 4220 | src = src_base; |
df7492f9 KH |
4221 | consumed_chars = consumed_chars_base; |
4222 | ONE_MORE_BYTE (c); | |
065e3595 | 4223 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4224 | char_offset++; |
df7492f9 | 4225 | coding->errors++; |
fb88bf2d | 4226 | } |
d46c5b12 | 4227 | |
df7492f9 | 4228 | no_more_source: |
ff0dacd7 | 4229 | if (last_id != charset_ascii) |
69a80ea3 | 4230 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4231 | coding->consumed_char += consumed_chars_base; |
4232 | coding->consumed = src_base - coding->source; | |
4233 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4234 | } |
4235 | ||
4236 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4237 | This function can encode charsets `ascii', `katakana-jisx0201', |
4238 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4239 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
4240 | (i.e. do not have extended leading-codes). Characters of other |
4241 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
4242 | SJIS text, else encode BIG5 text. */ | |
4243 | ||
df7492f9 KH |
4244 | static int |
4245 | encode_coding_sjis (coding) | |
4ed46869 | 4246 | struct coding_system *coding; |
4ed46869 | 4247 | { |
df7492f9 KH |
4248 | int multibytep = coding->dst_multibyte; |
4249 | int *charbuf = coding->charbuf; | |
4250 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4251 | unsigned char *dst = coding->destination + coding->produced; | |
4252 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4253 | int safe_room = 4; | |
4254 | int produced_chars = 0; | |
24a73b0a | 4255 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4256 | int ascii_compatible; |
4257 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4258 | struct charset *charset_kanji2; |
df7492f9 | 4259 | int c; |
a5d301df | 4260 | |
24a73b0a | 4261 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4262 | val = charset_list; |
4263 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4264 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
57a47f8a KH |
4265 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4266 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4267 | |
df7492f9 | 4268 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4269 | |
df7492f9 KH |
4270 | while (charbuf < charbuf_end) |
4271 | { | |
4272 | ASSURE_DESTINATION (safe_room); | |
4273 | c = *charbuf++; | |
b73bfc1c | 4274 | /* Now encode the character C. */ |
df7492f9 KH |
4275 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4276 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4277 | else if (CHAR_BYTE8_P (c)) |
4278 | { | |
4279 | c = CHAR_TO_BYTE8 (c); | |
4280 | EMIT_ONE_BYTE (c); | |
4281 | } | |
df7492f9 | 4282 | else |
b73bfc1c | 4283 | { |
df7492f9 KH |
4284 | unsigned code; |
4285 | struct charset *charset = char_charset (c, charset_list, &code); | |
4286 | ||
4287 | if (!charset) | |
4ed46869 | 4288 | { |
41cbe562 | 4289 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4290 | { |
41cbe562 KH |
4291 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4292 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4293 | } |
41cbe562 | 4294 | else |
b73bfc1c | 4295 | { |
41cbe562 KH |
4296 | c = coding->default_char; |
4297 | charset = char_charset (c, charset_list, &code); | |
b73bfc1c | 4298 | } |
b73bfc1c | 4299 | } |
df7492f9 KH |
4300 | if (code == CHARSET_INVALID_CODE (charset)) |
4301 | abort (); | |
4302 | if (charset == charset_kanji) | |
4303 | { | |
4304 | int c1, c2; | |
4305 | JIS_TO_SJIS (code); | |
4306 | c1 = code >> 8, c2 = code & 0xFF; | |
4307 | EMIT_TWO_BYTES (c1, c2); | |
4308 | } | |
4309 | else if (charset == charset_kana) | |
4310 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
4311 | else if (charset_kanji2 && charset == charset_kanji2) |
4312 | { | |
4313 | int c1, c2; | |
4314 | ||
4315 | c1 = code >> 8; | |
4316 | if (c1 == 0x21 || (c1 >= 0x23 && c1 < 0x25) | |
4317 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) | |
4318 | { | |
4319 | JIS_TO_SJIS2 (code); | |
4320 | c1 = code >> 8, c2 = code & 0xFF; | |
4321 | EMIT_TWO_BYTES (c1, c2); | |
4322 | } | |
4323 | else | |
4324 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4325 | } | |
df7492f9 KH |
4326 | else |
4327 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4328 | } | |
4329 | } | |
065e3595 | 4330 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4331 | coding->produced_char += produced_chars; |
4332 | coding->produced = dst - coding->destination; | |
4333 | return 0; | |
4334 | } | |
4335 | ||
4336 | static int | |
4337 | encode_coding_big5 (coding) | |
4338 | struct coding_system *coding; | |
4339 | { | |
4340 | int multibytep = coding->dst_multibyte; | |
4341 | int *charbuf = coding->charbuf; | |
4342 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4343 | unsigned char *dst = coding->destination + coding->produced; | |
4344 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4345 | int safe_room = 4; | |
4346 | int produced_chars = 0; | |
24a73b0a | 4347 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4348 | int ascii_compatible; |
4349 | struct charset *charset_roman, *charset_big5; | |
4350 | int c; | |
4351 | ||
24a73b0a | 4352 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4353 | val = charset_list; |
4354 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4355 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4356 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
4357 | ||
4358 | while (charbuf < charbuf_end) | |
4359 | { | |
4360 | ASSURE_DESTINATION (safe_room); | |
4361 | c = *charbuf++; | |
4362 | /* Now encode the character C. */ | |
4363 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
4364 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4365 | else if (CHAR_BYTE8_P (c)) |
4366 | { | |
4367 | c = CHAR_TO_BYTE8 (c); | |
4368 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
4369 | } |
4370 | else | |
4371 | { | |
df7492f9 KH |
4372 | unsigned code; |
4373 | struct charset *charset = char_charset (c, charset_list, &code); | |
4374 | ||
4375 | if (! charset) | |
b73bfc1c | 4376 | { |
41cbe562 | 4377 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4378 | { |
41cbe562 KH |
4379 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4380 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4381 | } |
41cbe562 | 4382 | else |
0eecad43 | 4383 | { |
41cbe562 KH |
4384 | c = coding->default_char; |
4385 | charset = char_charset (c, charset_list, &code); | |
0eecad43 | 4386 | } |
4ed46869 | 4387 | } |
df7492f9 KH |
4388 | if (code == CHARSET_INVALID_CODE (charset)) |
4389 | abort (); | |
4390 | if (charset == charset_big5) | |
b73bfc1c | 4391 | { |
df7492f9 KH |
4392 | int c1, c2; |
4393 | ||
4394 | c1 = code >> 8, c2 = code & 0xFF; | |
4395 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 4396 | } |
df7492f9 KH |
4397 | else |
4398 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 4399 | } |
4ed46869 | 4400 | } |
065e3595 | 4401 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4402 | coding->produced_char += produced_chars; |
4403 | coding->produced = dst - coding->destination; | |
4404 | return 0; | |
4ed46869 KH |
4405 | } |
4406 | ||
4407 | \f | |
df7492f9 | 4408 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
4409 | |
4410 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4411 | Check if a text is encoded in a coding system of which | |
4412 | encoder/decoder are written in CCL program. If it is, return | |
df7492f9 | 4413 | CATEGORY_MASK_CCL, else return 0. */ |
1397dc18 | 4414 | |
0a28aafb | 4415 | static int |
ff0dacd7 | 4416 | detect_coding_ccl (coding, detect_info) |
df7492f9 | 4417 | struct coding_system *coding; |
ff0dacd7 | 4418 | struct coding_detection_info *detect_info; |
1397dc18 | 4419 | { |
065e3595 | 4420 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4421 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4422 | int multibytep = coding->src_multibyte; |
4423 | int consumed_chars = 0; | |
4424 | int found = 0; | |
0e219d54 | 4425 | unsigned char *valids; |
df7492f9 KH |
4426 | int head_ascii = coding->head_ascii; |
4427 | Lisp_Object attrs; | |
4428 | ||
ff0dacd7 KH |
4429 | detect_info->checked |= CATEGORY_MASK_CCL; |
4430 | ||
df7492f9 | 4431 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 4432 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
4433 | attrs = CODING_ID_ATTRS (coding->id); |
4434 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4435 | src += head_ascii; | |
1397dc18 | 4436 | |
b73bfc1c | 4437 | while (1) |
1397dc18 | 4438 | { |
df7492f9 | 4439 | int c; |
065e3595 KH |
4440 | |
4441 | src_base = src; | |
df7492f9 | 4442 | ONE_MORE_BYTE (c); |
065e3595 | 4443 | if (c < 0 || ! valids[c]) |
df7492f9 | 4444 | break; |
ff0dacd7 KH |
4445 | if ((valids[c] > 1)) |
4446 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 4447 | } |
ff0dacd7 | 4448 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
4449 | return 0; |
4450 | ||
4451 | no_more_source: | |
ff0dacd7 KH |
4452 | detect_info->found |= found; |
4453 | return 1; | |
df7492f9 KH |
4454 | } |
4455 | ||
4456 | static void | |
4457 | decode_coding_ccl (coding) | |
4458 | struct coding_system *coding; | |
4459 | { | |
7c78e542 | 4460 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 4461 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
4462 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4463 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
4464 | int consumed_chars = 0; |
4465 | int multibytep = coding->src_multibyte; | |
4466 | struct ccl_program ccl; | |
4467 | int source_charbuf[1024]; | |
4468 | int source_byteidx[1024]; | |
24a73b0a | 4469 | Lisp_Object attrs, charset_list; |
df7492f9 | 4470 | |
24a73b0a | 4471 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4472 | setup_ccl_program (&ccl, CODING_CCL_DECODER (coding)); |
4473 | ||
4474 | while (src < src_end) | |
4475 | { | |
7c78e542 | 4476 | const unsigned char *p = src; |
df7492f9 KH |
4477 | int *source, *source_end; |
4478 | int i = 0; | |
4479 | ||
4480 | if (multibytep) | |
4481 | while (i < 1024 && p < src_end) | |
4482 | { | |
4483 | source_byteidx[i] = p - src; | |
4484 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
4485 | } | |
4486 | else | |
4487 | while (i < 1024 && p < src_end) | |
4488 | source_charbuf[i++] = *p++; | |
8f924df7 | 4489 | |
df7492f9 KH |
4490 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
4491 | ccl.last_block = 1; | |
4492 | ||
4493 | source = source_charbuf; | |
4494 | source_end = source + i; | |
4495 | while (source < source_end) | |
4496 | { | |
4497 | ccl_driver (&ccl, source, charbuf, | |
8dcbea82 KH |
4498 | source_end - source, charbuf_end - charbuf, |
4499 | charset_list); | |
df7492f9 KH |
4500 | source += ccl.consumed; |
4501 | charbuf += ccl.produced; | |
4502 | if (ccl.status != CCL_STAT_SUSPEND_BY_DST) | |
4503 | break; | |
4504 | } | |
4505 | if (source < source_end) | |
4506 | src += source_byteidx[source - source_charbuf]; | |
4507 | else | |
4508 | src = p; | |
4509 | consumed_chars += source - source_charbuf; | |
4510 | ||
4511 | if (ccl.status != CCL_STAT_SUSPEND_BY_SRC | |
4512 | && ccl.status != CODING_RESULT_INSUFFICIENT_SRC) | |
4513 | break; | |
4514 | } | |
4515 | ||
4516 | switch (ccl.status) | |
4517 | { | |
4518 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4519 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4520 | break; |
4521 | case CCL_STAT_SUSPEND_BY_DST: | |
4522 | break; | |
4523 | case CCL_STAT_QUIT: | |
4524 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4525 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4526 | break; |
4527 | default: | |
065e3595 | 4528 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4529 | break; |
4530 | } | |
4531 | coding->consumed_char += consumed_chars; | |
4532 | coding->consumed = src - coding->source; | |
4533 | coding->charbuf_used = charbuf - coding->charbuf; | |
4534 | } | |
4535 | ||
4536 | static int | |
4537 | encode_coding_ccl (coding) | |
4538 | struct coding_system *coding; | |
4539 | { | |
4540 | struct ccl_program ccl; | |
4541 | int multibytep = coding->dst_multibyte; | |
4542 | int *charbuf = coding->charbuf; | |
4543 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4544 | unsigned char *dst = coding->destination + coding->produced; | |
4545 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4546 | unsigned char *adjusted_dst_end = dst_end - 1; | |
4547 | int destination_charbuf[1024]; | |
4548 | int i, produced_chars = 0; | |
24a73b0a | 4549 | Lisp_Object attrs, charset_list; |
df7492f9 | 4550 | |
24a73b0a | 4551 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4552 | setup_ccl_program (&ccl, CODING_CCL_ENCODER (coding)); |
4553 | ||
4554 | ccl.last_block = coding->mode & CODING_MODE_LAST_BLOCK; | |
4555 | ccl.dst_multibyte = coding->dst_multibyte; | |
4556 | ||
4557 | while (charbuf < charbuf_end && dst < adjusted_dst_end) | |
4558 | { | |
4559 | int dst_bytes = dst_end - dst; | |
4560 | if (dst_bytes > 1024) | |
4561 | dst_bytes = 1024; | |
4562 | ||
4563 | ccl_driver (&ccl, charbuf, destination_charbuf, | |
8dcbea82 | 4564 | charbuf_end - charbuf, dst_bytes, charset_list); |
df7492f9 KH |
4565 | charbuf += ccl.consumed; |
4566 | if (multibytep) | |
4567 | for (i = 0; i < ccl.produced; i++) | |
4568 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); | |
4569 | else | |
4570 | { | |
4571 | for (i = 0; i < ccl.produced; i++) | |
4572 | *dst++ = destination_charbuf[i] & 0xFF; | |
4573 | produced_chars += ccl.produced; | |
4574 | } | |
4575 | } | |
4576 | ||
4577 | switch (ccl.status) | |
4578 | { | |
4579 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4580 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4581 | break; |
4582 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 4583 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
4584 | break; |
4585 | case CCL_STAT_QUIT: | |
4586 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4587 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4588 | break; |
4589 | default: | |
065e3595 | 4590 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 4591 | break; |
1397dc18 | 4592 | } |
df7492f9 KH |
4593 | |
4594 | coding->produced_char += produced_chars; | |
4595 | coding->produced = dst - coding->destination; | |
4596 | return 0; | |
1397dc18 KH |
4597 | } |
4598 | ||
df7492f9 | 4599 | |
1397dc18 | 4600 | \f |
df7492f9 | 4601 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 4602 | |
b73bfc1c | 4603 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 4604 | |
b73bfc1c | 4605 | static void |
df7492f9 | 4606 | decode_coding_raw_text (coding) |
4ed46869 | 4607 | struct coding_system *coding; |
4ed46869 | 4608 | { |
df7492f9 | 4609 | coding->chars_at_source = 1; |
2c78b7e1 KH |
4610 | coding->consumed_char = 0; |
4611 | coding->consumed = 0; | |
065e3595 | 4612 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 4613 | } |
4ed46869 | 4614 | |
df7492f9 KH |
4615 | static int |
4616 | encode_coding_raw_text (coding) | |
4617 | struct coding_system *coding; | |
4618 | { | |
4619 | int multibytep = coding->dst_multibyte; | |
4620 | int *charbuf = coding->charbuf; | |
4621 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
4622 | unsigned char *dst = coding->destination + coding->produced; | |
4623 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4624 | int produced_chars = 0; | |
b73bfc1c KH |
4625 | int c; |
4626 | ||
df7492f9 | 4627 | if (multibytep) |
b73bfc1c | 4628 | { |
df7492f9 | 4629 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 4630 | |
df7492f9 KH |
4631 | if (coding->src_multibyte) |
4632 | while (charbuf < charbuf_end) | |
4633 | { | |
4634 | ASSURE_DESTINATION (safe_room); | |
4635 | c = *charbuf++; | |
4636 | if (ASCII_CHAR_P (c)) | |
4637 | EMIT_ONE_ASCII_BYTE (c); | |
4638 | else if (CHAR_BYTE8_P (c)) | |
4639 | { | |
4640 | c = CHAR_TO_BYTE8 (c); | |
4641 | EMIT_ONE_BYTE (c); | |
4642 | } | |
4643 | else | |
4644 | { | |
4645 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 4646 | |
df7492f9 KH |
4647 | CHAR_STRING_ADVANCE (c, p1); |
4648 | while (p0 < p1) | |
9d123124 KH |
4649 | { |
4650 | EMIT_ONE_BYTE (*p0); | |
4651 | p0++; | |
4652 | } | |
df7492f9 KH |
4653 | } |
4654 | } | |
b73bfc1c | 4655 | else |
df7492f9 KH |
4656 | while (charbuf < charbuf_end) |
4657 | { | |
4658 | ASSURE_DESTINATION (safe_room); | |
4659 | c = *charbuf++; | |
4660 | EMIT_ONE_BYTE (c); | |
4661 | } | |
4662 | } | |
4663 | else | |
4ed46869 | 4664 | { |
df7492f9 | 4665 | if (coding->src_multibyte) |
d46c5b12 | 4666 | { |
df7492f9 KH |
4667 | int safe_room = MAX_MULTIBYTE_LENGTH; |
4668 | ||
4669 | while (charbuf < charbuf_end) | |
d46c5b12 | 4670 | { |
df7492f9 KH |
4671 | ASSURE_DESTINATION (safe_room); |
4672 | c = *charbuf++; | |
4673 | if (ASCII_CHAR_P (c)) | |
4674 | *dst++ = c; | |
4675 | else if (CHAR_BYTE8_P (c)) | |
4676 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 4677 | else |
df7492f9 KH |
4678 | CHAR_STRING_ADVANCE (c, dst); |
4679 | produced_chars++; | |
d46c5b12 KH |
4680 | } |
4681 | } | |
df7492f9 KH |
4682 | else |
4683 | { | |
4684 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
4685 | while (charbuf < charbuf_end && dst < dst_end) | |
4686 | *dst++ = *charbuf++; | |
4687 | produced_chars = dst - (coding->destination + coding->dst_bytes); | |
8f924df7 | 4688 | } |
4ed46869 | 4689 | } |
065e3595 | 4690 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4691 | coding->produced_char += produced_chars; |
4692 | coding->produced = dst - coding->destination; | |
4693 | return 0; | |
4ed46869 KH |
4694 | } |
4695 | ||
ff0dacd7 KH |
4696 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
4697 | Check if a text is encoded in a charset-based coding system. If it | |
4698 | is, return 1, else return 0. */ | |
4699 | ||
0a28aafb | 4700 | static int |
ff0dacd7 | 4701 | detect_coding_charset (coding, detect_info) |
df7492f9 | 4702 | struct coding_system *coding; |
ff0dacd7 | 4703 | struct coding_detection_info *detect_info; |
1397dc18 | 4704 | { |
065e3595 | 4705 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4706 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4707 | int multibytep = coding->src_multibyte; |
4708 | int consumed_chars = 0; | |
4709 | Lisp_Object attrs, valids; | |
584948ac | 4710 | int found = 0; |
1397dc18 | 4711 | |
ff0dacd7 KH |
4712 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
4713 | ||
df7492f9 KH |
4714 | coding = &coding_categories[coding_category_charset]; |
4715 | attrs = CODING_ID_ATTRS (coding->id); | |
4716 | valids = AREF (attrs, coding_attr_charset_valids); | |
4717 | ||
4718 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4719 | src += coding->head_ascii; | |
1397dc18 | 4720 | |
b73bfc1c | 4721 | while (1) |
1397dc18 | 4722 | { |
df7492f9 | 4723 | int c; |
1397dc18 | 4724 | |
065e3595 | 4725 | src_base = src; |
df7492f9 | 4726 | ONE_MORE_BYTE (c); |
065e3595 KH |
4727 | if (c < 0) |
4728 | continue; | |
df7492f9 KH |
4729 | if (NILP (AREF (valids, c))) |
4730 | break; | |
584948ac | 4731 | if (c >= 0x80) |
ff0dacd7 | 4732 | found = CATEGORY_MASK_CHARSET; |
df7492f9 | 4733 | } |
ff0dacd7 | 4734 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 4735 | return 0; |
4ed46869 | 4736 | |
df7492f9 | 4737 | no_more_source: |
ff0dacd7 KH |
4738 | detect_info->found |= found; |
4739 | return 1; | |
df7492f9 | 4740 | } |
b73bfc1c | 4741 | |
b73bfc1c | 4742 | static void |
df7492f9 | 4743 | decode_coding_charset (coding) |
4ed46869 | 4744 | struct coding_system *coding; |
4ed46869 | 4745 | { |
8f924df7 KH |
4746 | const unsigned char *src = coding->source + coding->consumed; |
4747 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4748 | const unsigned char *src_base; | |
69a80ea3 KH |
4749 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4750 | int *charbuf_end | |
4751 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4752 | int consumed_chars = 0, consumed_chars_base; |
4753 | int multibytep = coding->src_multibyte; | |
24a73b0a | 4754 | Lisp_Object attrs, charset_list, valids; |
ff0dacd7 KH |
4755 | int char_offset = coding->produced_char; |
4756 | int last_offset = char_offset; | |
4757 | int last_id = charset_ascii; | |
df7492f9 | 4758 | |
24a73b0a | 4759 | CODING_GET_INFO (coding, attrs, charset_list); |
4eb6d3f1 | 4760 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 4761 | |
df7492f9 | 4762 | while (1) |
4ed46869 | 4763 | { |
4eb6d3f1 | 4764 | int c; |
24a73b0a KH |
4765 | Lisp_Object val; |
4766 | struct charset *charset; | |
4767 | int dim; | |
4768 | int len = 1; | |
4769 | unsigned code; | |
df7492f9 KH |
4770 | |
4771 | src_base = src; | |
4772 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 4773 | |
df7492f9 KH |
4774 | if (charbuf >= charbuf_end) |
4775 | break; | |
4776 | ||
4eb6d3f1 | 4777 | ONE_MORE_BYTE (c); |
065e3595 KH |
4778 | if (c < 0) |
4779 | goto invalid_code; | |
24a73b0a KH |
4780 | code = c; |
4781 | ||
4782 | val = AREF (valids, c); | |
4783 | if (NILP (val)) | |
4784 | goto invalid_code; | |
4785 | if (INTEGERP (val)) | |
d46c5b12 | 4786 | { |
24a73b0a KH |
4787 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
4788 | dim = CHARSET_DIMENSION (charset); | |
4789 | while (len < dim) | |
b73bfc1c | 4790 | { |
24a73b0a KH |
4791 | ONE_MORE_BYTE (c); |
4792 | code = (code << 8) | c; | |
4793 | len++; | |
b73bfc1c | 4794 | } |
24a73b0a KH |
4795 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
4796 | charset, code, c); | |
d46c5b12 | 4797 | } |
df7492f9 | 4798 | else |
d46c5b12 | 4799 | { |
24a73b0a KH |
4800 | /* VAL is a list of charset IDs. It is assured that the |
4801 | list is sorted by charset dimensions (smaller one | |
4802 | comes first). */ | |
4803 | while (CONSP (val)) | |
4eb6d3f1 | 4804 | { |
24a73b0a | 4805 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 4806 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 4807 | while (len < dim) |
4eb6d3f1 | 4808 | { |
acb2a965 KH |
4809 | ONE_MORE_BYTE (c); |
4810 | code = (code << 8) | c; | |
f9d71dcd | 4811 | len++; |
4eb6d3f1 | 4812 | } |
24a73b0a KH |
4813 | CODING_DECODE_CHAR (coding, src, src_base, |
4814 | src_end, charset, code, c); | |
4815 | if (c >= 0) | |
4816 | break; | |
4817 | val = XCDR (val); | |
ff0dacd7 | 4818 | } |
d46c5b12 | 4819 | } |
24a73b0a KH |
4820 | if (c < 0) |
4821 | goto invalid_code; | |
4822 | if (charset->id != charset_ascii | |
4823 | && last_id != charset->id) | |
4824 | { | |
4825 | if (last_id != charset_ascii) | |
69a80ea3 | 4826 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4827 | last_id = charset->id; |
4828 | last_offset = char_offset; | |
4829 | } | |
4830 | ||
df7492f9 | 4831 | *charbuf++ = c; |
ff0dacd7 | 4832 | char_offset++; |
df7492f9 KH |
4833 | continue; |
4834 | ||
4835 | invalid_code: | |
4836 | src = src_base; | |
4837 | consumed_chars = consumed_chars_base; | |
4838 | ONE_MORE_BYTE (c); | |
065e3595 | 4839 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4840 | char_offset++; |
df7492f9 | 4841 | coding->errors++; |
4ed46869 KH |
4842 | } |
4843 | ||
df7492f9 | 4844 | no_more_source: |
ff0dacd7 | 4845 | if (last_id != charset_ascii) |
69a80ea3 | 4846 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4847 | coding->consumed_char += consumed_chars_base; |
4848 | coding->consumed = src_base - coding->source; | |
4849 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4850 | } |
4851 | ||
df7492f9 KH |
4852 | static int |
4853 | encode_coding_charset (coding) | |
4ed46869 | 4854 | struct coding_system *coding; |
4ed46869 | 4855 | { |
df7492f9 KH |
4856 | int multibytep = coding->dst_multibyte; |
4857 | int *charbuf = coding->charbuf; | |
4858 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4859 | unsigned char *dst = coding->destination + coding->produced; | |
4860 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4861 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
4862 | int produced_chars = 0; | |
24a73b0a | 4863 | Lisp_Object attrs, charset_list; |
df7492f9 | 4864 | int ascii_compatible; |
b73bfc1c | 4865 | int c; |
b73bfc1c | 4866 | |
24a73b0a | 4867 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 4868 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 4869 | |
df7492f9 | 4870 | while (charbuf < charbuf_end) |
4ed46869 | 4871 | { |
4eb6d3f1 | 4872 | struct charset *charset; |
df7492f9 | 4873 | unsigned code; |
8f924df7 | 4874 | |
df7492f9 KH |
4875 | ASSURE_DESTINATION (safe_room); |
4876 | c = *charbuf++; | |
4877 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
4878 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 4879 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 4880 | { |
16eafb5d KH |
4881 | c = CHAR_TO_BYTE8 (c); |
4882 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 4883 | } |
d46c5b12 | 4884 | else |
b73bfc1c | 4885 | { |
4eb6d3f1 KH |
4886 | charset = char_charset (c, charset_list, &code); |
4887 | if (charset) | |
4888 | { | |
4889 | if (CHARSET_DIMENSION (charset) == 1) | |
4890 | EMIT_ONE_BYTE (code); | |
4891 | else if (CHARSET_DIMENSION (charset) == 2) | |
4892 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
4893 | else if (CHARSET_DIMENSION (charset) == 3) | |
4894 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
4895 | else | |
4896 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
4897 | (code >> 8) & 0xFF, code & 0xFF); | |
4898 | } | |
4899 | else | |
41cbe562 KH |
4900 | { |
4901 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
4902 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4903 | else | |
4904 | c = coding->default_char; | |
4905 | EMIT_ONE_BYTE (c); | |
4906 | } | |
4ed46869 | 4907 | } |
4ed46869 KH |
4908 | } |
4909 | ||
065e3595 | 4910 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4911 | coding->produced_char += produced_chars; |
4912 | coding->produced = dst - coding->destination; | |
4913 | return 0; | |
4ed46869 KH |
4914 | } |
4915 | ||
4916 | \f | |
1397dc18 | 4917 | /*** 7. C library functions ***/ |
4ed46869 | 4918 | |
df7492f9 KH |
4919 | /* Setup coding context CODING from information about CODING_SYSTEM. |
4920 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
4921 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 4922 | |
ec6d2bb8 | 4923 | void |
e0e989f6 KH |
4924 | setup_coding_system (coding_system, coding) |
4925 | Lisp_Object coding_system; | |
4ed46869 KH |
4926 | struct coding_system *coding; |
4927 | { | |
df7492f9 KH |
4928 | Lisp_Object attrs; |
4929 | Lisp_Object eol_type; | |
4930 | Lisp_Object coding_type; | |
4608c386 | 4931 | Lisp_Object val; |
4ed46869 | 4932 | |
df7492f9 KH |
4933 | if (NILP (coding_system)) |
4934 | coding_system = Qno_conversion; | |
c07c8e12 | 4935 | |
df7492f9 | 4936 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 4937 | |
df7492f9 KH |
4938 | attrs = CODING_ID_ATTRS (coding->id); |
4939 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
1f5dbf34 | 4940 | |
df7492f9 KH |
4941 | coding->mode = 0; |
4942 | coding->head_ascii = -1; | |
4943 | coding->common_flags | |
4944 | = (VECTORP (eol_type) ? CODING_REQUIRE_DETECTION_MASK : 0); | |
5e5c78be KH |
