Commit | Line | Data |
---|---|---|
9542cb1f | 1 | /* Coding system handler (conversion, detection, etc). |
0b5538bd | 2 | Copyright (C) 2001, 2002, 2003, 2004, 2005 Free Software Foundation, Inc. |
ce03bf76 KH |
3 | Copyright (C) 1995, 1997, 1998, 2002, 2003, 2004, 2005 |
4 | National Institute of Advanced Industrial Science and Technology (AIST) | |
5 | Registration Number H14PRO021 | |
8f924df7 | 6 | Copyright (C) 2003 |
df7492f9 KH |
7 | National Institute of Advanced Industrial Science and Technology (AIST) |
8 | Registration Number H13PRO009 | |
4ed46869 | 9 | |
369314dc KH |
10 | This file is part of GNU Emacs. |
11 | ||
12 | GNU Emacs is free software; you can redistribute it and/or modify | |
13 | it under the terms of the GNU General Public License as published by | |
14 | the Free Software Foundation; either version 2, or (at your option) | |
15 | any later version. | |
4ed46869 | 16 | |
369314dc KH |
17 | GNU Emacs is distributed in the hope that it will be useful, |
18 | but WITHOUT ANY WARRANTY; without even the implied warranty of | |
19 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
20 | GNU General Public License for more details. | |
4ed46869 | 21 | |
369314dc KH |
22 | You should have received a copy of the GNU General Public License |
23 | along with GNU Emacs; see the file COPYING. If not, write to | |
4fc5845f LK |
24 | the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, |
25 | Boston, MA 02110-1301, USA. */ | |
4ed46869 KH |
26 | |
27 | /*** TABLE OF CONTENTS *** | |
28 | ||
b73bfc1c | 29 | 0. General comments |
4ed46869 | 30 | 1. Preamble |
df7492f9 KH |
31 | 2. Emacs' internal format (emacs-utf-8) handlers |
32 | 3. UTF-8 handlers | |
33 | 4. UTF-16 handlers | |
34 | 5. Charset-base coding systems handlers | |
35 | 6. emacs-mule (old Emacs' internal format) handlers | |
36 | 7. ISO2022 handlers | |
37 | 8. Shift-JIS and BIG5 handlers | |
38 | 9. CCL handlers | |
39 | 10. C library functions | |
40 | 11. Emacs Lisp library functions | |
41 | 12. Postamble | |
4ed46869 KH |
42 | |
43 | */ | |
44 | ||
df7492f9 | 45 | /*** 0. General comments *** |
b73bfc1c KH |
46 | |
47 | ||
df7492f9 | 48 | CODING SYSTEM |
4ed46869 | 49 | |
5bad0796 DL |
50 | A coding system is an object for an encoding mechanism that contains |
51 | information about how to convert byte sequences to character | |
e19c3639 KH |
52 | sequences and vice versa. When we say "decode", it means converting |
53 | a byte sequence of a specific coding system into a character | |
54 | sequence that is represented by Emacs' internal coding system | |
55 | `emacs-utf-8', and when we say "encode", it means converting a | |
56 | character sequence of emacs-utf-8 to a byte sequence of a specific | |
0ef69138 | 57 | coding system. |
4ed46869 | 58 | |
e19c3639 KH |
59 | In Emacs Lisp, a coding system is represented by a Lisp symbol. In |
60 | C level, a coding system is represented by a vector of attributes | |
5bad0796 | 61 | stored in the hash table Vcharset_hash_table. The conversion from |
e19c3639 KH |
62 | coding system symbol to attributes vector is done by looking up |
63 | Vcharset_hash_table by the symbol. | |
4ed46869 | 64 | |
e19c3639 | 65 | Coding systems are classified into the following types depending on |
5bad0796 | 66 | the encoding mechanism. Here's a brief description of the types. |
4ed46869 | 67 | |
df7492f9 KH |
68 | o UTF-8 |
69 | ||
70 | o UTF-16 | |
71 | ||
72 | o Charset-base coding system | |
73 | ||
74 | A coding system defined by one or more (coded) character sets. | |
5bad0796 | 75 | Decoding and encoding are done by a code converter defined for each |
df7492f9 KH |
76 | character set. |
77 | ||
5bad0796 | 78 | o Old Emacs internal format (emacs-mule) |
df7492f9 | 79 | |
5bad0796 | 80 | The coding system adopted by old versions of Emacs (20 and 21). |
4ed46869 | 81 | |
df7492f9 | 82 | o ISO2022-base coding system |
4ed46869 KH |
83 | |
84 | The most famous coding system for multiple character sets. X's | |
df7492f9 KH |
85 | Compound Text, various EUCs (Extended Unix Code), and coding systems |
86 | used in the Internet communication such as ISO-2022-JP are all | |
87 | variants of ISO2022. | |
4ed46869 | 88 | |
df7492f9 | 89 | o SJIS (or Shift-JIS or MS-Kanji-Code) |
93dec019 | 90 | |
4ed46869 KH |
91 | A coding system to encode character sets: ASCII, JISX0201, and |
92 | JISX0208. Widely used for PC's in Japan. Details are described in | |
df7492f9 | 93 | section 8. |
4ed46869 | 94 | |
df7492f9 | 95 | o BIG5 |
4ed46869 | 96 | |
df7492f9 | 97 | A coding system to encode character sets: ASCII and Big5. Widely |
cfb43547 | 98 | used for Chinese (mainly in Taiwan and Hong Kong). Details are |
df7492f9 KH |
99 | described in section 8. In this file, when we write "big5" (all |
100 | lowercase), we mean the coding system, and when we write "Big5" | |
101 | (capitalized), we mean the character set. | |
4ed46869 | 102 | |
df7492f9 | 103 | o CCL |
27901516 | 104 | |
5bad0796 | 105 | If a user wants to decode/encode text encoded in a coding system |
df7492f9 KH |
106 | not listed above, he can supply a decoder and an encoder for it in |
107 | CCL (Code Conversion Language) programs. Emacs executes the CCL | |
108 | program while decoding/encoding. | |
27901516 | 109 | |
df7492f9 | 110 | o Raw-text |
4ed46869 | 111 | |
5a936b46 | 112 | A coding system for text containing raw eight-bit data. Emacs |
5bad0796 | 113 | treats each byte of source text as a character (except for |
df7492f9 | 114 | end-of-line conversion). |
4ed46869 | 115 | |
df7492f9 KH |
116 | o No-conversion |
117 | ||
118 | Like raw text, but don't do end-of-line conversion. | |
4ed46869 | 119 | |
4ed46869 | 120 | |
df7492f9 | 121 | END-OF-LINE FORMAT |
4ed46869 | 122 | |
5bad0796 | 123 | How text end-of-line is encoded depends on operating system. For |
df7492f9 | 124 | instance, Unix's format is just one byte of LF (line-feed) code, |
f4dee582 | 125 | whereas DOS's format is two-byte sequence of `carriage-return' and |
d46c5b12 KH |
126 | `line-feed' codes. MacOS's format is usually one byte of |
127 | `carriage-return'. | |
4ed46869 | 128 | |
cfb43547 | 129 | Since text character encoding and end-of-line encoding are |
df7492f9 KH |
130 | independent, any coding system described above can take any format |
131 | of end-of-line (except for no-conversion). | |
4ed46869 | 132 | |
e19c3639 KH |
133 | STRUCT CODING_SYSTEM |
134 | ||
135 | Before using a coding system for code conversion (i.e. decoding and | |
136 | encoding), we setup a structure of type `struct coding_system'. | |
137 | This structure keeps various information about a specific code | |
5bad0796 | 138 | conversion (e.g. the location of source and destination data). |
4ed46869 KH |
139 | |
140 | */ | |
141 | ||
df7492f9 KH |
142 | /* COMMON MACROS */ |
143 | ||
144 | ||
4ed46869 KH |
145 | /*** GENERAL NOTES on `detect_coding_XXX ()' functions *** |
146 | ||
df7492f9 | 147 | These functions check if a byte sequence specified as a source in |
ff0dacd7 KH |
148 | CODING conforms to the format of XXX, and update the members of |
149 | DETECT_INFO. | |
df7492f9 | 150 | |
ff0dacd7 | 151 | Return 1 if the byte sequence conforms to XXX, otherwise return 0. |
df7492f9 KH |
152 | |
153 | Below is the template of these functions. */ | |
154 | ||
4ed46869 | 155 | #if 0 |
df7492f9 | 156 | static int |
ff0dacd7 | 157 | detect_coding_XXX (coding, detect_info) |
df7492f9 | 158 | struct coding_system *coding; |
ff0dacd7 | 159 | struct coding_detection_info *detect_info; |
4ed46869 | 160 | { |
f1d34bca MB |
161 | const unsigned char *src = coding->source; |
162 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 163 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 164 | int consumed_chars = 0; |
df7492f9 KH |
165 | int found = 0; |
166 | ...; | |
167 | ||
168 | while (1) | |
169 | { | |
170 | /* Get one byte from the source. If the souce is exausted, jump | |
171 | to no_more_source:. */ | |
172 | ONE_MORE_BYTE (c); | |
ff0dacd7 KH |
173 | |
174 | if (! __C_conforms_to_XXX___ (c)) | |
175 | break; | |
176 | if (! __C_strongly_suggests_XXX__ (c)) | |
177 | found = CATEGORY_MASK_XXX; | |
df7492f9 | 178 | } |
ff0dacd7 KH |
179 | /* The byte sequence is invalid for XXX. */ |
180 | detect_info->rejected |= CATEGORY_MASK_XXX; | |
df7492f9 | 181 | return 0; |
ff0dacd7 | 182 | |
df7492f9 | 183 | no_more_source: |
ff0dacd7 KH |
184 | /* The source exausted successfully. */ |
185 | detect_info->found |= found; | |
df7492f9 | 186 | return 1; |
4ed46869 KH |
187 | } |
188 | #endif | |
189 | ||
190 | /*** GENERAL NOTES on `decode_coding_XXX ()' functions *** | |
191 | ||
df7492f9 KH |
192 | These functions decode a byte sequence specified as a source by |
193 | CODING. The resulting multibyte text goes to a place pointed to by | |
194 | CODING->charbuf, the length of which should not exceed | |
195 | CODING->charbuf_size; | |
d46c5b12 | 196 | |
df7492f9 KH |
197 | These functions set the information of original and decoded texts in |
198 | CODING->consumed, CODING->consumed_char, and CODING->charbuf_used. | |
199 | They also set CODING->result to one of CODING_RESULT_XXX indicating | |
200 | how the decoding is finished. | |
d46c5b12 | 201 | |
df7492f9 | 202 | Below is the template of these functions. */ |
d46c5b12 | 203 | |
4ed46869 | 204 | #if 0 |
b73bfc1c | 205 | static void |
df7492f9 | 206 | decode_coding_XXXX (coding) |
4ed46869 | 207 | struct coding_system *coding; |
4ed46869 | 208 | { |
f1d34bca MB |
209 | const unsigned char *src = coding->source + coding->consumed; |
210 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
211 | /* SRC_BASE remembers the start position in source in each loop. |
212 | The loop will be exited when there's not enough source code, or | |
213 | when there's no room in CHARBUF for a decoded character. */ | |
f1d34bca | 214 | const unsigned char *src_base; |
df7492f9 | 215 | /* A buffer to produce decoded characters. */ |
69a80ea3 KH |
216 | int *charbuf = coding->charbuf + coding->charbuf_used; |
217 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
218 | int multibytep = coding->src_multibyte; |
219 | ||
220 | while (1) | |
221 | { | |
222 | src_base = src; | |
223 | if (charbuf < charbuf_end) | |
224 | /* No more room to produce a decoded character. */ | |
225 | break; | |
226 | ONE_MORE_BYTE (c); | |
227 | /* Decode it. */ | |
228 | } | |
229 | ||
230 | no_more_source: | |
231 | if (src_base < src_end | |
232 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
233 | /* If the source ends by partial bytes to construct a character, | |
234 | treat them as eight-bit raw data. */ | |
235 | while (src_base < src_end && charbuf < charbuf_end) | |
236 | *charbuf++ = *src_base++; | |
237 | /* Remember how many bytes and characters we consumed. If the | |
238 | source is multibyte, the bytes and chars are not identical. */ | |
239 | coding->consumed = coding->consumed_char = src_base - coding->source; | |
240 | /* Remember how many characters we produced. */ | |
241 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
242 | } |
243 | #endif | |
244 | ||
245 | /*** GENERAL NOTES on `encode_coding_XXX ()' functions *** | |
246 | ||
df7492f9 KH |
247 | These functions encode SRC_BYTES length text at SOURCE of Emacs' |
248 | internal multibyte format by CODING. The resulting byte sequence | |
b73bfc1c KH |
249 | goes to a place pointed to by DESTINATION, the length of which |
250 | should not exceed DST_BYTES. | |
d46c5b12 | 251 | |
df7492f9 KH |
252 | These functions set the information of original and encoded texts in |
253 | the members produced, produced_char, consumed, and consumed_char of | |
254 | the structure *CODING. They also set the member result to one of | |
255 | CODING_RESULT_XXX indicating how the encoding finished. | |
d46c5b12 | 256 | |
df7492f9 KH |
257 | DST_BYTES zero means that source area and destination area are |
258 | overlapped, which means that we can produce a encoded text until it | |
259 | reaches at the head of not-yet-encoded source text. | |
d46c5b12 | 260 | |
df7492f9 | 261 | Below is a template of these functions. */ |
4ed46869 | 262 | #if 0 |
b73bfc1c | 263 | static void |
df7492f9 | 264 | encode_coding_XXX (coding) |
4ed46869 | 265 | struct coding_system *coding; |
4ed46869 | 266 | { |
df7492f9 KH |
267 | int multibytep = coding->dst_multibyte; |
268 | int *charbuf = coding->charbuf; | |
269 | int *charbuf_end = charbuf->charbuf + coding->charbuf_used; | |
270 | unsigned char *dst = coding->destination + coding->produced; | |
271 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
272 | unsigned char *adjusted_dst_end = dst_end - _MAX_BYTES_PRODUCED_IN_LOOP_; | |
273 | int produced_chars = 0; | |
274 | ||
275 | for (; charbuf < charbuf_end && dst < adjusted_dst_end; charbuf++) | |
276 | { | |
277 | int c = *charbuf; | |
278 | /* Encode C into DST, and increment DST. */ | |
279 | } | |
280 | label_no_more_destination: | |
281 | /* How many chars and bytes we produced. */ | |
282 | coding->produced_char += produced_chars; | |
283 | coding->produced = dst - coding->destination; | |
4ed46869 KH |
284 | } |
285 | #endif | |
286 | ||
4ed46869 KH |
287 | \f |
288 | /*** 1. Preamble ***/ | |
289 | ||
68c45bf0 | 290 | #include <config.h> |
4ed46869 KH |
291 | #include <stdio.h> |
292 | ||
4ed46869 KH |
293 | #include "lisp.h" |
294 | #include "buffer.h" | |
df7492f9 | 295 | #include "character.h" |
4ed46869 KH |
296 | #include "charset.h" |
297 | #include "ccl.h" | |
df7492f9 | 298 | #include "composite.h" |
4ed46869 KH |
299 | #include "coding.h" |
300 | #include "window.h" | |
4ed46869 | 301 | |
df7492f9 | 302 | Lisp_Object Vcoding_system_hash_table; |
4ed46869 | 303 | |
df7492f9 | 304 | Lisp_Object Qcoding_system, Qcoding_aliases, Qeol_type; |
1965cb73 DL |
305 | Lisp_Object Qunix, Qdos; |
306 | extern Lisp_Object Qmac; /* frame.c */ | |
4ed46869 KH |
307 | Lisp_Object Qbuffer_file_coding_system; |
308 | Lisp_Object Qpost_read_conversion, Qpre_write_conversion; | |
df7492f9 | 309 | Lisp_Object Qdefault_char; |
27901516 | 310 | Lisp_Object Qno_conversion, Qundecided; |
df7492f9 | 311 | Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5; |
b49a1807 | 312 | Lisp_Object Qbig, Qlittle; |
bb0115a2 | 313 | Lisp_Object Qcoding_system_history; |
1397dc18 | 314 | Lisp_Object Qvalid_codes; |
a6f87d34 KH |
315 | Lisp_Object QCcategory, QCmnemonic, QCdefalut_char; |
316 | Lisp_Object QCdecode_translation_table, QCencode_translation_table; | |
317 | Lisp_Object QCpost_read_conversion, QCpre_write_conversion; | |
35befdaa | 318 | Lisp_Object QCascii_compatible_p; |
4ed46869 KH |
319 | |
320 | extern Lisp_Object Qinsert_file_contents, Qwrite_region; | |
387f6ba5 | 321 | Lisp_Object Qcall_process, Qcall_process_region; |
4ed46869 KH |
322 | Lisp_Object Qstart_process, Qopen_network_stream; |
323 | Lisp_Object Qtarget_idx; | |
324 | ||
065e3595 KH |
325 | Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source; |
326 | Lisp_Object Qinterrupted, Qinsufficient_memory; | |
327 | ||
44e8490d KH |
328 | /* If a symbol has this property, evaluate the value to define the |
329 | symbol as a coding system. */ | |
330 | static Lisp_Object Qcoding_system_define_form; | |
331 | ||
5d5bf4d8 KH |
332 | int coding_system_require_warning; |
333 | ||
d46c5b12 KH |
334 | Lisp_Object Vselect_safe_coding_system_function; |
335 | ||
7722baf9 EZ |
336 | /* Mnemonic string for each format of end-of-line. */ |
337 | Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; | |
338 | /* Mnemonic string to indicate format of end-of-line is not yet | |
4ed46869 | 339 | decided. */ |
7722baf9 | 340 | Lisp_Object eol_mnemonic_undecided; |
4ed46869 KH |
341 | |
342 | #ifdef emacs | |
343 | ||
4608c386 KH |
344 | Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
345 | ||
346 | Lisp_Object Qcoding_system_p, Qcoding_system_error; | |
4ed46869 | 347 | |
d46c5b12 KH |
348 | /* Coding system emacs-mule and raw-text are for converting only |
349 | end-of-line format. */ | |
350 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 351 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 352 | |
4ed46869 KH |
353 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
354 | routines by the following three variables. */ | |
355 | /* Coding-system for reading files and receiving data from process. */ | |
356 | Lisp_Object Vcoding_system_for_read; | |
357 | /* Coding-system for writing files and sending data to process. */ | |
358 | Lisp_Object Vcoding_system_for_write; | |
359 | /* Coding-system actually used in the latest I/O. */ | |
360 | Lisp_Object Vlast_coding_system_used; | |
065e3595 KH |
361 | /* Set to non-nil when an error is detected while code conversion. */ |
362 | Lisp_Object Vlast_code_conversion_error; | |
c4825358 | 363 | /* A vector of length 256 which contains information about special |
94487c4e | 364 | Latin codes (especially for dealing with Microsoft codes). */ |
3f003981 | 365 | Lisp_Object Vlatin_extra_code_table; |
c4825358 | 366 | |
9ce27fde KH |
367 | /* Flag to inhibit code conversion of end-of-line format. */ |
368 | int inhibit_eol_conversion; | |
369 | ||
74383408 KH |
370 | /* Flag to inhibit ISO2022 escape sequence detection. */ |
371 | int inhibit_iso_escape_detection; | |
372 | ||
ed29121d EZ |
373 | /* Flag to make buffer-file-coding-system inherit from process-coding. */ |
374 | int inherit_process_coding_system; | |
375 | ||
c4825358 | 376 | /* Coding system to be used to encode text for terminal display. */ |
4ed46869 KH |
377 | struct coding_system terminal_coding; |
378 | ||
c4825358 KH |
379 | /* Coding system to be used to encode text for terminal display when |
380 | terminal coding system is nil. */ | |
381 | struct coding_system safe_terminal_coding; | |
382 | ||
383 | /* Coding system of what is sent from terminal keyboard. */ | |
4ed46869 KH |
384 | struct coding_system keyboard_coding; |
385 | ||
02ba4723 KH |
386 | Lisp_Object Vfile_coding_system_alist; |
387 | Lisp_Object Vprocess_coding_system_alist; | |
388 | Lisp_Object Vnetwork_coding_system_alist; | |
4ed46869 | 389 | |
68c45bf0 PE |
390 | Lisp_Object Vlocale_coding_system; |
391 | ||
4ed46869 KH |
392 | #endif /* emacs */ |
393 | ||
f967223b KH |
394 | /* Flag to tell if we look up translation table on character code |
395 | conversion. */ | |
84fbb8a0 | 396 | Lisp_Object Venable_character_translation; |
f967223b KH |
397 | /* Standard translation table to look up on decoding (reading). */ |
398 | Lisp_Object Vstandard_translation_table_for_decode; | |
399 | /* Standard translation table to look up on encoding (writing). */ | |
400 | Lisp_Object Vstandard_translation_table_for_encode; | |
84fbb8a0 | 401 | |
f967223b KH |
402 | Lisp_Object Qtranslation_table; |
403 | Lisp_Object Qtranslation_table_id; | |
404 | Lisp_Object Qtranslation_table_for_decode; | |
405 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 KH |
406 | |
407 | /* Alist of charsets vs revision number. */ | |
df7492f9 | 408 | static Lisp_Object Vcharset_revision_table; |
4ed46869 | 409 | |
02ba4723 KH |
410 | /* Default coding systems used for process I/O. */ |
411 | Lisp_Object Vdefault_process_coding_system; | |
412 | ||
002fdb44 DL |
413 | /* Char table for translating Quail and self-inserting input. */ |
414 | Lisp_Object Vtranslation_table_for_input; | |
415 | ||
df7492f9 KH |
416 | /* Two special coding systems. */ |
417 | Lisp_Object Vsjis_coding_system; | |
418 | Lisp_Object Vbig5_coding_system; | |
419 | ||
df7492f9 KH |
420 | /* ISO2022 section */ |
421 | ||
422 | #define CODING_ISO_INITIAL(coding, reg) \ | |
423 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
424 | coding_attr_iso_initial), \ | |
425 | reg))) | |
426 | ||
427 | ||
428 | #define CODING_ISO_REQUEST(coding, charset_id) \ | |
429 | ((charset_id <= (coding)->max_charset_id \ | |
430 | ? (coding)->safe_charsets[charset_id] \ | |
431 | : -1)) | |
432 | ||
433 | ||
434 | #define CODING_ISO_FLAGS(coding) \ | |
435 | ((coding)->spec.iso_2022.flags) | |
436 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
437 | ((coding)->spec.iso_2022.current_designation[reg]) | |
438 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
439 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
440 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
441 | ((coding)->spec.iso_2022.single_shifting) | |
442 | #define CODING_ISO_BOL(coding) \ | |
443 | ((coding)->spec.iso_2022.bol) | |
444 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
445 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
446 | ||
447 | /* Control characters of ISO2022. */ | |
448 | /* code */ /* function */ | |
449 | #define ISO_CODE_LF 0x0A /* line-feed */ | |
450 | #define ISO_CODE_CR 0x0D /* carriage-return */ | |
451 | #define ISO_CODE_SO 0x0E /* shift-out */ | |
452 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
453 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
454 | #define ISO_CODE_ESC 0x1B /* escape */ | |
455 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
456 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
457 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
458 | ||
459 | /* All code (1-byte) of ISO2022 is classified into one of the | |
460 | followings. */ | |
461 | enum iso_code_class_type | |
462 | { | |
463 | ISO_control_0, /* Control codes in the range | |
464 | 0x00..0x1F and 0x7F, except for the | |
465 | following 5 codes. */ | |
df7492f9 KH |
466 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
467 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
468 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
469 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
470 | ISO_control_1, /* Control codes in the range | |
471 | 0x80..0x9F, except for the | |
472 | following 3 codes. */ | |
473 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
474 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
475 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
476 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
477 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
478 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
479 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
480 | }; | |
05e6f5dc | 481 | |
df7492f9 KH |
482 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