4945 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
4946 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
4947 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
4948 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
4949 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
4950 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 4951 | |
df7492f9 | 4952 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 KH |
4953 | coding->max_charset_id = SCHARS (val) - 1; |
4954 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 | 4955 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
4608c386 | 4956 | |
df7492f9 KH |
4957 | coding_type = CODING_ATTR_TYPE (attrs); |
4958 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 4959 | { |
df7492f9 KH |
4960 | coding->detector = NULL; |
4961 | coding->decoder = decode_coding_raw_text; | |
4962 | coding->encoder = encode_coding_raw_text; | |
4963 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 4964 | } |
df7492f9 | 4965 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 4966 | { |
df7492f9 KH |
4967 | int i; |
4968 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
4969 | ||
4970 | /* Invoke graphic register 0 to plane 0. */ | |
4971 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
4972 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
4973 | CODING_ISO_INVOCATION (coding, 1) | |
4974 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
4975 | /* Setup the initial status of designation. */ | |
4976 | for (i = 0; i < 4; i++) | |
4977 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
4978 | /* Not single shifting initially. */ | |
4979 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
4980 | /* Beginning of buffer should also be regarded as bol. */ | |
4981 | CODING_ISO_BOL (coding) = 1; | |
4982 | coding->detector = detect_coding_iso_2022; | |
4983 | coding->decoder = decode_coding_iso_2022; | |
4984 | coding->encoder = encode_coding_iso_2022; | |
4985 | if (flags & CODING_ISO_FLAG_SAFE) | |
4986 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 4987 | coding->common_flags |
df7492f9 KH |
4988 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
4989 | | CODING_REQUIRE_FLUSHING_MASK); | |
4990 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
4991 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
4992 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
4993 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
4994 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
4995 | { | |
4996 | setup_iso_safe_charsets (attrs); | |
4997 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
4998 | coding->max_charset_id = SCHARS (val) - 1; |
4999 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
5000 | } |
5001 | CODING_ISO_FLAGS (coding) = flags; | |
d46c5b12 | 5002 | } |
df7492f9 | 5003 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 5004 | { |
df7492f9 KH |
5005 | coding->detector = detect_coding_charset; |
5006 | coding->decoder = decode_coding_charset; | |
5007 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5008 | coding->common_flags |
df7492f9 | 5009 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5010 | } |
df7492f9 | 5011 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5012 | { |
df7492f9 KH |
5013 | coding->detector = detect_coding_utf_8; |
5014 | coding->decoder = decode_coding_utf_8; | |
5015 | coding->encoder = encode_coding_utf_8; | |
5016 | coding->common_flags | |
5017 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
5018 | } | |
5019 | else if (EQ (coding_type, Qutf_16)) | |
5020 | { | |
5021 | val = AREF (attrs, coding_attr_utf_16_bom); | |
5022 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_16_detect_bom | |
5023 | : EQ (val, Qt) ? utf_16_with_bom | |
5024 | : utf_16_without_bom); | |
5025 | val = AREF (attrs, coding_attr_utf_16_endian); | |
b49a1807 | 5026 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5027 | : utf_16_little_endian); |
e19c3639 | 5028 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5029 | coding->detector = detect_coding_utf_16; |
5030 | coding->decoder = decode_coding_utf_16; | |
5031 | coding->encoder = encode_coding_utf_16; | |
5032 | coding->common_flags | |
5033 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
b49a1807 KH |
5034 | if (CODING_UTF_16_BOM (coding) == utf_16_detect_bom) |
5035 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5036 | } |
df7492f9 | 5037 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5038 | { |
df7492f9 KH |
5039 | coding->detector = detect_coding_ccl; |
5040 | coding->decoder = decode_coding_ccl; | |
5041 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5042 | coding->common_flags |
df7492f9 KH |
5043 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5044 | | CODING_REQUIRE_FLUSHING_MASK); | |
5045 | } | |
5046 | else if (EQ (coding_type, Qemacs_mule)) | |
5047 | { | |
5048 | coding->detector = detect_coding_emacs_mule; | |
5049 | coding->decoder = decode_coding_emacs_mule; | |
5050 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5051 | coding->common_flags |
df7492f9 KH |
5052 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5053 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
5054 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5055 | { | |
5056 | Lisp_Object tail, safe_charsets; | |
5057 | int max_charset_id = 0; | |
5058 | ||
5059 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5060 | tail = XCDR (tail)) | |
5061 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5062 | max_charset_id = XFASTINT (XCAR (tail)); | |
5063 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), | |
5064 | make_number (255)); | |
5065 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5066 | tail = XCDR (tail)) | |
8f924df7 | 5067 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5068 | coding->max_charset_id = max_charset_id; |
8f924df7 | 5069 | coding->safe_charsets = (char *) SDATA (safe_charsets); |
df7492f9 KH |
5070 | } |
5071 | } | |
5072 | else if (EQ (coding_type, Qshift_jis)) | |
5073 | { | |
5074 | coding->detector = detect_coding_sjis; | |
5075 | coding->decoder = decode_coding_sjis; | |
5076 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5077 | coding->common_flags |
df7492f9 KH |
5078 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5079 | } | |
5080 | else if (EQ (coding_type, Qbig5)) | |
5081 | { | |
5082 | coding->detector = detect_coding_big5; | |
5083 | coding->decoder = decode_coding_big5; | |
5084 | coding->encoder = encode_coding_big5; | |
c952af22 | 5085 | coding->common_flags |
df7492f9 KH |
5086 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5087 | } | |
5088 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5089 | { |
df7492f9 KH |
5090 | coding->detector = NULL; |
5091 | coding->decoder = decode_coding_raw_text; | |
5092 | coding->encoder = encode_coding_raw_text; | |
4ed46869 | 5093 | } |
4ed46869 | 5094 | |
df7492f9 | 5095 | return; |
4ed46869 KH |
5096 | } |
5097 | ||
df7492f9 KH |
5098 | /* Return raw-text or one of its subsidiaries that has the same |
5099 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5100 | |
df7492f9 KH |
5101 | Lisp_Object |
5102 | raw_text_coding_system (coding_system) | |
5103 | Lisp_Object coding_system; | |
ec6d2bb8 | 5104 | { |
0be8721c | 5105 | Lisp_Object spec, attrs; |
df7492f9 | 5106 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5107 | |
d3e4cb56 KH |
5108 | if (NILP (coding_system)) |
5109 | return Qraw_text; | |
df7492f9 KH |
5110 | spec = CODING_SYSTEM_SPEC (coding_system); |
5111 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5112 | |
df7492f9 KH |
5113 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5114 | return coding_system; | |
ec6d2bb8 | 5115 | |
df7492f9 KH |
5116 | eol_type = AREF (spec, 2); |
5117 | if (VECTORP (eol_type)) | |
5118 | return Qraw_text; | |
5119 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5120 | raw_text_eol_type = AREF (spec, 2); | |
5121 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5122 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5123 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5124 | } |
5125 | ||
54f78171 | 5126 | |
df7492f9 KH |
5127 | /* If CODING_SYSTEM doesn't specify end-of-line format but PARENT |
5128 | does, return one of the subsidiary that has the same eol-spec as | |
5129 | PARENT. Otherwise, return CODING_SYSTEM. */ | |
5130 | ||
5131 | Lisp_Object | |
5132 | coding_inherit_eol_type (coding_system, parent) | |
b74e4686 | 5133 | Lisp_Object coding_system, parent; |
54f78171 | 5134 | { |
3e139625 | 5135 | Lisp_Object spec, eol_type; |
54f78171 | 5136 | |
d3e4cb56 KH |
5137 | if (NILP (coding_system)) |
5138 | coding_system = Qraw_text; | |
df7492f9 | 5139 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5140 | eol_type = AREF (spec, 2); |
d3e4cb56 KH |
5141 | if (VECTORP (eol_type) |
5142 | && ! NILP (parent)) | |
df7492f9 KH |
5143 | { |
5144 | Lisp_Object parent_spec; | |
df7492f9 KH |
5145 | Lisp_Object parent_eol_type; |
5146 | ||
5147 | parent_spec | |
5148 | = CODING_SYSTEM_SPEC (buffer_defaults.buffer_file_coding_system); | |
5149 | parent_eol_type = AREF (parent_spec, 2); | |
5150 | if (EQ (parent_eol_type, Qunix)) | |
5151 | coding_system = AREF (eol_type, 0); | |
5152 | else if (EQ (parent_eol_type, Qdos)) | |
5153 | coding_system = AREF (eol_type, 1); | |
5154 | else if (EQ (parent_eol_type, Qmac)) | |
5155 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5156 | } |
df7492f9 | 5157 | return coding_system; |
54f78171 KH |
5158 | } |
5159 | ||
4ed46869 KH |
5160 | /* Emacs has a mechanism to automatically detect a coding system if it |
5161 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
5162 | it's impossible to distinguish some coding systems accurately | |
5163 | because they use the same range of codes. So, at first, coding | |
5164 | systems are categorized into 7, those are: | |
5165 | ||
0ef69138 | 5166 | o coding-category-emacs-mule |
4ed46869 KH |
5167 | |
5168 | The category for a coding system which has the same code range | |
5169 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 5170 | symbol) `emacs-mule' by default. |
4ed46869 KH |
5171 | |
5172 | o coding-category-sjis | |
5173 | ||
5174 | The category for a coding system which has the same code range | |
5175 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 5176 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
5177 | |
5178 | o coding-category-iso-7 | |
5179 | ||
5180 | The category for a coding system which has the same code range | |
7717c392 | 5181 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
5182 | shift and single shift functions. This can encode/decode all |
5183 | charsets. Assigned the coding-system (Lisp symbol) | |
5184 | `iso-2022-7bit' by default. | |
5185 | ||
5186 | o coding-category-iso-7-tight | |
5187 | ||
5188 | Same as coding-category-iso-7 except that this can | |
5189 | encode/decode only the specified charsets. | |
4ed46869 KH |
5190 | |
5191 | o coding-category-iso-8-1 | |
5192 | ||
5193 | The category for a coding system which has the same code range | |
5194 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5195 | for DIMENSION1 charset. This doesn't use any locking shift |
5196 | and single shift functions. Assigned the coding-system (Lisp | |
5197 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
5198 | |
5199 | o coding-category-iso-8-2 | |
5200 | ||
5201 | The category for a coding system which has the same code range | |
5202 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5203 | for DIMENSION2 charset. This doesn't use any locking shift |
5204 | and single shift functions. Assigned the coding-system (Lisp | |
5205 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 5206 | |
7717c392 | 5207 | o coding-category-iso-7-else |
4ed46869 KH |
5208 | |
5209 | The category for a coding system which has the same code range | |
df7492f9 | 5210 | as ISO2022 of 7-bit environemnt but uses locking shift or |
7717c392 KH |
5211 | single shift functions. Assigned the coding-system (Lisp |
5212 | symbol) `iso-2022-7bit-lock' by default. | |
5213 | ||
5214 | o coding-category-iso-8-else | |
5215 | ||
5216 | The category for a coding system which has the same code range | |
df7492f9 | 5217 | as ISO2022 of 8-bit environemnt but uses locking shift or |
7717c392 KH |
5218 | single shift functions. Assigned the coding-system (Lisp |
5219 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
5220 | |
5221 | o coding-category-big5 | |
5222 | ||
5223 | The category for a coding system which has the same code range | |
5224 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5225 | `cn-big5' by default. |
4ed46869 | 5226 | |
fa42c37f KH |
5227 | o coding-category-utf-8 |
5228 | ||
5229 | The category for a coding system which has the same code range | |
6e76ae91 | 5230 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
5231 | symbol) `utf-8' by default. |
5232 | ||
5233 | o coding-category-utf-16-be | |
5234 | ||
5235 | The category for a coding system in which a text has an | |
5236 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
5237 | endian at the head. Assigned the coding-system (Lisp symbol) | |
5238 | `utf-16-be' by default. | |
5239 | ||
5240 | o coding-category-utf-16-le | |
5241 | ||
5242 | The category for a coding system in which a text has an | |
5243 | Unicode signature (cf. Unicode Standard) in the order of | |
5244 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
5245 | symbol) `utf-16-le' by default. | |
5246 | ||
1397dc18 KH |
5247 | o coding-category-ccl |
5248 | ||
5249 | The category for a coding system of which encoder/decoder is | |
5250 | written in CCL programs. The default value is nil, i.e., no | |
5251 | coding system is assigned. | |
5252 | ||
4ed46869 KH |
5253 | o coding-category-binary |
5254 | ||
5255 | The category for a coding system not categorized in any of the | |
5256 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5257 | `no-conversion' by default. |
4ed46869 KH |
5258 | |
5259 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 5260 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
5261 | What Emacs does actually is to detect a category of coding system. |
5262 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 5263 | decide only one possible category, it selects a category of the |
4ed46869 KH |
5264 | highest priority. Priorities of categories are also specified by a |
5265 | user in a Lisp variable `coding-category-list'. | |
5266 | ||
5267 | */ | |
5268 | ||
df7492f9 KH |
5269 | #define EOL_SEEN_NONE 0 |
5270 | #define EOL_SEEN_LF 1 | |
5271 | #define EOL_SEEN_CR 2 | |
5272 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 5273 | |
ff0dacd7 KH |
5274 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
5275 | SOURCE is encoded. If CATEGORY is one of | |
5276 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
5277 | two-byte, else they are encoded by one-byte. | |
5278 | ||
5279 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 5280 | |
bc4bc72a | 5281 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
5282 | |
5283 | static int | |
89528eb3 | 5284 | detect_eol (source, src_bytes, category) |
f6cbaf43 | 5285 | const unsigned char *source; |
df7492f9 | 5286 | EMACS_INT src_bytes; |
89528eb3 | 5287 | enum coding_category category; |
4ed46869 | 5288 | { |
f6cbaf43 | 5289 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 5290 | unsigned char c; |
df7492f9 KH |
5291 | int total = 0; |
5292 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 5293 | |
89528eb3 | 5294 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 5295 | { |
df7492f9 | 5296 | int msb, lsb; |
fa42c37f | 5297 | |
89528eb3 KH |
5298 | msb = category == (coding_category_utf_16_le |
5299 | | coding_category_utf_16_le_nosig); | |
df7492f9 | 5300 | lsb = 1 - msb; |
fa42c37f | 5301 | |
df7492f9 | 5302 | while (src + 1 < src_end) |
fa42c37f | 5303 | { |
df7492f9 KH |
5304 | c = src[lsb]; |
5305 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 5306 | { |
df7492f9 KH |
5307 | int this_eol; |
5308 | ||
5309 | if (c == '\n') | |
5310 | this_eol = EOL_SEEN_LF; | |
5311 | else if (src + 3 >= src_end | |
5312 | || src[msb + 2] != 0 | |
5313 | || src[lsb + 2] != '\n') | |
5314 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 5315 | else |
8f924df7 | 5316 | this_eol = EOL_SEEN_CRLF; |
df7492f9 KH |
5317 | |
5318 | if (eol_seen == EOL_SEEN_NONE) | |
5319 | /* This is the first end-of-line. */ | |
5320 | eol_seen = this_eol; | |
5321 | else if (eol_seen != this_eol) | |
fa42c37f | 5322 | { |
df7492f9 KH |
5323 | /* The found type is different from what found before. */ |
5324 | eol_seen = EOL_SEEN_LF; | |
5325 | break; | |
fa42c37f | 5326 | } |
df7492f9 KH |
5327 | if (++total == MAX_EOL_CHECK_COUNT) |
5328 | break; | |
fa42c37f | 5329 | } |
df7492f9 | 5330 | src += 2; |
fa42c37f | 5331 | } |
bcf26d6a | 5332 | } |
d46c5b12 | 5333 | else |
c4825358 | 5334 | { |
df7492f9 | 5335 | while (src < src_end) |
27901516 | 5336 | { |
df7492f9 KH |
5337 | c = *src++; |
5338 | if (c == '\n' || c == '\r') | |
5339 | { | |
5340 | int this_eol; | |
d46c5b12 | 5341 | |
df7492f9 KH |
5342 | if (c == '\n') |
5343 | this_eol = EOL_SEEN_LF; | |
5344 | else if (src >= src_end || *src != '\n') | |
5345 | this_eol = EOL_SEEN_CR; | |
5346 | else | |
5347 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 5348 | |
df7492f9 KH |
5349 | if (eol_seen == EOL_SEEN_NONE) |
5350 | /* This is the first end-of-line. */ | |
5351 | eol_seen = this_eol; | |
5352 | else if (eol_seen != this_eol) | |
5353 | { | |
5354 | /* The found type is different from what found before. */ | |
5355 | eol_seen = EOL_SEEN_LF; | |
5356 | break; | |
5357 | } | |
5358 | if (++total == MAX_EOL_CHECK_COUNT) | |
5359 | break; | |
5360 | } | |
5361 | } | |
73be902c | 5362 | } |
df7492f9 | 5363 | return eol_seen; |
73be902c KH |
5364 | } |
5365 | ||
df7492f9 | 5366 | |
24a73b0a | 5367 | static Lisp_Object |
df7492f9 KH |
5368 | adjust_coding_eol_type (coding, eol_seen) |
5369 | struct coding_system *coding; | |
5370 | int eol_seen; | |
73be902c | 5371 | { |
0be8721c | 5372 | Lisp_Object eol_type; |
8f924df7 | 5373 | |
df7492f9 KH |
5374 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
5375 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
5376 | { |
5377 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
5378 | eol_type = Qunix; | |
5379 | } | |
6f197c07 | 5380 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
5381 | { |
5382 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
5383 | eol_type = Qdos; | |
5384 | } | |
6f197c07 | 5385 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
5386 | { |
5387 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
5388 | eol_type = Qmac; | |
5389 | } | |
5390 | return eol_type; | |
d46c5b12 | 5391 | } |
4ed46869 | 5392 | |
df7492f9 KH |
5393 | /* Detect how a text specified in CODING is encoded. If a coding |
5394 | system is detected, update fields of CODING by the detected coding | |
5395 | system. */ | |
0a28aafb | 5396 | |
df7492f9 KH |
5397 | void |
5398 | detect_coding (coding) | |
d46c5b12 | 5399 | struct coding_system *coding; |
d46c5b12 | 5400 | { |
8f924df7 | 5401 | const unsigned char *src, *src_end; |
df7492f9 | 5402 | Lisp_Object attrs, coding_type; |
d46c5b12 | 5403 | |
df7492f9 KH |
5404 | coding->consumed = coding->consumed_char = 0; |
5405 | coding->produced = coding->produced_char = 0; | |
5406 | coding_set_source (coding); | |
1c3478b0 | 5407 | |
df7492f9 | 5408 | src_end = coding->source + coding->src_bytes; |
1c3478b0 | 5409 | |
df7492f9 KH |
5410 | /* If we have not yet decided the text encoding type, detect it |
5411 | now. */ | |
5412 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 5413 | { |
df7492f9 KH |
5414 | int c, i; |
5415 | ||
24a73b0a | 5416 | for (i = 0, src = coding->source; src < src_end; i++, src++) |
d46c5b12 | 5417 | { |
df7492f9 | 5418 | c = *src; |
75e2a253 | 5419 | if (c & 0x80 || (c < 0x20 && (c == ISO_CODE_ESC |
df7492f9 KH |
5420 | || c == ISO_CODE_SI |
5421 | || c == ISO_CODE_SO))) | |
5422 | break; | |
d46c5b12 | 5423 | } |
df7492f9 KH |
5424 | coding->head_ascii = src - (coding->source + coding->consumed); |
5425 | ||
5426 | if (coding->head_ascii < coding->src_bytes) | |
d46c5b12 | 5427 | { |
ff0dacd7 KH |
5428 | struct coding_detection_info detect_info; |
5429 | enum coding_category category; | |
5430 | struct coding_system *this; | |
df7492f9 | 5431 | |
ff0dacd7 | 5432 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
df7492f9 | 5433 | for (i = 0; i < coding_category_raw_text; i++) |
d46c5b12 | 5434 | { |
ff0dacd7 KH |
5435 | category = coding_priorities[i]; |
5436 | this = coding_categories + category; | |
df7492f9 | 5437 | if (this->id < 0) |
fa42c37f | 5438 | { |
df7492f9 | 5439 | /* No coding system of this category is defined. */ |
ff0dacd7 | 5440 | detect_info.rejected |= (1 << category); |
fa42c37f | 5441 | } |
ff0dacd7 | 5442 | else if (category >= coding_category_raw_text) |
89528eb3 | 5443 | continue; |
ff0dacd7 | 5444 | else if (detect_info.checked & (1 << category)) |
fa42c37f | 5445 | { |
ff0dacd7 KH |
5446 | if (detect_info.found & (1 << category)) |
5447 | break; | |
fa42c37f | 5448 | } |
ff0dacd7 KH |
5449 | else if ((*(this->detector)) (coding, &detect_info) |
5450 | && detect_info.found & (1 << category)) | |
24a73b0a KH |
5451 | { |
5452 | if (category == coding_category_utf_16_auto) | |
5453 | { | |
5454 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
5455 | category = coding_category_utf_16_le; | |
5456 | else | |
5457 | category = coding_category_utf_16_be; | |
5458 | } | |
5459 | break; | |
5460 | } | |
d46c5b12 | 5461 | } |
ff0dacd7 KH |
5462 | if (i < coding_category_raw_text) |
5463 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5464 | else if (detect_info.rejected == CATEGORY_MASK_ANY) | |
df7492f9 | 5465 | setup_coding_system (Qraw_text, coding); |
ff0dacd7 | 5466 | else if (detect_info.rejected) |
df7492f9 | 5467 | for (i = 0; i < coding_category_raw_text; i++) |
ff0dacd7 KH |
5468 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) |
5469 | { | |
5470 | this = coding_categories + coding_priorities[i]; | |
5471 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5472 | break; | |
5473 | } | |
d46c5b12 | 5474 | } |
b73bfc1c | 5475 | } |
24a73b0a KH |
5476 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
5477 | == coding_category_utf_16_auto) | |
b49a1807 KH |
5478 | { |
5479 | Lisp_Object coding_systems; | |
5480 | struct coding_detection_info detect_info; | |
5481 | ||
5482 | coding_systems | |
5483 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_16_bom); | |
5484 | detect_info.found = detect_info.rejected = 0; | |
5485 | if (CONSP (coding_systems) | |
24a73b0a | 5486 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
5487 | { |
5488 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
5489 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 5490 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
5491 | setup_coding_system (XCDR (coding_systems), coding); |
5492 | } | |
5493 | } | |
4ed46869 | 5494 | } |
4ed46869 | 5495 | |
d46c5b12 | 5496 | |
aaaf0b1e | 5497 | static void |
df7492f9 | 5498 | decode_eol (coding) |
aaaf0b1e | 5499 | struct coding_system *coding; |
aaaf0b1e | 5500 | { |
24a73b0a KH |
5501 | Lisp_Object eol_type; |
5502 | unsigned char *p, *pbeg, *pend; | |
5503 | ||
5504 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
5505 | if (EQ (eol_type, Qunix)) | |
5506 | return; | |
5507 | ||
5508 | if (NILP (coding->dst_object)) | |
5509 | pbeg = coding->destination; | |
5510 | else | |
5511 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
5512 | pend = pbeg + coding->produced; | |
5513 | ||
5514 | if (VECTORP (eol_type)) | |
aaaf0b1e | 5515 | { |
df7492f9 | 5516 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 5517 | |
24a73b0a | 5518 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 5519 | { |
df7492f9 KH |
5520 | if (*p == '\n') |
5521 | eol_seen |= EOL_SEEN_LF; | |
5522 | else if (*p == '\r') | |
aaaf0b1e | 5523 | { |
df7492f9 | 5524 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 5525 | { |
df7492f9 KH |
5526 | eol_seen |= EOL_SEEN_CRLF; |
5527 | p++; | |
aaaf0b1e | 5528 | } |
aaaf0b1e | 5529 | else |
df7492f9 | 5530 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 5531 | } |
aaaf0b1e | 5532 | } |
24a73b0a KH |
5533 | if (eol_seen != EOL_SEEN_NONE |
5534 | && eol_seen != EOL_SEEN_LF | |
5535 | && eol_seen != EOL_SEEN_CRLF | |
5536 | && eol_seen != EOL_SEEN_CR) | |
5537 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 5538 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 5539 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 5540 | } |
d46c5b12 | 5541 | |
24a73b0a | 5542 | if (EQ (eol_type, Qmac)) |
27901516 | 5543 | { |
24a73b0a | 5544 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
5545 | if (*p == '\r') |
5546 | *p = '\n'; | |
4ed46869 | 5547 | } |
24a73b0a | 5548 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 5549 | { |
24a73b0a | 5550 | int n = 0; |
b73bfc1c | 5551 | |
24a73b0a KH |
5552 | if (NILP (coding->dst_object)) |
5553 | { | |
5554 | for (p = pend - 2; p >= pbeg; p--) | |
5555 | if (*p == '\r') | |
5556 | { | |
5557 | safe_bcopy ((char *) (p + 1), (char *) p, pend-- - p - 1); | |
5558 | n++; | |
5559 | } | |
5560 | } | |
5561 | else | |
5562 | { | |
5563 | for (p = pend - 2; p >= pbeg; p--) | |
5564 | if (*p == '\r') | |
5565 | { | |
5566 | int pos_byte = coding->dst_pos_byte + (p - pbeg); | |
5567 | int pos = BYTE_TO_CHAR (pos_byte); | |
5568 | ||
5569 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
5570 | n++; | |
5571 | } | |
5572 | } | |
5573 | coding->produced -= n; | |
5574 | coding->produced_char -= n; | |
aaaf0b1e | 5575 | } |
4ed46869 KH |
5576 | } |
5577 | ||
7d64c6ad | 5578 | |
a6f87d34 KH |
5579 | /* Return a translation table (or list of them) from coding system |
5580 | attribute vector ATTRS for encoding (ENCODEP is nonzero) or | |
5581 | decoding (ENCODEP is zero). */ | |
7d64c6ad | 5582 | |
e6a54062 | 5583 | static Lisp_Object |
09ee6fdd KH |
5584 | get_translation_table (attrs, encodep, max_lookup) |
5585 | Lisp_Object attrs; | |
5586 | int encodep, *max_lookup; | |
7d64c6ad KH |
5587 | { |
5588 | Lisp_Object standard, translation_table; | |
09ee6fdd | 5589 | Lisp_Object val; |
7d64c6ad KH |
5590 | |
5591 | if (encodep) | |
5592 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
5593 | standard = Vstandard_translation_table_for_encode; | |
5594 | else | |
5595 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
5596 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 5597 | if (NILP (translation_table)) |
09ee6fdd KH |
5598 | translation_table = standard; |
5599 | else | |
a6f87d34 | 5600 | { |
09ee6fdd KH |
5601 | if (SYMBOLP (translation_table)) |
5602 | translation_table = Fget (translation_table, Qtranslation_table); | |
5603 | else if (CONSP (translation_table)) | |
5604 | { | |
5605 | translation_table = Fcopy_sequence (translation_table); | |
5606 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
5607 | if (SYMBOLP (XCAR (val))) | |
5608 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
5609 | } | |
5610 | if (CHAR_TABLE_P (standard)) | |
5611 | { | |
5612 | if (CONSP (translation_table)) | |
5613 | translation_table = nconc2 (translation_table, | |
5614 | Fcons (standard, Qnil)); | |
5615 | else | |
5616 | translation_table = Fcons (translation_table, | |
5617 | Fcons (standard, Qnil)); | |
5618 | } | |
a6f87d34 | 5619 | } |
2170c8f0 KH |
5620 | |
5621 | if (max_lookup) | |
09ee6fdd | 5622 | { |
2170c8f0 KH |
5623 | *max_lookup = 1; |
5624 | if (CHAR_TABLE_P (translation_table) | |
5625 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
5626 | { | |
5627 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
5628 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
5629 | *max_lookup = XFASTINT (val); | |
5630 | } | |
5631 | else if (CONSP (translation_table)) | |
5632 | { | |
5633 | Lisp_Object tail, val; | |
09ee6fdd | 5634 | |
2170c8f0 KH |
5635 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
5636 | if (CHAR_TABLE_P (XCAR (tail)) | |
5637 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
5638 | { | |
5639 | val = XCHAR_TABLE (XCAR (tail))->extras[1]; | |
5640 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
5641 | *max_lookup = XFASTINT (val); | |
5642 | } | |
5643 | } | |
a6f87d34 | 5644 | } |
7d64c6ad KH |
5645 | return translation_table; |
5646 | } | |
5647 | ||
09ee6fdd KH |
5648 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
5649 | do { \ | |
5650 | trans = Qnil; \ | |
5651 | if (CHAR_TABLE_P (table)) \ | |
5652 | { \ | |
5653 | trans = CHAR_TABLE_REF (table, c); \ | |
5654 | if (CHARACTERP (trans)) \ | |
5655 | c = XFASTINT (trans), trans = Qnil; \ | |
5656 | } \ | |
5657 | else if (CONSP (table)) \ | |
5658 | { \ | |
5659 | Lisp_Object tail; \ | |
5660 | \ | |
5661 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
5662 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
5663 | { \ | |
5664 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
5665 | if (CHARACTERP (trans)) \ | |
5666 | c = XFASTINT (trans), trans = Qnil; \ | |
5667 | else if (! NILP (trans)) \ | |
5668 | break; \ | |
5669 | } \ | |
5670 | } \ | |
e6a54062 KH |
5671 | } while (0) |
5672 | ||
7d64c6ad | 5673 | |
69a80ea3 KH |
5674 | static Lisp_Object |
5675 | get_translation (val, buf, buf_end, last_block, from_nchars, to_nchars) | |
5676 | Lisp_Object val; | |
5677 | int *buf, *buf_end; | |
5678 | int last_block; | |
5679 | int *from_nchars, *to_nchars; | |
5680 | { | |
433f7f87 KH |
5681 | /* VAL is TO or (([FROM-CHAR ...] . TO) ...) where TO is TO-CHAR or |
5682 | [TO-CHAR ...]. */ | |
69a80ea3 KH |
5683 | if (CONSP (val)) |
5684 | { | |
433f7f87 | 5685 | Lisp_Object from, tail; |
69a80ea3 KH |
5686 | int i, len; |
5687 | ||
433f7f87 | 5688 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
69a80ea3 | 5689 | { |
433f7f87 KH |
5690 | val = XCAR (tail); |
5691 | from = XCAR (val); | |
5692 | len = ASIZE (from); | |
5693 | for (i = 0; i < len; i++) | |
5694 | { | |
5695 | if (buf + i == buf_end) | |
5696 | { | |
5697 | if (! last_block) | |
5698 | return Qt; | |
5699 | break; | |
5700 | } | |
5701 | if (XINT (AREF (from, i)) != buf[i]) | |
5702 | break; | |
5703 | } | |
5704 | if (i == len) | |
5705 | { | |
5706 | val = XCDR (val); | |
5707 | *from_nchars = len; | |
5708 | break; | |
5709 | } | |
69a80ea3 | 5710 | } |
433f7f87 KH |
5711 | if (! CONSP (tail)) |
5712 | return Qnil; | |
69a80ea3 KH |
5713 | } |
5714 | if (VECTORP (val)) | |
5715 | *buf = XINT (AREF (val, 0)), *to_nchars = ASIZE (val); | |
5716 | else | |
5717 | *buf = XINT (val); | |
5718 | return val; | |
5719 | } | |
5720 | ||
5721 | ||
d46c5b12 | 5722 | static int |
69a80ea3 | 5723 | produce_chars (coding, translation_table, last_block) |
df7492f9 | 5724 | struct coding_system *coding; |
69a80ea3 KH |
5725 | Lisp_Object translation_table; |
5726 | int last_block; | |
4ed46869 | 5727 | { |
df7492f9 KH |
5728 | unsigned char *dst = coding->destination + coding->produced; |
5729 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5730 | int produced; | |
5731 | int produced_chars = 0; | |
69a80ea3 | 5732 | int carryover = 0; |
4ed46869 | 5733 | |
df7492f9 | 5734 | if (! coding->chars_at_source) |
4ed46869 | 5735 | { |
df7492f9 | 5736 | /* Characters are in coding->charbuf. */ |
fba4576f AS |
5737 | int *buf = coding->charbuf; |
5738 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 5739 | |
df7492f9 KH |
5740 | if (BUFFERP (coding->src_object) |
5741 | && EQ (coding->src_object, coding->dst_object)) | |
8f924df7 | 5742 | dst_end = ((unsigned char *) coding->source) + coding->consumed; |
4ed46869 | 5743 | |
df7492f9 | 5744 | while (buf < buf_end) |
4ed46869 | 5745 | { |
69a80ea3 | 5746 | int c = *buf, i; |
bc4bc72a | 5747 | |
df7492f9 KH |
5748 | if (c >= 0) |
5749 | { | |
69a80ea3 KH |
5750 | int from_nchars = 1, to_nchars = 1; |
5751 | Lisp_Object trans = Qnil; | |
5752 | ||
09ee6fdd | 5753 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 5754 | if (! NILP (trans)) |
69a80ea3 KH |
5755 | { |
5756 | trans = get_translation (trans, buf, buf_end, last_block, | |
5757 | &from_nchars, &to_nchars); | |
5758 | if (EQ (trans, Qt)) | |
5759 | break; | |
5760 | c = *buf; | |
5761 | } | |
5762 | ||
5763 | if (dst + MAX_MULTIBYTE_LENGTH * to_nchars > dst_end) | |
5764 | { | |
5765 | dst = alloc_destination (coding, | |
5766 | buf_end - buf | |
5767 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
5768 | dst); | |
5769 | dst_end = coding->destination + coding->dst_bytes; | |
5770 | } | |
5771 | ||
433f7f87 | 5772 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 5773 | { |
433f7f87 KH |
5774 | if (i > 0) |
5775 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
5776 | if (coding->dst_multibyte |
5777 | || ! CHAR_BYTE8_P (c)) | |
5778 | CHAR_STRING_ADVANCE (c, dst); | |
5779 | else | |
5780 | *dst++ = CHAR_TO_BYTE8 (c); | |
5781 | } | |
5782 | produced_chars += to_nchars; | |
5783 | *buf++ = to_nchars; | |
5784 | while (--from_nchars > 0) | |
5785 | *buf++ = 0; | |
d46c5b12 | 5786 | } |
df7492f9 | 5787 | else |
69a80ea3 KH |
5788 | /* This is an annotation datum. (-C) is the length. */ |
5789 | buf += -c; | |
4ed46869 | 5790 | } |
69a80ea3 | 5791 | carryover = buf_end - buf; |
4ed46869 | 5792 | } |
fa42c37f | 5793 | else |
fa42c37f | 5794 | { |
8f924df7 KH |
5795 | const unsigned char *src = coding->source; |
5796 | const unsigned char *src_end = src + coding->src_bytes; | |
df7492f9 | 5797 | Lisp_Object eol_type; |
fa42c37f | 5798 | |
df7492f9 | 5799 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
4ed46869 | 5800 | |
df7492f9 | 5801 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 5802 | { |
df7492f9 | 5803 | if (coding->src_multibyte) |
fa42c37f | 5804 | { |
71c81426 | 5805 | int multibytep = 1; |
df7492f9 | 5806 | int consumed_chars; |
d46c5b12 | 5807 | |
df7492f9 KH |
5808 | while (1) |
5809 | { | |
8f924df7 | 5810 | const unsigned char *src_base = src; |
df7492f9 | 5811 | int c; |
b73bfc1c | 5812 | |
df7492f9 KH |
5813 | ONE_MORE_BYTE (c); |
5814 | if (c == '\r') | |
5815 | { | |
5816 | if (EQ (eol_type, Qdos)) | |
5817 | { | |
98725083 KH |
5818 | if (src == src_end) |
5819 | { | |
065e3595 KH |
5820 | record_conversion_result |
5821 | (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
98725083 KH |
5822 | goto no_more_source; |
5823 | } | |
5824 | if (*src == '\n') | |
df7492f9 KH |
5825 | c = *src++; |
5826 | } | |
5827 | else if (EQ (eol_type, Qmac)) | |
5828 | c = '\n'; | |
5829 | } | |
5830 | if (dst == dst_end) | |
5831 | { | |
2c78b7e1 | 5832 | coding->consumed = src - coding->source; |
b73bfc1c | 5833 | |
2c78b7e1 | 5834 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5835 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5836 | if (dst == dst_end) |
5837 | { | |
5838 | dst = alloc_destination (coding, src_end - src + 1, | |
5839 | dst); | |
5840 | dst_end = coding->destination + coding->dst_bytes; | |
5841 | coding_set_source (coding); | |
5842 | src = coding->source + coding->consumed; | |
5843 | src_end = coding->source + coding->src_bytes; | |
5844 | } | |
df7492f9 KH |
5845 | } |
5846 | *dst++ = c; | |
5847 | produced_chars++; | |
5848 | } | |
5849 | no_more_source: | |
5850 | ; | |
fa42c37f KH |
5851 | } |
5852 | else | |
df7492f9 KH |
5853 | while (src < src_end) |
5854 | { | |
71c81426 | 5855 | int multibytep = 1; |
df7492f9 | 5856 | int c = *src++; |
b73bfc1c | 5857 | |
df7492f9 KH |
5858 | if (c == '\r') |
5859 | { | |
5860 | if (EQ (eol_type, Qdos)) | |
5861 | { | |
5862 | if (src < src_end | |
5863 | && *src == '\n') | |
5864 | c = *src++; | |
5865 | } | |
5866 | else if (EQ (eol_type, Qmac)) | |
5867 | c = '\n'; | |
5868 | } | |
5869 | if (dst >= dst_end - 1) | |
5870 | { | |
2c78b7e1 | 5871 | coding->consumed = src - coding->source; |
df7492f9 | 5872 | |
2c78b7e1 | 5873 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5874 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5875 | if (dst >= dst_end - 1) |
5876 | { | |
5877 | dst = alloc_destination (coding, src_end - src + 2, | |
5878 | dst); | |
5879 | dst_end = coding->destination + coding->dst_bytes; | |
5880 | coding_set_source (coding); | |
5881 | src = coding->source + coding->consumed; | |
5882 | src_end = coding->source + coding->src_bytes; | |
5883 | } | |
df7492f9 KH |
5884 | } |
5885 | EMIT_ONE_BYTE (c); | |
5886 | } | |
d46c5b12 | 5887 | } |
df7492f9 KH |
5888 | else |
5889 | { | |
5890 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 5891 | { |
df7492f9 | 5892 | int require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 5893 | |
df7492f9 | 5894 | if (require > 0) |
fa42c37f | 5895 | { |
df7492f9 KH |
5896 | EMACS_INT offset = src - coding->source; |
5897 | ||
5898 | dst = alloc_destination (coding, require, dst); | |
5899 | coding_set_source (coding); | |
5900 | src = coding->source + offset; | |
5901 | src_end = coding->source + coding->src_bytes; | |
fa42c37f KH |
5902 | } |
5903 | } | |
df7492f9 KH |
5904 | produced_chars = coding->src_chars; |
5905 | while (src < src_end) | |
fa42c37f | 5906 | { |
df7492f9 KH |
5907 | int c = *src++; |
5908 | ||
5909 | if (c == '\r') | |
5910 | { | |
5911 | if (EQ (eol_type, Qdos)) | |
5912 | { | |
5913 | if (src < src_end | |
5914 | && *src == '\n') | |
5915 | c = *src++; | |
5916 | produced_chars--; | |
5917 | } | |
5918 | else if (EQ (eol_type, Qmac)) | |
5919 | c = '\n'; | |
5920 | } | |
5921 | *dst++ = c; | |
fa42c37f KH |
5922 | } |
5923 | } | |
2c78b7e1 KH |
5924 | coding->consumed = coding->src_bytes; |
5925 | coding->consumed_char = coding->src_chars; | |
fa42c37f KH |
5926 | } |
5927 | ||
df7492f9 KH |
5928 | produced = dst - (coding->destination + coding->produced); |
5929 | if (BUFFERP (coding->dst_object)) | |
5930 | insert_from_gap (produced_chars, produced); | |
5931 | coding->produced += produced; | |
5932 | coding->produced_char += produced_chars; | |
69a80ea3 | 5933 | return carryover; |
fa42c37f KH |
5934 | } |
5935 | ||
ff0dacd7 KH |
5936 | /* Compose text in CODING->object according to the annotation data at |
5937 | CHARBUF. CHARBUF is an array: | |
5938 | [ -LENGTH ANNOTATION_MASK FROM TO METHOD COMP_LEN [ COMPONENTS... ] ] | |
df7492f9 | 5939 | */ |
4ed46869 | 5940 | |
df7492f9 | 5941 | static INLINE void |
69a80ea3 | 5942 | produce_composition (coding, charbuf, pos) |
4ed46869 | 5943 | struct coding_system *coding; |
df7492f9 | 5944 | int *charbuf; |
69a80ea3 | 5945 | EMACS_INT pos; |
4ed46869 | 5946 | { |
df7492f9 | 5947 | int len; |
69a80ea3 | 5948 | EMACS_INT to; |
df7492f9 | 5949 | enum composition_method method; |
df7492f9 | 5950 | Lisp_Object components; |
fa42c37f | 5951 | |
df7492f9 | 5952 | len = -charbuf[0]; |
69a80ea3 | 5953 | to = pos + charbuf[2]; |
9ffd559c KH |
5954 | if (to <= pos) |
5955 | return; | |
69a80ea3 | 5956 | method = (enum composition_method) (charbuf[3]); |
d46c5b12 | 5957 | |
df7492f9 KH |
5958 | if (method == COMPOSITION_RELATIVE) |
5959 | components = Qnil; | |
9ffd559c KH |
5960 | else if (method >= COMPOSITION_WITH_RULE |
5961 | && method <= COMPOSITION_WITH_RULE_ALTCHARS) | |
d46c5b12 | 5962 | { |
df7492f9 KH |
5963 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
5964 | int i; | |
b73bfc1c | 5965 | |
69a80ea3 KH |
5966 | len -= 4; |
5967 | charbuf += 4; | |
df7492f9 | 5968 | for (i = 0; i < len; i++) |
9ffd559c KH |
5969 | { |
5970 | args[i] = make_number (charbuf[i]); | |
5971 | if (args[i] < 0) | |
5972 | return; | |
5973 | } | |
df7492f9 KH |
5974 | components = (method == COMPOSITION_WITH_ALTCHARS |
5975 | ? Fstring (len, args) : Fvector (len, args)); | |
d46c5b12 | 5976 | } |
9ffd559c KH |
5977 | else |
5978 | return; | |
69a80ea3 | 5979 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
5980 | } |
5981 | ||
d46c5b12 | 5982 | |
ff0dacd7 KH |
5983 | /* Put `charset' property on text in CODING->object according to |
5984 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 5985 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 5986 | */ |
d46c5b12 | 5987 | |
ff0dacd7 | 5988 | static INLINE void |
69a80ea3 | 5989 | produce_charset (coding, charbuf, pos) |
d46c5b12 | 5990 | struct coding_system *coding; |
ff0dacd7 | 5991 | int *charbuf; |
69a80ea3 | 5992 | EMACS_INT pos; |
d46c5b12 | 5993 | { |
69a80ea3 KH |
5994 | EMACS_INT from = pos - charbuf[2]; |
5995 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); | |
b73bfc1c | 5996 | |
69a80ea3 | 5997 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
5998 | Qcharset, CHARSET_NAME (charset), |
5999 | coding->dst_object); | |
d46c5b12 KH |
6000 | } |
6001 | ||
d46c5b12 | 6002 | |
df7492f9 KH |
6003 | #define CHARBUF_SIZE 0x4000 |
6004 | ||
6005 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
6006 | do { \ | |
6007 | int size = CHARBUF_SIZE;; \ | |
6008 | \ | |
6009 | coding->charbuf = NULL; \ | |
6010 | while (size > 1024) \ | |
6011 | { \ | |
6012 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
6013 | if (coding->charbuf) \ | |
6014 | break; \ | |
6015 | size >>= 1; \ | |
6016 | } \ | |
6017 | if (! coding->charbuf) \ | |
6018 | { \ | |
065e3595 | 6019 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
df7492f9 KH |
6020 | return coding->result; \ |
6021 | } \ | |
6022 | coding->charbuf_size = size; \ | |
6023 | } while (0) | |
4ed46869 | 6024 | |
d46c5b12 KH |
6025 | |
6026 | static void | |
69a80ea3 | 6027 | produce_annotation (coding, pos) |
d46c5b12 | 6028 | struct coding_system *coding; |
69a80ea3 | 6029 | EMACS_INT pos; |
d46c5b12 | 6030 | { |
df7492f9 KH |
6031 | int *charbuf = coding->charbuf; |
6032 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 6033 | |
ff0dacd7 KH |
6034 | if (NILP (coding->dst_object)) |
6035 | return; | |
d46c5b12 | 6036 | |
df7492f9 | 6037 | while (charbuf < charbuf_end) |
a84f1519 | 6038 | { |
df7492f9 | 6039 | if (*charbuf >= 0) |
69a80ea3 | 6040 | pos += *charbuf++; |
d46c5b12 | 6041 | else |
d46c5b12 | 6042 | { |
df7492f9 | 6043 | int len = -*charbuf; |
ff0dacd7 | 6044 | switch (charbuf[1]) |
df7492f9 KH |
6045 | { |
6046 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
69a80ea3 | 6047 | produce_composition (coding, charbuf, pos); |
df7492f9 | 6048 | break; |
ff0dacd7 | 6049 | case CODING_ANNOTATE_CHARSET_MASK: |
69a80ea3 | 6050 | produce_charset (coding, charbuf, pos); |
ff0dacd7 | 6051 | break; |
df7492f9 KH |
6052 | default: |
6053 | abort (); | |
6054 | } | |
6055 | charbuf += len; | |
d46c5b12 | 6056 | } |
a84f1519 | 6057 | } |
d46c5b12 KH |
6058 | } |
6059 | ||
df7492f9 KH |
6060 | /* Decode the data at CODING->src_object into CODING->dst_object. |
6061 | CODING->src_object is a buffer, a string, or nil. | |
6062 | CODING->dst_object is a buffer. | |
d46c5b12 | 6063 | |
df7492f9 KH |
6064 | If CODING->src_object is a buffer, it must be the current buffer. |
6065 | In this case, if CODING->src_pos is positive, it is a position of | |
6066 | the source text in the buffer, otherwise, the source text is in the | |
6067 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
6068 | the text from GPT (which must be the same as PT). If this is the | |
6069 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6070 | negative. | |
d46c5b12 | 6071 | |
df7492f9 KH |
6072 | If CODING->src_object is a string, CODING->src_pos in an index to |
6073 | that string. | |
d46c5b12 | 6074 | |
df7492f9 KH |
6075 | If CODING->src_object is nil, CODING->source must already point to |
6076 | the non-relocatable memory area. In this case, CODING->src_pos is | |
6077 | an offset from CODING->source. | |
73be902c | 6078 | |
df7492f9 KH |
6079 | The decoded data is inserted at the current point of the buffer |
6080 | CODING->dst_object. | |
6081 | */ | |
d46c5b12 | 6082 | |
df7492f9 KH |
6083 | static int |
6084 | decode_coding (coding) | |
d46c5b12 | 6085 | struct coding_system *coding; |
d46c5b12 | 6086 | { |
df7492f9 | 6087 | Lisp_Object attrs; |
24a73b0a | 6088 | Lisp_Object undo_list; |
7d64c6ad | 6089 | Lisp_Object translation_table; |
69a80ea3 KH |
6090 | int carryover; |
6091 | int i; | |
d46c5b12 | 6092 | |
df7492f9 KH |
6093 | if (BUFFERP (coding->src_object) |
6094 | && coding->src_pos > 0 | |
6095 | && coding->src_pos < GPT | |
6096 | && coding->src_pos + coding->src_chars > GPT) | |
6097 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 6098 | |
24a73b0a | 6099 | undo_list = Qt; |
df7492f9 | 6100 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 6101 | { |
df7492f9 KH |
6102 | if (current_buffer != XBUFFER (coding->dst_object)) |
6103 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6104 | if (GPT != PT) | |
6105 | move_gap_both (PT, PT_BYTE); | |
24a73b0a KH |
6106 | undo_list = current_buffer->undo_list; |
6107 | current_buffer->undo_list = Qt; | |
1c3478b0 KH |
6108 | } |
6109 | ||
df7492f9 KH |
6110 | coding->consumed = coding->consumed_char = 0; |
6111 | coding->produced = coding->produced_char = 0; | |
6112 | coding->chars_at_source = 0; | |
065e3595 | 6113 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 6114 | coding->errors = 0; |
1c3478b0 | 6115 | |
df7492f9 KH |
6116 | ALLOC_CONVERSION_WORK_AREA (coding); |
6117 | ||
6118 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 6119 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 6120 | |
69a80ea3 | 6121 | carryover = 0; |
df7492f9 | 6122 | do |
b73bfc1c | 6123 | { |
69a80ea3 KH |
6124 | EMACS_INT pos = coding->dst_pos + coding->produced_char; |
6125 | ||
df7492f9 KH |
6126 | coding_set_source (coding); |
6127 | coding->annotated = 0; | |
69a80ea3 | 6128 | coding->charbuf_used = carryover; |
df7492f9 | 6129 | (*(coding->decoder)) (coding); |
df7492f9 | 6130 | coding_set_destination (coding); |
69a80ea3 | 6131 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 6132 | if (coding->annotated) |
69a80ea3 KH |
6133 | produce_annotation (coding, pos); |
6134 | for (i = 0; i < carryover; i++) | |
6135 | coding->charbuf[i] | |
6136 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 6137 | } |
df7492f9 KH |
6138 | while (coding->consumed < coding->src_bytes |
6139 | && ! coding->result); | |
d46c5b12 | 6140 | |
69a80ea3 KH |
6141 | if (carryover > 0) |
6142 | { | |
6143 | coding_set_destination (coding); | |
6144 | coding->charbuf_used = carryover; | |
6145 | produce_chars (coding, translation_table, 1); | |
6146 | } | |
6147 | ||
df7492f9 KH |
6148 | coding->carryover_bytes = 0; |
6149 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 6150 | { |
df7492f9 | 6151 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 6152 | const unsigned char *src; |
df7492f9 KH |
6153 | |
6154 | coding_set_source (coding); | |
6155 | coding_set_destination (coding); | |
6156 | src = coding->source + coding->consumed; | |
6157 | ||
6158 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 6159 | { |
df7492f9 KH |
6160 | /* Flush out unprocessed data as binary chars. We are sure |
6161 | that the number of data is less than the size of | |
6162 | coding->charbuf. */ | |
065e3595 | 6163 | coding->charbuf_used = 0; |
df7492f9 | 6164 | while (nbytes-- > 0) |
1c3478b0 | 6165 | { |
df7492f9 | 6166 | int c = *src++; |
98725083 KH |
6167 | |
6168 | coding->charbuf[coding->charbuf_used++] = (c & 0x80 ? - c : c); | |
1c3478b0 | 6169 | } |
f6cbaf43 | 6170 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 6171 | } |
d46c5b12 | 6172 | else |
df7492f9 KH |
6173 | { |
6174 | /* Record unprocessed bytes in coding->carryover. We are | |
6175 | sure that the number of data is less than the size of | |
6176 | coding->carryover. */ | |
6177 | unsigned char *p = coding->carryover; | |
6178 | ||
6179 | coding->carryover_bytes = nbytes; | |
6180 | while (nbytes-- > 0) | |
6181 | *p++ = *src++; | |
1c3478b0 | 6182 | } |
df7492f9 | 6183 | coding->consumed = coding->src_bytes; |
b73bfc1c | 6184 | } |
69f76525 | 6185 | |
24a73b0a KH |
6186 | if (BUFFERP (coding->dst_object)) |
6187 | { | |
6188 | current_buffer->undo_list = undo_list; | |
6189 | record_insert (coding->dst_pos, coding->produced_char); | |
6190 | } | |
6191 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix)) | |
6192 | decode_eol (coding); | |
73be902c | 6193 | return coding->result; |
4ed46869 KH |
6194 | } |
6195 | ||
aaaf0b1e | 6196 | |
e1c23804 | 6197 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
6198 | ending before LIMIT of CODING->src_object (buffer or string), store |
6199 | the data in BUF, set *STOP to a starting position of the next | |
6200 | composition (if any) or to LIMIT, and return the address of the | |
6201 | next element of BUF. | |
6202 | ||
6203 | If such an annotation is not found, set *STOP to a starting | |
6204 | position of a composition after POS (if any) or to LIMIT, and | |
6205 | return BUF. */ | |
6206 | ||
6207 | static INLINE int * | |
6208 | handle_composition_annotation (pos, limit, coding, buf, stop) | |
6209 | EMACS_INT pos, limit; | |
aaaf0b1e | 6210 | struct coding_system *coding; |
ff0dacd7 KH |
6211 | int *buf; |
6212 | EMACS_INT *stop; | |
aaaf0b1e | 6213 | { |
ff0dacd7 KH |
6214 | EMACS_INT start, end; |
6215 | Lisp_Object prop; | |
aaaf0b1e | 6216 | |
ff0dacd7 KH |
6217 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
6218 | || end > limit) | |
6219 | *stop = limit; | |
6220 | else if (start > pos) | |
6221 | *stop = start; | |
6222 | else | |
aaaf0b1e | 6223 | { |
ff0dacd7 | 6224 | if (start == pos) |
aaaf0b1e | 6225 | { |
ff0dacd7 KH |
6226 | /* We found a composition. Store the corresponding |
6227 | annotation data in BUF. */ | |
6228 | int *head = buf; | |
6229 | enum composition_method method = COMPOSITION_METHOD (prop); | |
6230 | int nchars = COMPOSITION_LENGTH (prop); | |
6231 | ||
69a80ea3 | 6232 | ADD_COMPOSITION_DATA (buf, nchars, method); |
ff0dacd7 | 6233 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 6234 | { |
ff0dacd7 KH |
6235 | Lisp_Object components; |
6236 | int len, i, i_byte; | |
6237 | ||
6238 | components = COMPOSITION_COMPONENTS (prop); | |
6239 | if (VECTORP (components)) | |
aaaf0b1e | 6240 | { |
ff0dacd7 KH |
6241 | len = XVECTOR (components)->size; |
6242 | for (i = 0; i < len; i++) | |
6243 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 6244 | } |
ff0dacd7 | 6245 | else if (STRINGP (components)) |
aaaf0b1e | 6246 | { |
8f924df7 | 6247 | len = SCHARS (components); |
ff0dacd7 KH |
6248 | i = i_byte = 0; |
6249 | while (i < len) | |
6250 | { | |
6251 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
6252 | buf++; | |
6253 | } | |
6254 | } | |
6255 | else if (INTEGERP (components)) | |
6256 | { | |
6257 | len = 1; | |
6258 | *buf++ = XINT (components); | |
6259 | } | |
6260 | else if (CONSP (components)) | |
6261 | { | |
6262 | for (len = 0; CONSP (components); | |
6263 | len++, components = XCDR (components)) | |
6264 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 6265 | } |
aaaf0b1e | 6266 | else |
ff0dacd7 KH |
6267 | abort (); |
6268 | *head -= len; | |
aaaf0b1e | 6269 | } |
aaaf0b1e | 6270 | } |
ff0dacd7 KH |
6271 | |
6272 | if (find_composition (end, limit, &start, &end, &prop, | |
6273 | coding->src_object) | |
6274 | && end <= limit) | |
6275 | *stop = start; | |
6276 | else | |
6277 | *stop = limit; | |
aaaf0b1e | 6278 | } |
ff0dacd7 KH |
6279 | return buf; |
6280 | } | |
6281 | ||
6282 | ||
e1c23804 | 6283 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
6284 | CODING->src_object (buffer of string), store the data in BUF, set |
6285 | *STOP to the position where the value of `charset' property changes | |
6286 | (limiting by LIMIT), and return the address of the next element of | |
6287 | BUF. | |
6288 | ||
6289 | If the property value is nil, set *STOP to the position where the | |
6290 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
6291 | ||
6292 | static INLINE int * | |
6293 | handle_charset_annotation (pos, limit, coding, buf, stop) | |
6294 | EMACS_INT pos, limit; | |
6295 | struct coding_system *coding; | |
6296 | int *buf; | |
6297 | EMACS_INT *stop; | |
6298 | { | |
6299 | Lisp_Object val, next; | |
6300 | int id; | |
6301 | ||
6302 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
6303 | if (! NILP (val) && CHARSETP (val)) | |
6304 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
6305 | else | |
6306 | id = -1; | |
69a80ea3 | 6307 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
6308 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
6309 | coding->src_object, | |
6310 | make_number (limit)); | |
6311 | *stop = XINT (next); | |
6312 | return buf; | |
6313 | } | |
6314 | ||
6315 | ||
df7492f9 | 6316 | static void |
09ee6fdd | 6317 | consume_chars (coding, translation_table, max_lookup) |
df7492f9 | 6318 | struct coding_system *coding; |
433f7f87 | 6319 | Lisp_Object translation_table; |
09ee6fdd | 6320 | int max_lookup; |
df7492f9 KH |
6321 | { |
6322 | int *buf = coding->charbuf; | |
ff0dacd7 | 6323 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 6324 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 6325 | const unsigned char *src_end = coding->source + coding->src_bytes; |
ff0dacd7 KH |
6326 | EMACS_INT pos = coding->src_pos + coding->consumed_char; |
6327 | EMACS_INT end_pos = coding->src_pos + coding->src_chars; | |
df7492f9 KH |
6328 | int multibytep = coding->src_multibyte; |
6329 | Lisp_Object eol_type; | |
6330 | int c; | |
ff0dacd7 | 6331 | EMACS_INT stop, stop_composition, stop_charset; |
09ee6fdd | 6332 | int *lookup_buf = NULL; |
433f7f87 KH |
6333 | |
6334 | if (! NILP (translation_table)) | |
09ee6fdd | 6335 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 6336 | |
df7492f9 KH |
6337 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6338 | if (VECTORP (eol_type)) | |
6339 | eol_type = Qunix; | |
88993dfd | 6340 | |
df7492f9 KH |
6341 | /* Note: composition handling is not yet implemented. */ |
6342 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 6343 | |
0b5670c9 KH |
6344 | if (NILP (coding->src_object)) |
6345 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 6346 | else |
0b5670c9 KH |
6347 | { |
6348 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
6349 | stop = stop_composition = pos; | |
6350 | else | |
6351 | stop = stop_composition = end_pos; | |
6352 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
6353 | stop = stop_charset = pos; | |
6354 | else | |