483 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 484 | |
df7492f9 KH |
485 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
486 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
487 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 488 | |
df7492f9 KH |
489 | /* If set, reset graphic planes and registers at end-of-line to the |
490 | initial state. */ | |
491 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 492 | |
df7492f9 KH |
493 | /* If set, reset graphic planes and registers before any control |
494 | characters to the initial state. */ | |
495 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 496 | |
df7492f9 KH |
497 | /* If set, encode by 7-bit environment. */ |
498 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 499 | |
df7492f9 KH |
500 | /* If set, use locking-shift function. */ |
501 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 502 | |
df7492f9 KH |
503 | /* If set, use single-shift function. Overwrite |
504 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
505 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 506 | |
df7492f9 KH |
507 | /* If set, use designation escape sequence. */ |
508 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 509 | |
df7492f9 KH |
510 | /* If set, produce revision number sequence. */ |
511 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 512 | |
df7492f9 KH |
513 | /* If set, produce ISO6429's direction specifying sequence. */ |
514 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 515 | |
df7492f9 KH |
516 | /* If set, assume designation states are reset at beginning of line on |
517 | output. */ | |
518 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 519 | |
df7492f9 KH |
520 | /* If set, designation sequence should be placed at beginning of line |
521 | on output. */ | |
522 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 523 | |
df7492f9 KH |
524 | /* If set, do not encode unsafe charactes on output. */ |
525 | #define CODING_ISO_FLAG_SAFE 0x0800 | |
aa72b389 | 526 | |
df7492f9 KH |
527 | /* If set, extra latin codes (128..159) are accepted as a valid code |
528 | on input. */ | |
529 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 530 | |
df7492f9 | 531 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 532 | |
df7492f9 | 533 | #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 |
aa72b389 | 534 | |
bf16eb23 | 535 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 536 | |
bf16eb23 | 537 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 538 | |
bf16eb23 | 539 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 540 | |
df7492f9 KH |
541 | /* A character to be produced on output if encoding of the original |
542 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
543 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 544 | |
4ed46869 | 545 | |
df7492f9 KH |
546 | /* UTF-16 section */ |
547 | #define CODING_UTF_16_BOM(coding) \ | |
548 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 549 | |
df7492f9 KH |
550 | #define CODING_UTF_16_ENDIAN(coding) \ |
551 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 552 | |
df7492f9 KH |
553 | #define CODING_UTF_16_SURROGATE(coding) \ |
554 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 555 | |
4ed46869 | 556 | |
df7492f9 KH |
557 | /* CCL section */ |
558 | #define CODING_CCL_DECODER(coding) \ | |
559 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
560 | #define CODING_CCL_ENCODER(coding) \ | |
561 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
562 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 563 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 564 | |
5a936b46 | 565 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 566 | |
df7492f9 KH |
567 | enum coding_category |
568 | { | |
569 | coding_category_iso_7, | |
570 | coding_category_iso_7_tight, | |
571 | coding_category_iso_8_1, | |
572 | coding_category_iso_8_2, | |
573 | coding_category_iso_7_else, | |
574 | coding_category_iso_8_else, | |
575 | coding_category_utf_8, | |
576 | coding_category_utf_16_auto, | |
577 | coding_category_utf_16_be, | |
578 | coding_category_utf_16_le, | |
579 | coding_category_utf_16_be_nosig, | |
580 | coding_category_utf_16_le_nosig, | |
581 | coding_category_charset, | |
582 | coding_category_sjis, | |
583 | coding_category_big5, | |
584 | coding_category_ccl, | |
585 | coding_category_emacs_mule, | |
586 | /* All above are targets of code detection. */ | |
587 | coding_category_raw_text, | |
588 | coding_category_undecided, | |
589 | coding_category_max | |
590 | }; | |
591 | ||
592 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
593 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
594 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
595 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
596 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
597 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
598 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
599 | #define CATEGORY_MASK_UTF_8 (1 << coding_category_utf_8) | |
b49a1807 | 600 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
601 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
602 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
603 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
604 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
605 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
606 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
607 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
608 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
609 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 610 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
611 | |
612 | /* This value is returned if detect_coding_mask () find nothing other | |
613 | than ASCII characters. */ | |
614 | #define CATEGORY_MASK_ANY \ | |
615 | (CATEGORY_MASK_ISO_7 \ | |
616 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
617 | | CATEGORY_MASK_ISO_8_1 \ | |
618 | | CATEGORY_MASK_ISO_8_2 \ | |
619 | | CATEGORY_MASK_ISO_7_ELSE \ | |
620 | | CATEGORY_MASK_ISO_8_ELSE \ | |
621 | | CATEGORY_MASK_UTF_8 \ | |
622 | | CATEGORY_MASK_UTF_16_BE \ | |
623 | | CATEGORY_MASK_UTF_16_LE \ | |
624 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
625 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
626 | | CATEGORY_MASK_CHARSET \ | |
627 | | CATEGORY_MASK_SJIS \ | |
628 | | CATEGORY_MASK_BIG5 \ | |
629 | | CATEGORY_MASK_CCL \ | |
630 | | CATEGORY_MASK_EMACS_MULE) | |
631 | ||
632 | ||
633 | #define CATEGORY_MASK_ISO_7BIT \ | |
634 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
635 | ||
636 | #define CATEGORY_MASK_ISO_8BIT \ | |
637 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
638 | ||
639 | #define CATEGORY_MASK_ISO_ELSE \ | |
640 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
641 | ||
642 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
643 | (CATEGORY_MASK_ISO_7 \ | |
644 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
645 | | CATEGORY_MASK_ISO_7_ELSE \ | |
646 | | CATEGORY_MASK_ISO_8_ELSE) | |
647 | ||
648 | #define CATEGORY_MASK_ISO \ | |
649 | ( CATEGORY_MASK_ISO_7BIT \ | |
650 | | CATEGORY_MASK_ISO_8BIT \ | |
651 | | CATEGORY_MASK_ISO_ELSE) | |
652 | ||
653 | #define CATEGORY_MASK_UTF_16 \ | |
654 | (CATEGORY_MASK_UTF_16_BE \ | |
655 | | CATEGORY_MASK_UTF_16_LE \ | |
656 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
657 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
658 | ||
659 | ||
660 | /* List of symbols `coding-category-xxx' ordered by priority. This | |
661 | variable is exposed to Emacs Lisp. */ | |
662 | static Lisp_Object Vcoding_category_list; | |
663 | ||
664 | /* Table of coding categories (Lisp symbols). This variable is for | |
665 | internal use oly. */ | |
666 | static Lisp_Object Vcoding_category_table; | |
667 | ||
668 | /* Table of coding-categories ordered by priority. */ | |
669 | static enum coding_category coding_priorities[coding_category_max]; | |
670 | ||
671 | /* Nth element is a coding context for the coding system bound to the | |
672 | Nth coding category. */ | |
673 | static struct coding_system coding_categories[coding_category_max]; | |
674 | ||
df7492f9 KH |
675 | /*** Commonly used macros and functions ***/ |
676 | ||
677 | #ifndef min | |
678 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
679 | #endif | |
680 | #ifndef max | |
681 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
682 | #endif | |
4ed46869 | 683 | |
24a73b0a KH |
684 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
685 | do { \ | |
686 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
687 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 688 | } while (0) |
4ed46869 | 689 | |
4ed46869 | 690 | |
df7492f9 KH |
691 | /* Safely get one byte from the source text pointed by SRC which ends |
692 | at SRC_END, and set C to that byte. If there are not enough bytes | |
065e3595 KH |
693 | in the source, it jumps to `no_more_source'. If multibytep is |
694 | nonzero, and a multibyte character is found at SRC, set C to the | |
695 | negative value of the character code. The caller should declare | |
696 | and set these variables appropriately in advance: | |
697 | src, src_end, multibytep */ | |
aa72b389 | 698 | |
065e3595 KH |
699 | #define ONE_MORE_BYTE(c) \ |
700 | do { \ | |
701 | if (src == src_end) \ | |
702 | { \ | |
703 | if (src_base < src) \ | |
704 | record_conversion_result \ | |
705 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
706 | goto no_more_source; \ | |
707 | } \ | |
708 | c = *src++; \ | |
709 | if (multibytep && (c & 0x80)) \ | |
710 | { \ | |
711 | if ((c & 0xFE) == 0xC0) \ | |
712 | c = ((c & 1) << 6) | *src++; \ | |
713 | else \ | |
714 | { \ | |
35befdaa KH |
715 | src--; \ |
716 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
717 | record_conversion_result \ |
718 | (coding, CODING_RESULT_INVALID_SRC); \ | |
719 | } \ | |
720 | } \ | |
721 | consumed_chars++; \ | |
aa72b389 KH |
722 | } while (0) |
723 | ||
aa72b389 | 724 | |
065e3595 KH |
725 | #define ONE_MORE_BYTE_NO_CHECK(c) \ |
726 | do { \ | |
727 | c = *src++; \ | |
728 | if (multibytep && (c & 0x80)) \ | |
729 | { \ | |
730 | if ((c & 0xFE) == 0xC0) \ | |
731 | c = ((c & 1) << 6) | *src++; \ | |
732 | else \ | |
733 | { \ | |
35befdaa KH |
734 | src--; \ |
735 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
736 | record_conversion_result \ |
737 | (coding, CODING_RESULT_INVALID_SRC); \ | |
738 | } \ | |
739 | } \ | |
740 | consumed_chars++; \ | |
aa72b389 KH |
741 | } while (0) |
742 | ||
aa72b389 | 743 | |
df7492f9 KH |
744 | /* Store a byte C in the place pointed by DST and increment DST to the |
745 | next free point, and increment PRODUCED_CHARS. The caller should | |
746 | assure that C is 0..127, and declare and set the variable `dst' | |
747 | appropriately in advance. | |
748 | */ | |
aa72b389 KH |
749 | |
750 | ||
df7492f9 KH |
751 | #define EMIT_ONE_ASCII_BYTE(c) \ |
752 | do { \ | |
753 | produced_chars++; \ | |
754 | *dst++ = (c); \ | |
b6871cc7 | 755 | } while (0) |
aa72b389 KH |
756 | |
757 | ||
df7492f9 | 758 | /* Like EMIT_ONE_ASCII_BYTE byt store two bytes; C1 and C2. */ |
aa72b389 | 759 | |
df7492f9 KH |
760 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
761 | do { \ | |
762 | produced_chars += 2; \ | |
763 | *dst++ = (c1), *dst++ = (c2); \ | |
764 | } while (0) | |
aa72b389 KH |
765 | |
766 | ||
df7492f9 KH |
767 | /* Store a byte C in the place pointed by DST and increment DST to the |
768 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is | |
769 | nonzero, store in an appropriate multibyte from. The caller should | |
770 | declare and set the variables `dst' and `multibytep' appropriately | |
771 | in advance. */ | |
772 | ||
773 | #define EMIT_ONE_BYTE(c) \ | |
774 | do { \ | |
775 | produced_chars++; \ | |
776 | if (multibytep) \ | |
777 | { \ | |
778 | int ch = (c); \ | |
779 | if (ch >= 0x80) \ | |
780 | ch = BYTE8_TO_CHAR (ch); \ | |
781 | CHAR_STRING_ADVANCE (ch, dst); \ | |
782 | } \ | |
783 | else \ | |
784 | *dst++ = (c); \ | |
aa72b389 | 785 | } while (0) |
aa72b389 | 786 | |
aa72b389 | 787 | |
df7492f9 | 788 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 789 | |
e19c3639 KH |
790 | #define EMIT_TWO_BYTES(c1, c2) \ |
791 | do { \ | |
792 | produced_chars += 2; \ | |
793 | if (multibytep) \ | |
794 | { \ | |
795 | int ch; \ | |
796 | \ | |
797 | ch = (c1); \ | |
798 | if (ch >= 0x80) \ | |
799 | ch = BYTE8_TO_CHAR (ch); \ | |
800 | CHAR_STRING_ADVANCE (ch, dst); \ | |
801 | ch = (c2); \ | |
802 | if (ch >= 0x80) \ | |
803 | ch = BYTE8_TO_CHAR (ch); \ | |
804 | CHAR_STRING_ADVANCE (ch, dst); \ | |
805 | } \ | |
806 | else \ | |
807 | { \ | |
808 | *dst++ = (c1); \ | |
809 | *dst++ = (c2); \ | |
810 | } \ | |
aa72b389 KH |
811 | } while (0) |
812 | ||
813 | ||
df7492f9 KH |
814 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
815 | do { \ | |
816 | EMIT_ONE_BYTE (c1); \ | |
817 | EMIT_TWO_BYTES (c2, c3); \ | |
818 | } while (0) | |
aa72b389 | 819 | |
aa72b389 | 820 | |
df7492f9 KH |
821 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
822 | do { \ | |
823 | EMIT_TWO_BYTES (c1, c2); \ | |
824 | EMIT_TWO_BYTES (c3, c4); \ | |
825 | } while (0) | |
aa72b389 | 826 | |
aa72b389 | 827 | |
f6cbaf43 KH |
828 | /* Prototypes for static functions. */ |
829 | static void record_conversion_result P_ ((struct coding_system *coding, | |
830 | enum coding_result_code result)); | |
831 | static int detect_coding_utf_8 P_ ((struct coding_system *, | |
832 | struct coding_detection_info *info)); | |
833 | static void decode_coding_utf_8 P_ ((struct coding_system *)); | |
834 | static int encode_coding_utf_8 P_ ((struct coding_system *)); | |
835 | ||
836 | static int detect_coding_utf_16 P_ ((struct coding_system *, | |
837 | struct coding_detection_info *info)); | |
838 | static void decode_coding_utf_16 P_ ((struct coding_system *)); | |
839 | static int encode_coding_utf_16 P_ ((struct coding_system *)); | |
840 | ||
841 | static int detect_coding_iso_2022 P_ ((struct coding_system *, | |
842 | struct coding_detection_info *info)); | |
843 | static void decode_coding_iso_2022 P_ ((struct coding_system *)); | |
844 | static int encode_coding_iso_2022 P_ ((struct coding_system *)); | |
845 | ||
846 | static int detect_coding_emacs_mule P_ ((struct coding_system *, | |
847 | struct coding_detection_info *info)); | |
848 | static void decode_coding_emacs_mule P_ ((struct coding_system *)); | |
849 | static int encode_coding_emacs_mule P_ ((struct coding_system *)); | |
850 | ||
851 | static int detect_coding_sjis P_ ((struct coding_system *, | |
852 | struct coding_detection_info *info)); | |
853 | static void decode_coding_sjis P_ ((struct coding_system *)); | |
854 | static int encode_coding_sjis P_ ((struct coding_system *)); | |
855 | ||
856 | static int detect_coding_big5 P_ ((struct coding_system *, | |
857 | struct coding_detection_info *info)); | |
858 | static void decode_coding_big5 P_ ((struct coding_system *)); | |
859 | static int encode_coding_big5 P_ ((struct coding_system *)); | |
860 | ||
861 | static int detect_coding_ccl P_ ((struct coding_system *, | |
862 | struct coding_detection_info *info)); | |
863 | static void decode_coding_ccl P_ ((struct coding_system *)); | |
864 | static int encode_coding_ccl P_ ((struct coding_system *)); | |
865 | ||
866 | static void decode_coding_raw_text P_ ((struct coding_system *)); | |
867 | static int encode_coding_raw_text P_ ((struct coding_system *)); | |
868 | ||
869 | static void coding_set_source P_ ((struct coding_system *)); | |
870 | static void coding_set_destination P_ ((struct coding_system *)); | |
871 | static void coding_alloc_by_realloc P_ ((struct coding_system *, EMACS_INT)); | |
872 | static void coding_alloc_by_making_gap P_ ((struct coding_system *, | |
873 | EMACS_INT)); | |
874 | static unsigned char *alloc_destination P_ ((struct coding_system *, | |
875 | EMACS_INT, unsigned char *)); | |
876 | static void setup_iso_safe_charsets P_ ((Lisp_Object)); | |
877 | static unsigned char *encode_designation_at_bol P_ ((struct coding_system *, | |
878 | int *, int *, | |
879 | unsigned char *)); | |
880 | static int detect_eol P_ ((const unsigned char *, | |
881 | EMACS_INT, enum coding_category)); | |
882 | static Lisp_Object adjust_coding_eol_type P_ ((struct coding_system *, int)); | |
883 | static void decode_eol P_ ((struct coding_system *)); | |
884 | static Lisp_Object get_translation_table P_ ((Lisp_Object, int, int *)); | |
885 | static Lisp_Object get_translation P_ ((Lisp_Object, int *, int *, | |
886 | int, int *, int *)); | |
887 | static int produce_chars P_ ((struct coding_system *, Lisp_Object, int)); | |
888 | static INLINE void produce_composition P_ ((struct coding_system *, int *, | |
889 | EMACS_INT)); | |
890 | static INLINE void produce_charset P_ ((struct coding_system *, int *, | |
891 | EMACS_INT)); | |
892 | static void produce_annotation P_ ((struct coding_system *, EMACS_INT)); | |
893 | static int decode_coding P_ ((struct coding_system *)); | |
894 | static INLINE int *handle_composition_annotation P_ ((EMACS_INT, EMACS_INT, | |
895 | struct coding_system *, | |
896 | int *, EMACS_INT *)); | |
897 | static INLINE int *handle_charset_annotation P_ ((EMACS_INT, EMACS_INT, | |
898 | struct coding_system *, | |
899 | int *, EMACS_INT *)); | |
900 | static void consume_chars P_ ((struct coding_system *, Lisp_Object, int)); | |
901 | static int encode_coding P_ ((struct coding_system *)); | |
902 | static Lisp_Object make_conversion_work_buffer P_ ((int)); | |
903 | static Lisp_Object code_conversion_restore P_ ((Lisp_Object)); | |
904 | static INLINE int char_encodable_p P_ ((int, Lisp_Object)); | |
905 | static Lisp_Object make_subsidiaries P_ ((Lisp_Object)); | |
906 | ||
065e3595 KH |
907 | static void |
908 | record_conversion_result (struct coding_system *coding, | |
909 | enum coding_result_code result) | |
910 | { | |
911 | coding->result = result; | |
912 | switch (result) | |
913 | { | |
914 | case CODING_RESULT_INSUFFICIENT_SRC: | |
915 | Vlast_code_conversion_error = Qinsufficient_source; | |
916 | break; | |
917 | case CODING_RESULT_INCONSISTENT_EOL: | |
918 | Vlast_code_conversion_error = Qinconsistent_eol; | |
919 | break; | |
920 | case CODING_RESULT_INVALID_SRC: | |
921 | Vlast_code_conversion_error = Qinvalid_source; | |
922 | break; | |
923 | case CODING_RESULT_INTERRUPT: | |
924 | Vlast_code_conversion_error = Qinterrupted; | |
925 | break; | |
926 | case CODING_RESULT_INSUFFICIENT_MEM: | |
927 | Vlast_code_conversion_error = Qinsufficient_memory; | |
928 | break; | |
35befdaa KH |
929 | default: |
930 | Vlast_code_conversion_error = intern ("Unknown error"); | |
065e3595 KH |
931 | } |
932 | } | |
933 | ||
df7492f9 KH |
934 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
935 | do { \ | |
936 | charset_map_loaded = 0; \ | |
937 | c = DECODE_CHAR (charset, code); \ | |
938 | if (charset_map_loaded) \ | |
939 | { \ | |
8f924df7 | 940 | const unsigned char *orig = coding->source; \ |
df7492f9 KH |
941 | EMACS_INT offset; \ |
942 | \ | |
943 | coding_set_source (coding); \ | |
944 | offset = coding->source - orig; \ | |
945 | src += offset; \ | |
946 | src_base += offset; \ | |
947 | src_end += offset; \ | |
948 | } \ | |
aa72b389 KH |
949 | } while (0) |
950 | ||
951 | ||
df7492f9 KH |
952 | #define ASSURE_DESTINATION(bytes) \ |
953 | do { \ | |
954 | if (dst + (bytes) >= dst_end) \ | |
955 | { \ | |
956 | int more_bytes = charbuf_end - charbuf + (bytes); \ | |
957 | \ | |
958 | dst = alloc_destination (coding, more_bytes, dst); \ | |
959 | dst_end = coding->destination + coding->dst_bytes; \ | |
960 | } \ | |
961 | } while (0) | |
aa72b389 | 962 | |
aa72b389 | 963 | |
aa72b389 | 964 | |
df7492f9 KH |
965 | static void |
966 | coding_set_source (coding) | |
aa72b389 | 967 | struct coding_system *coding; |
aa72b389 | 968 | { |
df7492f9 KH |
969 | if (BUFFERP (coding->src_object)) |
970 | { | |
2cb26057 | 971 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 972 | |
df7492f9 | 973 | if (coding->src_pos < 0) |
2cb26057 | 974 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 975 | else |
2cb26057 | 976 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 977 | } |
df7492f9 | 978 | else if (STRINGP (coding->src_object)) |
aa72b389 | 979 | { |
8f924df7 | 980 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 981 | } |
df7492f9 KH |
982 | else |
983 | /* Otherwise, the source is C string and is never relocated | |
984 | automatically. Thus we don't have to update anything. */ | |
985 | ; | |
986 | } | |
aa72b389 | 987 | |
df7492f9 KH |
988 | static void |
989 | coding_set_destination (coding) | |
990 | struct coding_system *coding; | |
991 | { | |
992 | if (BUFFERP (coding->dst_object)) | |
aa72b389 | 993 | { |
df7492f9 | 994 | if (coding->src_pos < 0) |
aa72b389 | 995 | { |
28f67a95 KH |
996 | coding->destination = BEG_ADDR + coding->dst_pos_byte - 1; |
997 | coding->dst_bytes = (GAP_END_ADDR | |
998 | - (coding->src_bytes - coding->consumed) | |
999 | - coding->destination); | |
aa72b389 | 1000 | } |
df7492f9 | 1001 | else |
28f67a95 KH |
1002 | { |
1003 | /* We are sure that coding->dst_pos_byte is before the gap | |
1004 | of the buffer. */ | |
1005 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
1006 | + coding->dst_pos_byte - 1); | |
1007 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) | |
1008 | - coding->destination); | |
1009 | } | |
df7492f9 KH |
1010 | } |
1011 | else | |
1012 | /* Otherwise, the destination is C string and is never relocated | |
1013 | automatically. Thus we don't have to update anything. */ | |
1014 | ; | |
1015 | } | |
1016 | ||
1017 | ||
1018 | static void | |
1019 | coding_alloc_by_realloc (coding, bytes) | |
1020 | struct coding_system *coding; | |
1021 | EMACS_INT bytes; | |
1022 | { | |
1023 | coding->destination = (unsigned char *) xrealloc (coding->destination, | |
1024 | coding->dst_bytes + bytes); | |
1025 | coding->dst_bytes += bytes; | |
1026 | } | |
1027 | ||
1028 | static void | |
1029 | coding_alloc_by_making_gap (coding, bytes) | |
1030 | struct coding_system *coding; | |
1031 | EMACS_INT bytes; | |
1032 | { | |
2c78b7e1 KH |
1033 | if (BUFFERP (coding->dst_object) |