6355 | stop_charset = end_pos; | |
6356 | } | |
ec6d2bb8 | 6357 | |
24a73b0a | 6358 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 6359 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 6360 | while (buf < buf_end) |
aaaf0b1e | 6361 | { |
433f7f87 KH |
6362 | Lisp_Object trans; |
6363 | ||
df7492f9 | 6364 | if (pos == stop) |
ec6d2bb8 | 6365 | { |
df7492f9 KH |
6366 | if (pos == end_pos) |
6367 | break; | |
ff0dacd7 KH |
6368 | if (pos == stop_composition) |
6369 | buf = handle_composition_annotation (pos, end_pos, coding, | |
6370 | buf, &stop_composition); | |
6371 | if (pos == stop_charset) | |
6372 | buf = handle_charset_annotation (pos, end_pos, coding, | |
6373 | buf, &stop_charset); | |
6374 | stop = (stop_composition < stop_charset | |
6375 | ? stop_composition : stop_charset); | |
df7492f9 KH |
6376 | } |
6377 | ||
6378 | if (! multibytep) | |
4776e638 | 6379 | { |
d3e4cb56 | 6380 | EMACS_INT bytes; |
aaaf0b1e | 6381 | |
d3e4cb56 KH |
6382 | if (! CODING_FOR_UNIBYTE (coding) |
6383 | && (bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
4776e638 KH |
6384 | c = STRING_CHAR_ADVANCE (src), pos += bytes; |
6385 | else | |
6386 | c = *src++, pos++; | |
6387 | } | |
df7492f9 | 6388 | else |
4776e638 | 6389 | c = STRING_CHAR_ADVANCE (src), pos++; |
df7492f9 KH |
6390 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
6391 | c = '\n'; | |
6392 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 6393 | { |
df7492f9 | 6394 | if (c == '\n') |
aaaf0b1e | 6395 | { |
df7492f9 KH |
6396 | if (EQ (eol_type, Qdos)) |
6397 | *buf++ = '\r'; | |
6398 | else | |
6399 | c = '\r'; | |
aaaf0b1e KH |
6400 | } |
6401 | } | |
433f7f87 | 6402 | |
e6a54062 | 6403 | trans = Qnil; |
09ee6fdd | 6404 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6405 | if (NILP (trans)) |
433f7f87 KH |
6406 | *buf++ = c; |
6407 | else | |
6408 | { | |
6409 | int from_nchars = 1, to_nchars = 1; | |
6410 | int *lookup_buf_end; | |
6411 | const unsigned char *p = src; | |
6412 | int i; | |
6413 | ||
6414 | lookup_buf[0] = c; | |
6415 | for (i = 1; i < max_lookup && p < src_end; i++) | |
6416 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
6417 | lookup_buf_end = lookup_buf + i; | |
6418 | trans = get_translation (trans, lookup_buf, lookup_buf_end, 1, | |
6419 | &from_nchars, &to_nchars); | |
6420 | if (EQ (trans, Qt) | |
6421 | || buf + to_nchars > buf_end) | |
6422 | break; | |
6423 | *buf++ = *lookup_buf; | |
6424 | for (i = 1; i < to_nchars; i++) | |
6425 | *buf++ = XINT (AREF (trans, i)); | |
6426 | for (i = 1; i < from_nchars; i++, pos++) | |
6427 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
6428 | } | |
aaaf0b1e | 6429 | } |
ec6d2bb8 | 6430 | |
df7492f9 KH |
6431 | coding->consumed = src - coding->source; |
6432 | coding->consumed_char = pos - coding->src_pos; | |
6433 | coding->charbuf_used = buf - coding->charbuf; | |
6434 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
6435 | } |
6436 | ||
4ed46869 | 6437 | |
df7492f9 KH |
6438 | /* Encode the text at CODING->src_object into CODING->dst_object. |
6439 | CODING->src_object is a buffer or a string. | |
6440 | CODING->dst_object is a buffer or nil. | |
6441 | ||
6442 | If CODING->src_object is a buffer, it must be the current buffer. | |
6443 | In this case, if CODING->src_pos is positive, it is a position of | |
6444 | the source text in the buffer, otherwise. the source text is in the | |
6445 | gap area of the buffer, and coding->src_pos specifies the offset of | |
6446 | the text from GPT (which must be the same as PT). If this is the | |
6447 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6448 | negative and CODING should not have `pre-write-conversion'. | |
6449 | ||
6450 | If CODING->src_object is a string, CODING should not have | |
6451 | `pre-write-conversion'. | |
6452 | ||
6453 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
6454 | the current point of that buffer. | |
6455 | ||
6456 | If CODING->dst_object is nil, the encoded data is placed at the | |
6457 | memory area specified by CODING->destination. */ | |
6458 | ||
6459 | static int | |
6460 | encode_coding (coding) | |
4ed46869 | 6461 | struct coding_system *coding; |
4ed46869 | 6462 | { |
df7492f9 | 6463 | Lisp_Object attrs; |
7d64c6ad | 6464 | Lisp_Object translation_table; |
09ee6fdd | 6465 | int max_lookup; |
9861e777 | 6466 | |
df7492f9 | 6467 | attrs = CODING_ID_ATTRS (coding->id); |
09ee6fdd | 6468 | translation_table = get_translation_table (attrs, 1, &max_lookup); |
4ed46869 | 6469 | |
df7492f9 | 6470 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 6471 | { |
df7492f9 KH |
6472 | set_buffer_internal (XBUFFER (coding->dst_object)); |
6473 | coding->dst_multibyte | |
6474 | = ! NILP (current_buffer->enable_multibyte_characters); | |
8844fa83 | 6475 | } |
4ed46869 | 6476 | |
b73bfc1c | 6477 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 6478 | coding->produced = coding->produced_char = 0; |
065e3595 | 6479 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 6480 | coding->errors = 0; |
b73bfc1c | 6481 | |
df7492f9 | 6482 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 6483 | |
df7492f9 KH |
6484 | do { |
6485 | coding_set_source (coding); | |
09ee6fdd | 6486 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
6487 | coding_set_destination (coding); |
6488 | (*(coding->encoder)) (coding); | |
6489 | } while (coding->consumed_char < coding->src_chars); | |
6490 | ||
6491 | if (BUFFERP (coding->dst_object)) | |
6492 | insert_from_gap (coding->produced_char, coding->produced); | |
6493 | ||
6494 | return (coding->result); | |
ec6d2bb8 KH |
6495 | } |
6496 | ||
fb88bf2d | 6497 | |
24a73b0a KH |
6498 | /* Name (or base name) of work buffer for code conversion. */ |
6499 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 6500 | |
24a73b0a KH |
6501 | /* A working buffer used by the top level conversion. Once it is |
6502 | created, it is never destroyed. It has the name | |
6503 | Vcode_conversion_workbuf_name. The other working buffers are | |
6504 | destroyed after the use is finished, and their names are modified | |
6505 | versions of Vcode_conversion_workbuf_name. */ | |
6506 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 6507 | |
24a73b0a KH |
6508 | /* 1 iff Vcode_conversion_reused_workbuf is already in use. */ |
6509 | static int reused_workbuf_in_use; | |
4ed46869 | 6510 | |
24a73b0a KH |
6511 | |
6512 | /* Return a working buffer of code convesion. MULTIBYTE specifies the | |
6513 | multibyteness of returning buffer. */ | |
b73bfc1c | 6514 | |
f6cbaf43 | 6515 | static Lisp_Object |
24a73b0a | 6516 | make_conversion_work_buffer (multibyte) |
f6cbaf43 | 6517 | int multibyte; |
df7492f9 | 6518 | { |
24a73b0a KH |
6519 | Lisp_Object name, workbuf; |
6520 | struct buffer *current; | |
4ed46869 | 6521 | |
24a73b0a | 6522 | if (reused_workbuf_in_use++) |
065e3595 KH |
6523 | { |
6524 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
6525 | workbuf = Fget_buffer_create (name); | |
6526 | } | |
df7492f9 | 6527 | else |
065e3595 KH |
6528 | { |
6529 | name = Vcode_conversion_workbuf_name; | |
6530 | workbuf = Fget_buffer_create (name); | |
6531 | if (NILP (Vcode_conversion_reused_workbuf)) | |
6532 | Vcode_conversion_reused_workbuf = workbuf; | |
6533 | } | |
24a73b0a KH |
6534 | current = current_buffer; |
6535 | set_buffer_internal (XBUFFER (workbuf)); | |
6536 | Ferase_buffer (); | |
df7492f9 | 6537 | current_buffer->undo_list = Qt; |
24a73b0a | 6538 | current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil; |
df7492f9 | 6539 | set_buffer_internal (current); |
24a73b0a | 6540 | return workbuf; |
df7492f9 | 6541 | } |
d46c5b12 | 6542 | |
24a73b0a | 6543 | |
4776e638 | 6544 | static Lisp_Object |
24a73b0a KH |
6545 | code_conversion_restore (arg) |
6546 | Lisp_Object arg; | |
4776e638 | 6547 | { |
24a73b0a KH |
6548 | Lisp_Object current, workbuf; |
6549 | ||
6550 | current = XCAR (arg); | |
6551 | workbuf = XCDR (arg); | |
6552 | if (! NILP (workbuf)) | |
6553 | { | |
6554 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
6555 | reused_workbuf_in_use = 0; | |
6556 | else if (! NILP (Fbuffer_live_p (workbuf))) | |
6557 | Fkill_buffer (workbuf); | |
6558 | } | |
6559 | set_buffer_internal (XBUFFER (current)); | |
4776e638 KH |
6560 | return Qnil; |
6561 | } | |
b73bfc1c | 6562 | |
24a73b0a KH |
6563 | Lisp_Object |
6564 | code_conversion_save (with_work_buf, multibyte) | |
4776e638 | 6565 | int with_work_buf, multibyte; |
df7492f9 | 6566 | { |
24a73b0a | 6567 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 6568 | |
4776e638 | 6569 | if (with_work_buf) |
24a73b0a KH |
6570 | workbuf = make_conversion_work_buffer (multibyte); |
6571 | record_unwind_protect (code_conversion_restore, | |
6572 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 6573 | return workbuf; |
df7492f9 | 6574 | } |
d46c5b12 | 6575 | |
df7492f9 KH |
6576 | int |
6577 | decode_coding_gap (coding, chars, bytes) | |
6578 | struct coding_system *coding; | |
6579 | EMACS_INT chars, bytes; | |
6580 | { | |
6581 | int count = specpdl_ptr - specpdl; | |
5e5c78be | 6582 | Lisp_Object attrs; |
fb88bf2d | 6583 | |
24a73b0a | 6584 | code_conversion_save (0, 0); |
ec6d2bb8 | 6585 | |
24a73b0a | 6586 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6587 | coding->src_chars = chars; |
6588 | coding->src_bytes = bytes; | |
6589 | coding->src_pos = -chars; | |
6590 | coding->src_pos_byte = -bytes; | |
6591 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 6592 | coding->dst_object = coding->src_object; |
df7492f9 KH |
6593 | coding->dst_pos = PT; |
6594 | coding->dst_pos_byte = PT_BYTE; | |
71c81426 | 6595 | coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters); |
98725083 | 6596 | coding->mode |= CODING_MODE_LAST_BLOCK; |
4ed46869 | 6597 | |
df7492f9 KH |
6598 | if (CODING_REQUIRE_DETECTION (coding)) |
6599 | detect_coding (coding); | |
8f924df7 | 6600 | |
df7492f9 | 6601 | decode_coding (coding); |
d46c5b12 | 6602 | |
5e5c78be KH |
6603 | attrs = CODING_ID_ATTRS (coding->id); |
6604 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 6605 | { |
5e5c78be KH |
6606 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
6607 | Lisp_Object val; | |
6608 | ||
6609 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
6610 | val = call1 (CODING_ATTR_POST_READ (attrs), |
6611 | make_number (coding->produced_char)); | |
5e5c78be KH |
6612 | CHECK_NATNUM (val); |
6613 | coding->produced_char += Z - prev_Z; | |
6614 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 6615 | } |
4ed46869 | 6616 | |
df7492f9 | 6617 | unbind_to (count, Qnil); |
b73bfc1c KH |
6618 | return coding->result; |
6619 | } | |
52d41803 | 6620 | |
4ed46869 | 6621 | int |
df7492f9 | 6622 | encode_coding_gap (coding, chars, bytes) |
4ed46869 | 6623 | struct coding_system *coding; |
df7492f9 | 6624 | EMACS_INT chars, bytes; |
4ed46869 | 6625 | { |
df7492f9 | 6626 | int count = specpdl_ptr - specpdl; |
4ed46869 | 6627 | |
24a73b0a | 6628 | code_conversion_save (0, 0); |
4ed46869 | 6629 | |
24a73b0a | 6630 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6631 | coding->src_chars = chars; |
6632 | coding->src_bytes = bytes; | |
6633 | coding->src_pos = -chars; | |
6634 | coding->src_pos_byte = -bytes; | |
6635 | coding->src_multibyte = chars < bytes; | |
6636 | coding->dst_object = coding->src_object; | |
6637 | coding->dst_pos = PT; | |
6638 | coding->dst_pos_byte = PT_BYTE; | |
4ed46869 | 6639 | |
df7492f9 | 6640 | encode_coding (coding); |
b73bfc1c | 6641 | |
df7492f9 KH |
6642 | unbind_to (count, Qnil); |
6643 | return coding->result; | |
6644 | } | |
4ed46869 | 6645 | |
d46c5b12 | 6646 | |
df7492f9 KH |
6647 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
6648 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 6649 | |
df7492f9 | 6650 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 6651 | |
df7492f9 KH |
6652 | If it is a buffer, the text is at point of the buffer. FROM and TO |
6653 | are positions in the buffer. | |
b73bfc1c | 6654 | |
df7492f9 KH |
6655 | If it is a string, the text is at the beginning of the string. |
6656 | FROM and TO are indices to the string. | |
4ed46869 | 6657 | |
df7492f9 KH |
6658 | If it is nil, the text is at coding->source. FROM and TO are |
6659 | indices to coding->source. | |
bb10be8b | 6660 | |
df7492f9 | 6661 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 6662 | |
df7492f9 KH |
6663 | If it is a buffer, the decoded text is inserted at point of the |
6664 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
6665 | is deleted. | |
4ed46869 | 6666 | |
df7492f9 KH |
6667 | If it is Qt, a string is made from the decoded text, and |
6668 | set in CODING->dst_object. | |
d46c5b12 | 6669 | |
df7492f9 | 6670 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 6671 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
6672 | CODING->destination by xmalloc. If the decoded text is longer than |
6673 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
6674 | */ | |
d46c5b12 | 6675 | |
df7492f9 KH |
6676 | void |
6677 | decode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6678 | dst_object) | |
d46c5b12 | 6679 | struct coding_system *coding; |
df7492f9 KH |
6680 | Lisp_Object src_object; |
6681 | EMACS_INT from, from_byte, to, to_byte; | |
6682 | Lisp_Object dst_object; | |
d46c5b12 | 6683 | { |
df7492f9 KH |
6684 | int count = specpdl_ptr - specpdl; |
6685 | unsigned char *destination; | |
6686 | EMACS_INT dst_bytes; | |
6687 | EMACS_INT chars = to - from; | |
6688 | EMACS_INT bytes = to_byte - from_byte; | |
6689 | Lisp_Object attrs; | |
4776e638 KH |
6690 | Lisp_Object buffer; |
6691 | int saved_pt = -1, saved_pt_byte; | |
d46c5b12 | 6692 | |
4776e638 | 6693 | buffer = Fcurrent_buffer (); |
93dec019 | 6694 | |
df7492f9 | 6695 | if (NILP (dst_object)) |
d46c5b12 | 6696 | { |
df7492f9 KH |
6697 | destination = coding->destination; |
6698 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 6699 | } |
93dec019 | 6700 | |
df7492f9 KH |
6701 | coding->src_object = src_object; |
6702 | coding->src_chars = chars; | |
6703 | coding->src_bytes = bytes; | |
6704 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 6705 | |
df7492f9 | 6706 | if (STRINGP (src_object)) |
d46c5b12 | 6707 | { |
df7492f9 KH |
6708 | coding->src_pos = from; |
6709 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6710 | } |
df7492f9 | 6711 | else if (BUFFERP (src_object)) |
88993dfd | 6712 | { |
df7492f9 KH |
6713 | set_buffer_internal (XBUFFER (src_object)); |
6714 | if (from != GPT) | |
6715 | move_gap_both (from, from_byte); | |
6716 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 6717 | { |
4776e638 | 6718 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6719 | TEMP_SET_PT_BOTH (from, from_byte); |
6720 | del_range_both (from, from_byte, to, to_byte, 1); | |
6721 | coding->src_pos = -chars; | |
6722 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 6723 | } |
df7492f9 | 6724 | else |
fb88bf2d | 6725 | { |
df7492f9 KH |
6726 | coding->src_pos = from; |
6727 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 6728 | } |
88993dfd KH |
6729 | } |
6730 | ||
df7492f9 KH |
6731 | if (CODING_REQUIRE_DETECTION (coding)) |
6732 | detect_coding (coding); | |
6733 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 6734 | |
2cb26057 KH |
6735 | if (EQ (dst_object, Qt) |
6736 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
6737 | && NILP (dst_object))) | |
b73bfc1c | 6738 | { |
24a73b0a | 6739 | coding->dst_object = code_conversion_save (1, 1); |
df7492f9 KH |
6740 | coding->dst_pos = BEG; |
6741 | coding->dst_pos_byte = BEG_BYTE; | |
6742 | coding->dst_multibyte = 1; | |
b73bfc1c | 6743 | } |
df7492f9 | 6744 | else if (BUFFERP (dst_object)) |
d46c5b12 | 6745 | { |
24a73b0a | 6746 | code_conversion_save (0, 0); |
df7492f9 KH |
6747 | coding->dst_object = dst_object; |
6748 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6749 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6750 | coding->dst_multibyte | |
6751 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
d46c5b12 KH |
6752 | } |
6753 | else | |
6754 | { | |
24a73b0a | 6755 | code_conversion_save (0, 0); |
df7492f9 KH |
6756 | coding->dst_object = Qnil; |
6757 | coding->dst_multibyte = 1; | |
d46c5b12 KH |
6758 | } |
6759 | ||
df7492f9 | 6760 | decode_coding (coding); |
fa46990e | 6761 | |
df7492f9 KH |
6762 | if (BUFFERP (coding->dst_object)) |
6763 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 6764 | |
df7492f9 | 6765 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 6766 | { |
df7492f9 KH |
6767 | struct gcpro gcpro1, gcpro2; |
6768 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; | |
2b4f9037 | 6769 | Lisp_Object val; |
d46c5b12 | 6770 | |
c0cc7f7f | 6771 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
df7492f9 KH |
6772 | GCPRO2 (coding->src_object, coding->dst_object); |
6773 | val = call1 (CODING_ATTR_POST_READ (attrs), | |
6774 | make_number (coding->produced_char)); | |
6775 | UNGCPRO; | |
6776 | CHECK_NATNUM (val); | |
6777 | coding->produced_char += Z - prev_Z; | |
6778 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 6779 | } |
de79a6a5 | 6780 | |
df7492f9 | 6781 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 6782 | { |
df7492f9 KH |
6783 | coding->dst_object = Fbuffer_string (); |
6784 | } | |
6785 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
6786 | { | |
6787 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6788 | if (dst_bytes < coding->produced) | |
6789 | { | |
6790 | destination | |
6791 | = (unsigned char *) xrealloc (destination, coding->produced); | |
6792 | if (! destination) | |
6793 | { | |
065e3595 KH |
6794 | record_conversion_result (coding, |
6795 | CODING_RESULT_INSUFFICIENT_DST); | |
df7492f9 KH |
6796 | unbind_to (count, Qnil); |
6797 | return; | |
6798 | } | |
6799 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
6800 | move_gap_both (BEGV, BEGV_BYTE); | |
6801 | bcopy (BEGV_ADDR, destination, coding->produced); | |
6802 | coding->destination = destination; | |
d46c5b12 | 6803 | } |
ec6d2bb8 | 6804 | } |
b73bfc1c | 6805 | |
4776e638 KH |
6806 | if (saved_pt >= 0) |
6807 | { | |
6808 | /* This is the case of: | |
6809 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
6810 | As we have moved PT while replacing the original buffer | |
6811 | contents, we must recover it now. */ | |
6812 | set_buffer_internal (XBUFFER (src_object)); | |
6813 | if (saved_pt < from) | |
6814 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
6815 | else if (saved_pt < from + chars) | |
6816 | TEMP_SET_PT_BOTH (from, from_byte); | |
6817 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
6818 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
6819 | saved_pt_byte + (coding->produced - bytes)); | |
6820 | else | |
6821 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
6822 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 6823 | } |
4776e638 | 6824 | |
065e3595 | 6825 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
6826 | } |
6827 | ||
d46c5b12 | 6828 | |
df7492f9 KH |
6829 | void |
6830 | encode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6831 | dst_object) | |
d46c5b12 | 6832 | struct coding_system *coding; |
df7492f9 KH |
6833 | Lisp_Object src_object; |
6834 | EMACS_INT from, from_byte, to, to_byte; | |
6835 | Lisp_Object dst_object; | |
d46c5b12 | 6836 | { |
b73bfc1c | 6837 | int count = specpdl_ptr - specpdl; |
df7492f9 KH |
6838 | EMACS_INT chars = to - from; |
6839 | EMACS_INT bytes = to_byte - from_byte; | |
6840 | Lisp_Object attrs; | |
4776e638 KH |
6841 | Lisp_Object buffer; |
6842 | int saved_pt = -1, saved_pt_byte; | |
df7492f9 | 6843 | |
4776e638 | 6844 | buffer = Fcurrent_buffer (); |
df7492f9 KH |
6845 | |
6846 | coding->src_object = src_object; | |
6847 | coding->src_chars = chars; | |
6848 | coding->src_bytes = bytes; | |
6849 | coding->src_multibyte = chars < bytes; | |
6850 | ||
6851 | attrs = CODING_ID_ATTRS (coding->id); | |
6852 | ||
6853 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
6bac5b12 | 6854 | { |
24a73b0a | 6855 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
6856 | set_buffer_internal (XBUFFER (coding->src_object)); |
6857 | if (STRINGP (src_object)) | |
6858 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
6859 | else if (BUFFERP (src_object)) | |
6860 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
6861 | else | |
6862 | insert_1_both (coding->source + from, chars, bytes, 0, 0, 0); | |
d46c5b12 | 6863 | |
df7492f9 KH |
6864 | if (EQ (src_object, dst_object)) |
6865 | { | |
6866 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 6867 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6868 | del_range_both (from, from_byte, to, to_byte, 1); |
6869 | set_buffer_internal (XBUFFER (coding->src_object)); | |
6870 | } | |
6871 | ||
ac87bbef KH |
6872 | call2 (CODING_ATTR_PRE_WRITE (attrs), |
6873 | make_number (BEG), make_number (Z)); | |
6874 | coding->src_object = Fcurrent_buffer (); | |
df7492f9 KH |
6875 | if (BEG != GPT) |
6876 | move_gap_both (BEG, BEG_BYTE); | |
6877 | coding->src_chars = Z - BEG; | |
6878 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
6879 | coding->src_pos = BEG; | |
6880 | coding->src_pos_byte = BEG_BYTE; | |
6881 | coding->src_multibyte = Z < Z_BYTE; | |
6882 | } | |
6883 | else if (STRINGP (src_object)) | |
d46c5b12 | 6884 | { |
24a73b0a | 6885 | code_conversion_save (0, 0); |
df7492f9 KH |
6886 | coding->src_pos = from; |
6887 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 6888 | } |
df7492f9 | 6889 | else if (BUFFERP (src_object)) |
b73bfc1c | 6890 | { |
24a73b0a | 6891 | code_conversion_save (0, 0); |
df7492f9 | 6892 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 6893 | if (EQ (src_object, dst_object)) |
d46c5b12 | 6894 | { |
4776e638 | 6895 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
6896 | coding->src_object = del_range_1 (from, to, 1, 1); |
6897 | coding->src_pos = 0; | |
6898 | coding->src_pos_byte = 0; | |
d46c5b12 | 6899 | } |
df7492f9 | 6900 | else |
d46c5b12 | 6901 | { |
ff0dacd7 KH |
6902 | if (from < GPT && to >= GPT) |
6903 | move_gap_both (from, from_byte); | |
df7492f9 KH |
6904 | coding->src_pos = from; |
6905 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6906 | } |
d46c5b12 | 6907 | } |
4776e638 | 6908 | else |
24a73b0a | 6909 | code_conversion_save (0, 0); |
d46c5b12 | 6910 | |
df7492f9 | 6911 | if (BUFFERP (dst_object)) |
88993dfd | 6912 | { |
df7492f9 | 6913 | coding->dst_object = dst_object; |
28f67a95 KH |
6914 | if (EQ (src_object, dst_object)) |
6915 | { | |
6916 | coding->dst_pos = from; | |
6917 | coding->dst_pos_byte = from_byte; | |
6918 | } | |
6919 | else | |
6920 | { | |
6921 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6922 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6923 | } | |
df7492f9 KH |
6924 | coding->dst_multibyte |
6925 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
88993dfd | 6926 | } |
df7492f9 | 6927 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 6928 | { |
df7492f9 | 6929 | coding->dst_object = Qnil; |
df7492f9 | 6930 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
6931 | if (coding->dst_bytes == 0) |
6932 | coding->dst_bytes = 1; | |
6933 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 6934 | coding->dst_multibyte = 0; |
d46c5b12 KH |
6935 | } |
6936 | else | |
6937 | { | |
df7492f9 KH |
6938 | coding->dst_object = Qnil; |
6939 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
6940 | } |
6941 | ||
df7492f9 | 6942 | encode_coding (coding); |
d46c5b12 | 6943 | |
df7492f9 | 6944 | if (EQ (dst_object, Qt)) |
d46c5b12 | 6945 | { |
df7492f9 KH |
6946 | if (BUFFERP (coding->dst_object)) |
6947 | coding->dst_object = Fbuffer_string (); | |
6948 | else | |
d46c5b12 | 6949 | { |
df7492f9 KH |
6950 | coding->dst_object |
6951 | = make_unibyte_string ((char *) coding->destination, | |
6952 | coding->produced); | |
6953 | xfree (coding->destination); | |
d46c5b12 | 6954 | } |
4ed46869 | 6955 | } |
d46c5b12 | 6956 | |
4776e638 KH |
6957 | if (saved_pt >= 0) |
6958 | { | |
6959 | /* This is the case of: | |
6960 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
6961 | As we have moved PT while replacing the original buffer | |
6962 | contents, we must recover it now. */ | |
6963 | set_buffer_internal (XBUFFER (src_object)); | |
6964 | if (saved_pt < from) | |
6965 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
6966 | else if (saved_pt < from + chars) | |
6967 | TEMP_SET_PT_BOTH (from, from_byte); | |
6968 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
6969 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
6970 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 6971 | else |
4776e638 KH |
6972 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
6973 | saved_pt_byte + (coding->produced - bytes)); | |
6974 | } | |
6975 | ||
df7492f9 | 6976 | unbind_to (count, Qnil); |
b73bfc1c KH |
6977 | } |
6978 | ||
df7492f9 | 6979 | |
b73bfc1c | 6980 | Lisp_Object |
df7492f9 | 6981 | preferred_coding_system () |
b73bfc1c | 6982 | { |
df7492f9 | 6983 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 6984 | |
df7492f9 | 6985 | return CODING_ID_NAME (id); |
4ed46869 KH |
6986 | } |
6987 | ||
6988 | \f | |
6989 | #ifdef emacs | |
1397dc18 | 6990 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 6991 | |
4ed46869 | 6992 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 6993 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 6994 | See the documentation of `define-coding-system' for information |
48b0f3ae PJ |
6995 | about coding-system objects. */) |
6996 | (obj) | |
4ed46869 KH |
6997 | Lisp_Object obj; |
6998 | { | |
df7492f9 | 6999 | return ((NILP (obj) || CODING_SYSTEM_P (obj)) ? Qt : Qnil); |
4ed46869 KH |
7000 | } |
7001 | ||
9d991de8 RS |
7002 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
7003 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae PJ |
7004 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
7005 | (prompt) | |
4ed46869 KH |
7006 | Lisp_Object prompt; |
7007 | { | |
e0e989f6 | 7008 | Lisp_Object val; |
9d991de8 RS |
7009 | do |
7010 | { | |
4608c386 KH |
7011 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
7012 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 7013 | } |
8f924df7 | 7014 | while (SCHARS (val) == 0); |
e0e989f6 | 7015 | return (Fintern (val, Qnil)); |
4ed46869 KH |
7016 | } |
7017 | ||
9b787f3e | 7018 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae PJ |
7019 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
7020 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. */) | |
7021 | (prompt, default_coding_system) | |
9b787f3e | 7022 | Lisp_Object prompt, default_coding_system; |
4ed46869 | 7023 | { |
f44d27ce | 7024 | Lisp_Object val; |
9b787f3e | 7025 | if (SYMBOLP (default_coding_system)) |
a3181084 | 7026 | XSETSTRING (default_coding_system, XPNTR (SYMBOL_NAME (default_coding_system))); |
4608c386 | 7027 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
7028 | Qt, Qnil, Qcoding_system_history, |
7029 | default_coding_system, Qnil); | |
8f924df7 | 7030 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
7031 | } |
7032 | ||