1034 | && EQ (coding->src_object, coding->dst_object)) | |
df7492f9 KH |
1035 | { |
1036 | EMACS_INT add = coding->src_bytes - coding->consumed; | |
1037 | ||
1038 | GAP_SIZE -= add; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
1039 | make_gap (bytes); | |
1040 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
1041 | } | |
307f5c57 | 1042 | else if (c >= 0x80) |
df7492f9 | 1043 | { |
2c78b7e1 KH |
1044 | Lisp_Object this_buffer; |
1045 | ||
1046 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
1047 | set_buffer_internal (XBUFFER (coding->dst_object)); |
1048 | make_gap (bytes); | |
1049 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 1050 | } |
df7492f9 | 1051 | } |
8f924df7 | 1052 | |
df7492f9 KH |
1053 | |
1054 | static unsigned char * | |
1055 | alloc_destination (coding, nbytes, dst) | |
1056 | struct coding_system *coding; | |
3e139625 | 1057 | EMACS_INT nbytes; |
df7492f9 KH |
1058 | unsigned char *dst; |
1059 | { | |
1060 | EMACS_INT offset = dst - coding->destination; | |
1061 | ||
1062 | if (BUFFERP (coding->dst_object)) | |
1063 | coding_alloc_by_making_gap (coding, nbytes); | |
aa72b389 | 1064 | else |
df7492f9 | 1065 | coding_alloc_by_realloc (coding, nbytes); |
065e3595 | 1066 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1067 | coding_set_destination (coding); |
1068 | dst = coding->destination + offset; | |
1069 | return dst; | |
1070 | } | |
aa72b389 | 1071 | |
ff0dacd7 KH |
1072 | /** Macros for annotations. */ |
1073 | ||
1074 | /* Maximum length of annotation data (sum of annotations for | |
1075 | composition and charset). */ | |
69a80ea3 | 1076 | #define MAX_ANNOTATION_LENGTH (4 + (MAX_COMPOSITION_COMPONENTS * 2) - 1 + 4) |
ff0dacd7 KH |
1077 | |
1078 | /* An annotation data is stored in the array coding->charbuf in this | |
1079 | format: | |
69a80ea3 | 1080 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1081 | LENGTH is the number of elements in the annotation. |
1082 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1083 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1084 | |
1085 | The format of the following elements depend on ANNOTATION_MASK. | |
1086 | ||
1087 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1088 | follows: | |
1089 | ... METHOD [ COMPOSITION-COMPONENTS ... ] | |
1090 | METHOD is one of enum composition_method. | |
1091 | Optionnal COMPOSITION-COMPONENTS are characters and composition | |
1092 | rules. | |
1093 | ||
1094 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
1095 | follows. */ | |
1096 | ||
69a80ea3 | 1097 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1098 | do { \ |
1099 | *(buf)++ = -(len); \ | |
1100 | *(buf)++ = (mask); \ | |
69a80ea3 | 1101 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1102 | coding->annotated = 1; \ |
1103 | } while (0); | |
1104 | ||
69a80ea3 KH |
1105 | #define ADD_COMPOSITION_DATA(buf, nchars, method) \ |
1106 | do { \ | |
1107 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ | |
1108 | *buf++ = method; \ | |
ff0dacd7 KH |
1109 | } while (0) |
1110 | ||
1111 | ||
69a80ea3 KH |
1112 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1113 | do { \ | |
1114 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1115 | *buf++ = id; \ | |
ff0dacd7 KH |
1116 | } while (0) |
1117 | ||
df7492f9 KH |
1118 | \f |
1119 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1120 | ||
1121 | ||
1122 | ||
1123 | \f | |
1124 | /*** 3. UTF-8 ***/ | |
1125 | ||
1126 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1127 | Check if a text is encoded in UTF-8. If it is, return 1, else |
1128 | return 0. */ | |
df7492f9 KH |
1129 | |
1130 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1131 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1132 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1133 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1134 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1135 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1136 | ||
1137 | static int | |
ff0dacd7 | 1138 | detect_coding_utf_8 (coding, detect_info) |
df7492f9 | 1139 | struct coding_system *coding; |
ff0dacd7 | 1140 | struct coding_detection_info *detect_info; |
df7492f9 | 1141 | { |
065e3595 | 1142 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1143 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1144 | int multibytep = coding->src_multibyte; |
1145 | int consumed_chars = 0; | |
1146 | int found = 0; | |
1147 | ||
ff0dacd7 | 1148 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1149 | /* A coding system of this category is always ASCII compatible. */ |
1150 | src += coding->head_ascii; | |
1151 | ||
1152 | while (1) | |
aa72b389 | 1153 | { |
df7492f9 | 1154 | int c, c1, c2, c3, c4; |
aa72b389 | 1155 | |
065e3595 | 1156 | src_base = src; |
df7492f9 | 1157 | ONE_MORE_BYTE (c); |
065e3595 | 1158 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1159 | continue; |
1160 | ONE_MORE_BYTE (c1); | |
065e3595 | 1161 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1162 | break; |
1163 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1164 | { |
ff0dacd7 | 1165 | found = CATEGORY_MASK_UTF_8; |
df7492f9 | 1166 | continue; |
aa72b389 | 1167 | } |
df7492f9 | 1168 | ONE_MORE_BYTE (c2); |
065e3595 | 1169 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1170 | break; |
1171 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1172 | { |
ff0dacd7 | 1173 | found = CATEGORY_MASK_UTF_8; |
df7492f9 | 1174 | continue; |
aa72b389 | 1175 | } |
df7492f9 | 1176 | ONE_MORE_BYTE (c3); |
065e3595 | 1177 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1178 | break; |
1179 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1180 | { |
ff0dacd7 | 1181 | found = CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1182 | continue; |
1183 | } | |
1184 | ONE_MORE_BYTE (c4); | |
065e3595 | 1185 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1186 | break; |
1187 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1188 | { | |
ff0dacd7 | 1189 | found = CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1190 | continue; |
1191 | } | |
1192 | break; | |
aa72b389 | 1193 | } |
ff0dacd7 | 1194 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1195 | return 0; |
aa72b389 | 1196 | |
df7492f9 | 1197 | no_more_source: |
065e3595 | 1198 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1199 | { |
ff0dacd7 | 1200 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1201 | return 0; |
aa72b389 | 1202 | } |
ff0dacd7 KH |
1203 | detect_info->found |= found; |
1204 | return 1; | |
aa72b389 KH |
1205 | } |
1206 | ||
4ed46869 | 1207 | |
b73bfc1c | 1208 | static void |
df7492f9 | 1209 | decode_coding_utf_8 (coding) |
b73bfc1c | 1210 | struct coding_system *coding; |
b73bfc1c | 1211 | { |
8f924df7 KH |
1212 | const unsigned char *src = coding->source + coding->consumed; |
1213 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1214 | const unsigned char *src_base; | |
69a80ea3 KH |
1215 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1216 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
1217 | int consumed_chars = 0, consumed_chars_base; |
1218 | int multibytep = coding->src_multibyte; | |
24a73b0a | 1219 | Lisp_Object attr, charset_list; |
4ed46869 | 1220 | |
24a73b0a | 1221 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 KH |
1222 | |
1223 | while (1) | |
b73bfc1c | 1224 | { |
df7492f9 | 1225 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1226 | |
df7492f9 KH |
1227 | src_base = src; |
1228 | consumed_chars_base = consumed_chars; | |
4af310db | 1229 | |
df7492f9 KH |
1230 | if (charbuf >= charbuf_end) |
1231 | break; | |
1232 | ||
1233 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1234 | if (c1 < 0) |
1235 | { | |
1236 | c = - c1; | |
1237 | } | |
1238 | else if (UTF_8_1_OCTET_P(c1)) | |
df7492f9 KH |
1239 | { |
1240 | c = c1; | |
4af310db | 1241 | } |
df7492f9 | 1242 | else |
4af310db | 1243 | { |
df7492f9 | 1244 | ONE_MORE_BYTE (c2); |
065e3595 | 1245 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1246 | goto invalid_code; |
1247 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1248 | { |
b0edb2c5 DL |
1249 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1250 | /* Reject overlong sequences here and below. Encoders | |
1251 | producing them are incorrect, they can be misleading, | |
1252 | and they mess up read/write invariance. */ | |
1253 | if (c < 128) | |
1254 | goto invalid_code; | |
4af310db | 1255 | } |
df7492f9 | 1256 | else |
aa72b389 | 1257 | { |
df7492f9 | 1258 | ONE_MORE_BYTE (c3); |
065e3595 | 1259 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1260 | goto invalid_code; |
1261 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1262 | { |
1263 | c = (((c1 & 0xF) << 12) | |
1264 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1265 | if (c < 0x800 |
1266 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1267 | goto invalid_code; |
1268 | } | |
df7492f9 KH |
1269 | else |
1270 | { | |
1271 | ONE_MORE_BYTE (c4); | |
065e3595 | 1272 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1273 | goto invalid_code; |
1274 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1275 | { |
df7492f9 KH |
1276 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1277 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1278 | if (c < 0x10000) |
1279 | goto invalid_code; | |
1280 | } | |
df7492f9 KH |
1281 | else |
1282 | { | |
1283 | ONE_MORE_BYTE (c5); | |
065e3595 | 1284 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1285 | goto invalid_code; |
1286 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1287 | { | |
1288 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1289 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1290 | | (c5 & 0x3F)); | |
b0edb2c5 | 1291 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1292 | goto invalid_code; |
1293 | } | |
1294 | else | |
1295 | goto invalid_code; | |
1296 | } | |
1297 | } | |
aa72b389 | 1298 | } |
b73bfc1c | 1299 | } |
df7492f9 KH |
1300 | |
1301 | *charbuf++ = c; | |
1302 | continue; | |
1303 | ||
1304 | invalid_code: | |
1305 | src = src_base; | |
1306 | consumed_chars = consumed_chars_base; | |
1307 | ONE_MORE_BYTE (c); | |
1308 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1309 | coding->errors++; | |
aa72b389 | 1310 | } |
307f5c57 MB |
1311 | else |
1312 | return 0; | |
aa72b389 | 1313 | |
df7492f9 KH |
1314 | no_more_source: |
1315 | coding->consumed_char += consumed_chars_base; | |
1316 | coding->consumed = src_base - coding->source; | |
1317 | coding->charbuf_used = charbuf - coding->charbuf; | |
1318 | } | |
1319 | ||
1320 | ||
1321 | static int | |
1322 | encode_coding_utf_8 (coding) | |
1323 | struct coding_system *coding; | |
1324 | { | |
1325 | int multibytep = coding->dst_multibyte; | |
1326 | int *charbuf = coding->charbuf; | |
1327 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1328 | unsigned char *dst = coding->destination + coding->produced; | |
1329 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
e19c3639 | 1330 | int produced_chars = 0; |
df7492f9 KH |
1331 | int c; |
1332 | ||
1333 | if (multibytep) | |
aa72b389 | 1334 | { |
df7492f9 KH |
1335 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1336 | ||
1337 | while (charbuf < charbuf_end) | |
b73bfc1c | 1338 | { |
df7492f9 | 1339 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1340 | |
df7492f9 KH |
1341 | ASSURE_DESTINATION (safe_room); |
1342 | c = *charbuf++; | |
28f67a95 KH |
1343 | if (CHAR_BYTE8_P (c)) |
1344 | { | |
1345 | c = CHAR_TO_BYTE8 (c); | |
1346 | EMIT_ONE_BYTE (c); | |
1347 | } | |
1348 | else | |
1349 | { | |
1350 | CHAR_STRING_ADVANCE (c, pend); | |
1351 | for (p = str; p < pend; p++) | |
1352 | EMIT_ONE_BYTE (*p); | |
1353 | } | |
b73bfc1c | 1354 | } |
aa72b389 | 1355 | } |
df7492f9 KH |
1356 | else |
1357 | { | |
1358 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1359 | ||
1360 | while (charbuf < charbuf_end) | |
b73bfc1c | 1361 | { |
df7492f9 KH |
1362 | ASSURE_DESTINATION (safe_room); |
1363 | c = *charbuf++; | |
f03caae0 KH |
1364 | if (CHAR_BYTE8_P (c)) |
1365 | *dst++ = CHAR_TO_BYTE8 (c); | |
1366 | else | |
1367 | dst += CHAR_STRING (c, dst); | |
df7492f9 | 1368 | produced_chars++; |
4ed46869 KH |
1369 | } |
1370 | } | |
065e3595 | 1371 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1372 | coding->produced_char += produced_chars; |
1373 | coding->produced = dst - coding->destination; | |
1374 | return 0; | |
4ed46869 KH |
1375 | } |
1376 | ||
b73bfc1c | 1377 | |
df7492f9 | 1378 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
1379 | Check if a text is encoded in one of UTF-16 based coding systems. |
1380 | If it is, return 1, else return 0. */ | |
aa72b389 | 1381 | |
df7492f9 KH |
1382 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1383 | (((val) & 0xFC00) == 0xD800) | |
1384 | ||
1385 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1386 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1387 | |
df7492f9 KH |
1388 | #define UTF_16_INVALID_P(val) \ |
1389 | (((val) == 0xFFFE) \ | |
1390 | || ((val) == 0xFFFF) \ | |
1391 | || UTF_16_LOW_SURROGATE_P (val)) | |
aa72b389 | 1392 | |
aa72b389 | 1393 | |
df7492f9 | 1394 | static int |
ff0dacd7 | 1395 | detect_coding_utf_16 (coding, detect_info) |
aa72b389 | 1396 | struct coding_system *coding; |
ff0dacd7 | 1397 | struct coding_detection_info *detect_info; |
aa72b389 | 1398 | { |
8f924df7 KH |
1399 | const unsigned char *src = coding->source, *src_base = src; |
1400 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
1401 | int multibytep = coding->src_multibyte; |
1402 | int consumed_chars = 0; | |
1403 | int c1, c2; | |
aa72b389 | 1404 | |
ff0dacd7 | 1405 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1406 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1407 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1408 | { |
1409 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1410 | return 0; | |
1411 | } | |
24a73b0a | 1412 | |
df7492f9 KH |
1413 | ONE_MORE_BYTE (c1); |
1414 | ONE_MORE_BYTE (c2); | |
df7492f9 | 1415 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1416 | { |
b49a1807 KH |
1417 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1418 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1419 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1420 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1421 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1422 | } |
df7492f9 | 1423 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1424 | { |
b49a1807 KH |
1425 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1426 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1427 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1428 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1429 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1430 | } | |
065e3595 | 1431 | else if (c1 >= 0 && c2 >= 0) |
24a73b0a | 1432 | { |
24a73b0a KH |
1433 | detect_info->rejected |
1434 | |= (CATEGORY_MASK_UTF_16_BE | CATEGORY_MASK_UTF_16_LE); | |
ff0dacd7 | 1435 | } |
df7492f9 | 1436 | no_more_source: |
ff0dacd7 | 1437 | return 1; |
df7492f9 | 1438 | } |
aa72b389 | 1439 | |
df7492f9 KH |
1440 | static void |
1441 | decode_coding_utf_16 (coding) | |
1442 | struct coding_system *coding; | |
1443 | { | |
8f924df7 KH |
1444 | const unsigned char *src = coding->source + coding->consumed; |
1445 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1446 | const unsigned char *src_base; | |
69a80ea3 KH |
1447 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1448 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
1449 | int consumed_chars = 0, consumed_chars_base; |
1450 | int multibytep = coding->src_multibyte; | |
1451 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1452 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); | |
1453 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
24a73b0a | 1454 | Lisp_Object attr, charset_list; |
df7492f9 | 1455 | |
24a73b0a | 1456 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1457 | |
b49a1807 | 1458 | if (bom == utf_16_with_bom) |
aa72b389 | 1459 | { |
df7492f9 | 1460 | int c, c1, c2; |
4af310db | 1461 | |
aa72b389 | 1462 | src_base = src; |
df7492f9 KH |
1463 | ONE_MORE_BYTE (c1); |
1464 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1465 | c = (c1 << 8) | c2; |
aa72b389 | 1466 | |
b49a1807 KH |
1467 | if (endian == utf_16_big_endian |
1468 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1469 | { |
b49a1807 KH |
1470 | /* The first two bytes are not BOM. Treat them as bytes |
1471 | for a normal character. */ | |
1472 | src = src_base; | |
1473 | coding->errors++; | |
aa72b389 | 1474 | } |
b49a1807 KH |
1475 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1476 | } | |
1477 | else if (bom == utf_16_detect_bom) | |
1478 | { | |
1479 | /* We have already tried to detect BOM and failed in | |
1480 | detect_coding. */ | |
1481 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; | |
df7492f9 | 1482 | } |
aa72b389 | 1483 | |
df7492f9 KH |
1484 | while (1) |
1485 | { | |
1486 | int c, c1, c2; | |
1487 | ||
1488 | src_base = src; | |
1489 | consumed_chars_base = consumed_chars; | |
1490 | ||
1491 | if (charbuf + 2 >= charbuf_end) | |
1492 | break; | |
1493 | ||
1494 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1495 | if (c1 < 0) |
1496 | { | |
1497 | *charbuf++ = -c1; | |
1498 | continue; | |
1499 | } | |
df7492f9 | 1500 | ONE_MORE_BYTE (c2); |
065e3595 KH |
1501 | if (c2 < 0) |
1502 | { | |
1503 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1504 | *charbuf++ = -c2; | |
1505 | continue; | |
1506 | } | |
df7492f9 | 1507 | c = (endian == utf_16_big_endian |
e19c3639 | 1508 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
df7492f9 | 1509 | if (surrogate) |
fd3ae0b9 | 1510 | { |
df7492f9 | 1511 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1512 | { |
df7492f9 KH |
1513 | if (endian == utf_16_big_endian) |
1514 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1515 | else | |
1516 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1517 | *charbuf++ = c1; | |
1518 | *charbuf++ = c2; | |
1519 | coding->errors++; | |
1520 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1521 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1522 | else |
df7492f9 | 1523 | *charbuf++ = c; |
fd3ae0b9 KH |
1524 | } |
1525 | else | |
df7492f9 KH |
1526 | { |
1527 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1528 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1529 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1530 | } |
fd3ae0b9 | 1531 | } |
aa72b389 | 1532 | else |
df7492f9 KH |
1533 | { |
1534 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1535 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1536 | else | |
1537 | *charbuf++ = c; | |
8f924df7 | 1538 | } |
aa72b389 | 1539 | } |
df7492f9 KH |
1540 | |
1541 | no_more_source: | |
1542 | coding->consumed_char += consumed_chars_base; | |
1543 | coding->consumed = src_base - coding->source; | |
1544 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1545 | } |
b73bfc1c | 1546 | |
df7492f9 KH |
1547 | static int |
1548 | encode_coding_utf_16 (coding) | |
1549 | struct coding_system *coding; | |
1550 | { | |
1551 | int multibytep = coding->dst_multibyte; | |
1552 | int *charbuf = coding->charbuf; | |
1553 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1554 | unsigned char *dst = coding->destination + coding->produced; | |
1555 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1556 | int safe_room = 8; | |
1557 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1558 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; | |
1559 | int produced_chars = 0; | |
24a73b0a | 1560 | Lisp_Object attrs, charset_list; |
df7492f9 | 1561 | int c; |
4ed46869 | 1562 | |
24a73b0a | 1563 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 1564 | |
b49a1807 | 1565 | if (bom != utf_16_without_bom) |
df7492f9 KH |
1566 | { |
1567 | ASSURE_DESTINATION (safe_room); | |
1568 | if (big_endian) | |
df7492f9 | 1569 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1570 | else |
1571 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
df7492f9 KH |
1572 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1573 | } | |
1574 | ||
1575 | while (charbuf < charbuf_end) | |
1576 | { | |
1577 | ASSURE_DESTINATION (safe_room); | |
1578 | c = *charbuf++; | |
e19c3639 KH |
1579 | if (c >= MAX_UNICODE_CHAR) |
1580 | c = coding->default_char; | |
df7492f9 KH |
1581 | |
1582 | if (c < 0x10000) | |
1583 | { | |
1584 | if (big_endian) | |
1585 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1586 | else | |
1587 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1588 | } | |
1589 | else | |
1590 | { | |
1591 | int c1, c2; | |
1592 | ||
1593 | c -= 0x10000; | |
1594 | c1 = (c >> 10) + 0xD800; | |
1595 | c2 = (c & 0x3FF) + 0xDC00; | |
1596 | if (big_endian) | |
1597 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1598 | else | |
1599 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1600 | } | |
1601 | } | |
065e3595 | 1602 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1603 | coding->produced = dst - coding->destination; |
1604 | coding->produced_char += produced_chars; | |
1605 | return 0; | |
1606 | } | |
1607 | ||
1608 | \f | |
1609 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1610 | ||
1611 | /* Emacs' internal format for representation of multiple character | |
1612 | sets is a kind of multi-byte encoding, i.e. characters are | |
1613 | represented by variable-length sequences of one-byte codes. | |
1614 | ||
1615 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1616 | represented by one-byte sequences which are their ASCII codes, in | |
1617 | the range 0x00 through 0x7F. | |
1618 | ||
1619 | 8-bit characters of the range 0x80..0x9F are represented by | |
1620 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1621 | code + 0x20). | |
1622 | ||
1623 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1624 | one-byte sequences which are their 8-bit code. | |
1625 | ||
1626 | The other characters are represented by a sequence of `base | |
1627 | leading-code', optional `extended leading-code', and one or two | |
1628 | `position-code's. The length of the sequence is determined by the | |
1629 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1630 | whereas extended leading-code and position-code take the range 0xA0 | |
1631 | through 0xFF. See `charset.h' for more details about leading-code | |
1632 | and position-code. | |
1633 | ||
1634 | --- CODE RANGE of Emacs' internal format --- | |
1635 | character set range | |
1636 | ------------- ----- | |
1637 | ascii 0x00..0x7F | |
1638 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1639 | eight-bit-graphic 0xA0..0xBF | |
1640 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1641 | --------------------------------------------- | |
1642 | ||
1643 | As this is the internal character representation, the format is | |
1644 | usually not used externally (i.e. in a file or in a data sent to a | |
1645 | process). But, it is possible to have a text externally in this | |
1646 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1647 | ||
1648 | In that case, a sequence of one-byte codes has a slightly different | |
1649 | form. | |
1650 | ||
1651 | At first, all characters in eight-bit-control are represented by | |
1652 | one-byte sequences which are their 8-bit code. | |
1653 | ||
1654 | Next, character composition data are represented by the byte | |
1655 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1656 | where, | |
1657 | METHOD is 0xF0 plus one of composition method (enum | |
1658 | composition_method), | |
1659 | ||
1660 | BYTES is 0xA0 plus a byte length of this composition data, | |
1661 | ||
1662 | CHARS is 0x20 plus a number of characters composed by this | |
1663 | data, | |
1664 | ||
1665 | COMPONENTs are characters of multibye form or composition | |
1666 | rules encoded by two-byte of ASCII codes. | |
1667 | ||
1668 | In addition, for backward compatibility, the following formats are | |
1669 | also recognized as composition data on decoding. | |
1670 | ||
1671 | 0x80 MSEQ ... | |
1672 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1673 | ||
1674 | Here, | |
1675 | MSEQ is a multibyte form but in these special format: | |
1676 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1677 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1678 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1679 | represents a composition rule. | |
1680 | */ | |
1681 | ||
1682 | char emacs_mule_bytes[256]; | |
1683 | ||
df7492f9 | 1684 | int |
ff0dacd7 | 1685 | emacs_mule_char (coding, src, nbytes, nchars, id) |
df7492f9 | 1686 | struct coding_system *coding; |
065e3595 | 1687 | const unsigned char *src; |
ff0dacd7 | 1688 | int *nbytes, *nchars, *id; |
df7492f9 | 1689 | { |
8f924df7 KH |
1690 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1691 | const unsigned char *src_base = src; | |
df7492f9 | 1692 | int multibytep = coding->src_multibyte; |
df7492f9 KH |
1693 | struct charset *charset; |
1694 | unsigned code; | |
1695 | int c; | |
1696 | int consumed_chars = 0; | |
1697 | ||
1698 | ONE_MORE_BYTE (c); | |
065e3595 | 1699 | if (c < 0) |
df7492f9 | 1700 | { |
065e3595 KH |
1701 | c = -c; |
1702 | charset = emacs_mule_charset[0]; | |
1703 | } | |
1704 | else | |
1705 | { | |
1706 | switch (emacs_mule_bytes[c]) | |
b73bfc1c | 1707 | { |
065e3595 | 1708 | case 2: |
df7492f9 KH |
1709 | if (! (charset = emacs_mule_charset[c])) |
1710 | goto invalid_code; | |
1711 | ONE_MORE_BYTE (c); | |
9ffd559c | 1712 | if (c < 0xA0) |
065e3595 | 1713 | goto invalid_code; |
df7492f9 | 1714 | code = c & 0x7F; |
065e3595 KH |
1715 | break; |
1716 | ||
1717 | case 3: | |
1718 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
1719 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
1720 | { | |
1721 | ONE_MORE_BYTE (c); | |
9ffd559c | 1722 | if (c < 0xA0 || ! (charset = emacs_mule_charset[c])) |
065e3595 KH |
1723 | goto invalid_code; |
1724 | ONE_MORE_BYTE (c); | |
9ffd559c | 1725 | if (c < 0xA0) |
065e3595 KH |
1726 | goto invalid_code; |
1727 | code = c & 0x7F; | |
1728 | } | |
1729 | else | |
1730 | { | |
1731 | if (! (charset = emacs_mule_charset[c])) | |
1732 | goto invalid_code; | |
1733 | ONE_MORE_BYTE (c); | |
9ffd559c | 1734 | if (c < 0xA0) |
065e3595 KH |
1735 | goto invalid_code; |
1736 | code = (c & 0x7F) << 8; | |
1737 | ONE_MORE_BYTE (c); | |
9ffd559c | 1738 | if (c < 0xA0) |
065e3595 KH |
1739 | goto invalid_code; |
1740 | code |= c & 0x7F; | |
1741 | } | |
1742 | break; | |
1743 | ||
1744 | case 4: | |
1745 | ONE_MORE_BYTE (c); | |
1746 | if (c < 0 || ! (charset = emacs_mule_charset[c])) | |
df7492f9 KH |
1747 | goto invalid_code; |
1748 | ONE_MORE_BYTE (c); | |
9ffd559c | 1749 | if (c < 0xA0) |
065e3595 | 1750 | goto invalid_code; |
781d7a48 | 1751 | code = (c & 0x7F) << 8; |
df7492f9 | 1752 | ONE_MORE_BYTE (c); |
9ffd559c | 1753 | if (c < 0xA0) |
065e3595 | 1754 | goto invalid_code; |
df7492f9 | 1755 | code |= c & 0x7F; |
065e3595 | 1756 | break; |
df7492f9 | 1757 | |
065e3595 KH |
1758 | case 1: |
1759 | code = c; | |
1760 | charset = CHARSET_FROM_ID (ASCII_BYTE_P (code) | |
1761 | ? charset_ascii : charset_eight_bit); | |
1762 | break; | |
df7492f9 | 1763 | |
065e3595 KH |
1764 | default: |
1765 | abort (); | |
1766 | } | |
1767 | c = DECODE_CHAR (charset, code); | |
1768 | if (c < 0) | |
1769 | goto invalid_code; | |
df7492f9 | 1770 | } |
df7492f9 KH |
1771 | *nbytes = src - src_base; |
1772 | *nchars = consumed_chars; | |
ff0dacd7 KH |
1773 | if (id) |
1774 | *id = charset->id; | |
df7492f9 KH |
1775 | return c; |
1776 | ||
1777 | no_more_source: | |
1778 | return -2; | |
1779 | ||
1780 | invalid_code: | |
1781 | return -1; | |
1782 | } | |
1783 | ||
1784 | ||
1785 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1786 | Check if a text is encoded in `emacs-mule'. If it is, return 1, |
1787 | else return 0. */ | |
df7492f9 KH |
1788 | |
1789 | static int | |
ff0dacd7 | 1790 | detect_coding_emacs_mule (coding, detect_info) |
df7492f9 | 1791 | struct coding_system *coding; |
ff0dacd7 | 1792 | struct coding_detection_info *detect_info; |
df7492f9 | 1793 | { |
065e3595 | 1794 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1795 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1796 | int multibytep = coding->src_multibyte; |
1797 | int consumed_chars = 0; | |
1798 | int c; | |
1799 | int found = 0; | |
1800 | ||
ff0dacd7 | 1801 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1802 | /* A coding system of this category is always ASCII compatible. */ |
1803 | src += coding->head_ascii; | |
1804 | ||
1805 | while (1) | |
1806 | { | |
065e3595 | 1807 | src_base = src; |
df7492f9 | 1808 | ONE_MORE_BYTE (c); |
065e3595 KH |
1809 | if (c < 0) |
1810 | continue; | |
df7492f9 KH |
1811 | if (c == 0x80) |
1812 | { | |
1813 | /* Perhaps the start of composite character. We simple skip | |
1814 | it because analyzing it is too heavy for detecting. But, | |
1815 | at least, we check that the composite character | |
1816 | constitues of more than 4 bytes. */ | |
8f924df7 | 1817 | const unsigned char *src_base; |
df7492f9 KH |
1818 | |
1819 | repeat: | |
1820 | src_base = src; | |
1821 | do | |
1822 | { | |
1823 | ONE_MORE_BYTE (c); | |
1824 | } | |
1825 | while (c >= 0xA0); | |
1826 | ||
1827 | if (src - src_base <= 4) | |
1828 | break; | |
ff0dacd7 | 1829 | found = CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1830 | if (c == 0x80) |
1831 | goto repeat; | |
b73bfc1c | 1832 | } |
df7492f9 KH |
1833 | |
1834 | if (c < 0x80) | |
b73bfc1c | 1835 | { |
df7492f9 KH |
1836 | if (c < 0x20 |
1837 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1838 | break; | |
1839 | } | |
1840 | else | |
1841 | { | |
0e219d54 | 1842 | int more_bytes = emacs_mule_bytes[*src_base] - 1; |
df7492f9 | 1843 | |
0e219d54 | 1844 | while (more_bytes > 0) |
df7492f9 KH |
1845 | { |
1846 | ONE_MORE_BYTE (c); | |
0e219d54 KH |
1847 | if (c < 0xA0) |
1848 | { | |
1849 | src--; /* Unread the last byte. */ | |
1850 | break; | |
1851 | } | |
1852 | more_bytes--; | |
df7492f9 | 1853 | } |
0e219d54 | 1854 | if (more_bytes != 0) |
df7492f9 | 1855 | break; |
ff0dacd7 | 1856 | found = CATEGORY_MASK_EMACS_MULE; |
4ed46869 KH |
1857 | } |
1858 | } | |
ff0dacd7 | 1859 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1860 | return 0; |
1861 | ||
1862 | no_more_source: | |
065e3595 | 1863 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 1864 | { |
ff0dacd7 | 1865 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
89528eb3 KH |
1866 | return 0; |
1867 | } | |
ff0dacd7 KH |
1868 | detect_info->found |= found; |
1869 | return 1; | |
4ed46869 KH |
1870 | } |
1871 | ||
b73bfc1c | 1872 | |
df7492f9 KH |
1873 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
1874 | ||
1875 | /* Decode a character represented as a component of composition | |
1876 | sequence of Emacs 20/21 style at SRC. Set C to that character and | |
1877 | update SRC to the head of next character (or an encoded composition | |
1878 | rule). If SRC doesn't points a composition component, set C to -1. | |
1879 | If SRC points an invalid byte sequence, global exit by a return | |
1880 | value 0. */ | |
1881 | ||
1882 | #define DECODE_EMACS_MULE_COMPOSITION_CHAR(buf) \ | |
1883 | if (1) \ | |
1884 | { \ | |
1885 | int c; \ | |
1886 | int nbytes, nchars; \ | |
1887 | \ | |
1888 | if (src == src_end) \ | |
1889 | break; \ | |
ff0dacd7 | 1890 | c = emacs_mule_char (coding, src, &nbytes, &nchars, NULL);\ |
df7492f9 KH |
1891 | if (c < 0) \ |
1892 | { \ | |
1893 | if (c == -2) \ | |
1894 | break; \ | |
1895 | goto invalid_code; \ | |
1896 | } \ | |
1897 | *buf++ = c; \ | |
1898 | src += nbytes; \ | |
1899 | consumed_chars += nchars; \ | |
1900 | } \ | |
1901 | else | |
1902 | ||
1903 | ||
1904 | /* Decode a composition rule represented as a component of composition | |
781d7a48 KH |
1905 | sequence of Emacs 20 style at SRC. Store the decoded rule in *BUF, |
1906 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1907 | to -1. */ | |
df7492f9 | 1908 | |
781d7a48 | 1909 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(buf) \ |
df7492f9 KH |
1910 | do { \ |
1911 | int c, gref, nref; \ | |
1912 | \ | |
781d7a48 | 1913 | if (src >= src_end) \ |
df7492f9 KH |
1914 | goto invalid_code; \ |
1915 | ONE_MORE_BYTE_NO_CHECK (c); \ | |
781d7a48 | 1916 | c -= 0x20; \ |
df7492f9 KH |
1917 | if (c < 0 || c >= 81) \ |
1918 | goto invalid_code; \ | |
1919 | \ | |
1920 | gref = c / 9, nref = c % 9; \ | |
1921 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1922 | } while (0) | |
1923 | ||
1924 | ||
781d7a48 KH |
1925 | /* Decode a composition rule represented as a component of composition |
1926 | sequence of Emacs 21 style at SRC. Store the decoded rule in *BUF, | |
1927 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1928 | to -1. */ | |
1929 | ||
1930 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(buf) \ | |
1931 | do { \ | |
1932 | int gref, nref; \ | |
1933 | \ | |
1934 | if (src + 1>= src_end) \ | |
1935 | goto invalid_code; \ | |
1936 | ONE_MORE_BYTE_NO_CHECK (gref); \ | |
1937 | gref -= 0x20; \ | |
1938 | ONE_MORE_BYTE_NO_CHECK (nref); \ | |
1939 | nref -= 0x20; \ | |
1940 | if (gref < 0 || gref >= 81 \ | |
1941 | || nref < 0 || nref >= 81) \ | |
1942 | goto invalid_code; \ | |
1943 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1944 | } while (0) | |
1945 | ||
1946 | ||
df7492f9 | 1947 | #define DECODE_EMACS_MULE_21_COMPOSITION(c) \ |
aa72b389 | 1948 | do { \ |
df7492f9 | 1949 | /* Emacs 21 style format. The first three bytes at SRC are \ |
781d7a48 | 1950 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is \ |
df7492f9 KH |
1951 | the byte length of this composition information, CHARS is the \ |
1952 | number of characters composed by this composition. */ \ | |
781d7a48 KH |
1953 | enum composition_method method = c - 0xF2; \ |
1954 | int *charbuf_base = charbuf; \ | |
df7492f9 KH |
1955 | int consumed_chars_limit; \ |
1956 | int nbytes, nchars; \ | |
1957 | \ | |
1958 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
1959 | if (c < 0) \ |
1960 | goto invalid_code; \ | |
df7492f9 KH |
1961 | nbytes = c - 0xA0; \ |
1962 | if (nbytes < 3) \ | |
1963 | goto invalid_code; \ | |
1964 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
1965 | if (c < 0) \ |
1966 | goto invalid_code; \ | |
df7492f9 | 1967 | nchars = c - 0xA0; \ |
69a80ea3 | 1968 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ |
df7492f9 KH |
1969 | consumed_chars_limit = consumed_chars_base + nbytes; \ |
1970 | if (method != COMPOSITION_RELATIVE) \ | |
aa72b389 | 1971 | { \ |
df7492f9 KH |
1972 | int i = 0; \ |
1973 | while (consumed_chars < consumed_chars_limit) \ | |
aa72b389 | 1974 | { \ |
df7492f9 | 1975 | if (i % 2 && method != COMPOSITION_WITH_ALTCHARS) \ |
781d7a48 | 1976 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (charbuf); \ |
df7492f9 KH |
1977 | else \ |
1978 | DECODE_EMACS_MULE_COMPOSITION_CHAR (charbuf); \ | |
781d7a48 | 1979 | i++; \ |
aa72b389 | 1980 | } \ |
df7492f9 KH |
1981 | if (consumed_chars < consumed_chars_limit) \ |
1982 | goto invalid_code; \ | |
781d7a48 | 1983 | charbuf_base[0] -= i; \ |
aa72b389 KH |
1984 | } \ |
1985 | } while (0) | |
93dec019 | 1986 | |
aa72b389 | 1987 | |
df7492f9 KH |
1988 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION(c) \ |
1989 | do { \ | |
1990 | /* Emacs 20 style format for relative composition. */ \ | |
1991 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 1992 | enum composition_method method = COMPOSITION_RELATIVE; \ |
df7492f9 KH |
1993 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
1994 | int *buf = components; \ | |
1995 | int i, j; \ | |
1996 | \ | |
1997 | src = src_base; \ | |
1998 | ONE_MORE_BYTE (c); /* skip 0x80 */ \ | |
1999 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
2000 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
2001 | if (i < 2) \ | |
2002 | goto invalid_code; \ | |
69a80ea3 | 2003 | ADD_COMPOSITION_DATA (charbuf, i, method); \ |
df7492f9 KH |
2004 | for (j = 0; j < i; j++) \ |
2005 | *charbuf++ = components[j]; \ | |
2006 | } while (0) | |
2007 | ||
2008 | ||
2009 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION(c) \ | |
2010 | do { \ | |
2011 | /* Emacs 20 style format for rule-base composition. */ \ | |
2012 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 2013 | enum composition_method method = COMPOSITION_WITH_RULE; \ |
df7492f9 KH |
2014 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
2015 | int *buf = components; \ | |
2016 | int i, j; \ | |
2017 | \ | |
2018 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
2019 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
2020 | { \ | |
781d7a48 | 2021 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (buf); \ |
df7492f9 KH |
2022 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ |
2023 | } \ | |
2024 | if (i < 1 || (buf - components) % 2 == 0) \ | |
2025 | goto invalid_code; \ | |
2026 | if (charbuf + i + (i / 2) + 1 < charbuf_end) \ | |
2027 | goto no_more_source; \ | |
69a80ea3 | 2028 | ADD_COMPOSITION_DATA (buf, i, method); \ |
df7492f9 KH |
2029 | for (j = 0; j < i; j++) \ |
2030 | *charbuf++ = components[j]; \ | |
2031 | for (j = 0; j < i; j += 2) \ | |
2032 | *charbuf++ = components[j]; \ | |
2033 | } while (0) | |
2034 | ||
aa72b389 KH |
2035 | |
2036 | static void | |
df7492f9 | 2037 | decode_coding_emacs_mule (coding) |
aa72b389 | 2038 | struct coding_system *coding; |
aa72b389 | 2039 | { |
8f924df7 KH |
2040 | const unsigned char *src = coding->source + coding->consumed; |
2041 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2042 | const unsigned char *src_base; | |
69a80ea3 KH |
2043 | int *charbuf = coding->charbuf + coding->charbuf_used; |
2044 | int *charbuf_end | |
2045 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 | 2046 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2047 | int multibytep = coding->src_multibyte; |
24a73b0a | 2048 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2049 | int char_offset = coding->produced_char; |
2050 | int last_offset = char_offset; | |
2051 | int last_id = charset_ascii; | |
aa72b389 | 2052 | |
24a73b0a | 2053 | CODING_GET_INFO (coding, attrs, charset_list); |
aa72b389 | 2054 | |
aa72b389 KH |
2055 | while (1) |
2056 | { | |
df7492f9 KH |
2057 | int c; |
2058 | ||
aa72b389 | 2059 | src_base = src; |
df7492f9 KH |
2060 | consumed_chars_base = consumed_chars; |
2061 | ||
2062 | if (charbuf >= charbuf_end) | |
2063 | break; | |
aa72b389 | 2064 | |
df7492f9 | 2065 | ONE_MORE_BYTE (c); |
065e3595 KH |
2066 | if (c < 0) |
2067 | { | |
2068 | *charbuf++ = -c; | |
2069 | char_offset++; | |
2070 | } | |
2071 | else if (c < 0x80) | |
aa72b389 | 2072 | { |
df7492f9 KH |
2073 | *charbuf++ = c; |
2074 | char_offset++; | |
aa72b389 | 2075 | } |
df7492f9 KH |
2076 | else if (c == 0x80) |
2077 | { | |
df7492f9 | 2078 | ONE_MORE_BYTE (c); |
065e3595 KH |
2079 | if (c < 0) |
2080 | goto invalid_code; | |
781d7a48 KH |
2081 | if (c - 0xF2 >= COMPOSITION_RELATIVE |
2082 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) | |
df7492f9 KH |
2083 | DECODE_EMACS_MULE_21_COMPOSITION (c); |
2084 | else if (c < 0xC0) | |
2085 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (c); | |
2086 | else if (c == 0xFF) | |
2087 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (c); | |
2088 | else | |
2089 | goto invalid_code; | |
2090 | } | |
2091 | else if (c < 0xA0 && emacs_mule_bytes[c] > 1) | |
2092 | { | |
2093 | int nbytes, nchars; | |
ff0dacd7 KH |
2094 | int id; |
2095 | ||
781d7a48 KH |
2096 | src = src_base; |
2097 | consumed_chars = consumed_chars_base; | |
ff0dacd7 | 2098 | c = emacs_mule_char (coding, src, &nbytes, &nchars, &id); |
df7492f9 KH |
2099 | if (c < 0) |
2100 | { | |
2101 | if (c == -2) | |
2102 | break; | |
2103 | goto invalid_code; | |
2104 | } | |
ff0dacd7 KH |
2105 | if (last_id != id) |
2106 | { | |
2107 | if (last_id != charset_ascii) | |
69a80ea3 | 2108 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
2109 | last_id = id; |
2110 | last_offset = char_offset; | |
2111 | } | |
df7492f9 | 2112 | *charbuf++ = c; |
781d7a48 KH |
2113 | src += nbytes; |
2114 | consumed_chars += nchars; | |
df7492f9 KH |
2115 | char_offset++; |
2116 | } | |
2117 | continue; | |
2118 | ||
2119 | invalid_code: | |
2120 | src = src_base; | |
2121 | consumed_chars = consumed_chars_base; | |
2122 | ONE_MORE_BYTE (c); | |
2123 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2124 | char_offset++; |
df7492f9 KH |
2125 | coding->errors++; |
2126 | } | |
2127 | ||
2128 | no_more_source: | |
ff0dacd7 | 2129 | if (last_id != charset_ascii) |
69a80ea3 | 2130 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2131 | coding->consumed_char += consumed_chars_base; |
2132 | coding->consumed = src_base - coding->source; | |
2133 | coding->charbuf_used = charbuf - coding->charbuf; | |
2134 | } | |
2135 | ||
2136 | ||
2137 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2138 | do { \ | |
2139 | if (id < 0xA0) \ | |
2140 | codes[0] = id, codes[1] = 0; \ | |
2141 | else if (id < 0xE0) \ | |
2142 | codes[0] = 0x9A, codes[1] = id; \ | |
2143 | else if (id < 0xF0) \ | |
2144 | codes[0] = 0x9B, codes[1] = id; \ | |
2145 | else if (id < 0xF5) \ | |
2146 | codes[0] = 0x9C, codes[1] = id; \ | |
2147 | else \ | |
2148 | codes[0] = 0x9D, codes[1] = id; \ | |
2149 | } while (0); | |
2150 | ||
aa72b389 | 2151 | |
df7492f9 KH |
2152 | static int |
2153 | encode_coding_emacs_mule (coding) | |
2154 | struct coding_system *coding; | |
2155 | { | |
2156 | int multibytep = coding->dst_multibyte; | |
2157 | int *charbuf = coding->charbuf; | |
2158 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2159 | unsigned char *dst = coding->destination + coding->produced; | |
2160 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2161 | int safe_room = 8; | |
df7492f9 | 2162 | int produced_chars = 0; |
24a73b0a | 2163 | Lisp_Object attrs, charset_list; |
df7492f9 | 2164 | int c; |
ff0dacd7 | 2165 | int preferred_charset_id = -1; |
df7492f9 | 2166 | |
24a73b0a | 2167 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2168 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2169 | { | |
2170 | CODING_ATTR_CHARSET_LIST (attrs) | |
2171 | = charset_list = Vemacs_mule_charset_list; | |
2172 | } | |
df7492f9 KH |
2173 | |
2174 | while (charbuf < charbuf_end) | |
2175 | { | |
2176 | ASSURE_DESTINATION (safe_room); | |
2177 | c = *charbuf++; | |
ff0dacd7 KH |
2178 | |
2179 | if (c < 0) | |
2180 | { | |
2181 | /* Handle an annotation. */ | |
2182 | switch (*charbuf) | |
2183 | { | |
2184 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2185 | /* Not yet implemented. */ | |
2186 | break; | |
2187 | case CODING_ANNOTATE_CHARSET_MASK: | |
2188 | preferred_charset_id = charbuf[3]; | |
2189 | if (preferred_charset_id >= 0 | |
2190 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2191 | charset_list))) | |
2192 | preferred_charset_id = -1; | |
2193 | break; | |
2194 | default: | |
2195 | abort (); | |
2196 | } | |
2197 | charbuf += -c - 1; | |
2198 | continue; | |
2199 | } | |
2200 | ||
df7492f9 KH |
2201 | if (ASCII_CHAR_P (c)) |
2202 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2203 | else if (CHAR_BYTE8_P (c)) |
2204 | { | |
2205 | c = CHAR_TO_BYTE8 (c); | |
2206 | EMIT_ONE_BYTE (c); | |
2207 | } | |
df7492f9 | 2208 | else |
aa72b389 | 2209 | { |
df7492f9 KH |
2210 | struct charset *charset; |
2211 | unsigned code; | |
2212 | int dimension; | |
2213 | int emacs_mule_id; | |
2214 | unsigned char leading_codes[2]; | |
2215 | ||
ff0dacd7 KH |
2216 | if (preferred_charset_id >= 0) |
2217 | { | |
2218 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
2219 | if (! CHAR_CHARSET_P (c, charset)) | |
2220 | charset = char_charset (c, charset_list, NULL); | |
2221 | } | |
2222 | else | |
2223 | charset = char_charset (c, charset_list, &code); | |
df7492f9 KH |
2224 | if (! charset) |
2225 | { | |
2226 | c = coding->default_char; | |
2227 | if (ASCII_CHAR_P (c)) | |
2228 | { | |
2229 | EMIT_ONE_ASCII_BYTE (c); | |
2230 | continue; | |
2231 | } | |
2232 | charset = char_charset (c, charset_list, &code); | |
2233 | } | |
2234 | dimension = CHARSET_DIMENSION (charset); | |
2235 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2236 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2237 | EMIT_ONE_BYTE (leading_codes[0]); | |
2238 | if (leading_codes[1]) | |
2239 | EMIT_ONE_BYTE (leading_codes[1]); | |
2240 | if (dimension == 1) | |
1fa663f9 | 2241 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2242 | else |