7033 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
7034 | 1, 1, 0, | |
48b0f3ae | 7035 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
7036 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
7037 | It is valid if it is nil or a symbol defined as a coding system by the | |
7038 | function `define-coding-system'. */) | |
df7492f9 | 7039 | (coding_system) |
4ed46869 KH |
7040 | Lisp_Object coding_system; |
7041 | { | |
b7826503 | 7042 | CHECK_SYMBOL (coding_system); |
4ed46869 KH |
7043 | if (!NILP (Fcoding_system_p (coding_system))) |
7044 | return coding_system; | |
7045 | while (1) | |
02ba4723 | 7046 | Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil)); |
4ed46869 | 7047 | } |
df7492f9 | 7048 | |
3a73fa5d | 7049 | \f |
89528eb3 KH |
7050 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
7051 | HIGHEST is nonzero, return the coding system of the highest | |
7052 | priority among the detected coding systems. Otherwize return a | |
7053 | list of detected coding systems sorted by their priorities. If | |
7054 | MULTIBYTEP is nonzero, it is assumed that the bytes are in correct | |
7055 | multibyte form but contains only ASCII and eight-bit chars. | |
7056 | Otherwise, the bytes are raw bytes. | |
7057 | ||
7058 | CODING-SYSTEM controls the detection as below: | |
7059 | ||
7060 | If it is nil, detect both text-format and eol-format. If the | |
7061 | text-format part of CODING-SYSTEM is already specified | |
7062 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
7063 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
7064 | detect only text-format. */ | |
7065 | ||
d46c5b12 | 7066 | Lisp_Object |
24a73b0a KH |
7067 | detect_coding_system (src, src_chars, src_bytes, highest, multibytep, |
7068 | coding_system) | |
8f924df7 | 7069 | const unsigned char *src; |
24a73b0a | 7070 | int src_chars, src_bytes, highest; |
0a28aafb | 7071 | int multibytep; |
df7492f9 | 7072 | Lisp_Object coding_system; |
4ed46869 | 7073 | { |
8f924df7 | 7074 | const unsigned char *src_end = src + src_bytes; |
df7492f9 KH |
7075 | Lisp_Object attrs, eol_type; |
7076 | Lisp_Object val; | |
7077 | struct coding_system coding; | |
89528eb3 | 7078 | int id; |
ff0dacd7 | 7079 | struct coding_detection_info detect_info; |
24a73b0a | 7080 | enum coding_category base_category; |
b73bfc1c | 7081 | |
df7492f9 KH |
7082 | if (NILP (coding_system)) |
7083 | coding_system = Qundecided; | |
7084 | setup_coding_system (coding_system, &coding); | |
7085 | attrs = CODING_ID_ATTRS (coding.id); | |
7086 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 7087 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 7088 | |
df7492f9 | 7089 | coding.source = src; |
24a73b0a | 7090 | coding.src_chars = src_chars; |
df7492f9 KH |
7091 | coding.src_bytes = src_bytes; |
7092 | coding.src_multibyte = multibytep; | |
7093 | coding.consumed = 0; | |
89528eb3 | 7094 | coding.mode |= CODING_MODE_LAST_BLOCK; |
d46c5b12 | 7095 | |
ff0dacd7 | 7096 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 7097 | |
89528eb3 | 7098 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
7099 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
7100 | if (base_category == coding_category_undecided) | |
4ed46869 | 7101 | { |
ff0dacd7 KH |
7102 | enum coding_category category; |
7103 | struct coding_system *this; | |
7104 | int c, i; | |
88993dfd | 7105 | |
24a73b0a KH |
7106 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
7107 | for (i = 0; src < src_end; i++, src++) | |
4ed46869 | 7108 | { |
df7492f9 | 7109 | c = *src; |
75e2a253 | 7110 | if (c & 0x80 || (c < 0x20 && (c == ISO_CODE_ESC |
24a73b0a KH |
7111 | || c == ISO_CODE_SI |
7112 | || c == ISO_CODE_SO))) | |
d46c5b12 | 7113 | break; |
4ed46869 | 7114 | } |
df7492f9 | 7115 | coding.head_ascii = src - coding.source; |
88993dfd | 7116 | |
df7492f9 KH |
7117 | if (src < src_end) |
7118 | for (i = 0; i < coding_category_raw_text; i++) | |
7119 | { | |
ff0dacd7 KH |
7120 | category = coding_priorities[i]; |
7121 | this = coding_categories + category; | |
b843d1ae | 7122 | |
df7492f9 KH |
7123 | if (this->id < 0) |
7124 | { | |
7125 | /* No coding system of this category is defined. */ | |
ff0dacd7 | 7126 | detect_info.rejected |= (1 << category); |
df7492f9 | 7127 | } |
ff0dacd7 | 7128 | else if (category >= coding_category_raw_text) |
89528eb3 | 7129 | continue; |
ff0dacd7 KH |
7130 | else if (detect_info.checked & (1 << category)) |
7131 | { | |
7132 | if (highest | |
7133 | && (detect_info.found & (1 << category))) | |
7134 | break; | |
7135 | } | |
df7492f9 KH |
7136 | else |
7137 | { | |
ff0dacd7 | 7138 | if ((*(this->detector)) (&coding, &detect_info) |
89528eb3 | 7139 | && highest |
ff0dacd7 | 7140 | && (detect_info.found & (1 << category))) |
24a73b0a KH |
7141 | { |
7142 | if (category == coding_category_utf_16_auto) | |
7143 | { | |
7144 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
7145 | category = coding_category_utf_16_le; | |
7146 | else | |
7147 | category = coding_category_utf_16_be; | |
7148 | } | |
7149 | break; | |
7150 | } | |
df7492f9 KH |
7151 | } |
7152 | } | |
ec6d2bb8 | 7153 | |
ff0dacd7 | 7154 | if (detect_info.rejected == CATEGORY_MASK_ANY) |
ec6d2bb8 | 7155 | { |
ff0dacd7 | 7156 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
89528eb3 KH |
7157 | id = coding_categories[coding_category_raw_text].id; |
7158 | val = Fcons (make_number (id), Qnil); | |
7159 | } | |
ff0dacd7 | 7160 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 7161 | { |
ff0dacd7 | 7162 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
7163 | id = coding_categories[coding_category_undecided].id; |
7164 | val = Fcons (make_number (id), Qnil); | |
7165 | } | |
7166 | else if (highest) | |
7167 | { | |
ff0dacd7 | 7168 | if (detect_info.found) |
ec6d2bb8 | 7169 | { |
ff0dacd7 KH |
7170 | detect_info.found = 1 << category; |
7171 | val = Fcons (make_number (this->id), Qnil); | |
7172 | } | |
7173 | else | |
7174 | for (i = 0; i < coding_category_raw_text; i++) | |
7175 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
7176 | { | |
7177 | detect_info.found = 1 << coding_priorities[i]; | |
7178 | id = coding_categories[coding_priorities[i]].id; | |
7179 | val = Fcons (make_number (id), Qnil); | |
7180 | break; | |
7181 | } | |
7182 | } | |
89528eb3 KH |
7183 | else |
7184 | { | |
ff0dacd7 KH |
7185 | int mask = detect_info.rejected | detect_info.found; |
7186 | int found = 0; | |
89528eb3 | 7187 | val = Qnil; |
ec6d2bb8 | 7188 | |
89528eb3 | 7189 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
7190 | { |
7191 | category = coding_priorities[i]; | |
7192 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 7193 | { |
ff0dacd7 KH |
7194 | found |= 1 << category; |
7195 | id = coding_categories[category].id; | |
7196 | val = Fcons (make_number (id), val); | |
7197 | } | |
7198 | } | |
7199 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
7200 | { | |
7201 | category = coding_priorities[i]; | |
7202 | if (detect_info.found & (1 << category)) | |
7203 | { | |
7204 | id = coding_categories[category].id; | |
7205 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 7206 | } |
ec6d2bb8 | 7207 | } |
ff0dacd7 | 7208 | detect_info.found |= found; |
ec6d2bb8 | 7209 | } |
ec6d2bb8 | 7210 | } |
24a73b0a KH |
7211 | else if (base_category == coding_category_utf_16_auto) |
7212 | { | |
7213 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
7214 | { | |
7215 | enum coding_category category; | |
7216 | struct coding_system *this; | |
7217 | ||
7218 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
7219 | this = coding_categories + coding_category_utf_16_le; | |
7220 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
7221 | this = coding_categories + coding_category_utf_16_be; | |
7222 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
7223 | this = coding_categories + coding_category_utf_16_be_nosig; | |
7224 | else | |
7225 | this = coding_categories + coding_category_utf_16_le_nosig; | |
7226 | val = Fcons (make_number (this->id), Qnil); | |
7227 | } | |
7228 | } | |
df7492f9 KH |
7229 | else |
7230 | { | |
ff0dacd7 | 7231 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 7232 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 7233 | } |
df7492f9 | 7234 | |
89528eb3 | 7235 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 7236 | { |
89528eb3 | 7237 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol; |
df7492f9 KH |
7238 | Lisp_Object tail; |
7239 | ||
89528eb3 KH |
7240 | if (VECTORP (eol_type)) |
7241 | { | |
ff0dacd7 | 7242 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
89528eb3 KH |
7243 | normal_eol = detect_eol (coding.source, src_bytes, |
7244 | coding_category_raw_text); | |
ff0dacd7 KH |
7245 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
7246 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
7247 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
7248 | coding_category_utf_16_be); | |
ff0dacd7 KH |
7249 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
7250 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
7251 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
7252 | coding_category_utf_16_le); | |
7253 | } | |
7254 | else | |
7255 | { | |
7256 | if (EQ (eol_type, Qunix)) | |
7257 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
7258 | else if (EQ (eol_type, Qdos)) | |
7259 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
7260 | else | |
7261 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
7262 | } | |
7263 | ||
df7492f9 KH |
7264 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
7265 | { | |
89528eb3 | 7266 | enum coding_category category; |
df7492f9 | 7267 | int this_eol; |
89528eb3 KH |
7268 | |
7269 | id = XINT (XCAR (tail)); | |
7270 | attrs = CODING_ID_ATTRS (id); | |
7271 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
7272 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
7273 | if (VECTORP (eol_type)) |
7274 | { | |
89528eb3 KH |
7275 | if (category == coding_category_utf_16_be |
7276 | || category == coding_category_utf_16_be_nosig) | |
7277 | this_eol = utf_16_be_eol; | |
7278 | else if (category == coding_category_utf_16_le | |
7279 | || category == coding_category_utf_16_le_nosig) | |
7280 | this_eol = utf_16_le_eol; | |
df7492f9 | 7281 | else |
89528eb3 KH |
7282 | this_eol = normal_eol; |
7283 | ||
df7492f9 KH |
7284 | if (this_eol == EOL_SEEN_LF) |
7285 | XSETCAR (tail, AREF (eol_type, 0)); | |
7286 | else if (this_eol == EOL_SEEN_CRLF) | |
7287 | XSETCAR (tail, AREF (eol_type, 1)); | |
7288 | else if (this_eol == EOL_SEEN_CR) | |
7289 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
7290 | else |
7291 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 7292 | } |
89528eb3 KH |
7293 | else |
7294 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
7295 | } |
7296 | } | |
ec6d2bb8 | 7297 | |
03699b14 | 7298 | return (highest ? XCAR (val) : val); |
ec6d2bb8 KH |
7299 | } |
7300 | ||
ec6d2bb8 | 7301 | |
d46c5b12 KH |
7302 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
7303 | 2, 3, 0, | |
48b0f3ae PJ |
7304 | doc: /* Detect coding system of the text in the region between START and END. |
7305 | Return a list of possible coding systems ordered by priority. | |
ec6d2bb8 | 7306 | |
48b0f3ae PJ |
7307 | If only ASCII characters are found, it returns a list of single element |
7308 | `undecided' or its subsidiary coding system according to a detected | |
7309 | end-of-line format. | |
ec6d2bb8 | 7310 | |
48b0f3ae PJ |
7311 | If optional argument HIGHEST is non-nil, return the coding system of |
7312 | highest priority. */) | |
7313 | (start, end, highest) | |
d46c5b12 KH |
7314 | Lisp_Object start, end, highest; |
7315 | { | |
7316 | int from, to; | |
7317 | int from_byte, to_byte; | |
ec6d2bb8 | 7318 | |
b7826503 PJ |
7319 | CHECK_NUMBER_COERCE_MARKER (start); |
7320 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 7321 | |
d46c5b12 KH |
7322 | validate_region (&start, &end); |
7323 | from = XINT (start), to = XINT (end); | |
7324 | from_byte = CHAR_TO_BYTE (from); | |
7325 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 7326 | |
d46c5b12 KH |
7327 | if (from < GPT && to >= GPT) |
7328 | move_gap_both (to, to_byte); | |
c210f766 | 7329 | |
d46c5b12 | 7330 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 7331 | to - from, to_byte - from_byte, |
0a28aafb KH |
7332 | !NILP (highest), |
7333 | !NILP (current_buffer | |
df7492f9 KH |
7334 | ->enable_multibyte_characters), |
7335 | Qnil); | |
ec6d2bb8 KH |
7336 | } |
7337 | ||
d46c5b12 KH |
7338 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
7339 | 1, 2, 0, | |
48b0f3ae PJ |
7340 | doc: /* Detect coding system of the text in STRING. |
7341 | Return a list of possible coding systems ordered by priority. | |
fb88bf2d | 7342 | |
48b0f3ae PJ |
7343 | If only ASCII characters are found, it returns a list of single element |
7344 | `undecided' or its subsidiary coding system according to a detected | |
7345 | end-of-line format. | |
d46c5b12 | 7346 | |
48b0f3ae PJ |
7347 | If optional argument HIGHEST is non-nil, return the coding system of |
7348 | highest priority. */) | |
7349 | (string, highest) | |
d46c5b12 KH |
7350 | Lisp_Object string, highest; |
7351 | { | |
b7826503 | 7352 | CHECK_STRING (string); |
b73bfc1c | 7353 | |
24a73b0a KH |
7354 | return detect_coding_system (SDATA (string), |
7355 | SCHARS (string), SBYTES (string), | |
8f924df7 | 7356 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 7357 | Qnil); |
4ed46869 | 7358 | } |
4ed46869 | 7359 | |
b73bfc1c | 7360 | |
df7492f9 KH |
7361 | static INLINE int |
7362 | char_encodable_p (c, attrs) | |
7363 | int c; | |
7364 | Lisp_Object attrs; | |
05e6f5dc | 7365 | { |
df7492f9 | 7366 | Lisp_Object tail; |
df7492f9 | 7367 | struct charset *charset; |
7d64c6ad | 7368 | Lisp_Object translation_table; |
d46c5b12 | 7369 | |
7d64c6ad | 7370 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 7371 | if (! NILP (translation_table)) |
7d64c6ad | 7372 | c = translate_char (translation_table, c); |
df7492f9 KH |
7373 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
7374 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 7375 | { |
df7492f9 KH |
7376 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
7377 | if (CHAR_CHARSET_P (c, charset)) | |
7378 | break; | |
e133c8fa | 7379 | } |
df7492f9 | 7380 | return (! NILP (tail)); |
05e6f5dc | 7381 | } |
83fa074f | 7382 | |
fb88bf2d | 7383 | |
df7492f9 KH |
7384 | /* Return a list of coding systems that safely encode the text between |
7385 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
7386 | systems not to check. The returned list doesn't contain any such | |
48468dac | 7387 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 7388 | unibyte, return t. */ |
e077cc80 | 7389 | |
df7492f9 KH |
7390 | DEFUN ("find-coding-systems-region-internal", |
7391 | Ffind_coding_systems_region_internal, | |
7392 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
7393 | doc: /* Internal use only. */) | |
7394 | (start, end, exclude) | |
7395 | Lisp_Object start, end, exclude; | |
7396 | { | |
7397 | Lisp_Object coding_attrs_list, safe_codings; | |
7398 | EMACS_INT start_byte, end_byte; | |
7c78e542 | 7399 | const unsigned char *p, *pbeg, *pend; |
df7492f9 KH |
7400 | int c; |
7401 | Lisp_Object tail, elt; | |
d46c5b12 | 7402 | |
df7492f9 KH |
7403 | if (STRINGP (start)) |
7404 | { | |
7405 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 7406 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
7407 | return Qt; |
7408 | start_byte = 0; | |
8f924df7 | 7409 | end_byte = SBYTES (start); |
df7492f9 KH |
7410 | } |
7411 | else | |
d46c5b12 | 7412 | { |
df7492f9 KH |
7413 | CHECK_NUMBER_COERCE_MARKER (start); |
7414 | CHECK_NUMBER_COERCE_MARKER (end); | |
7415 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
7416 | args_out_of_range (start, end); | |
7417 | if (NILP (current_buffer->enable_multibyte_characters)) | |
7418 | return Qt; | |
7419 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7420 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7421 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
7422 | return Qt; | |
d46c5b12 | 7423 | |
e1c23804 | 7424 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 7425 | { |
e1c23804 DL |
7426 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7427 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7428 | else |
e1c23804 | 7429 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
7430 | } |
7431 | } | |
7432 | ||
df7492f9 KH |
7433 | coding_attrs_list = Qnil; |
7434 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
7435 | if (NILP (exclude) | |
7436 | || NILP (Fmemq (XCAR (tail), exclude))) | |
7437 | { | |
7438 | Lisp_Object attrs; | |
d46c5b12 | 7439 | |
df7492f9 KH |
7440 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
7441 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
7442 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
7443 | { |
7444 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 7445 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
7446 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
7447 | } | |
df7492f9 | 7448 | } |
d46c5b12 | 7449 | |
df7492f9 | 7450 | if (STRINGP (start)) |
8f924df7 | 7451 | p = pbeg = SDATA (start); |
df7492f9 KH |
7452 | else |
7453 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
7454 | pend = p + (end_byte - start_byte); | |
b843d1ae | 7455 | |
df7492f9 KH |
7456 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
7457 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 7458 | |
05e6f5dc | 7459 | while (p < pend) |
72d1a715 | 7460 | { |
df7492f9 KH |
7461 | if (ASCII_BYTE_P (*p)) |
7462 | p++; | |
72d1a715 RS |
7463 | else |
7464 | { | |
df7492f9 | 7465 | c = STRING_CHAR_ADVANCE (p); |
12410ef1 | 7466 | |
df7492f9 KH |
7467 | charset_map_loaded = 0; |
7468 | for (tail = coding_attrs_list; CONSP (tail);) | |
7469 | { | |
7470 | elt = XCAR (tail); | |
7471 | if (NILP (elt)) | |
7472 | tail = XCDR (tail); | |
7473 | else if (char_encodable_p (c, elt)) | |
7474 | tail = XCDR (tail); | |
7475 | else if (CONSP (XCDR (tail))) | |
7476 | { | |
7477 | XSETCAR (tail, XCAR (XCDR (tail))); | |
7478 | XSETCDR (tail, XCDR (XCDR (tail))); | |
7479 | } | |
7480 | else | |
7481 | { | |
7482 | XSETCAR (tail, Qnil); | |
7483 | tail = XCDR (tail); | |
7484 | } | |
7485 | } | |
7486 | if (charset_map_loaded) | |
7487 | { | |
7488 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 7489 | |
df7492f9 | 7490 | if (STRINGP (start)) |
8f924df7 | 7491 | pbeg = SDATA (start); |
df7492f9 KH |
7492 | else |
7493 | pbeg = BYTE_POS_ADDR (start_byte); | |
7494 | p = pbeg + p_offset; | |
7495 | pend = pbeg + pend_offset; | |
7496 | } | |
7497 | } | |
ec6d2bb8 | 7498 | } |
fb88bf2d | 7499 | |
988b3759 | 7500 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
7501 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
7502 | if (! NILP (XCAR (tail))) | |
7503 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 7504 | |
05e6f5dc KH |
7505 | return safe_codings; |
7506 | } | |
4956c225 | 7507 | |
d46c5b12 | 7508 | |
8f924df7 KH |
7509 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
7510 | Sunencodable_char_position, 3, 5, 0, | |
7511 | doc: /* | |
7512 | Return position of first un-encodable character in a region. | |
7513 | START and END specfiy the region and CODING-SYSTEM specifies the | |
7514 | encoding to check. Return nil if CODING-SYSTEM does encode the region. | |
d46c5b12 | 7515 | |
8f924df7 KH |
7516 | If optional 4th argument COUNT is non-nil, it specifies at most how |
7517 | many un-encodable characters to search. In this case, the value is a | |
7518 | list of positions. | |
d46c5b12 | 7519 | |
8f924df7 KH |
7520 | If optional 5th argument STRING is non-nil, it is a string to search |
7521 | for un-encodable characters. In that case, START and END are indexes | |
7522 | to the string. */) | |
7523 | (start, end, coding_system, count, string) | |
7524 | Lisp_Object start, end, coding_system, count, string; | |
7525 | { | |
7526 | int n; | |
7527 | struct coding_system coding; | |
7d64c6ad | 7528 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 KH |
7529 | Lisp_Object positions; |
7530 | int from, to; | |
7531 | const unsigned char *p, *stop, *pend; | |
7532 | int ascii_compatible; | |
fb88bf2d | 7533 | |
8f924df7 KH |
7534 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
7535 | attrs = CODING_ID_ATTRS (coding.id); | |
7536 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
7537 | return Qnil; | |
7538 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
7539 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 7540 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 7541 | |
8f924df7 KH |
7542 | if (NILP (string)) |
7543 | { | |
7544 | validate_region (&start, &end); | |
7545 | from = XINT (start); | |
7546 | to = XINT (end); | |
7547 | if (NILP (current_buffer->enable_multibyte_characters) | |
7548 | || (ascii_compatible | |
7549 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
7550 | return Qnil; | |
7551 | p = CHAR_POS_ADDR (from); | |
7552 | pend = CHAR_POS_ADDR (to); | |
7553 | if (from < GPT && to >= GPT) | |
7554 | stop = GPT_ADDR; | |
7555 | else | |
7556 | stop = pend; | |
7557 | } | |
7558 | else | |
7559 | { | |
7560 | CHECK_STRING (string); | |
7561 | CHECK_NATNUM (start); | |
7562 | CHECK_NATNUM (end); | |
7563 | from = XINT (start); | |
7564 | to = XINT (end); | |
7565 | if (from > to | |
7566 | || to > SCHARS (string)) | |
7567 | args_out_of_range_3 (string, start, end); | |
7568 | if (! STRING_MULTIBYTE (string)) | |
7569 | return Qnil; | |
7570 | p = SDATA (string) + string_char_to_byte (string, from); | |
7571 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
7572 | if (ascii_compatible && (to - from) == (pend - p)) | |
7573 | return Qnil; | |
7574 | } | |
f2558efd | 7575 | |
8f924df7 KH |
7576 | if (NILP (count)) |
7577 | n = 1; | |
7578 | else | |
b73bfc1c | 7579 | { |
8f924df7 KH |
7580 | CHECK_NATNUM (count); |
7581 | n = XINT (count); | |
b73bfc1c KH |
7582 | } |
7583 | ||
8f924df7 KH |
7584 | positions = Qnil; |
7585 | while (1) | |
d46c5b12 | 7586 | { |
8f924df7 | 7587 | int c; |
ec6d2bb8 | 7588 | |
8f924df7 KH |
7589 | if (ascii_compatible) |
7590 | while (p < stop && ASCII_BYTE_P (*p)) | |
7591 | p++, from++; | |
7592 | if (p >= stop) | |
0e79d667 | 7593 | { |
8f924df7 KH |
7594 | if (p >= pend) |
7595 | break; | |
7596 | stop = pend; | |
7597 | p = GAP_END_ADDR; | |
0e79d667 | 7598 | } |
ec6d2bb8 | 7599 | |
8f924df7 KH |
7600 | c = STRING_CHAR_ADVANCE (p); |
7601 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
7602 | && ! char_charset (translate_char (translation_table, c), |
7603 | charset_list, NULL)) | |
ec6d2bb8 | 7604 | { |
8f924df7 KH |
7605 | positions = Fcons (make_number (from), positions); |
7606 | n--; | |
7607 | if (n == 0) | |
7608 | break; | |
ec6d2bb8 KH |
7609 | } |
7610 | ||
8f924df7 KH |
7611 | from++; |
7612 | } | |
d46c5b12 | 7613 | |
8f924df7 KH |
7614 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
7615 | } | |
d46c5b12 | 7616 | |
d46c5b12 | 7617 | |
df7492f9 KH |
7618 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
7619 | Scheck_coding_systems_region, 3, 3, 0, | |
7620 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 7621 | |
df7492f9 KH |
7622 | START and END are buffer positions specifying the region. |
7623 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 7624 | |
df7492f9 KH |
7625 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
7626 | CODING-SYSTEM is a member of CODING-SYSTEM-LIst and can't encode the | |
7627 | whole region, POS0, POS1, ... are buffer positions where non-encodable | |
7628 | characters are found. | |
93dec019 | 7629 | |
df7492f9 KH |
7630 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
7631 | value is nil. | |
93dec019 | 7632 | |
df7492f9 KH |
7633 | START may be a string. In that case, check if the string is |
7634 | encodable, and the value contains indices to the string instead of | |
7635 | buffer positions. END is ignored. */) | |
7636 | (start, end, coding_system_list) | |
7637 | Lisp_Object start, end, coding_system_list; | |
05e6f5dc | 7638 | { |
df7492f9 KH |
7639 | Lisp_Object list; |
7640 | EMACS_INT start_byte, end_byte; | |
7641 | int pos; | |
7c78e542 | 7642 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 7643 | int c; |
7d64c6ad | 7644 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 7645 | |
05e6f5dc KH |
7646 | if (STRINGP (start)) |
7647 | { | |
df7492f9 | 7648 | if (!STRING_MULTIBYTE (start) |
8f924df7 | 7649 | && SCHARS (start) != SBYTES (start)) |
df7492f9 KH |
7650 | return Qnil; |
7651 | start_byte = 0; | |
8f924df7 | 7652 | end_byte = SBYTES (start); |
df7492f9 | 7653 | pos = 0; |
d46c5b12 | 7654 | } |
05e6f5dc | 7655 | else |
b73bfc1c | 7656 | { |
b7826503 PJ |
7657 | CHECK_NUMBER_COERCE_MARKER (start); |
7658 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
7659 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
7660 | args_out_of_range (start, end); | |
7661 | if (NILP (current_buffer->enable_multibyte_characters)) | |
df7492f9 KH |
7662 | return Qnil; |
7663 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7664 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7665 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
05e6f5dc | 7666 | return Qt; |
df7492f9 | 7667 | |
e1c23804 | 7668 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 7669 | { |
e1c23804 DL |
7670 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7671 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7672 | else |
e1c23804 | 7673 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 7674 | } |
e1c23804 | 7675 | pos = XINT (start); |
b73bfc1c | 7676 | } |
7553d0e1 | 7677 | |
df7492f9 KH |
7678 | list = Qnil; |
7679 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 7680 | { |
df7492f9 | 7681 | elt = XCAR (tail); |
7d64c6ad | 7682 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
7683 | ASET (attrs, coding_attr_trans_tbl, |
7684 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 7685 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
7686 | } |
7687 | ||
df7492f9 | 7688 | if (STRINGP (start)) |
8f924df7 | 7689 | p = pbeg = SDATA (start); |
72d1a715 | 7690 | else |
df7492f9 KH |
7691 | p = pbeg = BYTE_POS_ADDR (start_byte); |
7692 | pend = p + (end_byte - start_byte); | |
4ed46869 | 7693 | |
df7492f9 KH |
7694 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
7695 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 7696 | |
df7492f9 | 7697 | while (p < pend) |
d46c5b12 | 7698 | { |
df7492f9 KH |
7699 | if (ASCII_BYTE_P (*p)) |
7700 | p++; | |
e133c8fa | 7701 | else |
05e6f5dc | 7702 | { |
df7492f9 KH |
7703 | c = STRING_CHAR_ADVANCE (p); |
7704 | ||
7705 | charset_map_loaded = 0; | |
7706 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
7707 | { | |
7708 | elt = XCDR (XCAR (tail)); | |
7709 | if (! char_encodable_p (c, XCAR (elt))) | |
7710 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
7711 | } | |
7712 | if (charset_map_loaded) | |
7713 | { | |
7714 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
7715 | ||
7716 | if (STRINGP (start)) | |