df7492f9 | 2243 | { |
1fa663f9 | 2244 | code |= 0x8080; |
df7492f9 KH |
2245 | EMIT_ONE_BYTE (code >> 8); |
2246 | EMIT_ONE_BYTE (code & 0xFF); | |
2247 | } | |
aa72b389 | 2248 | } |
aa72b389 | 2249 | } |
065e3595 | 2250 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2251 | coding->produced_char += produced_chars; |
2252 | coding->produced = dst - coding->destination; | |
2253 | return 0; | |
aa72b389 | 2254 | } |
b73bfc1c | 2255 | |
4ed46869 | 2256 | \f |
df7492f9 | 2257 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2258 | |
2259 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2260 | Since the intention of this note is to help understand the |
5a936b46 | 2261 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2262 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2263 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2264 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2265 | |
2266 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2267 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2268 | is encoded using bytes less than 128. This may make the encoded |
2269 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2270 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2271 | Significant Bit). |
b73bfc1c | 2272 | |
cfb43547 DL |
2273 | There are two kinds of character sets: control character sets and |
2274 | graphic character sets. The former contain control characters such | |
4ed46869 | 2275 | as `newline' and `escape' to provide control functions (control |
39787efd | 2276 | functions are also provided by escape sequences). The latter |
cfb43547 | 2277 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2278 | two control character sets and many graphic character sets. |
2279 | ||
2280 | Graphic character sets are classified into one of the following | |
39787efd KH |
2281 | four classes, according to the number of bytes (DIMENSION) and |
2282 | number of characters in one dimension (CHARS) of the set: | |
2283 | - DIMENSION1_CHARS94 | |
2284 | - DIMENSION1_CHARS96 | |
2285 | - DIMENSION2_CHARS94 | |
2286 | - DIMENSION2_CHARS96 | |
2287 | ||
2288 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2289 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2290 | hereafter). The <F> of each character set is decided by ECMA(*) |
2291 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2292 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2293 | |
2294 | Note (*): ECMA = European Computer Manufacturers Association | |
2295 | ||
cfb43547 | 2296 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2297 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2298 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2299 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2300 | o DIMENSION2_CHARS96 -- none for the moment | |
2301 | ||
39787efd | 2302 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2303 | C0 [0x00..0x1F] -- control character plane 0 |
2304 | GL [0x20..0x7F] -- graphic character plane 0 | |
2305 | C1 [0x80..0x9F] -- control character plane 1 | |
2306 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2307 | ||
2308 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2309 | C1 by an escape sequence. The most common case is that: |
2310 | - ISO646's control character set is designated/invoked to C0, and | |
2311 | - ISO6429's control character set is designated/invoked to C1, | |
2312 | and usually these designations/invocations are omitted in encoded | |
2313 | text. In a 7-bit environment, only C0 can be used, and a control | |
2314 | character for C1 is encoded by an appropriate escape sequence to | |
2315 | fit into the environment. All control characters for C1 are | |
2316 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2317 | |
2318 | A graphic character set is at first designated to one of four | |
2319 | graphic registers (G0 through G3), then these graphic registers are | |
2320 | invoked to GL or GR. These designations and invocations can be | |
2321 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2322 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2323 | these invocations and designations are omitted in encoded text. | |
2324 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2325 | |
39787efd KH |
2326 | When a graphic character set of CHARS94 is invoked to GL, codes |
2327 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2328 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2329 | be used. | |
4ed46869 KH |
2330 | |
2331 | There are two ways of invocation: locking-shift and single-shift. | |
2332 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2333 | invocation, whereas with single-shift, the invocation affects the |
2334 | following character only and doesn't affect the locking-shift | |
2335 | state. Invocations are done by the following control characters or | |
2336 | escape sequences: | |
4ed46869 KH |
2337 | |
2338 | ---------------------------------------------------------------------- | |
39787efd | 2339 | abbrev function cntrl escape seq description |
4ed46869 | 2340 | ---------------------------------------------------------------------- |
39787efd KH |
2341 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2342 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2343 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2344 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2345 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2346 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2347 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2348 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2349 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2350 | ---------------------------------------------------------------------- |
39787efd KH |
2351 | (*) These are not used by any known coding system. |
2352 | ||
2353 | Control characters for these functions are defined by macros | |
2354 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2355 | |
39787efd | 2356 | Designations are done by the following escape sequences: |
4ed46869 KH |
2357 | ---------------------------------------------------------------------- |
2358 | escape sequence description | |
2359 | ---------------------------------------------------------------------- | |
2360 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2361 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2362 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2363 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2364 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2365 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2366 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2367 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2368 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2369 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2370 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2371 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2372 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2373 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2374 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2375 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2376 | ---------------------------------------------------------------------- | |
2377 | ||
2378 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2379 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2380 | |
2381 | Note (*): Although these designations are not allowed in ISO2022, | |
2382 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2383 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2384 | 7-bit environment, non-locking-shift, and non-single-shift. |
2385 | ||
2386 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2387 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2388 | |
cfb43547 | 2389 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2390 | same multilingual text in ISO2022. Actually, there exist many |
2391 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2392 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2393 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2394 | localized platforms), and all of these are variants of ISO2022. |
2395 | ||
2396 | In addition to the above, Emacs handles two more kinds of escape | |
2397 | sequences: ISO6429's direction specification and Emacs' private | |
2398 | sequence for specifying character composition. | |
2399 | ||
39787efd | 2400 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2401 | o CSI ']' -- end of the current direction |
2402 | o CSI '0' ']' -- end of the current direction | |
2403 | o CSI '1' ']' -- start of left-to-right text | |
2404 | o CSI '2' ']' -- start of right-to-left text | |
2405 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2406 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2407 | ||
2408 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2409 | o ESC '0' -- start relative composition |
2410 | o ESC '1' -- end composition | |
2411 | o ESC '2' -- start rule-base composition (*) | |
2412 | o ESC '3' -- start relative composition with alternate chars (**) | |
2413 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2414 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2415 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2416 | |
5a936b46 DL |
2417 | (*) This form is used only in Emacs 20.7 and older versions, |
2418 | but newer versions can safely decode it. | |
cfb43547 | 2419 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2420 | and older versions can't decode it. |
ec6d2bb8 | 2421 | |
cfb43547 | 2422 | Here's a list of example usages of these composition escape |
b73bfc1c | 2423 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2424 | |
b73bfc1c | 2425 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2426 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2427 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2428 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2429 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2430 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2431 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2432 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2433 | |
2434 | enum iso_code_class_type iso_code_class[256]; | |
2435 | ||
df7492f9 KH |
2436 | #define SAFE_CHARSET_P(coding, id) \ |
2437 | ((id) <= (coding)->max_charset_id \ | |
2438 | && (coding)->safe_charsets[id] >= 0) | |
2439 | ||
2440 | ||
2441 | #define SHIFT_OUT_OK(category) \ | |
2442 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
2443 | ||
2444 | static void | |
f0064e1f DL |
2445 | setup_iso_safe_charsets (attrs) |
2446 | Lisp_Object attrs; | |
df7492f9 KH |
2447 | { |
2448 | Lisp_Object charset_list, safe_charsets; | |
2449 | Lisp_Object request; | |
2450 | Lisp_Object reg_usage; | |
2451 | Lisp_Object tail; | |
2452 | int reg94, reg96; | |
2453 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
2454 | int max_charset_id; | |
2455 | ||
2456 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2457 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2458 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2459 | { | |
2460 | CODING_ATTR_CHARSET_LIST (attrs) | |
2461 | = charset_list = Viso_2022_charset_list; | |
2462 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
2463 | } | |
2464 | ||
2465 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2466 | return; | |
2467 | ||
2468 | max_charset_id = 0; | |
2469 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2470 | { | |
2471 | int id = XINT (XCAR (tail)); | |
2472 | if (max_charset_id < id) | |
2473 | max_charset_id = id; | |
2474 | } | |
d46c5b12 | 2475 | |
df7492f9 KH |
2476 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
2477 | make_number (255)); | |
2478 | request = AREF (attrs, coding_attr_iso_request); | |
2479 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2480 | reg94 = XINT (XCAR (reg_usage)); | |
2481 | reg96 = XINT (XCDR (reg_usage)); | |
2482 | ||
2483 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2484 | { | |
2485 | Lisp_Object id; | |
2486 | Lisp_Object reg; | |
2487 | struct charset *charset; | |
2488 | ||
2489 | id = XCAR (tail); | |
2490 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2491 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2492 | if (! NILP (reg)) |
8f924df7 | 2493 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2494 | else if (charset->iso_chars_96) |
2495 | { | |
2496 | if (reg96 < 4) | |
8f924df7 | 2497 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2498 | } |
2499 | else | |
2500 | { | |
2501 | if (reg94 < 4) | |
8f924df7 | 2502 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2503 | } |
2504 | } | |
2505 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2506 | } | |
d46c5b12 | 2507 | |
b6871cc7 | 2508 | |
4ed46869 | 2509 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
2510 | Check if a text is encoded in one of ISO-2022 based codig systems. |
2511 | If it is, return 1, else return 0. */ | |
4ed46869 | 2512 | |
0a28aafb | 2513 | static int |
ff0dacd7 | 2514 | detect_coding_iso_2022 (coding, detect_info) |
df7492f9 | 2515 | struct coding_system *coding; |
ff0dacd7 | 2516 | struct coding_detection_info *detect_info; |
4ed46869 | 2517 | { |
8f924df7 KH |
2518 | const unsigned char *src = coding->source, *src_base = src; |
2519 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 2520 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 2521 | int single_shifting = 0; |
df7492f9 KH |
2522 | int id; |
2523 | int c, c1; | |
2524 | int consumed_chars = 0; | |
2525 | int i; | |
ff0dacd7 KH |
2526 | int rejected = 0; |
2527 | int found = 0; | |
2528 | ||
2529 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2530 | |
2531 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2532 | { | |
2533 | struct coding_system *this = &(coding_categories[i]); | |
2534 | Lisp_Object attrs, val; | |
2535 | ||
2536 | attrs = CODING_ID_ATTRS (this->id); | |
2537 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
2538 | && ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs), Viso_2022_charset_list)) | |
2539 | setup_iso_safe_charsets (attrs); | |
2540 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
2541 | this->max_charset_id = SCHARS (val) - 1; |
2542 | this->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
2543 | } |
2544 | ||
2545 | /* A coding system of this category is always ASCII compatible. */ | |
2546 | src += coding->head_ascii; | |
3f003981 | 2547 | |
ff0dacd7 | 2548 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 2549 | { |
065e3595 | 2550 | src_base = src; |
df7492f9 | 2551 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2552 | switch (c) |
2553 | { | |
2554 | case ISO_CODE_ESC: | |
74383408 KH |
2555 | if (inhibit_iso_escape_detection) |
2556 | break; | |
f46869e4 | 2557 | single_shifting = 0; |
df7492f9 | 2558 | ONE_MORE_BYTE (c); |
d46c5b12 | 2559 | if (c >= '(' && c <= '/') |
4ed46869 | 2560 | { |
bf9cdd4e | 2561 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 2562 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2563 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2564 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
2565 | /* Invalid designation sequence. Just ignore. */ |
2566 | break; | |
bf9cdd4e KH |
2567 | } |
2568 | else if (c == '$') | |
2569 | { | |
2570 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 2571 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
2572 | if (c >= '@' && c <= 'B') |
2573 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
ff0dacd7 | 2574 | id = iso_charset_table[1][0][c]; |
bf9cdd4e | 2575 | else if (c >= '(' && c <= '/') |
bcf26d6a | 2576 | { |
df7492f9 | 2577 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2578 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2579 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
2580 | /* Invalid designation sequence. Just ignore. */ |
2581 | break; | |
bcf26d6a | 2582 | } |
bf9cdd4e | 2583 | else |
ff0dacd7 | 2584 | /* Invalid designation sequence. Just ignore it. */ |
d46c5b12 KH |
2585 | break; |
2586 | } | |
ae9ff118 | 2587 | else if (c == 'N' || c == 'O') |
d46c5b12 | 2588 | { |
ae9ff118 | 2589 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
2590 | single_shifting = 1; |
2591 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
d46c5b12 | 2592 | break; |
4ed46869 | 2593 | } |
ec6d2bb8 KH |
2594 | else if (c >= '0' && c <= '4') |
2595 | { | |
2596 | /* ESC <Fp> for start/end composition. */ | |
ff0dacd7 | 2597 | found |= CATEGORY_MASK_ISO; |
ec6d2bb8 KH |
2598 | break; |
2599 | } | |
bf9cdd4e | 2600 | else |
df7492f9 | 2601 | { |
ff0dacd7 | 2602 | /* Invalid escape sequence. Just ignore it. */ |
df7492f9 KH |
2603 | break; |
2604 | } | |
d46c5b12 KH |
2605 | |
2606 | /* We found a valid designation sequence for CHARSET. */ | |
ff0dacd7 | 2607 | rejected |= CATEGORY_MASK_ISO_8BIT; |
df7492f9 KH |
2608 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], |
2609 | id)) | |
ff0dacd7 | 2610 | found |= CATEGORY_MASK_ISO_7; |
d46c5b12 | 2611 | else |
ff0dacd7 | 2612 | rejected |= CATEGORY_MASK_ISO_7; |
df7492f9 KH |
2613 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], |
2614 | id)) | |
ff0dacd7 | 2615 | found |= CATEGORY_MASK_ISO_7_TIGHT; |
d46c5b12 | 2616 | else |
ff0dacd7 | 2617 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; |
df7492f9 KH |
2618 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], |
2619 | id)) | |
ff0dacd7 | 2620 | found |= CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 | 2621 | else |
ff0dacd7 | 2622 | rejected |= CATEGORY_MASK_ISO_7_ELSE; |
df7492f9 KH |
2623 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], |
2624 | id)) | |
ff0dacd7 | 2625 | found |= CATEGORY_MASK_ISO_8_ELSE; |
ae9ff118 | 2626 | else |
ff0dacd7 | 2627 | rejected |= CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
2628 | break; |
2629 | ||
4ed46869 | 2630 | case ISO_CODE_SO: |
d46c5b12 | 2631 | case ISO_CODE_SI: |
ff0dacd7 | 2632 | /* Locking shift out/in. */ |
74383408 KH |
2633 | if (inhibit_iso_escape_detection) |
2634 | break; | |
f46869e4 | 2635 | single_shifting = 0; |
ff0dacd7 KH |
2636 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
2637 | found |= CATEGORY_MASK_ISO_ELSE; | |
d46c5b12 KH |
2638 | break; |
2639 | ||
4ed46869 | 2640 | case ISO_CODE_CSI: |
ff0dacd7 | 2641 | /* Control sequence introducer. */ |
f46869e4 | 2642 | single_shifting = 0; |
ff0dacd7 KH |
2643 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2644 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
2645 | goto check_extra_latin; | |
2646 | ||
4ed46869 KH |
2647 | case ISO_CODE_SS2: |
2648 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
2649 | /* Single shift. */ |
2650 | if (inhibit_iso_escape_detection) | |
2651 | break; | |
75e2a253 | 2652 | single_shifting = 0; |
ff0dacd7 KH |
2653 | rejected |= CATEGORY_MASK_ISO_7BIT; |
2654 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2655 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 | 2656 | found |= CATEGORY_MASK_ISO_8_1, single_shifting = 1; |
ff0dacd7 KH |
2657 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
2658 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 KH |
2659 | found |= CATEGORY_MASK_ISO_8_2, single_shifting = 1; |
2660 | if (single_shifting) | |
2661 | break; | |
ff0dacd7 | 2662 | goto check_extra_latin; |
4ed46869 KH |
2663 | |
2664 | default: | |
065e3595 KH |
2665 | if (c < 0) |
2666 | continue; | |
4ed46869 | 2667 | if (c < 0x80) |
f46869e4 KH |
2668 | { |
2669 | single_shifting = 0; | |
2670 | break; | |
2671 | } | |
ff0dacd7 | 2672 | if (c >= 0xA0) |
c4825358 | 2673 | { |
ff0dacd7 KH |
2674 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2675 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 2676 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
2677 | 0xA0..0FF. If the byte length is even, we include |
2678 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
2679 | only when we are not single shifting. */ | |
2680 | if (! single_shifting | |
2681 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 2682 | { |
e17de821 | 2683 | int i = 1; |
b73bfc1c KH |
2684 | while (src < src_end) |
2685 | { | |
df7492f9 | 2686 | ONE_MORE_BYTE (c); |
b73bfc1c KH |
2687 | if (c < 0xA0) |
2688 | break; | |
2689 | i++; | |
2690 | } | |
2691 | ||
2692 | if (i & 1 && src < src_end) | |
ff0dacd7 | 2693 | rejected |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2694 | else |
ff0dacd7 | 2695 | found |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2696 | } |
ff0dacd7 | 2697 | break; |
4ed46869 | 2698 | } |
ff0dacd7 KH |
2699 | check_extra_latin: |
2700 | single_shifting = 0; | |
2701 | if (! VECTORP (Vlatin_extra_code_table) | |
2702 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
2703 | { | |
2704 | rejected = CATEGORY_MASK_ISO; | |
2705 | break; | |
2706 | } | |
2707 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2708 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2709 | found |= CATEGORY_MASK_ISO_8_1; | |
2710 | else | |
2711 | rejected |= CATEGORY_MASK_ISO_8_1; | |
75e2a253 | 2712 | rejected |= CATEGORY_MASK_ISO_8_2; |
4ed46869 KH |
2713 | } |
2714 | } | |
ff0dacd7 KH |
2715 | detect_info->rejected |= CATEGORY_MASK_ISO; |
2716 | return 0; | |
4ed46869 | 2717 | |
df7492f9 | 2718 | no_more_source: |
ff0dacd7 KH |
2719 | detect_info->rejected |= rejected; |
2720 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 2721 | return 1; |
4ed46869 | 2722 | } |
ec6d2bb8 | 2723 | |
4ed46869 | 2724 | |
134b9549 KH |
2725 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
2726 | escape sequence should be kept. */ | |
df7492f9 KH |
2727 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
2728 | do { \ | |
2729 | int id, prev; \ | |
2730 | \ | |
2731 | if (final < '0' || final >= 128 \ | |
2732 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
2733 | || !SAFE_CHARSET_P (coding, id)) \ | |
2734 | { \ | |
2735 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
2736 | chars_96 = -1; \ |
2737 | break; \ | |
df7492f9 KH |
2738 | } \ |
2739 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
2740 | if (id == charset_jisx0201_roman) \ |
2741 | { \ | |
2742 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