8f924df7 | 7717 | pbeg = SDATA (start); |
df7492f9 KH |
7718 | else |
7719 | pbeg = BYTE_POS_ADDR (start_byte); | |
7720 | p = pbeg + p_offset; | |
7721 | pend = pbeg + pend_offset; | |
7722 | } | |
05e6f5dc | 7723 | } |
df7492f9 | 7724 | pos++; |
d46c5b12 | 7725 | } |
4ed46869 | 7726 | |
df7492f9 KH |
7727 | tail = list; |
7728 | list = Qnil; | |
7729 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 7730 | { |
df7492f9 KH |
7731 | elt = XCAR (tail); |
7732 | if (CONSP (XCDR (XCDR (elt)))) | |
7733 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
7734 | list); | |
ec6d2bb8 | 7735 | } |
2b4f9037 | 7736 | |
df7492f9 | 7737 | return list; |
d46c5b12 KH |
7738 | } |
7739 | ||
3fd9494b | 7740 | |
b73bfc1c | 7741 | Lisp_Object |
df7492f9 KH |
7742 | code_convert_region (start, end, coding_system, dst_object, encodep, norecord) |
7743 | Lisp_Object start, end, coding_system, dst_object; | |
7744 | int encodep, norecord; | |
4ed46869 | 7745 | { |
3a73fa5d | 7746 | struct coding_system coding; |
df7492f9 KH |
7747 | EMACS_INT from, from_byte, to, to_byte; |
7748 | Lisp_Object src_object; | |
4ed46869 | 7749 | |
b7826503 PJ |
7750 | CHECK_NUMBER_COERCE_MARKER (start); |
7751 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
7752 | if (NILP (coding_system)) |
7753 | coding_system = Qno_conversion; | |
7754 | else | |
7755 | CHECK_CODING_SYSTEM (coding_system); | |
7756 | src_object = Fcurrent_buffer (); | |
7757 | if (NILP (dst_object)) | |
7758 | dst_object = src_object; | |
7759 | else if (! EQ (dst_object, Qt)) | |
7760 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 7761 | |
d46c5b12 KH |
7762 | validate_region (&start, &end); |
7763 | from = XFASTINT (start); | |
df7492f9 | 7764 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 7765 | to = XFASTINT (end); |
df7492f9 | 7766 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 7767 | |
df7492f9 KH |
7768 | setup_coding_system (coding_system, &coding); |
7769 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 7770 | |
df7492f9 KH |
7771 | if (encodep) |
7772 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7773 | dst_object); | |
7774 | else | |
7775 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7776 | dst_object); | |
7777 | if (! norecord) | |
7778 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 7779 | |
df7492f9 KH |
7780 | return (BUFFERP (dst_object) |
7781 | ? make_number (coding.produced_char) | |
7782 | : coding.dst_object); | |
4031e2bf | 7783 | } |
78108bcd | 7784 | |
4ed46869 | 7785 | |
4031e2bf | 7786 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 7787 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 7788 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
7789 | When called from a program, takes four arguments: |
7790 | START, END, CODING-SYSTEM, and DESTINATION. | |
7791 | START and END are buffer positions. | |
8844fa83 | 7792 | |
df7492f9 KH |
7793 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
7794 | If nil, the region between START and END is replace by the decoded text. | |
7795 | If buffer, the decoded text is inserted in the buffer. | |
7796 | If t, the decoded text is returned. | |
8844fa83 | 7797 | |
48b0f3ae PJ |
7798 | This function sets `last-coding-system-used' to the precise coding system |
7799 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7800 | not fully specified.) | |
7801 | It returns the length of the decoded text. */) | |
df7492f9 KH |
7802 | (start, end, coding_system, destination) |
7803 | Lisp_Object start, end, coding_system, destination; | |
4031e2bf | 7804 | { |
df7492f9 | 7805 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 7806 | } |
8844fa83 | 7807 | |
3a73fa5d | 7808 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
7809 | 3, 4, "r\nzCoding system: ", |
7810 | doc: /* Encode the current region by specified coding system. | |
48b0f3ae PJ |
7811 | When called from a program, takes three arguments: |
7812 | START, END, and CODING-SYSTEM. START and END are buffer positions. | |
d46c5b12 | 7813 | |
df7492f9 KH |
7814 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
7815 | If nil, the region between START and END is replace by the encoded text. | |
7816 | If buffer, the encoded text is inserted in the buffer. | |
7817 | If t, the encoded text is returned. | |
2391eaa4 | 7818 | |
48b0f3ae PJ |
7819 | This function sets `last-coding-system-used' to the precise coding system |
7820 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7821 | not fully specified.) | |
7822 | It returns the length of the encoded text. */) | |
df7492f9 KH |
7823 | (start, end, coding_system, destination) |
7824 | Lisp_Object start, end, coding_system, destination; | |
3a73fa5d | 7825 | { |
df7492f9 | 7826 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
7827 | } |
7828 | ||
7829 | Lisp_Object | |
df7492f9 KH |
7830 | code_convert_string (string, coding_system, dst_object, |
7831 | encodep, nocopy, norecord) | |
7832 | Lisp_Object string, coding_system, dst_object; | |
7833 | int encodep, nocopy, norecord; | |
b73bfc1c | 7834 | { |
4031e2bf | 7835 | struct coding_system coding; |
df7492f9 | 7836 | EMACS_INT chars, bytes; |
ec6d2bb8 | 7837 | |
b7826503 | 7838 | CHECK_STRING (string); |
d46c5b12 | 7839 | if (NILP (coding_system)) |
4956c225 | 7840 | { |
df7492f9 KH |
7841 | if (! norecord) |
7842 | Vlast_coding_system_used = Qno_conversion; | |
7843 | if (NILP (dst_object)) | |
7844 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 7845 | } |
b73bfc1c | 7846 | |
df7492f9 KH |
7847 | if (NILP (coding_system)) |
7848 | coding_system = Qno_conversion; | |
7849 | else | |
7850 | CHECK_CODING_SYSTEM (coding_system); | |
7851 | if (NILP (dst_object)) | |
7852 | dst_object = Qt; | |
7853 | else if (! EQ (dst_object, Qt)) | |
7854 | CHECK_BUFFER (dst_object); | |
73be902c | 7855 | |
df7492f9 | 7856 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 7857 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
7858 | chars = SCHARS (string); |
7859 | bytes = SBYTES (string); | |
df7492f9 KH |
7860 | if (encodep) |
7861 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7862 | else | |
7863 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7864 | if (! norecord) | |
7865 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 7866 | |
df7492f9 KH |
7867 | return (BUFFERP (dst_object) |
7868 | ? make_number (coding.produced_char) | |
7869 | : coding.dst_object); | |
4ed46869 | 7870 | } |
73be902c | 7871 | |
b73bfc1c | 7872 | |
ecec61c1 | 7873 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 7874 | Do not set Vlast_coding_system_used. |
4ed46869 | 7875 | |
ec6d2bb8 KH |
7876 | This function is called only from macros DECODE_FILE and |
7877 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 7878 | |
ecec61c1 KH |
7879 | Lisp_Object |
7880 | code_convert_string_norecord (string, coding_system, encodep) | |
7881 | Lisp_Object string, coding_system; | |
7882 | int encodep; | |
4ed46869 | 7883 | { |
0be8721c | 7884 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
7885 | } |
7886 | ||
4ed46869 | 7887 | |
df7492f9 KH |
7888 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
7889 | 2, 4, 0, | |
7890 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
7891 | ||
7892 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
7893 | if the decoding operation is trivial. | |
ecec61c1 | 7894 | |
df7492f9 | 7895 | Optional fourth arg BUFFER non-nil meant that the decoded text is |
a3f6ee6d | 7896 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 | 7897 | the return value is BUFFER. |
ecec61c1 | 7898 | |
df7492f9 KH |
7899 | This function sets `last-coding-system-used' to the precise coding system |
7900 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7901 | not fully specified. */) | |
7902 | (string, coding_system, nocopy, buffer) | |
7903 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 7904 | { |
df7492f9 KH |
7905 | return code_convert_string (string, coding_system, buffer, |
7906 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
7907 | } |
7908 | ||
df7492f9 KH |
7909 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
7910 | 2, 4, 0, | |
7911 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
7912 | ||
7913 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
7914 | itself if the encoding operation is trivial. | |
7915 | ||
7916 | Optional fourth arg BUFFER non-nil meant that the encoded text is | |
a3f6ee6d | 7917 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 KH |
7918 | the return value is BUFFER. |
7919 | ||
7920 | This function sets `last-coding-system-used' to the precise coding system | |
7921 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7922 | not fully specified.) */) | |
7923 | (string, coding_system, nocopy, buffer) | |
7924 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 7925 | { |
df7492f9 | 7926 | return code_convert_string (string, coding_system, buffer, |
c197f191 | 7927 | 1, ! NILP (nocopy), 1); |
4ed46869 | 7928 | } |
df7492f9 | 7929 | |
3a73fa5d | 7930 | \f |
4ed46869 | 7931 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
7932 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
7933 | Return the corresponding character. */) | |
7934 | (code) | |
4ed46869 | 7935 | Lisp_Object code; |
4ed46869 | 7936 | { |
df7492f9 KH |
7937 | Lisp_Object spec, attrs, val; |
7938 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
7939 | int c; | |
4ed46869 | 7940 | |
df7492f9 KH |
7941 | CHECK_NATNUM (code); |
7942 | c = XFASTINT (code); | |
7943 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
7944 | attrs = AREF (spec, 0); | |
4ed46869 | 7945 | |
df7492f9 KH |
7946 | if (ASCII_BYTE_P (c) |
7947 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7948 | return code; | |
4ed46869 | 7949 | |
df7492f9 KH |
7950 | val = CODING_ATTR_CHARSET_LIST (attrs); |
7951 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
7952 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
7953 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 7954 | |
df7492f9 KH |
7955 | if (c <= 0x7F) |
7956 | charset = charset_roman; | |
7957 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 7958 | { |
df7492f9 KH |
7959 | charset = charset_kana; |
7960 | c -= 0x80; | |
4ed46869 | 7961 | } |
55ab7be3 | 7962 | else |
4ed46869 | 7963 | { |
004068e4 | 7964 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
7965 | |
7966 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
7967 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
7968 | error ("Invalid code: %d", code); | |
7969 | SJIS_TO_JIS (c); | |
7970 | charset = charset_kanji; | |
4ed46869 | 7971 | } |
df7492f9 KH |
7972 | c = DECODE_CHAR (charset, c); |
7973 | if (c < 0) | |
7974 | error ("Invalid code: %d", code); | |
7975 | return make_number (c); | |
93dec019 | 7976 | } |
4ed46869 | 7977 | |
48b0f3ae | 7978 | |
4ed46869 | 7979 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
7980 | doc: /* Encode a Japanese character CHAR to shift_jis encoding. |
7981 | Return the corresponding code in SJIS. */) | |
7982 | (ch) | |
df7492f9 | 7983 | Lisp_Object ch; |
4ed46869 | 7984 | { |
df7492f9 KH |
7985 | Lisp_Object spec, attrs, charset_list; |
7986 | int c; | |
7987 | struct charset *charset; | |
7988 | unsigned code; | |
48b0f3ae | 7989 | |
df7492f9 KH |
7990 | CHECK_CHARACTER (ch); |
7991 | c = XFASTINT (ch); | |
7992 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
7993 | attrs = AREF (spec, 0); | |
7994 | ||
7995 | if (ASCII_CHAR_P (c) | |
7996 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7997 | return ch; | |
7998 | ||
7999 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
8000 | charset = char_charset (c, charset_list, &code); | |
8001 | if (code == CHARSET_INVALID_CODE (charset)) | |
8002 | error ("Can't encode by shift_jis encoding: %d", c); | |
8003 | JIS_TO_SJIS (code); | |
8004 | ||
8005 | return make_number (code); | |
4ed46869 KH |
8006 | } |
8007 | ||
8008 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
8009 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
8010 | Return the corresponding character. */) | |
8011 | (code) | |
4ed46869 | 8012 | Lisp_Object code; |
d46c5b12 | 8013 | { |
df7492f9 KH |
8014 | Lisp_Object spec, attrs, val; |
8015 | struct charset *charset_roman, *charset_big5, *charset; | |
8016 | int c; | |
6289dd10 | 8017 | |
df7492f9 KH |
8018 | CHECK_NATNUM (code); |
8019 | c = XFASTINT (code); | |
8020 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
8021 | attrs = AREF (spec, 0); | |
4ed46869 | 8022 | |
df7492f9 KH |
8023 | if (ASCII_BYTE_P (c) |
8024 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8025 | return code; | |
6289dd10 | 8026 | |
df7492f9 KH |
8027 | val = CODING_ATTR_CHARSET_LIST (attrs); |
8028 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
8029 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 8030 | |
df7492f9 KH |
8031 | if (c <= 0x7F) |
8032 | charset = charset_roman; | |
c28a9453 KH |
8033 | else |
8034 | { | |
df7492f9 KH |
8035 | int b1 = c >> 8, b2 = c & 0x7F; |
8036 | if (b1 < 0xA1 || b1 > 0xFE | |
8037 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
8038 | error ("Invalid code: %d", code); | |
8039 | charset = charset_big5; | |
c28a9453 | 8040 | } |
df7492f9 KH |
8041 | c = DECODE_CHAR (charset, (unsigned )c); |
8042 | if (c < 0) | |
8043 | error ("Invalid code: %d", code); | |
8044 | return make_number (c); | |
d46c5b12 | 8045 | } |
6289dd10 | 8046 | |
4ed46869 | 8047 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
48b0f3ae PJ |
8048 | doc: /* Encode the Big5 character CHAR to BIG5 coding system. |
8049 | Return the corresponding character code in Big5. */) | |
8050 | (ch) | |
4ed46869 KH |
8051 | Lisp_Object ch; |
8052 | { | |
df7492f9 KH |
8053 | Lisp_Object spec, attrs, charset_list; |
8054 | struct charset *charset; | |
8055 | int c; | |
8056 | unsigned code; | |
8057 | ||
8058 | CHECK_CHARACTER (ch); | |
8059 | c = XFASTINT (ch); | |
8060 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
8061 | attrs = AREF (spec, 0); | |
8062 | if (ASCII_CHAR_P (c) | |
8063 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8064 | return ch; | |
8065 | ||
8066 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
8067 | charset = char_charset (c, charset_list, &code); | |
8068 | if (code == CHARSET_INVALID_CODE (charset)) | |
8069 | error ("Can't encode by Big5 encoding: %d", c); | |
8070 | ||
8071 | return make_number (code); | |
4ed46869 | 8072 | } |
48b0f3ae | 8073 | |
3a73fa5d | 8074 | \f |
1ba9e4ab KH |
8075 | DEFUN ("set-terminal-coding-system-internal", |
8076 | Fset_terminal_coding_system_internal, | |
48b0f3ae PJ |
8077 | Sset_terminal_coding_system_internal, 1, 1, 0, |
8078 | doc: /* Internal use only. */) | |
8079 | (coding_system) | |
b74e4686 | 8080 | Lisp_Object coding_system; |
4ed46869 | 8081 | { |
b7826503 | 8082 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
8083 | setup_coding_system (Fcheck_coding_system (coding_system), |
8084 | &terminal_coding); | |
48b0f3ae | 8085 | |
70c22245 | 8086 | /* We had better not send unsafe characters to terminal. */ |
df7492f9 KH |
8087 | terminal_coding.mode |= CODING_MODE_SAFE_ENCODING; |
8088 | /* Characer composition should be disabled. */ | |
8089 | terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
8090 | terminal_coding.src_multibyte = 1; |
8091 | terminal_coding.dst_multibyte = 0; | |
4ed46869 KH |
8092 | return Qnil; |
8093 | } | |
8094 | ||
c4825358 KH |
8095 | DEFUN ("set-safe-terminal-coding-system-internal", |
8096 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 8097 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 8098 | doc: /* Internal use only. */) |
48b0f3ae | 8099 | (coding_system) |
b74e4686 | 8100 | Lisp_Object coding_system; |
d46c5b12 | 8101 | { |
b7826503 | 8102 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
8103 | setup_coding_system (Fcheck_coding_system (coding_system), |
8104 | &safe_terminal_coding); | |
df7492f9 KH |
8105 | /* Characer composition should be disabled. */ |
8106 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
8107 | safe_terminal_coding.src_multibyte = 1; |
8108 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
8109 | return Qnil; |
8110 | } | |
4ed46869 | 8111 | |
4ed46869 KH |
8112 | DEFUN ("terminal-coding-system", |
8113 | Fterminal_coding_system, Sterminal_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
8114 | doc: /* Return coding system specified for terminal output. */) |
8115 | () | |
4ed46869 | 8116 | { |
df7492f9 | 8117 | return CODING_ID_NAME (terminal_coding.id); |
4ed46869 KH |
8118 | } |
8119 | ||
1ba9e4ab KH |
8120 | DEFUN ("set-keyboard-coding-system-internal", |
8121 | Fset_keyboard_coding_system_internal, | |
48b0f3ae PJ |
8122 | Sset_keyboard_coding_system_internal, 1, 1, 0, |
8123 | doc: /* Internal use only. */) | |
8124 | (coding_system) | |
4ed46869 KH |
8125 | Lisp_Object coding_system; |
8126 | { | |
b7826503 | 8127 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
8128 | setup_coding_system (Fcheck_coding_system (coding_system), |
8129 | &keyboard_coding); | |
8130 | /* Characer composition should be disabled. */ | |
8131 | keyboard_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
8132 | return Qnil; |
8133 | } | |
8134 | ||
8135 | DEFUN ("keyboard-coding-system", | |
8136 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
8137 | doc: /* Return coding system specified for decoding keyboard input. */) |
8138 | () | |
4ed46869 | 8139 | { |
df7492f9 | 8140 | return CODING_ID_NAME (keyboard_coding.id); |
4ed46869 KH |
8141 | } |
8142 | ||
4ed46869 | 8143 | \f |
a5d301df KH |
8144 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
8145 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
8146 | doc: /* Choose a coding system for an operation based on the target name. |
8147 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
8148 | DECODING-SYSTEM is the coding system to use for decoding | |
8149 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
8150 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 8151 | |
48b0f3ae PJ |
8152 | The first argument OPERATION specifies an I/O primitive: |
8153 | For file I/O, `insert-file-contents' or `write-region'. | |
8154 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
8155 | For network I/O, `open-network-stream'. | |
05e6f5dc | 8156 | |
48b0f3ae PJ |
8157 | The remaining arguments should be the same arguments that were passed |
8158 | to the primitive. Depending on which primitive, one of those arguments | |
8159 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
8160 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 8161 | |
48b0f3ae PJ |
8162 | TARGET has a meaning which depends on OPERATION: |
8163 | For file I/O, TARGET is a file name. | |
8164 | For process I/O, TARGET is a process name. | |
8165 | For network I/O, TARGET is a service name or a port number | |
05e6f5dc | 8166 | |
48b0f3ae PJ |
8167 | This function looks up what specified for TARGET in, |
8168 | `file-coding-system-alist', `process-coding-system-alist', | |
8169 | or `network-coding-system-alist' depending on OPERATION. | |
8170 | They may specify a coding system, a cons of coding systems, | |
8171 | or a function symbol to call. | |
8172 | In the last case, we call the function with one argument, | |
8173 | which is a list of all the arguments given to this function. | |
8174 | ||
8175 | usage: (find-operation-coding-system OPERATION ARGUMENTS ...) */) | |
8176 | (nargs, args) | |
4ed46869 KH |
8177 | int nargs; |
8178 | Lisp_Object *args; | |
6b89e3aa | 8179 | { |
4ed46869 KH |
8180 | Lisp_Object operation, target_idx, target, val; |
8181 | register Lisp_Object chain; | |
177c0ea7 | 8182 | |
4ed46869 KH |
8183 | if (nargs < 2) |
8184 | error ("Too few arguments"); | |
8185 | operation = args[0]; | |
8186 | if (!SYMBOLP (operation) | |
8187 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
df7492f9 | 8188 | error ("Invalid first arguement"); |
4ed46869 KH |
8189 | if (nargs < 1 + XINT (target_idx)) |
8190 | error ("Too few arguments for operation: %s", | |
8f924df7 | 8191 | SDATA (SYMBOL_NAME (operation))); |
4ed46869 KH |
8192 | target = args[XINT (target_idx) + 1]; |
8193 | if (!(STRINGP (target) | |
8194 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) | |
df7492f9 | 8195 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
4ed46869 | 8196 | |
2e34157c RS |
8197 | chain = ((EQ (operation, Qinsert_file_contents) |
8198 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 8199 | ? Vfile_coding_system_alist |
2e34157c | 8200 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
8201 | ? Vnetwork_coding_system_alist |
8202 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
8203 | if (NILP (chain)) |
8204 | return Qnil; | |
8205 | ||
03699b14 | 8206 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 8207 | { |
f44d27ce | 8208 | Lisp_Object elt; |
6b89e3aa | 8209 | |
df7492f9 | 8210 | elt = XCAR (chain); |
4ed46869 KH |
8211 | if (CONSP (elt) |
8212 | && ((STRINGP (target) | |
03699b14 KR |
8213 | && STRINGP (XCAR (elt)) |
8214 | && fast_string_match (XCAR (elt), target) >= 0) | |
8215 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 8216 | { |
03699b14 | 8217 | val = XCDR (elt); |
b19fd4c5 KH |
8218 | /* Here, if VAL is both a valid coding system and a valid |
8219 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
8220 | if (CONSP (val)) |
8221 | return val; | |
8222 | if (! SYMBOLP (val)) | |
8223 | return Qnil; | |
8224 | if (! NILP (Fcoding_system_p (val))) | |
8225 | return Fcons (val, val); | |
b19fd4c5 | 8226 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 8227 | { |
b19fd4c5 KH |
8228 | val = call1 (val, Flist (nargs, args)); |
8229 | if (CONSP (val)) | |
8230 | return val; | |
8231 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
8232 | return Fcons (val, val); | |
6b89e3aa | 8233 | } |
02ba4723 | 8234 | return Qnil; |
6b89e3aa KH |
8235 | } |
8236 | } | |
4ed46869 | 8237 | return Qnil; |
6b89e3aa KH |
8238 | } |
8239 | ||
df7492f9 | 8240 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 8241 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 8242 | doc: /* Assign higher priority to the coding systems given as arguments. |
ff563fce | 8243 | If multiple coding systems belongs to the same category, |
a3181084 DL |
8244 | all but the first one are ignored. |
8245 | ||
8246 | usage: (set-coding-system-priority ...) */) | |
df7492f9 KH |
8247 | (nargs, args) |
8248 | int nargs; | |
8249 | Lisp_Object *args; | |
8250 | { | |
8251 | int i, j; | |
8252 | int changed[coding_category_max]; | |
8253 | enum coding_category priorities[coding_category_max]; | |
8254 | ||
8255 | bzero (changed, sizeof changed); | |
6b89e3aa | 8256 | |
df7492f9 | 8257 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 8258 | { |
df7492f9 KH |
8259 | enum coding_category category; |
8260 | Lisp_Object spec, attrs; | |
6b89e3aa | 8261 | |
df7492f9 KH |
8262 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
8263 | attrs = AREF (spec, 0); | |
8264 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8265 | if (changed[category]) | |
8266 | /* Ignore this coding system because a coding system of the | |
8267 | same category already had a higher priority. */ | |
8268 | continue; | |
8269 | changed[category] = 1; | |
8270 | priorities[j++] = category; | |
8271 | if (coding_categories[category].id >= 0 | |
8272 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
8273 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 8274 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 8275 | } |
6b89e3aa | 8276 | |
df7492f9 KH |
8277 | /* Now we have decided top J priorities. Reflect the order of the |
8278 | original priorities to the remaining priorities. */ | |
6b89e3aa | 8279 | |
df7492f9 | 8280 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 8281 | { |
df7492f9 KH |
8282 | while (j < coding_category_max |
8283 | && changed[coding_priorities[j]]) | |
8284 | j++; | |
8285 | if (j == coding_category_max) | |
8286 | abort (); | |
8287 | priorities[i] = coding_priorities[j]; | |
8288 | } | |
6b89e3aa | 8289 | |
df7492f9 | 8290 | bcopy (priorities, coding_priorities, sizeof priorities); |
177c0ea7 | 8291 | |
ff563fce KH |
8292 | /* Update `coding-category-list'. */ |
8293 | Vcoding_category_list = Qnil; | |
8294 | for (i = coding_category_max - 1; i >= 0; i--) | |
8295 | Vcoding_category_list | |
8296 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
8297 | Vcoding_category_list); | |
6b89e3aa | 8298 | |
df7492f9 | 8299 | return Qnil; |
6b89e3aa KH |
8300 | } |
8301 | ||
df7492f9 KH |
8302 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
8303 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 DL |
8304 | doc: /* Return a list of coding systems ordered by their priorities. |
8305 | HIGHESTP non-nil means just return the highest priority one. */) | |
df7492f9 KH |
8306 | (highestp) |
8307 | Lisp_Object highestp; | |
d46c5b12 KH |
8308 | { |
8309 | int i; | |
df7492f9 | 8310 | Lisp_Object val; |
6b89e3aa | 8311 | |
df7492f9 | 8312 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 8313 | { |
df7492f9 KH |
8314 | enum coding_category category = coding_priorities[i]; |
8315 | int id = coding_categories[category].id; | |
8316 | Lisp_Object attrs; | |
068a9dbd | 8317 | |
df7492f9 KH |
8318 | if (id < 0) |
8319 | continue; | |
8320 | attrs = CODING_ID_ATTRS (id); | |
8321 | if (! NILP (highestp)) | |
8322 | return CODING_ATTR_BASE_NAME (attrs); | |
8323 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
8324 | } | |
8325 | return Fnreverse (val); | |
8326 | } | |
068a9dbd | 8327 | |
f0064e1f | 8328 | static char *suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
8329 | |
8330 | static Lisp_Object | |
df7492f9 KH |
8331 | make_subsidiaries (base) |
8332 | Lisp_Object base; | |
068a9dbd | 8333 | { |
df7492f9 | 8334 | Lisp_Object subsidiaries; |
8f924df7 | 8335 | int base_name_len = SBYTES (SYMBOL_NAME (base)); |
df7492f9 KH |
8336 | char *buf = (char *) alloca (base_name_len + 6); |
8337 | int i; | |
068a9dbd | 8338 | |
8f924df7 | 8339 | bcopy (SDATA (SYMBOL_NAME (base)), buf, base_name_len); |
df7492f9 KH |
8340 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
8341 | for (i = 0; i < 3; i++) | |
068a9dbd | 8342 | { |
df7492f9 KH |
8343 | bcopy (suffixes[i], buf + base_name_len, strlen (suffixes[i]) + 1); |
8344 | ASET (subsidiaries, i, intern (buf)); | |
068a9dbd | 8345 | } |
df7492f9 | 8346 | return subsidiaries; |
068a9dbd KH |
8347 | } |
8348 | ||
8349 | ||
df7492f9 KH |
8350 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
8351 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
8352 | doc: /* For internal use only. |
8353 | usage: (define-coding-system-internal ...) */) | |
df7492f9 KH |
8354 | (nargs, args) |
8355 | int nargs; | |
8356 | Lisp_Object *args; | |
068a9dbd | 8357 | { |
df7492f9 KH |
8358 | Lisp_Object name; |
8359 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
8360 | Lisp_Object attrs; /* Vector of attributes. */ | |
8361 | Lisp_Object eol_type; | |
8362 | Lisp_Object aliases; | |
8363 | Lisp_Object coding_type, charset_list, safe_charsets; | |
8364 | enum coding_category category; | |
8365 | Lisp_Object tail, val; | |
8366 | int max_charset_id = 0; | |
8367 | int i; | |
068a9dbd | 8368 | |
df7492f9 KH |
8369 | if (nargs < coding_arg_max) |
8370 | goto short_args; | |
068a9dbd | 8371 | |
df7492f9 | 8372 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 8373 | |
df7492f9 KH |
8374 | name = args[coding_arg_name]; |
8375 | CHECK_SYMBOL (name); | |
8376 | CODING_ATTR_BASE_NAME (attrs) = name; | |
068a9dbd | 8377 | |
df7492f9 KH |
8378 | val = args[coding_arg_mnemonic]; |
8379 | if (! STRINGP (val)) | |
8380 | CHECK_CHARACTER (val); | |
8381 | CODING_ATTR_MNEMONIC (attrs) = val; | |
068a9dbd | 8382 | |
df7492f9 KH |
8383 | coding_type = args[coding_arg_coding_type]; |
8384 | CHECK_SYMBOL (coding_type); | |
8385 | CODING_ATTR_TYPE (attrs) = coding_type; | |
068a9dbd | 8386 | |
df7492f9 KH |
8387 | charset_list = args[coding_arg_charset_list]; |
8388 | if (SYMBOLP (charset_list)) | |
8389 | { | |
8390 | if (EQ (charset_list, Qiso_2022)) | |
8391 | { | |
8392 | if (! EQ (coding_type, Qiso_2022)) | |
8393 | error ("Invalid charset-list"); | |
8394 | charset_list = Viso_2022_charset_list; | |
8395 | } | |
8396 | else if (EQ (charset_list, Qemacs_mule)) | |
8397 | { | |
8398 | if (! EQ (coding_type, Qemacs_mule)) | |
8399 | error ("Invalid charset-list"); | |
8400 | charset_list = Vemacs_mule_charset_list; | |
8401 | } | |
8402 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8403 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
8404 | max_charset_id = XFASTINT (XCAR (tail)); | |
8405 | } | |
068a9dbd KH |
8406 | else |
8407 | { | |
df7492f9 KH |
8408 | charset_list = Fcopy_sequence (charset_list); |
8409 | for (tail = charset_list; !NILP (tail); tail = Fcdr (tail)) | |
068a9dbd | 8410 | { |
df7492f9 KH |
8411 | struct charset *charset; |
8412 | ||
8413 | val = Fcar (tail); | |
8414 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8415 | if (EQ (coding_type, Qiso_2022) | |
8416 | ? CHARSET_ISO_FINAL (charset) < 0 | |
8417 | : EQ (coding_type, Qemacs_mule) | |
8418 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
8419 | : 0) | |
8420 | error ("Can't handle charset `%s'", | |
8f924df7 | 8421 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 8422 | |
8f924df7 | 8423 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
8424 | if (max_charset_id < charset->id) |
8425 | max_charset_id = charset->id; | |
068a9dbd KH |
8426 | } |
8427 | } | |
df7492f9 | 8428 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; |
068a9dbd | 8429 | |
df7492f9 KH |
8430 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
8431 | make_number (255)); | |
8432 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8f924df7 | 8433 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 8434 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; |
068a9dbd | 8435 | |
584948ac | 8436 | CODING_ATTR_ASCII_COMPAT (attrs) = args[coding_arg_ascii_compatible_p]; |
3a73fa5d | 8437 | |
df7492f9 | 8438 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 8439 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 8440 | CHECK_SYMBOL (val); |
df7492f9 | 8441 | CODING_ATTR_DECODE_TBL (attrs) = val; |
3a73fa5d | 8442 | |
df7492f9 | 8443 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 8444 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 8445 | CHECK_SYMBOL (val); |
df7492f9 | 8446 | CODING_ATTR_ENCODE_TBL (attrs) = val; |
d46c5b12 | 8447 | |
df7492f9 KH |
8448 | val = args[coding_arg_post_read_conversion]; |
8449 | CHECK_SYMBOL (val); | |
8450 | CODING_ATTR_POST_READ (attrs) = val; | |
d46c5b12 | 8451 | |
df7492f9 KH |
8452 | val = args[coding_arg_pre_write_conversion]; |
8453 | CHECK_SYMBOL (val); | |
8454 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
3a73fa5d | 8455 | |
df7492f9 KH |
8456 | val = args[coding_arg_default_char]; |
8457 | if (NILP (val)) | |
8458 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
8459 | else | |
8460 | { | |
8f924df7 | 8461 | CHECK_CHARACTER (val); |
df7492f9 KH |
8462 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; |
8463 | } | |
4031e2bf | 8464 | |
8f924df7 KH |
8465 | val = args[coding_arg_for_unibyte]; |
8466 | CODING_ATTR_FOR_UNIBYTE (attrs) = NILP (val) ? Qnil : Qt; | |
3a73fa5d | 8467 | |
df7492f9 KH |
8468 | val = args[coding_arg_plist]; |
8469 | CHECK_LIST (val); | |
8470 | CODING_ATTR_PLIST (attrs) = val; | |
3a73fa5d | 8471 | |
df7492f9 KH |
8472 | if (EQ (coding_type, Qcharset)) |
8473 | { | |
c7c66a95 KH |
8474 | /* Generate a lisp vector of 256 elements. Each element is nil, |
8475 | integer, or a list of charset IDs. | |
3a73fa5d | 8476 | |
c7c66a95 KH |
8477 | If Nth element is nil, the byte code N is invalid in this |
8478 | coding system. | |
4ed46869 | 8479 | |
c7c66a95 KH |
8480 | If Nth element is a number NUM, N is the first byte of a |
8481 | charset whose ID is NUM. | |
4ed46869 | 8482 | |
c7c66a95 KH |
8483 | If Nth element is a list of charset IDs, N is the first byte |
8484 | of one of them. The list is sorted by dimensions of the | |
2bc515e4 | 8485 | charsets. A charset of smaller dimension comes firtst. */ |
df7492f9 | 8486 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 8487 | |
5c99c2e6 | 8488 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 8489 | { |
c7c66a95 KH |
8490 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
8491 | int dim = CHARSET_DIMENSION (charset); | |
8492 | int idx = (dim - 1) * 4; | |
4ed46869 | 8493 | |
5c99c2e6 | 8494 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
584948ac | 8495 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
4031e2bf | 8496 | |
15d143f7 KH |
8497 | for (i = charset->code_space[idx]; |
8498 | i <= charset->code_space[idx + 1]; i++) | |
8499 | { | |
c7c66a95 KH |
8500 | Lisp_Object tmp, tmp2; |
8501 | int dim2; | |
ec6d2bb8 | 8502 | |
c7c66a95 KH |
8503 | tmp = AREF (val, i); |
8504 | if (NILP (tmp)) | |
8505 | tmp = XCAR (tail); | |
8506 | else if (NUMBERP (tmp)) | |
8507 | { | |
8508 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
8509 | if (dim < dim2) | |
c7c66a95 | 8510 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
8511 | else |
8512 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 8513 | } |
15d143f7 | 8514 | else |
c7c66a95 KH |
8515 | { |
8516 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
8517 | { | |
8518 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
8519 | if (dim < dim2) | |
8520 | break; | |
8521 | } | |
8522 | if (NILP (tmp2)) | |
8523 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
8524 | else | |
8525 | { | |
8526 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
8527 | XSETCAR (tmp2, XCAR (tail)); | |
8528 | } | |
8529 | } | |
8530 | ASET (val, i, tmp); | |
15d143f7 | 8531 | } |
df7492f9 KH |
8532 | } |
8533 | ASET (attrs, coding_attr_charset_valids, val); | |
8534 | category = coding_category_charset; | |
8535 | } | |
8536 | else if (EQ (coding_type, Qccl)) | |
8537 | { | |
8538 | Lisp_Object valids; | |
ecec61c1 | 8539 | |
df7492f9 KH |
8540 | if (nargs < coding_arg_ccl_max) |
8541 | goto short_args; | |
ecec61c1 | 8542 | |
df7492f9 KH |
8543 | val = args[coding_arg_ccl_decoder]; |
8544 | CHECK_CCL_PROGRAM (val); | |
8545 | if (VECTORP (val)) | |
8546 | val = Fcopy_sequence (val); | |
8547 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 8548 | |
df7492f9 KH |
8549 | val = args[coding_arg_ccl_encoder]; |
8550 | CHECK_CCL_PROGRAM (val); | |
8551 | if (VECTORP (val)) | |
8552 | val = Fcopy_sequence (val); | |
8553 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 8554 | |
df7492f9 KH |
8555 | val = args[coding_arg_ccl_valids]; |
8556 | valids = Fmake_string (make_number (256), make_number (0)); | |
8557 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
8558 | { | |
8dcbea82 | 8559 | int from, to; |
ecec61c1 | 8560 | |
df7492f9 KH |
8561 | val = Fcar (tail); |
8562 | if (INTEGERP (val)) | |
8dcbea82 KH |
8563 | { |
8564 | from = to = XINT (val); | |
8565 | if (from < 0 || from > 255) | |
8566 | args_out_of_range_3 (val, make_number (0), make_number (255)); | |
8567 | } | |
df7492f9 KH |
8568 | else |
8569 | { | |
df7492f9 | 8570 | CHECK_CONS (val); |
8f924df7 KH |
8571 | CHECK_NATNUM_CAR (val); |
8572 | CHECK_NATNUM_CDR (val); | |
df7492f9 | 8573 | from = XINT (XCAR (val)); |
8f924df7 | 8574 | if (from > 255) |
8dcbea82 KH |
8575 | args_out_of_range_3 (XCAR (val), |
8576 | make_number (0), make_number (255)); | |
df7492f9 | 8577 | to = XINT (XCDR (val)); |
8dcbea82 KH |
8578 | if (to < from || to > 255) |
8579 | args_out_of_range_3 (XCDR (val), | |
8580 | XCAR (val), make_number (255)); | |
df7492f9 | 8581 | } |
8dcbea82 | 8582 | for (i = from; i <= to; i++) |
8f924df7 | 8583 | SSET (valids, i, 1); |
df7492f9 KH |
8584 | } |
8585 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 8586 | |
df7492f9 | 8587 | category = coding_category_ccl; |
55ab7be3 | 8588 | } |
df7492f9 | 8589 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 8590 | { |
df7492f9 | 8591 | Lisp_Object bom, endian; |
4ed46869 | 8592 | |
584948ac | 8593 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; |
4ed46869 | 8594 | |
df7492f9 KH |
8595 | if (nargs < coding_arg_utf16_max) |
8596 | goto short_args; | |
4ed46869 | 8597 | |
df7492f9 KH |
8598 | bom = args[coding_arg_utf16_bom]; |
8599 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
8600 | { | |
8601 | CHECK_CONS (bom); | |
8f924df7 KH |
8602 | val = XCAR (bom); |
8603 | CHECK_CODING_SYSTEM (val); | |
8604 | val = XCDR (bom); | |
8605 | CHECK_CODING_SYSTEM (val); | |
df7492f9 KH |
8606 | } |
8607 | ASET (attrs, coding_attr_utf_16_bom, bom); | |
8608 | ||
8609 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
8610 | CHECK_SYMBOL (endian); |
8611 | if (NILP (endian)) | |
8612 | endian = Qbig; | |
8613 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 8614 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
8615 | ASET (attrs, coding_attr_utf_16_endian, endian); |
8616 | ||
8617 | category = (CONSP (bom) | |
8618 | ? coding_category_utf_16_auto | |
8619 | : NILP (bom) | |
b49a1807 | 8620 | ? (EQ (endian, Qbig) |
df7492f9 KH |
8621 | ? coding_category_utf_16_be_nosig |
8622 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 8623 | : (EQ (endian, Qbig) |
df7492f9 KH |
8624 | ? coding_category_utf_16_be |
8625 | : coding_category_utf_16_le)); | |
8626 | } | |
8627 | else if (EQ (coding_type, Qiso_2022)) | |
8628 | { | |
8629 | Lisp_Object initial, reg_usage, request, flags; | |
4776e638 | 8630 | int i; |
1397dc18 | 8631 | |
df7492f9 KH |
8632 | if (nargs < coding_arg_iso2022_max) |
8633 | goto short_args; | |
8634 | ||
8635 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
8636 | CHECK_VECTOR (initial); | |
8637 | for (i = 0; i < 4; i++) | |
8638 | { | |
8639 | val = Faref (initial, make_number (i)); | |
8640 | if (! NILP (val)) | |
8641 | { | |
584948ac KH |
8642 | struct charset *charset; |
8643 | ||
8644 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8645 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
8646 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
8647 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8648 | } |
8649 | else | |
8650 | ASET (initial, i, make_number (-1)); | |
8651 | } | |
8652 | ||
8653 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
8654 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
8655 | CHECK_NUMBER_CAR (reg_usage); |
8656 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
8657 | |
8658 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
8659 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 8660 | { |
df7492f9 | 8661 | int id; |
8f924df7 | 8662 | Lisp_Object tmp; |
df7492f9 KH |
8663 | |
8664 | val = Fcar (tail); | |
8665 | CHECK_CONS (val); | |
8f924df7 KH |
8666 | tmp = XCAR (val); |
8667 | CHECK_CHARSET_GET_ID (tmp, id); | |
8668 | CHECK_NATNUM_CDR (val); | |
df7492f9 KH |
8669 | if (XINT (XCDR (val)) >= 4) |
8670 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
8f924df7 | 8671 | XSETCAR (val, make_number (id)); |
1397dc18 | 8672 | } |
4ed46869 | 8673 | |
df7492f9 KH |
8674 | flags = args[coding_arg_iso2022_flags]; |
8675 | CHECK_NATNUM (flags); | |
8676 | i = XINT (flags); | |
8677 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
8678 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
8679 | ||
8680 | ASET (attrs, coding_attr_iso_initial, initial); | |
8681 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
8682 | ASET (attrs, coding_attr_iso_request, request); | |
8683 | ASET (attrs, coding_attr_iso_flags, flags); | |
8684 | setup_iso_safe_charsets (attrs); | |
8685 | ||
8686 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
8687 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
8688 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
8689 | ? coding_category_iso_7_else | |
8690 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
8691 | ? coding_category_iso_7 | |
8692 | : coding_category_iso_7_tight); | |
8693 | else | |
8694 | { | |
8695 | int id = XINT (AREF (initial, 1)); | |
8696 | ||
c6fb6e98 | 8697 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
8698 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
8699 | || id < 0) | |
8700 | ? coding_category_iso_8_else | |
8701 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
8702 | ? coding_category_iso_8_1 | |
8703 | : coding_category_iso_8_2); | |
8704 | } | |
0ce7886f KH |
8705 | if (category != coding_category_iso_8_1 |
8706 | && category != coding_category_iso_8_2) | |
8707 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; | |
df7492f9 KH |
8708 | } |
8709 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 8710 | { |
df7492f9 KH |
8711 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
8712 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
584948ac | 8713 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
df7492f9 | 8714 | category = coding_category_emacs_mule; |
c28a9453 | 8715 | } |
df7492f9 | 8716 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 8717 | { |
df7492f9 KH |
8718 | |
8719 | struct charset *charset; | |
8720 | ||
7d64c6ad | 8721 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 8722 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 8723 | error ("There should be three or four charsets"); |
df7492f9 KH |
8724 | |
8725 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8726 | if (CHARSET_DIMENSION (charset) != 1) | |
8727 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8728 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8729 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8730 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8731 | |
8732 | charset_list = XCDR (charset_list); | |
8733 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8734 | if (CHARSET_DIMENSION (charset) != 1) | |
8735 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8736 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
8737 | |
8738 | charset_list = XCDR (charset_list); | |
8739 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8740 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
8741 | error ("Dimension of charset %s is not two", |
8742 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
8743 | ||
8744 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
8745 | if (! NILP (charset_list)) |
8746 | { | |
8747 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8748 | if (CHARSET_DIMENSION (charset) != 2) | |
8749 | error ("Dimension of charset %s is not two", | |
8750 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
8751 | } | |
df7492f9 KH |
8752 | |
8753 | category = coding_category_sjis; | |
8754 | Vsjis_coding_system = name; | |
c28a9453 | 8755 | } |
df7492f9 KH |
8756 | else if (EQ (coding_type, Qbig5)) |
8757 | { | |
8758 | struct charset *charset; | |
4ed46869 | 8759 | |
df7492f9 KH |
8760 | if (XINT (Flength (charset_list)) != 2) |
8761 | error ("There should be just two charsets"); | |
8762 | ||
8763 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8764 | if (CHARSET_DIMENSION (charset) != 1) | |
8765 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8766 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8767 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8768 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8769 | |
8770 | charset_list = XCDR (charset_list); | |
8771 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8772 | if (CHARSET_DIMENSION (charset) != 2) | |
8773 | error ("Dimension of charset %s is not two", | |
8f924df7 | 8774 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 8775 | |
df7492f9 KH |
8776 | category = coding_category_big5; |
8777 | Vbig5_coding_system = name; | |
8778 | } | |
8779 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 8780 | { |
584948ac KH |
8781 | category = coding_category_raw_text; |
8782 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
c28a9453 | 8783 | } |
df7492f9 | 8784 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 8785 | { |
584948ac KH |
8786 | category = coding_category_utf_8; |
8787 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
4ed46869 | 8788 | } |
df7492f9 KH |
8789 | else if (EQ (coding_type, Qundecided)) |
8790 | category = coding_category_undecided; | |
4ed46869 | 8791 | else |
df7492f9 | 8792 | error ("Invalid coding system type: %s", |
8f924df7 | 8793 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 8794 | |
df7492f9 | 8795 | CODING_ATTR_CATEGORY (attrs) = make_number (category); |
01378f49 KH |
8796 | CODING_ATTR_PLIST (attrs) |
8797 | = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category), | |
8798 | CODING_ATTR_PLIST (attrs))); | |
c4825358 | 8799 | |
df7492f9 KH |
8800 | eol_type = args[coding_arg_eol_type]; |
8801 | if (! NILP (eol_type) | |
8802 | && ! EQ (eol_type, Qunix) | |
8803 | && ! EQ (eol_type, Qdos) | |
8804 | && ! EQ (eol_type, Qmac)) | |
8805 | error ("Invalid eol-type"); | |
4ed46869 | 8806 | |
df7492f9 | 8807 | aliases = Fcons (name, Qnil); |
4ed46869 | 8808 | |
df7492f9 KH |
8809 | if (NILP (eol_type)) |
8810 | { | |
8811 | eol_type = make_subsidiaries (name); | |
8812 | for (i = 0; i < 3; i++) | |
1397dc18 | 8813 | { |
df7492f9 KH |
8814 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
8815 | ||
8816 | this_name = AREF (eol_type, i); | |
8817 | this_aliases = Fcons (this_name, Qnil); | |
8818 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
8819 | this_spec = Fmake_vector (make_number (3), attrs); | |
8820 | ASET (this_spec, 1, this_aliases); | |
8821 | ASET (this_spec, 2, this_eol_type); | |
8822 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
8823 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
8824 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
8825 | Vcoding_system_alist); | |
1397dc18 | 8826 | } |
d46c5b12 | 8827 | } |
4ed46869 | 8828 | |
df7492f9 KH |
8829 | spec_vec = Fmake_vector (make_number (3), attrs); |
8830 | ASET (spec_vec, 1, aliases); | |
8831 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 8832 | |
df7492f9 KH |
8833 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
8834 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
8835 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
8836 | Vcoding_system_alist); | |
48b0f3ae | 8837 | |
df7492f9 KH |
8838 | { |
8839 | int id = coding_categories[category].id; | |
48b0f3ae | 8840 | |
df7492f9 KH |
8841 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
8842 | setup_coding_system (name, &coding_categories[category]); | |
8843 | } | |
48b0f3ae | 8844 | |
d46c5b12 | 8845 | return Qnil; |
48b0f3ae | 8846 | |
df7492f9 KH |
8847 | short_args: |
8848 | return Fsignal (Qwrong_number_of_arguments, | |
8849 | Fcons (intern ("define-coding-system-internal"), | |
8850 | make_number (nargs))); | |
d46c5b12 | 8851 | } |
4ed46869 | 8852 | |
d6925f38 | 8853 | |
a6f87d34 KH |
8854 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
8855 | 3, 3, 0, | |
8856 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
8857 | (coding_system, prop, val) | |
8858 | Lisp_Object coding_system, prop, val; | |
8859 | { | |
8860 | Lisp_Object spec, attrs, plist; | |
8861 | ||
8862 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8863 | attrs = AREF (spec, 0); | |
8864 | if (EQ (prop, QCmnemonic)) | |
8865 | { | |
8866 | if (! STRINGP (val)) | |
8867 | CHECK_CHARACTER (val); | |
8868 | CODING_ATTR_MNEMONIC (attrs) = val; | |
8869 | } | |
8870 | else if (EQ (prop, QCdefalut_char)) | |
8871 | { | |
8872 | if (NILP (val)) | |
8873 | val = make_number (' '); | |
8874 | else | |
8875 | CHECK_CHARACTER (val); | |
8876 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; | |
8877 | } | |
8878 | else if (EQ (prop, QCdecode_translation_table)) | |
8879 | { | |
8880 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
8881 | CHECK_SYMBOL (val); | |
8882 | CODING_ATTR_DECODE_TBL (attrs) = val; | |
8883 | } | |
8884 | else if (EQ (prop, QCencode_translation_table)) | |
8885 | { | |
8886 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
8887 | CHECK_SYMBOL (val); | |
8888 | CODING_ATTR_ENCODE_TBL (attrs) = val; | |
8889 | } | |
8890 | else if (EQ (prop, QCpost_read_conversion)) | |
8891 | { | |
8892 | CHECK_SYMBOL (val); | |
8893 | CODING_ATTR_POST_READ (attrs) = val; | |
8894 | } | |
8895 | else if (EQ (prop, QCpre_write_conversion)) | |
8896 | { | |
8897 | CHECK_SYMBOL (val); | |
8898 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
8899 | } | |
8900 | ||
8901 | CODING_ATTR_PLIST (attrs) | |
8902 | = Fplist_put (CODING_ATTR_PLIST (attrs), prop, val); | |
8903 | return val; | |
8904 | } | |
8905 | ||
8906 | ||
df7492f9 KH |
8907 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
8908 | Sdefine_coding_system_alias, 2, 2, 0, | |
8909 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
8910 | (alias, coding_system) | |
8911 | Lisp_Object alias, coding_system; | |
66cfb530 | 8912 | { |
df7492f9 | 8913 | Lisp_Object spec, aliases, eol_type; |
4ed46869 | 8914 | |
df7492f9 KH |
8915 | CHECK_SYMBOL (alias); |
8916 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8917 | aliases = AREF (spec, 1); | |
d6925f38 KH |
8918 | /* ALISES should be a list of length more than zero, and the first |
8919 | element is a base coding system. Append ALIAS at the tail of the | |
8920 | list. */ | |
df7492f9 KH |
8921 | while (!NILP (XCDR (aliases))) |
8922 | aliases = XCDR (aliases); | |
8f924df7 | 8923 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 8924 | |
df7492f9 KH |
8925 | eol_type = AREF (spec, 2); |
8926 | if (VECTORP (eol_type)) | |
4ed46869 | 8927 | { |
df7492f9 KH |
8928 | Lisp_Object subsidiaries; |
8929 | int i; | |
4ed46869 | 8930 | |
df7492f9 KH |
8931 | subsidiaries = make_subsidiaries (alias); |
8932 | for (i = 0; i < 3; i++) | |
8933 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
8934 | AREF (eol_type, i)); | |
4ed46869 | 8935 | } |
df7492f9 KH |
8936 | |
8937 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 8938 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
5bad0796 DL |
8939 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), |
8940 | Vcoding_system_alist); | |
66cfb530 | 8941 | |
4ed46869 KH |
8942 | return Qnil; |
8943 | } | |
8944 | ||
df7492f9 KH |
8945 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
8946 | 1, 1, 0, | |
8947 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 8948 | Any alias or subsidiary coding system is not a base coding system. */) |
df7492f9 KH |
8949 | (coding_system) |
8950 | Lisp_Object coding_system; | |
d46c5b12 | 8951 | { |
df7492f9 | 8952 | Lisp_Object spec, attrs; |
d46c5b12 | 8953 | |
df7492f9 KH |
8954 | if (NILP (coding_system)) |
8955 | return (Qno_conversion); | |
8956 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8957 | attrs = AREF (spec, 0); | |
8958 | return CODING_ATTR_BASE_NAME (attrs); | |
8959 | } | |
1397dc18 | 8960 | |
df7492f9 KH |
8961 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
8962 | 1, 1, 0, | |
8963 | doc: "Return the property list of CODING-SYSTEM.") | |
8964 | (coding_system) | |
8965 | Lisp_Object coding_system; | |
8966 | { | |
8967 | Lisp_Object spec, attrs; | |
1397dc18 | 8968 | |
df7492f9 KH |
8969 | if (NILP (coding_system)) |
8970 | coding_system = Qno_conversion; | |
8971 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8972 | attrs = AREF (spec, 0); | |
8973 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
8974 | } |
8975 | ||
df7492f9 KH |
8976 | |
8977 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
8978 | 1, 1, 0, | |
da7db224 | 8979 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
df7492f9 KH |
8980 | (coding_system) |
8981 | Lisp_Object coding_system; | |
66cfb530 | 8982 | { |
df7492f9 | 8983 | Lisp_Object spec; |
84d60297 | 8984 | |
df7492f9 KH |
8985 | if (NILP (coding_system)) |
8986 | coding_system = Qno_conversion; | |
8987 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 8988 | return AREF (spec, 1); |
df7492f9 | 8989 | } |
66cfb530 | 8990 | |
df7492f9 KH |
8991 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
8992 | Scoding_system_eol_type, 1, 1, 0, | |
8993 | doc: /* Return eol-type of CODING-SYSTEM. | |
8994 | An eol-type is integer 0, 1, 2, or a vector of coding systems. | |
66cfb530 | 8995 | |
df7492f9 KH |
8996 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
8997 | and CR respectively. | |
66cfb530 | 8998 | |
df7492f9 KH |
8999 | A vector value indicates that a format of end-of-line should be |
9000 | detected automatically. Nth element of the vector is the subsidiary | |
9001 | coding system whose eol-type is N. */) | |
6b89e3aa KH |
9002 | (coding_system) |
9003 | Lisp_Object coding_system; | |
9004 | { | |
df7492f9 KH |
9005 | Lisp_Object spec, eol_type; |
9006 | int n; | |
6b89e3aa | 9007 | |
df7492f9 KH |
9008 | if (NILP (coding_system)) |
9009 | coding_system = Qno_conversion; | |
9010 | if (! CODING_SYSTEM_P (coding_system)) | |
9011 | return Qnil; | |
9012 | spec = CODING_SYSTEM_SPEC (coding_system); | |
9013 | eol_type = AREF (spec, 2); | |
9014 | if (VECTORP (eol_type)) | |
9015 | return Fcopy_sequence (eol_type); | |
9016 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
9017 | return make_number (n); | |
6b89e3aa KH |
9018 | } |
9019 | ||
4ed46869 KH |
9020 | #endif /* emacs */ |
9021 | ||
9022 | \f | |
1397dc18 | 9023 | /*** 9. Post-amble ***/ |
4ed46869 | 9024 | |
dfcf069d | 9025 | void |
4ed46869 KH |
9026 | init_coding_once () |
9027 | { | |
9028 | int i; | |
9029 | ||
df7492f9 KH |
9030 | for (i = 0; i < coding_category_max; i++) |
9031 | { | |
9032 | coding_categories[i].id = -1; | |
9033 | coding_priorities[i] = i; | |
9034 | } | |
4ed46869 KH |
9035 | |
9036 | /* ISO2022 specific initialize routine. */ | |
9037 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 9038 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
9039 | for (i = 0x21; i < 0x7F; i++) |
9040 | iso_code_class[i] = ISO_graphic_plane_0; | |
9041 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 9042 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
9043 | for (i = 0xA1; i < 0xFF; i++) |
9044 | iso_code_class[i] = ISO_graphic_plane_1; | |
9045 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
9046 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