2743 | id = charset_ascii; \ | |
2744 | } \ | |
2745 | else if (id == charset_jisx0208_1978) \ | |
2746 | { \ | |
2747 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
2748 | id = charset_jisx0208; \ | |
2749 | } \ | |
df7492f9 KH |
2750 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
2751 | /* If there was an invalid designation to REG previously, and this \ | |
2752 | designation is ASCII to REG, we should keep this designation \ | |
2753 | sequence. */ \ | |
2754 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 2755 | chars_96 = -1; \ |
4ed46869 KH |
2756 | } while (0) |
2757 | ||
d46c5b12 | 2758 | |
df7492f9 KH |
2759 | #define MAYBE_FINISH_COMPOSITION() \ |
2760 | do { \ | |
2761 | int i; \ | |
2762 | if (composition_state == COMPOSING_NO) \ | |
2763 | break; \ | |
2764 | /* It is assured that we have enough room for producing \ | |
2765 | characters stored in the table `components'. */ \ | |
2766 | if (charbuf + component_idx > charbuf_end) \ | |
2767 | goto no_more_source; \ | |
2768 | composition_state = COMPOSING_NO; \ | |
2769 | if (method == COMPOSITION_RELATIVE \ | |
2770 | || method == COMPOSITION_WITH_ALTCHARS) \ | |
2771 | { \ | |
2772 | for (i = 0; i < component_idx; i++) \ | |
2773 | *charbuf++ = components[i]; \ | |
2774 | char_offset += component_idx; \ | |
2775 | } \ | |
2776 | else \ | |
2777 | { \ | |
2778 | for (i = 0; i < component_idx; i += 2) \ | |
2779 | *charbuf++ = components[i]; \ | |
2780 | char_offset += (component_idx / 2) + 1; \ | |
2781 | } \ | |
2782 | } while (0) | |
2783 | ||
d46c5b12 | 2784 | |
aa72b389 KH |
2785 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
2786 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 | |
2787 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
2788 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
2789 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
aa72b389 | 2790 | */ |
ec6d2bb8 | 2791 | |
df7492f9 KH |
2792 | #define DECODE_COMPOSITION_START(c1) \ |
2793 | do { \ | |
2794 | if (c1 == '0' \ | |
781d7a48 | 2795 | && composition_state == COMPOSING_COMPONENT_RULE) \ |
df7492f9 KH |
2796 | { \ |
2797 | component_len = component_idx; \ | |
2798 | composition_state = COMPOSING_CHAR; \ | |
2799 | } \ | |
2800 | else \ | |
2801 | { \ | |
8f924df7 | 2802 | const unsigned char *p; \ |
df7492f9 KH |
2803 | \ |
2804 | MAYBE_FINISH_COMPOSITION (); \ | |
2805 | if (charbuf + MAX_COMPOSITION_COMPONENTS > charbuf_end) \ | |
2806 | goto no_more_source; \ | |
2807 | for (p = src; p < src_end - 1; p++) \ | |
2808 | if (*p == ISO_CODE_ESC && p[1] == '1') \ | |
2809 | break; \ | |
2810 | if (p == src_end - 1) \ | |
2811 | { \ | |
2812 | if (coding->mode & CODING_MODE_LAST_BLOCK) \ | |
2813 | goto invalid_code; \ | |
2814 | goto no_more_source; \ | |
2815 | } \ | |
2816 | \ | |
2817 | /* This is surely the start of a composition. */ \ | |
2818 | method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
2819 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
2820 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
2821 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
2822 | composition_state = (c1 <= '2' ? COMPOSING_CHAR \ | |
2823 | : COMPOSING_COMPONENT_CHAR); \ | |
2824 | component_idx = component_len = 0; \ | |
2825 | } \ | |
ec6d2bb8 KH |
2826 | } while (0) |
2827 | ||
ec6d2bb8 | 2828 | |
df7492f9 KH |
2829 | /* Handle compositoin end sequence ESC 1. */ |
2830 | ||
2831 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 2832 | do { \ |
df7492f9 KH |
2833 | int nchars = (component_len > 0 ? component_idx - component_len \ |
2834 | : method == COMPOSITION_RELATIVE ? component_idx \ | |
2835 | : (component_idx + 1) / 2); \ | |
2836 | int i; \ | |
2837 | int *saved_charbuf = charbuf; \ | |
2838 | \ | |
69a80ea3 | 2839 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ |
df7492f9 | 2840 | if (method != COMPOSITION_RELATIVE) \ |
ec6d2bb8 | 2841 | { \ |
df7492f9 KH |
2842 | if (component_len == 0) \ |
2843 | for (i = 0; i < component_idx; i++) \ | |
2844 | *charbuf++ = components[i]; \ | |
2845 | else \ | |
2846 | for (i = 0; i < component_len; i++) \ | |
2847 | *charbuf++ = components[i]; \ | |
2848 | *saved_charbuf = saved_charbuf - charbuf; \ | |
ec6d2bb8 | 2849 | } \ |
df7492f9 KH |
2850 | if (method == COMPOSITION_WITH_RULE) \ |
2851 | for (i = 0; i < component_idx; i += 2, char_offset++) \ | |
2852 | *charbuf++ = components[i]; \ | |
ec6d2bb8 | 2853 | else \ |
df7492f9 KH |
2854 | for (i = component_len; i < component_idx; i++, char_offset++) \ |
2855 | *charbuf++ = components[i]; \ | |
2856 | coding->annotated = 1; \ | |
2857 | composition_state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
2858 | } while (0) |
2859 | ||
df7492f9 | 2860 | |
ec6d2bb8 KH |
2861 | /* Decode a composition rule from the byte C1 (and maybe one more byte |
2862 | from SRC) and store one encoded composition rule in | |
2863 | coding->cmp_data. */ | |
2864 | ||
2865 | #define DECODE_COMPOSITION_RULE(c1) \ | |
2866 | do { \ | |
ec6d2bb8 KH |
2867 | (c1) -= 32; \ |
2868 | if (c1 < 81) /* old format (before ver.21) */ \ | |
2869 | { \ | |
2870 | int gref = (c1) / 9; \ | |
2871 | int nref = (c1) % 9; \ | |
2872 | if (gref == 4) gref = 10; \ | |
2873 | if (nref == 4) nref = 10; \ | |
df7492f9 | 2874 | c1 = COMPOSITION_ENCODE_RULE (gref, nref); \ |
ec6d2bb8 | 2875 | } \ |
b73bfc1c | 2876 | else if (c1 < 93) /* new format (after ver.21) */ \ |
ec6d2bb8 KH |
2877 | { \ |
2878 | ONE_MORE_BYTE (c2); \ | |
df7492f9 | 2879 | c1 = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \ |
ec6d2bb8 | 2880 | } \ |
df7492f9 KH |
2881 | else \ |
2882 | c1 = 0; \ | |
ec6d2bb8 | 2883 | } while (0) |
88993dfd | 2884 | |
d46c5b12 | 2885 | |
4ed46869 KH |
2886 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
2887 | ||
b73bfc1c | 2888 | static void |
df7492f9 | 2889 | decode_coding_iso_2022 (coding) |
4ed46869 | 2890 | struct coding_system *coding; |
4ed46869 | 2891 | { |
8f924df7 KH |
2892 | const unsigned char *src = coding->source + coding->consumed; |
2893 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2894 | const unsigned char *src_base; | |
69a80ea3 | 2895 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ff0dacd7 | 2896 | int *charbuf_end |
69a80ea3 | 2897 | = coding->charbuf + coding->charbuf_size - 4 - MAX_ANNOTATION_LENGTH; |
df7492f9 | 2898 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2899 | int multibytep = coding->src_multibyte; |
4ed46869 | 2900 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
2901 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
2902 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 2903 | int charset_id_2, charset_id_3; |
df7492f9 KH |
2904 | struct charset *charset; |
2905 | int c; | |
2906 | /* For handling composition sequence. */ | |
2907 | #define COMPOSING_NO 0 | |
2908 | #define COMPOSING_CHAR 1 | |
2909 | #define COMPOSING_RULE 2 | |
2910 | #define COMPOSING_COMPONENT_CHAR 3 | |
2911 | #define COMPOSING_COMPONENT_RULE 4 | |
2912 | ||
2913 | int composition_state = COMPOSING_NO; | |
2914 | enum composition_method method; | |
2915 | int components[MAX_COMPOSITION_COMPONENTS * 2 + 1]; | |
2916 | int component_idx; | |
2917 | int component_len; | |
24a73b0a | 2918 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2919 | int char_offset = coding->produced_char; |
2920 | int last_offset = char_offset; | |
2921 | int last_id = charset_ascii; | |
df7492f9 | 2922 | |
24a73b0a | 2923 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 2924 | setup_iso_safe_charsets (attrs); |
b73bfc1c KH |
2925 | |
2926 | while (1) | |
4ed46869 | 2927 | { |
463f5630 | 2928 | int c1, c2; |
b73bfc1c KH |
2929 | |
2930 | src_base = src; | |
df7492f9 KH |
2931 | consumed_chars_base = consumed_chars; |
2932 | ||
2933 | if (charbuf >= charbuf_end) | |
2934 | break; | |
2935 | ||
b73bfc1c | 2936 | ONE_MORE_BYTE (c1); |
065e3595 KH |
2937 | if (c1 < 0) |
2938 | goto invalid_code; | |
4ed46869 | 2939 | |
98725083 | 2940 | /* We produce at most one character. */ |
4ed46869 KH |
2941 | switch (iso_code_class [c1]) |
2942 | { | |
2943 | case ISO_0x20_or_0x7F: | |
df7492f9 | 2944 | if (composition_state != COMPOSING_NO) |
ec6d2bb8 | 2945 | { |
df7492f9 KH |
2946 | if (composition_state == COMPOSING_RULE |
2947 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2948 | { | |
2949 | DECODE_COMPOSITION_RULE (c1); | |
2950 | components[component_idx++] = c1; | |
2951 | composition_state--; | |
2952 | continue; | |
2953 | } | |
4ed46869 | 2954 | } |
df7492f9 KH |
2955 | if (charset_id_0 < 0 |
2956 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
2957 | /* This is SPACE or DEL. */ |
2958 | charset = CHARSET_FROM_ID (charset_ascii); | |
2959 | else | |
2960 | charset = CHARSET_FROM_ID (charset_id_0); | |
2961 | break; | |
4ed46869 KH |
2962 | |
2963 | case ISO_graphic_plane_0: | |
781d7a48 | 2964 | if (composition_state != COMPOSING_NO) |
b73bfc1c | 2965 | { |
781d7a48 KH |
2966 | if (composition_state == COMPOSING_RULE |
2967 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2968 | { | |
2969 | DECODE_COMPOSITION_RULE (c1); | |
2970 | components[component_idx++] = c1; | |
2971 | composition_state--; | |
2972 | continue; | |
2973 | } | |
b73bfc1c | 2974 | } |
134b9549 KH |
2975 | if (charset_id_0 < 0) |
2976 | charset = CHARSET_FROM_ID (charset_ascii); | |
2977 | else | |
2978 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
2979 | break; |
2980 | ||
2981 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
2982 | if (charset_id_1 < 0 |
2983 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
2984 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
2985 | goto invalid_code; | |
4ed46869 KH |
2986 | /* This is a graphic character, we fall down ... */ |
2987 | ||
2988 | case ISO_graphic_plane_1: | |
df7492f9 KH |
2989 | if (charset_id_1 < 0) |
2990 | goto invalid_code; | |
2991 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
2992 | break; |
2993 | ||
df7492f9 KH |
2994 | case ISO_control_0: |
2995 | MAYBE_FINISH_COMPOSITION (); | |
2996 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
2997 | break; |
2998 | ||
df7492f9 KH |
2999 | case ISO_control_1: |
3000 | MAYBE_FINISH_COMPOSITION (); | |
3001 | goto invalid_code; | |
3002 | ||
4ed46869 | 3003 | case ISO_shift_out: |
df7492f9 KH |
3004 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3005 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3006 | goto invalid_code; | |
3007 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3008 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3009 | continue; |
4ed46869 KH |
3010 | |
3011 | case ISO_shift_in: | |
df7492f9 KH |
3012 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3013 | goto invalid_code; | |
3014 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3015 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3016 | continue; |
4ed46869 KH |
3017 | |
3018 | case ISO_single_shift_2_7: | |
3019 | case ISO_single_shift_2: | |
df7492f9 KH |
3020 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3021 | goto invalid_code; | |
4ed46869 KH |
3022 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3023 | c1 = 'N'; | |
3024 | goto label_escape_sequence; | |
3025 | ||
3026 | case ISO_single_shift_3: | |
df7492f9 KH |
3027 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3028 | goto invalid_code; | |
4ed46869 KH |
3029 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3030 | c1 = 'O'; | |
3031 | goto label_escape_sequence; | |
3032 | ||
3033 | case ISO_control_sequence_introducer: | |
3034 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3035 | c1 = '['; | |
3036 | goto label_escape_sequence; | |
3037 | ||
3038 | case ISO_escape: | |
3039 | ONE_MORE_BYTE (c1); | |
3040 | label_escape_sequence: | |
df7492f9 | 3041 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3042 | designation, direction specification, and character |
3043 | composition specification. */ | |
3044 | switch (c1) | |
3045 | { | |
3046 | case '&': /* revision of following character set */ | |
3047 | ONE_MORE_BYTE (c1); | |
3048 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3049 | goto invalid_code; |
4ed46869 KH |
3050 | ONE_MORE_BYTE (c1); |
3051 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3052 | goto invalid_code; |
4ed46869 KH |
3053 | ONE_MORE_BYTE (c1); |
3054 | goto label_escape_sequence; | |
3055 | ||
3056 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3057 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3058 | goto invalid_code; | |
134b9549 KH |
3059 | { |
3060 | int reg, chars96; | |
3061 | ||
3062 | ONE_MORE_BYTE (c1); | |
3063 | if (c1 >= '@' && c1 <= 'B') | |
3064 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3065 | or JISX0208.1980 */ |
134b9549 KH |
3066 | reg = 0, chars96 = 0; |
3067 | } | |
3068 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3069 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3070 | reg = c1 - 0x28, chars96 = 0; | |
3071 | ONE_MORE_BYTE (c1); | |
3072 | } | |
3073 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3074 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3075 | reg = c1 - 0x2C, chars96 = 1; | |
3076 | ONE_MORE_BYTE (c1); | |
3077 | } | |
3078 | else | |
3079 | goto invalid_code; | |
3080 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3081 | /* We must update these variables now. */ | |
3082 | if (reg == 0) | |
3083 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3084 | else if (reg == 1) | |
3085 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3086 | if (chars96 < 0) | |
3087 | goto invalid_code; | |
3088 | } | |
b73bfc1c | 3089 | continue; |
4ed46869 KH |
3090 | |
3091 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3092 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3093 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3094 | goto invalid_code; | |
3095 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3096 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3097 | continue; |
4ed46869 KH |
3098 | |
3099 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3100 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3101 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3102 | goto invalid_code; | |
3103 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3104 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3105 | continue; |
4ed46869 KH |
3106 | |
3107 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3108 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3109 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3110 | goto invalid_code; | |
134b9549 KH |
3111 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3112 | if (charset_id_2 < 0) | |
3113 | charset = CHARSET_FROM_ID (charset_ascii); | |
3114 | else | |
3115 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3116 | ONE_MORE_BYTE (c1); |
e7046a18 | 3117 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3118 | goto invalid_code; |
4ed46869 KH |
3119 | break; |
3120 | ||
3121 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3122 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3123 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3124 | goto invalid_code; | |
134b9549 KH |
3125 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3126 | if (charset_id_3 < 0) | |
3127 | charset = CHARSET_FROM_ID (charset_ascii); | |
3128 | else | |
3129 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3130 | ONE_MORE_BYTE (c1); |
e7046a18 | 3131 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3132 | goto invalid_code; |
4ed46869 KH |
3133 | break; |
3134 | ||
ec6d2bb8 | 3135 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3136 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3137 | goto invalid_code; | |
ec6d2bb8 | 3138 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3139 | continue; |
4ed46869 | 3140 | |
ec6d2bb8 | 3141 | case '1': /* end composition */ |
df7492f9 KH |
3142 | if (composition_state == COMPOSING_NO) |
3143 | goto invalid_code; | |
3144 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3145 | continue; |
4ed46869 KH |
3146 | |
3147 | case '[': /* specification of direction */ | |
df7492f9 KH |
3148 | if (! CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION) |
3149 | goto invalid_code; | |
4ed46869 | 3150 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3151 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
df7492f9 | 3152 | left-to-right, and nozero means right-to-left. */ |
4ed46869 KH |
3153 | ONE_MORE_BYTE (c1); |
3154 | switch (c1) | |
3155 | { | |
3156 | case ']': /* end of the current direction */ | |
d46c5b12 | 3157 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3158 | |
3159 | case '0': /* end of the current direction */ | |
3160 | case '1': /* start of left-to-right direction */ | |
3161 | ONE_MORE_BYTE (c1); | |
3162 | if (c1 == ']') | |
d46c5b12 | 3163 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3164 | else |
df7492f9 | 3165 | goto invalid_code; |
4ed46869 KH |
3166 | break; |
3167 | ||
3168 | case '2': /* start of right-to-left direction */ | |
3169 | ONE_MORE_BYTE (c1); | |
3170 | if (c1 == ']') | |
d46c5b12 | 3171 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3172 | else |
df7492f9 | 3173 | goto invalid_code; |
4ed46869 KH |
3174 | break; |
3175 | ||
3176 | default: | |
df7492f9 | 3177 | goto invalid_code; |
4ed46869 | 3178 | } |
b73bfc1c | 3179 | continue; |
4ed46869 | 3180 | |
103e0180 | 3181 | case '%': |
103e0180 KH |
3182 | ONE_MORE_BYTE (c1); |
3183 | if (c1 == '/') | |
3184 | { | |
3185 | /* CTEXT extended segment: | |
3186 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3187 | We keep these bytes as is for the moment. | |
3188 | They may be decoded by post-read-conversion. */ | |
3189 | int dim, M, L; | |
4776e638 | 3190 | int size; |
8f924df7 | 3191 | |
103e0180 KH |
3192 | ONE_MORE_BYTE (dim); |
3193 | ONE_MORE_BYTE (M); | |
3194 | ONE_MORE_BYTE (L); | |
3195 | size = ((M - 128) * 128) + (L - 128); | |
4776e638 KH |
3196 | if (charbuf + 8 + size > charbuf_end) |
3197 | goto break_loop; | |
3198 | *charbuf++ = ISO_CODE_ESC; | |
3199 | *charbuf++ = '%'; | |
3200 | *charbuf++ = '/'; | |
3201 | *charbuf++ = dim; | |
3202 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3203 | *charbuf++ = BYTE8_TO_CHAR (L); | |
103e0180 KH |
3204 | while (size-- > 0) |
3205 | { | |
3206 | ONE_MORE_BYTE (c1); | |
4776e638 | 3207 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3208 | } |
103e0180 KH |
3209 | } |
3210 | else if (c1 == 'G') | |
3211 | { | |
103e0180 KH |
3212 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3213 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3214 | We keep these bytes as is for the moment. | |
3215 | They may be decoded by post-read-conversion. */ | |
4776e638 KH |
3216 | int *p = charbuf; |
3217 | ||
3218 | if (p + 6 > charbuf_end) | |
3219 | goto break_loop; | |
3220 | *p++ = ISO_CODE_ESC; | |
3221 | *p++ = '%'; | |
3222 | *p++ = 'G'; | |
3223 | while (p < charbuf_end) | |
103e0180 KH |
3224 | { |
3225 | ONE_MORE_BYTE (c1); | |
3226 | if (c1 == ISO_CODE_ESC | |
3227 | && src + 1 < src_end | |
3228 | && src[0] == '%' | |
3229 | && src[1] == '@') | |
9ffd559c KH |
3230 | { |
3231 | src += 2; | |
3232 | break; | |
3233 | } | |
4776e638 | 3234 | *p++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3235 | } |
4776e638 KH |
3236 | if (p + 3 > charbuf_end) |
3237 | goto break_loop; | |
3238 | *p++ = ISO_CODE_ESC; | |
3239 | *p++ = '%'; | |
3240 | *p++ = '@'; | |
3241 | charbuf = p; | |
103e0180 KH |
3242 | } |
3243 | else | |
4776e638 | 3244 | goto invalid_code; |
103e0180 | 3245 | continue; |
4776e638 | 3246 | break; |
103e0180 | 3247 | |
4ed46869 | 3248 | default: |
df7492f9 KH |
3249 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3250 | goto invalid_code; | |
134b9549 KH |
3251 | { |
3252 | int reg, chars96; | |
3253 | ||
3254 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3255 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3256 | reg = c1 - 0x28, chars96 = 0; | |
3257 | ONE_MORE_BYTE (c1); | |
3258 | } | |
3259 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3260 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3261 | reg = c1 - 0x2C, chars96 = 1; | |
3262 | ONE_MORE_BYTE (c1); | |
3263 | } | |
3264 | else | |
3265 | goto invalid_code; | |
3266 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3267 | /* We must update these variables now. */ | |
3268 | if (reg == 0) | |
3269 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3270 | else if (reg == 1) | |
3271 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3272 | if (chars96 < 0) | |
3273 | goto invalid_code; | |
3274 | } | |
b73bfc1c | 3275 | continue; |
4ed46869 | 3276 | } |
b73bfc1c | 3277 | } |
4ed46869 | 3278 | |
ff0dacd7 KH |
3279 | if (charset->id != charset_ascii |
3280 | && last_id != charset->id) | |
3281 | { | |
3282 | if (last_id != charset_ascii) | |
69a80ea3 | 3283 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3284 | last_id = charset->id; |
3285 | last_offset = char_offset; | |
3286 | } | |
3287 | ||
b73bfc1c | 3288 | /* Now we know CHARSET and 1st position code C1 of a character. |
df7492f9 KH |
3289 | Produce a decoded character while getting 2nd position code |
3290 | C2 if necessary. */ | |
3291 | c1 &= 0x7F; | |
3292 | if (CHARSET_DIMENSION (charset) > 1) | |
b73bfc1c KH |
3293 | { |
3294 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3295 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) |
b73bfc1c | 3296 | /* C2 is not in a valid range. */ |
df7492f9 KH |
3297 | goto invalid_code; |
3298 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3299 | if (CHARSET_DIMENSION (charset) > 2) | |
3300 | { | |
3301 | ONE_MORE_BYTE (c2); | |
3302 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) | |
3303 | /* C2 is not in a valid range. */ | |
3304 | goto invalid_code; | |
3305 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3306 | } | |
3307 | } | |
3308 | ||
3309 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); | |
3310 | if (c < 0) | |
3311 | { | |
3312 | MAYBE_FINISH_COMPOSITION (); | |
3313 | for (; src_base < src; src_base++, char_offset++) | |
3314 | { | |
3315 | if (ASCII_BYTE_P (*src_base)) | |
3316 | *charbuf++ = *src_base; | |
3317 | else | |
3318 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3319 | } | |