9047 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
9048 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
9049 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
9050 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
9051 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
9052 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
9053 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
9054 | ||
df7492f9 KH |
9055 | for (i = 0; i < 256; i++) |
9056 | { | |
9057 | emacs_mule_bytes[i] = 1; | |
9058 | } | |
7c78e542 KH |
9059 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
9060 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
9061 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
9062 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
9063 | } |
9064 | ||
9065 | #ifdef emacs | |
9066 | ||
dfcf069d | 9067 | void |
e0e989f6 KH |
9068 | syms_of_coding () |
9069 | { | |
df7492f9 | 9070 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
9071 | { |
9072 | Lisp_Object args[2]; | |
9073 | args[0] = QCtest; | |
9074 | args[1] = Qeq; | |
9075 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
9076 | } | |
df7492f9 KH |
9077 | |
9078 | staticpro (&Vsjis_coding_system); | |
9079 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 9080 | |
df7492f9 KH |
9081 | staticpro (&Vbig5_coding_system); |
9082 | Vbig5_coding_system = Qnil; | |
9083 | ||
24a73b0a KH |
9084 | staticpro (&Vcode_conversion_reused_workbuf); |
9085 | Vcode_conversion_reused_workbuf = Qnil; | |
9086 | ||
9087 | staticpro (&Vcode_conversion_workbuf_name); | |
9088 | Vcode_conversion_workbuf_name = build_string (" *code-conversion-work*"); | |
e0e989f6 | 9089 | |
24a73b0a | 9090 | reused_workbuf_in_use = 0; |
df7492f9 KH |
9091 | |
9092 | DEFSYM (Qcharset, "charset"); | |
9093 | DEFSYM (Qtarget_idx, "target-idx"); | |
9094 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
9095 | Fset (Qcoding_system_history, Qnil); |
9096 | ||
9ce27fde | 9097 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 9098 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 9099 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
9100 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
9101 | ||
df7492f9 | 9102 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 9103 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
9104 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
9105 | ||
df7492f9 | 9106 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 9107 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
9108 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
9109 | ||
df7492f9 | 9110 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 9111 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
9112 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
9113 | ||
df7492f9 | 9114 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 9115 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
9116 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
9117 | ||
df7492f9 KH |
9118 | DEFSYM (Qcoding_system, "coding-system"); |
9119 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 9120 | |
df7492f9 KH |
9121 | DEFSYM (Qeol_type, "eol-type"); |
9122 | DEFSYM (Qunix, "unix"); | |
9123 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 9124 | |
df7492f9 KH |
9125 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
9126 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
9127 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
9128 | DEFSYM (Qdefault_char, "default-char"); | |
9129 | DEFSYM (Qundecided, "undecided"); | |
9130 | DEFSYM (Qno_conversion, "no-conversion"); | |
9131 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 9132 | |
df7492f9 | 9133 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 9134 | |
df7492f9 | 9135 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 9136 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 9137 | |
df7492f9 | 9138 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
9139 | DEFSYM (Qbig, "big"); |
9140 | DEFSYM (Qlittle, "little"); | |
27901516 | 9141 | |
df7492f9 KH |
9142 | DEFSYM (Qshift_jis, "shift-jis"); |
9143 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 9144 | |
df7492f9 | 9145 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 9146 | |
df7492f9 | 9147 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 KH |
9148 | Fput (Qcoding_system_error, Qerror_conditions, |
9149 | Fcons (Qcoding_system_error, Fcons (Qerror, Qnil))); | |
9150 | Fput (Qcoding_system_error, Qerror_message, | |
9ce27fde | 9151 | build_string ("Invalid coding system")); |
4ed46869 | 9152 | |
05e6f5dc KH |
9153 | /* Intern this now in case it isn't already done. |
9154 | Setting this variable twice is harmless. | |
9155 | But don't staticpro it here--that is done in alloc.c. */ | |
9156 | Qchar_table_extra_slots = intern ("char-table-extra-slots"); | |
70c22245 | 9157 | |
df7492f9 | 9158 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 9159 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
9160 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
9161 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
9162 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 9163 | |
df7492f9 | 9164 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 9165 | |
df7492f9 | 9166 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 9167 | |
01378f49 | 9168 | DEFSYM (QCcategory, ":category"); |
a6f87d34 KH |
9169 | DEFSYM (QCmnemonic, ":mnemonic"); |
9170 | DEFSYM (QCdefalut_char, ":default-char"); | |
9171 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); | |
9172 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
9173 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
9174 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
01378f49 | 9175 | |
df7492f9 KH |
9176 | Vcoding_category_table |
9177 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
9178 | staticpro (&Vcoding_category_table); | |
9179 | /* Followings are target of code detection. */ | |
9180 | ASET (Vcoding_category_table, coding_category_iso_7, | |
9181 | intern ("coding-category-iso-7")); | |
9182 | ASET (Vcoding_category_table, coding_category_iso_7_tight, | |
9183 | intern ("coding-category-iso-7-tight")); | |
9184 | ASET (Vcoding_category_table, coding_category_iso_8_1, | |
9185 | intern ("coding-category-iso-8-1")); | |
9186 | ASET (Vcoding_category_table, coding_category_iso_8_2, | |
9187 | intern ("coding-category-iso-8-2")); | |
9188 | ASET (Vcoding_category_table, coding_category_iso_7_else, | |
9189 | intern ("coding-category-iso-7-else")); | |
9190 | ASET (Vcoding_category_table, coding_category_iso_8_else, | |
9191 | intern ("coding-category-iso-8-else")); | |
9192 | ASET (Vcoding_category_table, coding_category_utf_8, | |
9193 | intern ("coding-category-utf-8")); | |
9194 | ASET (Vcoding_category_table, coding_category_utf_16_be, | |
9195 | intern ("coding-category-utf-16-be")); | |
ff563fce KH |
9196 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
9197 | intern ("coding-category-utf-16-auto")); | |
df7492f9 KH |
9198 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
9199 | intern ("coding-category-utf-16-le")); | |
9200 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, | |
9201 | intern ("coding-category-utf-16-be-nosig")); | |
9202 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, | |
9203 | intern ("coding-category-utf-16-le-nosig")); | |
9204 | ASET (Vcoding_category_table, coding_category_charset, | |
9205 | intern ("coding-category-charset")); | |
9206 | ASET (Vcoding_category_table, coding_category_sjis, | |
9207 | intern ("coding-category-sjis")); | |
9208 | ASET (Vcoding_category_table, coding_category_big5, | |
9209 | intern ("coding-category-big5")); | |
9210 | ASET (Vcoding_category_table, coding_category_ccl, | |
9211 | intern ("coding-category-ccl")); | |
9212 | ASET (Vcoding_category_table, coding_category_emacs_mule, | |
9213 | intern ("coding-category-emacs-mule")); | |
9214 | /* Followings are NOT target of code detection. */ | |
9215 | ASET (Vcoding_category_table, coding_category_raw_text, | |
9216 | intern ("coding-category-raw-text")); | |
9217 | ASET (Vcoding_category_table, coding_category_undecided, | |
9218 | intern ("coding-category-undecided")); | |
ecf488bc | 9219 | |
065e3595 KH |
9220 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
9221 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
9222 | DEFSYM (Qinvalid_source, "invalid-source"); | |
9223 | DEFSYM (Qinterrupted, "interrupted"); | |
9224 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
9225 | ||
4ed46869 KH |
9226 | defsubr (&Scoding_system_p); |
9227 | defsubr (&Sread_coding_system); | |
9228 | defsubr (&Sread_non_nil_coding_system); | |
9229 | defsubr (&Scheck_coding_system); | |
9230 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 9231 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 9232 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 9233 | defsubr (&Sunencodable_char_position); |
df7492f9 | 9234 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
9235 | defsubr (&Sdecode_coding_region); |
9236 | defsubr (&Sencode_coding_region); | |
9237 | defsubr (&Sdecode_coding_string); | |
9238 | defsubr (&Sencode_coding_string); | |
9239 | defsubr (&Sdecode_sjis_char); | |
9240 | defsubr (&Sencode_sjis_char); | |
9241 | defsubr (&Sdecode_big5_char); | |
9242 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 9243 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 9244 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 9245 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 9246 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 9247 | defsubr (&Skeyboard_coding_system); |
a5d301df | 9248 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 9249 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 9250 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 9251 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 9252 | defsubr (&Scoding_system_put); |
df7492f9 KH |
9253 | defsubr (&Scoding_system_base); |
9254 | defsubr (&Scoding_system_plist); | |
9255 | defsubr (&Scoding_system_aliases); | |
9256 | defsubr (&Scoding_system_eol_type); | |
9257 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 9258 | |
4608c386 | 9259 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
48b0f3ae PJ |
9260 | doc: /* List of coding systems. |
9261 | ||
9262 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 9263 | updated by the functions `define-coding-system' and |
48b0f3ae | 9264 | `define-coding-system-alias'. */); |
4608c386 KH |
9265 | Vcoding_system_list = Qnil; |
9266 | ||
9267 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, | |
48b0f3ae PJ |
9268 | doc: /* Alist of coding system names. |
9269 | Each element is one element list of coding system name. | |
9270 | This variable is given to `completing-read' as TABLE argument. | |
9271 | ||
9272 | Do not alter the value of this variable manually. This variable should be | |
9273 | updated by the functions `make-coding-system' and | |
9274 | `define-coding-system-alias'. */); | |
4608c386 KH |
9275 | Vcoding_system_alist = Qnil; |
9276 | ||
4ed46869 | 9277 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
48b0f3ae PJ |
9278 | doc: /* List of coding-categories (symbols) ordered by priority. |
9279 | ||
9280 | On detecting a coding system, Emacs tries code detection algorithms | |
9281 | associated with each coding-category one by one in this order. When | |
9282 | one algorithm agrees with a byte sequence of source text, the coding | |
9283 | system bound to the corresponding coding-category is selected. */); | |
4ed46869 KH |
9284 | { |
9285 | int i; | |
9286 | ||
9287 | Vcoding_category_list = Qnil; | |
df7492f9 | 9288 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 9289 | Vcoding_category_list |
d46c5b12 KH |
9290 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
9291 | Vcoding_category_list); | |
4ed46869 KH |
9292 | } |
9293 | ||
9294 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, | |
48b0f3ae PJ |
9295 | doc: /* Specify the coding system for read operations. |
9296 | It is useful to bind this variable with `let', but do not set it globally. | |
9297 | If the value is a coding system, it is used for decoding on read operation. | |
9298 | If not, an appropriate element is used from one of the coding system alists: | |
9299 | There are three such tables, `file-coding-system-alist', | |
9300 | `process-coding-system-alist', and `network-coding-system-alist'. */); | |
4ed46869 KH |
9301 | Vcoding_system_for_read = Qnil; |
9302 | ||
9303 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, | |
48b0f3ae PJ |
9304 | doc: /* Specify the coding system for write operations. |
9305 | Programs bind this variable with `let', but you should not set it globally. | |
9306 | If the value is a coding system, it is used for encoding of output, | |
9307 | when writing it to a file and when sending it to a file or subprocess. | |
9308 | ||
9309 | If this does not specify a coding system, an appropriate element | |
9310 | is used from one of the coding system alists: | |
9311 | There are three such tables, `file-coding-system-alist', | |
9312 | `process-coding-system-alist', and `network-coding-system-alist'. | |
9313 | For output to files, if the above procedure does not specify a coding system, | |
9314 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
9315 | Vcoding_system_for_write = Qnil; |
9316 | ||
9317 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, | |
df7492f9 KH |
9318 | doc: /* |
9319 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
9320 | Vlast_coding_system_used = Qnil; |
9321 | ||
065e3595 KH |
9322 | DEFVAR_LISP ("last-code-conversion-error", &Vlast_code_conversion_error, |
9323 | doc: /* | |
9324 | Error status of the last code conversion. | |
9325 | ||
9326 | When an error was detected in the last code conversion, this variable | |
9327 | is set to one of the following symbols. | |
9328 | `insufficient-source' | |
9329 | `inconsistent-eol' | |
9330 | `invalid-source' | |
9331 | `interrupted' | |
9332 | `insufficient-memory' | |
9333 | When no error was detected, the value doesn't change. So, to check | |
9334 | the error status of a code conversion by this variable, you must | |
9335 | explicitly set this variable to nil before performing code | |
9336 | conversion. */); | |
9337 | Vlast_code_conversion_error = Qnil; | |
9338 | ||
9ce27fde | 9339 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
df7492f9 KH |
9340 | doc: /* |
9341 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
9342 | See info node `Coding Systems' and info node `Text and Binary' concerning |
9343 | such conversion. */); | |
9ce27fde KH |
9344 | inhibit_eol_conversion = 0; |
9345 | ||
ed29121d | 9346 | DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
df7492f9 KH |
9347 | doc: /* |
9348 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
9349 | Bind it to t if the process output is to be treated as if it were a file |
9350 | read from some filesystem. */); | |
ed29121d EZ |
9351 | inherit_process_coding_system = 0; |
9352 | ||
02ba4723 | 9353 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
df7492f9 KH |
9354 | doc: /* |
9355 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
9356 | The format is ((PATTERN . VAL) ...), |
9357 | where PATTERN is a regular expression matching a file name, | |
9358 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9359 | If VAL is a coding system, it is used for both decoding and encoding | |
9360 | the file contents. | |
9361 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9362 | and the cdr part is used for encoding. | |
9363 | If VAL is a function symbol, the function must return a coding system | |
0192762c DL |
9364 | or a cons of coding systems which are used as above. The function gets |
9365 | the arguments with which `find-operation-coding-systems' was called. | |
48b0f3ae PJ |
9366 | |
9367 | See also the function `find-operation-coding-system' | |
9368 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
9369 | Vfile_coding_system_alist = Qnil; |
9370 | ||
9371 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, | |
df7492f9 KH |
9372 | doc: /* |
9373 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
9374 | The format is ((PATTERN . VAL) ...), |
9375 | where PATTERN is a regular expression matching a program name, | |
9376 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9377 | If VAL is a coding system, it is used for both decoding what received | |
9378 | from the program and encoding what sent to the program. | |
9379 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9380 | and the cdr part is used for encoding. | |
9381 | If VAL is a function symbol, the function must return a coding system | |
9382 | or a cons of coding systems which are used as above. | |
9383 | ||
9384 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
9385 | Vprocess_coding_system_alist = Qnil; |
9386 | ||
9387 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, | |
df7492f9 KH |
9388 | doc: /* |
9389 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
9390 | The format is ((PATTERN . VAL) ...), |
9391 | where PATTERN is a regular expression matching a network service name | |
9392 | or is a port number to connect to, | |
9393 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9394 | If VAL is a coding system, it is used for both decoding what received | |
9395 | from the network stream and encoding what sent to the network stream. | |
9396 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9397 | and the cdr part is used for encoding. | |
9398 | If VAL is a function symbol, the function must return a coding system | |
9399 | or a cons of coding systems which are used as above. | |
9400 | ||
9401 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 9402 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 9403 | |
68c45bf0 | 9404 | DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
75205970 RS |
9405 | doc: /* Coding system to use with system messages. |
9406 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
9407 | Vlocale_coding_system = Qnil; |
9408 | ||
005f0d35 | 9409 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
7722baf9 | 9410 | DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
df7492f9 KH |
9411 | doc: /* |
9412 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
7722baf9 | 9413 | eol_mnemonic_unix = build_string (":"); |
4ed46869 | 9414 | |
7722baf9 | 9415 | DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
df7492f9 KH |
9416 | doc: /* |
9417 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
7722baf9 | 9418 | eol_mnemonic_dos = build_string ("\\"); |
4ed46869 | 9419 | |
7722baf9 | 9420 | DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
df7492f9 KH |
9421 | doc: /* |
9422 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
7722baf9 | 9423 | eol_mnemonic_mac = build_string ("/"); |
4ed46869 | 9424 | |
7722baf9 | 9425 | DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
df7492f9 KH |
9426 | doc: /* |
9427 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
7722baf9 | 9428 | eol_mnemonic_undecided = build_string (":"); |
4ed46869 | 9429 | |
84fbb8a0 | 9430 | DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
df7492f9 KH |
9431 | doc: /* |
9432 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 9433 | Venable_character_translation = Qt; |
bdd9fb48 | 9434 | |
f967223b | 9435 | DEFVAR_LISP ("standard-translation-table-for-decode", |
48b0f3ae PJ |
9436 | &Vstandard_translation_table_for_decode, |
9437 | doc: /* Table for translating characters while decoding. */); | |
f967223b | 9438 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 9439 | |
f967223b | 9440 | DEFVAR_LISP ("standard-translation-table-for-encode", |
48b0f3ae PJ |
9441 | &Vstandard_translation_table_for_encode, |
9442 | doc: /* Table for translating characters while encoding. */); | |
f967223b | 9443 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 9444 | |
df7492f9 | 9445 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table, |
48b0f3ae PJ |
9446 | doc: /* Alist of charsets vs revision numbers. |
9447 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
9448 | designate it with the escape sequence identifying revision (cdr part |
9449 | of the element). */); | |
9450 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
9451 | |
9452 | DEFVAR_LISP ("default-process-coding-system", | |
9453 | &Vdefault_process_coding_system, | |
48b0f3ae PJ |
9454 | doc: /* Cons of coding systems used for process I/O by default. |
9455 | The car part is used for decoding a process output, | |
9456 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 9457 | Vdefault_process_coding_system = Qnil; |
c4825358 | 9458 | |
3f003981 | 9459 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
df7492f9 KH |
9460 | doc: /* |
9461 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
9462 | This is a vector of length 256. |
9463 | If Nth element is non-nil, the existence of code N in a file | |
9464 | \(or output of subprocess) doesn't prevent it to be detected as | |
9465 | a coding system of ISO 2022 variant which has a flag | |
9466 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
9467 | or reading output of a subprocess. | |
9468 | Only 128th through 159th elements has a meaning. */); | |
3f003981 | 9469 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
9470 | |
9471 | DEFVAR_LISP ("select-safe-coding-system-function", | |
9472 | &Vselect_safe_coding_system_function, | |
df7492f9 KH |
9473 | doc: /* |
9474 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
9475 | |
9476 | If set, this function is called to force a user to select a proper | |
9477 | coding system which can encode the text in the case that a default | |
9478 | coding system used in each operation can't encode the text. | |
9479 | ||
9480 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
9481 | Vselect_safe_coding_system_function = Qnil; |
9482 | ||
5d5bf4d8 KH |
9483 | DEFVAR_BOOL ("coding-system-require-warning", |
9484 | &coding_system_require_warning, | |
9485 | doc: /* Internal use only. | |
6b89e3aa KH |
9486 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
9487 | called even if `coding-system-for-write' is non-nil. The command | |
9488 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
9489 | coding_system_require_warning = 0; |
9490 | ||
9491 | ||
22ab2303 | 9492 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
74383408 | 9493 | &inhibit_iso_escape_detection, |
df7492f9 KH |
9494 | doc: /* |
9495 | If non-nil, Emacs ignores ISO2022's escape sequence on code detection. | |
48b0f3ae PJ |
9496 | |
9497 | By default, on reading a file, Emacs tries to detect how the text is | |
9498 | encoded. This code detection is sensitive to escape sequences. If | |
9499 | the sequence is valid as ISO2022, the code is determined as one of | |
9500 | the ISO2022 encodings, and the file is decoded by the corresponding | |
9501 | coding system (e.g. `iso-2022-7bit'). | |
9502 | ||
9503 | However, there may be a case that you want to read escape sequences in | |
9504 | a file as is. In such a case, you can set this variable to non-nil. | |
9505 | Then, as the code detection ignores any escape sequences, no file is | |
9506 | detected as encoded in some ISO2022 encoding. The result is that all | |
9507 | escape sequences become visible in a buffer. | |
9508 | ||
9509 | The default value is nil, and it is strongly recommended not to change | |
9510 | it. That is because many Emacs Lisp source files that contain | |
9511 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
9512 | in Emacs's distribution, and they won't be decoded correctly on | |
9513 | reading if you suppress escape sequence detection. | |
9514 | ||
9515 | The other way to read escape sequences in a file without decoding is | |
9516 | to explicitly specify some coding system that doesn't use ISO2022's | |
9517 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); | |
74383408 | 9518 | inhibit_iso_escape_detection = 0; |
002fdb44 DL |
9519 | |
9520 | DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input, | |
15c8f9d1 DL |
9521 | doc: /* Char table for translating self-inserting characters. |
9522 | This is applied to the result of input methods, not their input. See also | |
9523 | `keyboard-translate-table'. */); | |
002fdb44 | 9524 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 9525 | |
2c78b7e1 KH |
9526 | { |
9527 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 9528 | Lisp_Object plist[16]; |
2c78b7e1 KH |
9529 | int i; |
9530 | ||
9531 | for (i = 0; i < coding_arg_max; i++) | |
9532 | args[i] = Qnil; | |
9533 | ||
9534 | plist[0] = intern (":name"); | |
9535 | plist[1] = args[coding_arg_name] = Qno_conversion; | |
9536 | plist[2] = intern (":mnemonic"); | |
9537 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); | |
9538 | plist[4] = intern (":coding-type"); | |
9539 | plist[5] = args[coding_arg_coding_type] = Qraw_text; | |
9540 | plist[6] = intern (":ascii-compatible-p"); | |
9541 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; | |
9542 | plist[8] = intern (":default-char"); | |
9543 | plist[9] = args[coding_arg_default_char] = make_number (0); | |
8f924df7 KH |
9544 | plist[10] = intern (":for-unibyte"); |
9545 | plist[11] = args[coding_arg_for_unibyte] = Qt; | |
9546 | plist[12] = intern (":docstring"); | |
9547 | plist[13] = build_string ("Do no conversion.\n\ | |
2c78b7e1 KH |
9548 | \n\ |
9549 | When you visit a file with this coding, the file is read into a\n\ | |
9550 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
9551 | character."); | |
8f924df7 KH |
9552 | plist[14] = intern (":eol-type"); |
9553 | plist[15] = args[coding_arg_eol_type] = Qunix; | |
9554 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 KH |
9555 | Fdefine_coding_system_internal (coding_arg_max, args); |
9556 | } | |
9557 | ||
9558 | setup_coding_system (Qno_conversion, &keyboard_coding); | |
9559 | setup_coding_system (Qno_conversion, &terminal_coding); | |
9560 | setup_coding_system (Qno_conversion, &safe_terminal_coding); | |
ff563fce KH |
9561 | |
9562 | { | |
9563 | int i; | |
9564 | ||
9565 | for (i = 0; i < coding_category_max; i++) | |
9566 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
9567 | } | |
4ed46869 KH |
9568 | } |
9569 | ||
68c45bf0 PE |
9570 | char * |
9571 | emacs_strerror (error_number) | |
9572 | int error_number; | |
9573 | { | |
9574 | char *str; | |
9575 | ||
ca9c0567 | 9576 | synchronize_system_messages_locale (); |
68c45bf0 PE |
9577 | str = strerror (error_number); |
9578 | ||
9579 | if (! NILP (Vlocale_coding_system)) | |
9580 | { | |
9581 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
9582 | Vlocale_coding_system, | |
9583 | 0); | |
d5db4077 | 9584 | str = (char *) SDATA (dec); |
68c45bf0 PE |
9585 | } |
9586 | ||
9587 | return str; | |
9588 | } | |
9589 | ||
4ed46869 | 9590 | #endif /* emacs */ |
9ffd559c KH |
9591 | |
9592 | /* arch-tag: 3a3a2b01-5ff6-4071-9afe-f5b808d9229d | |
9593 | (do not change this comment) */ |