3320 | } | |
3321 | else if (composition_state == COMPOSING_NO) | |
3322 | { | |
3323 | *charbuf++ = c; | |
3324 | char_offset++; | |
4ed46869 | 3325 | } |
df7492f9 | 3326 | else |
781d7a48 KH |
3327 | { |
3328 | components[component_idx++] = c; | |
3329 | if (method == COMPOSITION_WITH_RULE | |
3330 | || (method == COMPOSITION_WITH_RULE_ALTCHARS | |
3331 | && composition_state == COMPOSING_COMPONENT_CHAR)) | |
3332 | composition_state++; | |
4ed46869 KH |
3333 | } |
3334 | continue; | |
3335 | ||
df7492f9 KH |
3336 | invalid_code: |
3337 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3338 | src = src_base; |
df7492f9 KH |
3339 | consumed_chars = consumed_chars_base; |
3340 | ONE_MORE_BYTE (c); | |
065e3595 | 3341 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3342 | char_offset++; |
df7492f9 | 3343 | coding->errors++; |
4776e638 KH |
3344 | continue; |
3345 | ||
3346 | break_loop: | |
3347 | break; | |
4ed46869 | 3348 | } |
fb88bf2d | 3349 | |
df7492f9 | 3350 | no_more_source: |
ff0dacd7 | 3351 | if (last_id != charset_ascii) |
69a80ea3 | 3352 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
3353 | coding->consumed_char += consumed_chars_base; |
3354 | coding->consumed = src_base - coding->source; | |
3355 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3356 | } |
3357 | ||
b73bfc1c | 3358 | |
f4dee582 | 3359 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3360 | |
3361 | /* | |
f4dee582 | 3362 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 3363 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 3364 | variant has the following specifications: |
df7492f9 | 3365 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
3366 | 2. Allows short-form designation? |
3367 | 3. ASCII should be designated to G0 before control characters? | |
3368 | 4. ASCII should be designated to G0 at end of line? | |
3369 | 5. 7-bit environment or 8-bit environment? | |
3370 | 6. Use locking-shift? | |
3371 | 7. Use Single-shift? | |
3372 | And the following two are only for Japanese: | |
3373 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
3374 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
3375 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
3376 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 3377 | details. |
4ed46869 KH |
3378 | */ |
3379 | ||
3380 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
3381 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
3382 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
3383 | designation sequence of short-form. */ | |
4ed46869 KH |
3384 | |
3385 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
3386 | do { \ | |
df7492f9 | 3387 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
4ed46869 KH |
3388 | char *intermediate_char_94 = "()*+"; \ |
3389 | char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
3390 | int revision = -1; \ |
3391 | int c; \ | |
3392 | \ | |
3393 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 3394 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
3395 | \ |
3396 | if (revision >= 0) \ | |
70c22245 | 3397 | { \ |
df7492f9 KH |
3398 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
3399 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 3400 | } \ |
df7492f9 | 3401 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
3402 | if (CHARSET_DIMENSION (charset) == 1) \ |
3403 | { \ | |
df7492f9 KH |
3404 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
3405 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 3406 | else \ |
df7492f9 KH |
3407 | c = intermediate_char_96[reg]; \ |
3408 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
3409 | } \ |
3410 | else \ | |
3411 | { \ | |
df7492f9 KH |
3412 | EMIT_ONE_ASCII_BYTE ('$'); \ |
3413 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 3414 | { \ |
df7492f9 | 3415 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
3416 | || reg != 0 \ |
3417 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 3418 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
3419 | } \ |
3420 | else \ | |
df7492f9 | 3421 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 3422 | } \ |
df7492f9 KH |
3423 | EMIT_ONE_ASCII_BYTE (final_char); \ |
3424 | \ | |
3425 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
3426 | } while (0) |
3427 | ||
df7492f9 | 3428 | |
4ed46869 KH |
3429 | /* The following two macros produce codes (control character or escape |
3430 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
3431 | single-shift-3). */ | |
3432 | ||
df7492f9 KH |
3433 | #define ENCODE_SINGLE_SHIFT_2 \ |
3434 | do { \ | |
3435 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3436 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
3437 | else \ | |
3438 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
3439 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3440 | } while (0) |
3441 | ||
df7492f9 KH |
3442 | |
3443 | #define ENCODE_SINGLE_SHIFT_3 \ | |
3444 | do { \ | |
3445 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3446 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
3447 | else \ | |
3448 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
3449 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3450 | } while (0) |
3451 | ||
df7492f9 | 3452 | |
4ed46869 KH |
3453 | /* The following four macros produce codes (control character or |
3454 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
3455 | shift-out, locking-shift-2, and locking-shift-3). */ | |
3456 | ||
df7492f9 KH |
3457 | #define ENCODE_SHIFT_IN \ |
3458 | do { \ | |
3459 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
3460 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
3461 | } while (0) |
3462 | ||
df7492f9 KH |
3463 | |
3464 | #define ENCODE_SHIFT_OUT \ | |
3465 | do { \ | |
3466 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
3467 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
3468 | } while (0) |
3469 | ||
df7492f9 KH |
3470 | |
3471 | #define ENCODE_LOCKING_SHIFT_2 \ | |
3472 | do { \ | |
3473 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3474 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
3475 | } while (0) |
3476 | ||
df7492f9 KH |
3477 | |
3478 | #define ENCODE_LOCKING_SHIFT_3 \ | |
3479 | do { \ | |
3480 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3481 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
3482 | } while (0) |
3483 | ||
df7492f9 | 3484 | |
f4dee582 RS |
3485 | /* Produce codes for a DIMENSION1 character whose character set is |
3486 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
3487 | sequences are also produced in advance if necessary. */ |
3488 | ||
6e85d753 KH |
3489 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
3490 | do { \ | |
df7492f9 | 3491 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3492 | \ |
3493 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3494 | && id == charset_ascii) \ | |
3495 | { \ | |
3496 | id = charset_jisx0201_roman; \ | |
3497 | charset = CHARSET_FROM_ID (id); \ | |
3498 | } \ | |
3499 | \ | |
df7492f9 | 3500 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3501 | { \ |
df7492f9 KH |
3502 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3503 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 3504 | else \ |
df7492f9 KH |
3505 | EMIT_ONE_BYTE (c1 | 0x80); \ |
3506 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3507 | break; \ |
3508 | } \ | |
df7492f9 | 3509 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3510 | { \ |
df7492f9 | 3511 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
3512 | break; \ |
3513 | } \ | |
df7492f9 | 3514 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3515 | { \ |
df7492f9 | 3516 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
3517 | break; \ |
3518 | } \ | |
6e85d753 KH |
3519 | else \ |
3520 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3521 | must invoke it, or, at first, designate it to some graphic \ | |
3522 | register. Then repeat the loop to actually produce the \ | |
3523 | character. */ \ | |
df7492f9 KH |
3524 | dst = encode_invocation_designation (charset, coding, dst, \ |
3525 | &produced_chars); \ | |
4ed46869 KH |
3526 | } while (1) |
3527 | ||
df7492f9 | 3528 | |
f4dee582 RS |
3529 | /* Produce codes for a DIMENSION2 character whose character set is |
3530 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
3531 | invocation codes are also produced in advance if necessary. */ |
3532 | ||
6e85d753 KH |
3533 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
3534 | do { \ | |
df7492f9 | 3535 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3536 | \ |
3537 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3538 | && id == charset_jisx0208) \ | |
3539 | { \ | |
3540 | id = charset_jisx0208_1978; \ | |
3541 | charset = CHARSET_FROM_ID (id); \ | |
3542 | } \ | |
3543 | \ | |
df7492f9 | 3544 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3545 | { \ |
df7492f9 KH |
3546 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3547 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 3548 | else \ |
df7492f9 KH |
3549 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
3550 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3551 | break; \ |
3552 | } \ | |
df7492f9 | 3553 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3554 | { \ |
df7492f9 | 3555 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
3556 | break; \ |
3557 | } \ | |
df7492f9 | 3558 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3559 | { \ |
df7492f9 | 3560 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
3561 | break; \ |
3562 | } \ | |
6e85d753 KH |
3563 | else \ |
3564 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3565 | must invoke it, or, at first, designate it to some graphic \ | |
3566 | register. Then repeat the loop to actually produce the \ | |
3567 | character. */ \ | |
df7492f9 KH |
3568 | dst = encode_invocation_designation (charset, coding, dst, \ |
3569 | &produced_chars); \ | |
4ed46869 KH |
3570 | } while (1) |
3571 | ||
05e6f5dc | 3572 | |
df7492f9 KH |
3573 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
3574 | do { \ | |
3575 | int code = ENCODE_CHAR ((charset),(c)); \ | |
3576 | \ | |
3577 | if (CHARSET_DIMENSION (charset) == 1) \ | |
3578 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
3579 | else \ | |
3580 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 3581 | } while (0) |
bdd9fb48 | 3582 | |
05e6f5dc | 3583 | |
4ed46869 | 3584 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 3585 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
3586 | Return new DST. */ |
3587 | ||
3588 | unsigned char * | |
df7492f9 KH |
3589 | encode_invocation_designation (charset, coding, dst, p_nchars) |
3590 | struct charset *charset; | |
4ed46869 KH |
3591 | struct coding_system *coding; |
3592 | unsigned char *dst; | |
df7492f9 | 3593 | int *p_nchars; |
4ed46869 | 3594 | { |
df7492f9 KH |
3595 | int multibytep = coding->dst_multibyte; |
3596 | int produced_chars = *p_nchars; | |
4ed46869 | 3597 | int reg; /* graphic register number */ |
df7492f9 | 3598 | int id = CHARSET_ID (charset); |
4ed46869 KH |
3599 | |
3600 | /* At first, check designations. */ | |
3601 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 3602 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
3603 | break; |
3604 | ||
3605 | if (reg >= 4) | |
3606 | { | |
3607 | /* CHARSET is not yet designated to any graphic registers. */ | |
3608 | /* At first check the requested designation. */ | |
df7492f9 KH |
3609 | reg = CODING_ISO_REQUEST (coding, id); |
3610 | if (reg < 0) | |
1ba9e4ab KH |
3611 | /* Since CHARSET requests no special designation, designate it |
3612 | to graphic register 0. */ | |
4ed46869 KH |
3613 | reg = 0; |
3614 | ||
3615 | ENCODE_DESIGNATION (charset, reg, coding); | |
3616 | } | |
3617 | ||
df7492f9 KH |
3618 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
3619 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
3620 | { |
3621 | /* Since the graphic register REG is not invoked to any graphic | |
3622 | planes, invoke it to graphic plane 0. */ | |
3623 | switch (reg) | |
3624 | { | |
3625 | case 0: /* graphic register 0 */ | |
3626 | ENCODE_SHIFT_IN; | |
3627 | break; | |
3628 | ||
3629 | case 1: /* graphic register 1 */ | |
3630 | ENCODE_SHIFT_OUT; | |
3631 | break; | |
3632 | ||
3633 | case 2: /* graphic register 2 */ | |
df7492f9 | 3634 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3635 | ENCODE_SINGLE_SHIFT_2; |
3636 | else | |
3637 | ENCODE_LOCKING_SHIFT_2; | |
3638 | break; | |
3639 | ||
3640 | case 3: /* graphic register 3 */ | |
df7492f9 | 3641 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3642 | ENCODE_SINGLE_SHIFT_3; |
3643 | else | |
3644 | ENCODE_LOCKING_SHIFT_3; | |
3645 | break; | |
3646 | } | |
3647 | } | |
b73bfc1c | 3648 | |
df7492f9 | 3649 | *p_nchars = produced_chars; |
4ed46869 KH |
3650 | return dst; |
3651 | } | |
3652 | ||
df7492f9 KH |
3653 | /* The following three macros produce codes for indicating direction |
3654 | of text. */ | |
3655 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 3656 | do { \ |
df7492f9 KH |
3657 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
3658 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 3659 | else \ |
df7492f9 | 3660 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
3661 | } while (0) |
3662 | ||
ec6d2bb8 | 3663 | |
df7492f9 KH |
3664 | #define ENCODE_DIRECTION_R2L() \ |
3665 | do { \ | |
3666 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
3667 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
3668 | } while (0) |
3669 | ||
ec6d2bb8 | 3670 | |
df7492f9 | 3671 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 3672 | do { \ |
df7492f9 KH |
3673 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
3674 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
ec6d2bb8 | 3675 | } while (0) |
4ed46869 | 3676 | |
4ed46869 KH |
3677 | |
3678 | /* Produce codes for designation and invocation to reset the graphic | |
3679 | planes and registers to initial state. */ | |
df7492f9 KH |
3680 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
3681 | do { \ | |
3682 | int reg; \ | |
3683 | struct charset *charset; \ | |
3684 | \ | |
3685 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
3686 | ENCODE_SHIFT_IN; \ | |
3687 | for (reg = 0; reg < 4; reg++) \ | |
3688 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
3689 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
3690 | != CODING_ISO_INITIAL (coding, reg))) \ | |
3691 | { \ | |
3692 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
3693 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
3694 | } \ | |
4ed46869 KH |
3695 | } while (0) |
3696 | ||
df7492f9 | 3697 | |
bdd9fb48 | 3698 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 3699 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
3700 | |
3701 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
3702 | find all the necessary designations. */ |
3703 | ||
b73bfc1c | 3704 | static unsigned char * |
df7492f9 | 3705 | encode_designation_at_bol (coding, charbuf, charbuf_end, dst) |
e0e989f6 | 3706 | struct coding_system *coding; |
df7492f9 KH |
3707 | int *charbuf, *charbuf_end; |
3708 | unsigned char *dst; | |
e0e989f6 | 3709 | { |
df7492f9 | 3710 | struct charset *charset; |
bdd9fb48 KH |
3711 | /* Table of charsets to be designated to each graphic register. */ |
3712 | int r[4]; | |
df7492f9 KH |
3713 | int c, found = 0, reg; |
3714 | int produced_chars = 0; | |
3715 | int multibytep = coding->dst_multibyte; | |
3716 | Lisp_Object attrs; | |
3717 | Lisp_Object charset_list; | |
3718 | ||
3719 | attrs = CODING_ID_ATTRS (coding->id); | |
3720 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
3721 | if (EQ (charset_list, Qiso_2022)) | |
3722 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
3723 | |
3724 | for (reg = 0; reg < 4; reg++) | |
3725 | r[reg] = -1; | |
3726 | ||
b73bfc1c | 3727 | while (found < 4) |
e0e989f6 | 3728 | { |
df7492f9 KH |
3729 | int id; |
3730 | ||
3731 | c = *charbuf++; | |
b73bfc1c KH |
3732 | if (c == '\n') |
3733 | break; | |
df7492f9 KH |
3734 | charset = char_charset (c, charset_list, NULL); |
3735 | id = CHARSET_ID (charset); | |
3736 | reg = CODING_ISO_REQUEST (coding, id); | |
3737 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
3738 | { |
3739 | found++; | |
df7492f9 | 3740 | r[reg] = id; |
bdd9fb48 | 3741 | } |
bdd9fb48 KH |
3742 | } |
3743 | ||
3744 | if (found) | |
3745 | { | |
3746 | for (reg = 0; reg < 4; reg++) | |
3747 | if (r[reg] >= 0 | |
df7492f9 KH |
3748 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
3749 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 3750 | } |
b73bfc1c KH |
3751 | |
3752 | return dst; | |
e0e989f6 KH |
3753 | } |
3754 | ||
4ed46869 KH |
3755 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
3756 | ||
df7492f9 KH |
3757 | static int |
3758 | encode_coding_iso_2022 (coding) | |
4ed46869 | 3759 | struct coding_system *coding; |
4ed46869 | 3760 | { |
df7492f9 KH |
3761 | int multibytep = coding->dst_multibyte; |
3762 | int *charbuf = coding->charbuf; | |
3763 | int *charbuf_end = charbuf + coding->charbuf_used; | |
3764 | unsigned char *dst = coding->destination + coding->produced; | |
3765 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
3766 | int safe_room = 16; | |
3767 | int bol_designation | |
3768 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
3769 | && CODING_ISO_BOL (coding)); | |
3770 | int produced_chars = 0; | |
3771 | Lisp_Object attrs, eol_type, charset_list; | |
3772 | int ascii_compatible; | |
b73bfc1c | 3773 | int c; |
ff0dacd7 | 3774 | int preferred_charset_id = -1; |
05e6f5dc | 3775 | |
24a73b0a KH |
3776 | CODING_GET_INFO (coding, attrs, charset_list); |
3777 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
3778 | if (VECTORP (eol_type)) | |
3779 | eol_type = Qunix; | |
3780 | ||
004068e4 | 3781 | setup_iso_safe_charsets (attrs); |
ff0dacd7 KH |
3782 | /* Charset list may have been changed. */ |
3783 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); \ | |
8f924df7 | 3784 | coding->safe_charsets = (char *) SDATA (CODING_ATTR_SAFE_CHARSETS(attrs)); |
0eecad43 | 3785 | |
df7492f9 | 3786 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
bdd9fb48 | 3787 | |
df7492f9 | 3788 | while (charbuf < charbuf_end) |
4ed46869 | 3789 | { |
df7492f9 | 3790 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 3791 | |
df7492f9 | 3792 | if (bol_designation) |
b73bfc1c | 3793 | { |
df7492f9 | 3794 | unsigned char *dst_prev = dst; |
4ed46869 | 3795 | |
bdd9fb48 | 3796 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
3797 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
3798 | bol_designation = 0; | |
3799 | /* We are sure that designation sequences are all ASCII bytes. */ | |
3800 | produced_chars += dst - dst_prev; | |
e0e989f6 KH |
3801 | } |
3802 | ||
df7492f9 | 3803 | c = *charbuf++; |
ec6d2bb8 | 3804 | |
ff0dacd7 KH |
3805 | if (c < 0) |
3806 | { | |
3807 | /* Handle an annotation. */ | |
3808 | switch (*charbuf) | |
ec6d2bb8 | 3809 | { |
ff0dacd7 KH |
3810 | case CODING_ANNOTATE_COMPOSITION_MASK: |
3811 | /* Not yet implemented. */ | |
3812 | break; | |
3813 | case CODING_ANNOTATE_CHARSET_MASK: | |
cf7dfdf5 | 3814 | preferred_charset_id = charbuf[2]; |
ff0dacd7 KH |
3815 | if (preferred_charset_id >= 0 |
3816 | && NILP (Fmemq (make_number (preferred_charset_id), | |
3817 | charset_list))) | |
3818 | preferred_charset_id = -1; | |
3819 | break; | |
3820 | default: | |
3821 | abort (); | |
4ed46869 | 3822 | } |
ff0dacd7 KH |
3823 | charbuf += -c - 1; |
3824 | continue; | |
4ed46869 | 3825 | } |
ec6d2bb8 | 3826 | |
b73bfc1c KH |
3827 | /* Now encode the character C. */ |
3828 | if (c < 0x20 || c == 0x7F) | |
3829 | { | |
df7492f9 KH |
3830 | if (c == '\n' |
3831 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 3832 | { |
df7492f9 KH |
3833 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
3834 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3835 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 3836 | { |
df7492f9 KH |
3837 | int i; |
3838 | ||
3839 | for (i = 0; i < 4; i++) | |
3840 | CODING_ISO_DESIGNATION (coding, i) | |
3841 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 3842 | } |
df7492f9 KH |
3843 | bol_designation |
3844 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 3845 | } |
df7492f9 KH |
3846 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
3847 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3848 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 3849 | } |
df7492f9 | 3850 | else if (ASCII_CHAR_P (c)) |
88993dfd | 3851 | { |
df7492f9 KH |
3852 | if (ascii_compatible) |
3853 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 3854 | else |
19a8d9e0 | 3855 | { |
bf16eb23 KH |
3856 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
3857 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 3858 | } |
4ed46869 | 3859 | } |
16eafb5d | 3860 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 3861 | { |
16eafb5d KH |
3862 | c = CHAR_TO_BYTE8 (c); |
3863 | EMIT_ONE_BYTE (c); | |
88993dfd | 3864 | } |
b73bfc1c | 3865 | else |
df7492f9 | 3866 | { |
ff0dacd7 | 3867 | struct charset *charset; |
b73bfc1c | 3868 | |
ff0dacd7 KH |
3869 | if (preferred_charset_id >= 0) |
3870 | { | |
3871 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
3872 | if (! CHAR_CHARSET_P (c, charset)) | |
3873 | charset = char_charset (c, charset_list, NULL); | |
3874 | } | |
3875 | else | |
3876 | charset = char_charset (c, charset_list, NULL); | |
df7492f9 KH |
3877 | if (!charset) |
3878 | { | |
41cbe562 KH |
3879 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
3880 | { | |
3881 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
3882 | charset = CHARSET_FROM_ID (charset_ascii); | |
3883 | } | |
3884 | else | |
3885 | { | |
3886 | c = coding->default_char; | |
3887 | charset = char_charset (c, charset_list, NULL); | |
3888 | } | |
df7492f9 KH |
3889 | } |
3890 | ENCODE_ISO_CHARACTER (charset, c); | |
3891 | } | |
84fbb8a0 | 3892 | } |
b73bfc1c | 3893 | |
df7492f9 KH |
3894 | if (coding->mode & CODING_MODE_LAST_BLOCK |
3895 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
3896 | { | |
3897 | ASSURE_DESTINATION (safe_room); | |
3898 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3899 | } | |
065e3595 | 3900 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
3901 | CODING_ISO_BOL (coding) = bol_designation; |
3902 | coding->produced_char += produced_chars; | |
3903 | coding->produced = dst - coding->destination; | |
3904 | return 0; | |
4ed46869 KH |
3905 | } |
3906 | ||
3907 | \f | |
df7492f9 | 3908 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 3909 | |
df7492f9 | 3910 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
3911 | quite widely. So, for the moment, Emacs supports them in the bare |
3912 | C code. But, in the future, they may be supported only by CCL. */ | |
3913 | ||
3914 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
3915 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
3916 | as is. A character of charset katakana-jisx0201 is encoded by | |
3917 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
3918 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 3919 | so that it fit in the range below. |
4ed46869 KH |
3920 | |
3921 | --- CODE RANGE of SJIS --- | |
3922 | (character set) (range) | |
3923 | ASCII 0x00 .. 0x7F | |
df7492f9 | 3924 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 3925 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 3926 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
3927 | ------------------------------- |
3928 | ||
3929 | */ | |
3930 | ||
3931 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
3932 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 3933 | character set and is encoded in two-byte. |
4ed46869 KH |
3934 | |
3935 | --- CODE RANGE of BIG5 --- | |
3936 | (character set) (range) | |
3937 | ASCII 0x00 .. 0x7F | |
3938 | Big5 (1st byte) 0xA1 .. 0xFE | |
3939 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
3940 | -------------------------- | |
3941 | ||
df7492f9 | 3942 | */ |
4ed46869 KH |
3943 | |
3944 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3945 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 3946 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 3947 | |
0a28aafb | 3948 | static int |
ff0dacd7 | 3949 | detect_coding_sjis (coding, detect_info) |
df7492f9 | 3950 | struct coding_system *coding; |
ff0dacd7 | 3951 | struct coding_detection_info *detect_info; |
4ed46869 | 3952 | { |
065e3595 | 3953 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 3954 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
3955 | int multibytep = coding->src_multibyte; |
3956 | int consumed_chars = 0; | |
3957 | int found = 0; | |
b73bfc1c | 3958 | int c; |
df7492f9 | 3959 | |
ff0dacd7 | 3960 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3961 | /* A coding system of this category is always ASCII compatible. */ |
3962 | src += coding->head_ascii; | |
4ed46869 | 3963 | |
b73bfc1c | 3964 | while (1) |
4ed46869 | 3965 | { |
065e3595 | 3966 | src_base = src; |
df7492f9 | 3967 | ONE_MORE_BYTE (c); |
682169fe KH |
3968 | if (c < 0x80) |
3969 | continue; | |
df7492f9 | 3970 | if ((c >= 0x81 && c <= 0x9F) || (c >= 0xE0 && c <= 0xEF)) |
4ed46869 | 3971 | { |
df7492f9 | 3972 | ONE_MORE_BYTE (c); |
682169fe | 3973 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 3974 | break; |
ff0dacd7 | 3975 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 3976 | } |
df7492f9 | 3977 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 3978 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
3979 | else |
3980 | break; | |
4ed46869 | 3981 | } |
ff0dacd7 | 3982 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3983 | return 0; |
3984 | ||
3985 | no_more_source: | |
065e3595 | 3986 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 3987 | { |
ff0dacd7 | 3988 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 3989 | return 0; |
4ed46869 | 3990 | } |
ff0dacd7 KH |
3991 | detect_info->found |= found; |
3992 | return 1; | |
4ed46869 KH |
3993 | } |
3994 | ||
3995 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3996 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 3997 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 3998 | |
0a28aafb | 3999 | static int |
ff0dacd7 | 4000 | detect_coding_big5 (coding, detect_info) |
df7492f9 | 4001 | struct coding_system *coding; |
ff0dacd7 | 4002 | struct coding_detection_info *detect_info; |
4ed46869 | 4003 | { |
065e3595 | 4004 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4005 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4006 | int multibytep = coding->src_multibyte; |
4007 | int consumed_chars = 0; | |
4008 | int found = 0; | |
b73bfc1c | 4009 | int c; |
fa42c37f | 4010 | |
ff0dacd7 | 4011 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4012 | /* A coding system of this category is always ASCII compatible. */ |
4013 | src += coding->head_ascii; | |
fa42c37f | 4014 | |
b73bfc1c | 4015 | while (1) |
fa42c37f | 4016 | { |
065e3595 | 4017 | src_base = src; |
df7492f9 KH |
4018 | ONE_MORE_BYTE (c); |
4019 | if (c < 0x80) | |
fa42c37f | 4020 | continue; |
df7492f9 | 4021 | if (c >= 0xA1) |
fa42c37f | 4022 | { |
df7492f9 KH |
4023 | ONE_MORE_BYTE (c); |
4024 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4025 | return 0; |
ff0dacd7 | 4026 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4027 | } |
df7492f9 KH |
4028 | else |
4029 | break; | |
fa42c37f | 4030 | } |
ff0dacd7 | 4031 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4032 | return 0; |
fa42c37f | 4033 | |
df7492f9 | 4034 | no_more_source: |
065e3595 | 4035 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4036 | { |
ff0dacd7 | 4037 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4038 | return 0; |
4039 | } | |
ff0dacd7 KH |
4040 | detect_info->found |= found; |
4041 | return 1; | |
fa42c37f KH |
4042 | } |
4043 | ||
4ed46869 KH |
4044 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
4045 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
fa42c37f | 4046 | |
b73bfc1c | 4047 | static void |
df7492f9 | 4048 | decode_coding_sjis (coding) |
4ed46869 | 4049 | struct coding_system *coding; |
4ed46869 | 4050 | { |
8f924df7 KH |
4051 | const unsigned char *src = coding->source + coding->consumed; |
4052 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4053 | const unsigned char *src_base; | |
69a80ea3 KH |
4054 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4055 | int *charbuf_end | |
4056 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4057 | int consumed_chars = 0, consumed_chars_base; |
4058 | int multibytep = coding->src_multibyte; | |
4059 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4060 | struct charset *charset_kanji2; |
24a73b0a | 4061 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4062 | int char_offset = coding->produced_char; |
4063 | int last_offset = char_offset; | |
4064 | int last_id = charset_ascii; | |
a5d301df | 4065 | |
24a73b0a | 4066 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4067 | |
4068 | val = charset_list; | |
4069 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4070 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4071 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4072 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4073 | |
b73bfc1c | 4074 | while (1) |
4ed46869 | 4075 | { |
df7492f9 | 4076 | int c, c1; |
24a73b0a | 4077 | struct charset *charset; |
fa42c37f | 4078 | |
b73bfc1c | 4079 | src_base = src; |
df7492f9 | 4080 | consumed_chars_base = consumed_chars; |
fa42c37f | 4081 | |
df7492f9 KH |
4082 | if (charbuf >= charbuf_end) |
4083 | break; | |
4084 | ||
4085 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4086 | if (c < 0) |
4087 | goto invalid_code; | |
24a73b0a KH |
4088 | if (c < 0x80) |
4089 | charset = charset_roman; | |
57a47f8a | 4090 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4091 | goto invalid_code; |
57a47f8a KH |
4092 | else if (c >= 0xA1 && c <= 0xDF) |
4093 | { | |
4094 | /* SJIS -> JISX0201-Kana */ | |
4095 | c &= 0x7F; | |
4096 | charset = charset_kana; | |
4097 | } | |
4098 | else if (c <= 0xEF) | |
df7492f9 | 4099 | { |
57a47f8a KH |
4100 | /* SJIS -> JISX0208 */ |
4101 | ONE_MORE_BYTE (c1); | |
4102 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4103 | goto invalid_code; |
57a47f8a KH |
4104 | c = (c << 8) | c1; |
4105 | SJIS_TO_JIS (c); | |
4106 | charset = charset_kanji; | |
4107 | } | |
4108 | else if (c <= 0xFC && charset_kanji2) | |
4109 | { | |
c6876370 | 4110 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4111 | ONE_MORE_BYTE (c1); |
4112 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4113 | goto invalid_code; |
57a47f8a KH |
4114 | c = (c << 8) | c1; |
4115 | SJIS_TO_JIS2 (c); | |
4116 | charset = charset_kanji2; | |
df7492f9 | 4117 | } |
57a47f8a KH |
4118 | else |
4119 | goto invalid_code; | |
24a73b0a KH |
4120 | if (charset->id != charset_ascii |
4121 | && last_id != charset->id) | |
4122 | { | |
4123 | if (last_id != charset_ascii) | |
69a80ea3 | 4124 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4125 | last_id = charset->id; |
4126 | last_offset = char_offset; | |
4127 | } | |
4128 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4129 | *charbuf++ = c; |
ff0dacd7 | 4130 | char_offset++; |
df7492f9 | 4131 | continue; |
b73bfc1c | 4132 | |
df7492f9 KH |
4133 | invalid_code: |
4134 | src = src_base; | |
4135 | consumed_chars = consumed_chars_base; | |
4136 | ONE_MORE_BYTE (c); | |
065e3595 | 4137 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4138 | char_offset++; |
df7492f9 KH |
4139 | coding->errors++; |
4140 | } | |
fa42c37f | 4141 | |
df7492f9 | 4142 | no_more_source: |
ff0dacd7 | 4143 | if (last_id != charset_ascii) |
69a80ea3 | 4144 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4145 | coding->consumed_char += consumed_chars_base; |
4146 | coding->consumed = src_base - coding->source; | |
4147 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4148 | } |
4149 | ||
b73bfc1c | 4150 | static void |
df7492f9 | 4151 | decode_coding_big5 (coding) |
4ed46869 | 4152 | struct coding_system *coding; |
4ed46869 | 4153 | { |
8f924df7 KH |
4154 | const unsigned char *src = coding->source + coding->consumed; |
4155 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4156 | const unsigned char *src_base; | |
69a80ea3 KH |
4157 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4158 | int *charbuf_end | |
4159 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4160 | int consumed_chars = 0, consumed_chars_base; |
4161 | int multibytep = coding->src_multibyte; | |
4162 | struct charset *charset_roman, *charset_big5; | |
24a73b0a | 4163 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4164 | int char_offset = coding->produced_char; |
4165 | int last_offset = char_offset; | |
4166 | int last_id = charset_ascii; | |
df7492f9 | 4167 | |
24a73b0a | 4168 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4169 | val = charset_list; |
4170 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4171 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4172 | |
b73bfc1c | 4173 | while (1) |
4ed46869 | 4174 | { |
df7492f9 | 4175 | int c, c1; |
24a73b0a | 4176 | struct charset *charset; |
b73bfc1c KH |
4177 | |
4178 | src_base = src; | |
df7492f9 KH |
4179 | consumed_chars_base = consumed_chars; |
4180 | ||
4181 | if (charbuf >= charbuf_end) | |
4182 | break; | |
4183 | ||
4184 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4185 | |
065e3595 KH |
4186 | if (c < 0) |
4187 | goto invalid_code; | |
24a73b0a KH |
4188 | if (c < 0x80) |
4189 | charset = charset_roman; | |
4190 | else | |
4ed46869 | 4191 | { |
24a73b0a KH |
4192 | /* BIG5 -> Big5 */ |
4193 | if (c < 0xA1 || c > 0xFE) | |
4194 | goto invalid_code; | |
4195 | ONE_MORE_BYTE (c1); | |
4196 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4197 | goto invalid_code; | |
4198 | c = c << 8 | c1; | |
4199 | charset = charset_big5; | |
4ed46869 | 4200 | } |
24a73b0a KH |
4201 | if (charset->id != charset_ascii |
4202 | && last_id != charset->id) | |
df7492f9 | 4203 | { |
24a73b0a | 4204 | if (last_id != charset_ascii) |
69a80ea3 | 4205 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4206 | last_id = charset->id; |
4207 | last_offset = char_offset; | |
4ed46869 | 4208 | } |
24a73b0a | 4209 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4210 | *charbuf++ = c; |
ff0dacd7 | 4211 | char_offset++; |
fb88bf2d KH |
4212 | continue; |
4213 | ||
df7492f9 | 4214 | invalid_code: |
4ed46869 | 4215 | src = src_base; |
df7492f9 KH |
4216 | consumed_chars = consumed_chars_base; |
4217 | ONE_MORE_BYTE (c); | |
065e3595 | 4218 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4219 | char_offset++; |
df7492f9 | 4220 | coding->errors++; |
fb88bf2d | 4221 | } |
d46c5b12 | 4222 | |
df7492f9 | 4223 | no_more_source: |
ff0dacd7 | 4224 | if (last_id != charset_ascii) |
69a80ea3 | 4225 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4226 | coding->consumed_char += consumed_chars_base; |
4227 | coding->consumed = src_base - coding->source; | |
4228 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4229 | } |
4230 | ||
4231 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4232 | This function can encode charsets `ascii', `katakana-jisx0201', |
4233 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4234 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
4235 | (i.e. do not have extended leading-codes). Characters of other |
4236 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
4237 | SJIS text, else encode BIG5 text. */ | |
4238 | ||
df7492f9 KH |
4239 | static int |
4240 | encode_coding_sjis (coding) | |
4ed46869 | 4241 | struct coding_system *coding; |
4ed46869 | 4242 | { |
df7492f9 KH |
4243 | int multibytep = coding->dst_multibyte; |
4244 | int *charbuf = coding->charbuf; | |
4245 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4246 | unsigned char *dst = coding->destination + coding->produced; | |
4247 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4248 | int safe_room = 4; | |
4249 | int produced_chars = 0; | |
24a73b0a | 4250 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4251 | int ascii_compatible; |
4252 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4253 | struct charset *charset_kanji2; |
df7492f9 | 4254 | int c; |
a5d301df | 4255 | |
24a73b0a | 4256 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4257 | val = charset_list; |
4258 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4259 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
57a47f8a KH |
4260 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4261 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4262 | |
df7492f9 | 4263 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4264 | |
df7492f9 KH |
4265 | while (charbuf < charbuf_end) |
4266 | { | |
4267 | ASSURE_DESTINATION (safe_room); | |
4268 | c = *charbuf++; | |
b73bfc1c | 4269 | /* Now encode the character C. */ |
df7492f9 KH |
4270 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4271 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4272 | else if (CHAR_BYTE8_P (c)) |
4273 | { | |
4274 | c = CHAR_TO_BYTE8 (c); | |
4275 | EMIT_ONE_BYTE (c); | |
4276 | } | |
df7492f9 | 4277 | else |
b73bfc1c | 4278 | { |
df7492f9 KH |
4279 | unsigned code; |
4280 | struct charset *charset = char_charset (c, charset_list, &code); | |
4281 | ||
4282 | if (!charset) | |
4ed46869 | 4283 | { |
41cbe562 | 4284 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4285 | { |
41cbe562 KH |
4286 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4287 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4288 | } |
41cbe562 | 4289 | else |
b73bfc1c | 4290 | { |
41cbe562 KH |
4291 | c = coding->default_char; |
4292 | charset = char_charset (c, charset_list, &code); | |
b73bfc1c | 4293 | } |
b73bfc1c | 4294 | } |
df7492f9 KH |
4295 | if (code == CHARSET_INVALID_CODE (charset)) |
4296 | abort (); | |
4297 | if (charset == charset_kanji) | |
4298 | { | |
4299 | int c1, c2; | |
4300 | JIS_TO_SJIS (code); | |
4301 | c1 = code >> 8, c2 = code & 0xFF; | |
4302 | EMIT_TWO_BYTES (c1, c2); | |
4303 | } | |
4304 | else if (charset == charset_kana) | |
4305 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
4306 | else if (charset_kanji2 && charset == charset_kanji2) |
4307 | { | |
4308 | int c1, c2; | |
4309 | ||
4310 | c1 = code >> 8; | |
4311 | if (c1 == 0x21 || (c1 >= 0x23 && c1 < 0x25) | |
4312 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) | |
4313 | { | |
4314 | JIS_TO_SJIS2 (code); | |
4315 | c1 = code >> 8, c2 = code & 0xFF; | |
4316 | EMIT_TWO_BYTES (c1, c2); | |
4317 | } | |
4318 | else | |
4319 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4320 | } | |
df7492f9 KH |
4321 | else |
4322 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4323 | } | |
4324 | } | |
065e3595 | 4325 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4326 | coding->produced_char += produced_chars; |
4327 | coding->produced = dst - coding->destination; | |
4328 | return 0; | |
4329 | } | |
4330 | ||
4331 | static int | |
4332 | encode_coding_big5 (coding) | |
4333 | struct coding_system *coding; | |
4334 | { | |
4335 | int multibytep = coding->dst_multibyte; | |
4336 | int *charbuf = coding->charbuf; | |
4337 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4338 | unsigned char *dst = coding->destination + coding->produced; | |
4339 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4340 | int safe_room = 4; | |
4341 | int produced_chars = 0; | |
24a73b0a | 4342 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4343 | int ascii_compatible; |
4344 | struct charset *charset_roman, *charset_big5; | |
4345 | int c; | |
4346 | ||
24a73b0a | 4347 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4348 | val = charset_list; |
4349 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4350 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4351 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
4352 | ||
4353 | while (charbuf < charbuf_end) | |
4354 | { | |
4355 | ASSURE_DESTINATION (safe_room); | |
4356 | c = *charbuf++; | |
4357 | /* Now encode the character C. */ | |
4358 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
4359 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4360 | else if (CHAR_BYTE8_P (c)) |
4361 | { | |
4362 | c = CHAR_TO_BYTE8 (c); | |
4363 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
4364 | } |
4365 | else | |
4366 | { | |
df7492f9 KH |
4367 | unsigned code; |
4368 | struct charset *charset = char_charset (c, charset_list, &code); | |
4369 | ||
4370 | if (! charset) | |
b73bfc1c | 4371 | { |
41cbe562 | 4372 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4373 | { |
41cbe562 KH |
4374 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4375 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4376 | } |
41cbe562 | 4377 | else |
0eecad43 | 4378 | { |
41cbe562 KH |
4379 | c = coding->default_char; |
4380 | charset = char_charset (c, charset_list, &code); | |
0eecad43 | 4381 | } |
4ed46869 | 4382 | } |
df7492f9 KH |
4383 | if (code == CHARSET_INVALID_CODE (charset)) |
4384 | abort (); | |
4385 | if (charset == charset_big5) | |
b73bfc1c | 4386 | { |
df7492f9 KH |
4387 | int c1, c2; |
4388 | ||
4389 | c1 = code >> 8, c2 = code & 0xFF; | |
4390 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 4391 | } |
df7492f9 KH |
4392 | else |
4393 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 4394 | } |
4ed46869 | 4395 | } |
065e3595 | 4396 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4397 | coding->produced_char += produced_chars; |
4398 | coding->produced = dst - coding->destination; | |
4399 | return 0; | |
4ed46869 KH |
4400 | } |
4401 | ||
4402 | \f | |
df7492f9 | 4403 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
4404 | |
4405 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4406 | Check if a text is encoded in a coding system of which | |
4407 | encoder/decoder are written in CCL program. If it is, return | |
df7492f9 | 4408 | CATEGORY_MASK_CCL, else return 0. */ |
1397dc18 | 4409 | |
0a28aafb | 4410 | static int |
ff0dacd7 | 4411 | detect_coding_ccl (coding, detect_info) |
df7492f9 | 4412 | struct coding_system *coding; |
ff0dacd7 | 4413 | struct coding_detection_info *detect_info; |
1397dc18 | 4414 | { |
065e3595 | 4415 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4416 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4417 | int multibytep = coding->src_multibyte; |
4418 | int consumed_chars = 0; | |
4419 | int found = 0; | |
0e219d54 | 4420 | unsigned char *valids; |
df7492f9 KH |
4421 | int head_ascii = coding->head_ascii; |
4422 | Lisp_Object attrs; | |
4423 | ||
ff0dacd7 KH |
4424 | detect_info->checked |= CATEGORY_MASK_CCL; |
4425 | ||
df7492f9 | 4426 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 4427 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
4428 | attrs = CODING_ID_ATTRS (coding->id); |
4429 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4430 | src += head_ascii; | |
1397dc18 | 4431 | |
b73bfc1c | 4432 | while (1) |
1397dc18 | 4433 | { |
df7492f9 | 4434 | int c; |
065e3595 KH |
4435 | |
4436 | src_base = src; | |
df7492f9 | 4437 | ONE_MORE_BYTE (c); |
065e3595 | 4438 | if (c < 0 || ! valids[c]) |
df7492f9 | 4439 | break; |
ff0dacd7 KH |
4440 | if ((valids[c] > 1)) |
4441 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 4442 | } |
ff0dacd7 | 4443 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
4444 | return 0; |
4445 | ||
4446 | no_more_source: | |
ff0dacd7 KH |
4447 | detect_info->found |= found; |
4448 | return 1; | |
df7492f9 KH |
4449 | } |
4450 | ||
4451 | static void | |
4452 | decode_coding_ccl (coding) | |
4453 | struct coding_system *coding; | |
4454 | { | |
7c78e542 | 4455 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 4456 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
4457 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4458 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
4459 | int consumed_chars = 0; |
4460 | int multibytep = coding->src_multibyte; | |
4461 | struct ccl_program ccl; | |
4462 | int source_charbuf[1024]; | |
4463 | int source_byteidx[1024]; | |
24a73b0a | 4464 | Lisp_Object attrs, charset_list; |
df7492f9 | 4465 | |
24a73b0a | 4466 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4467 | setup_ccl_program (&ccl, CODING_CCL_DECODER (coding)); |
4468 | ||
4469 | while (src < src_end) | |
4470 | { | |
7c78e542 | 4471 | const unsigned char *p = src; |
df7492f9 KH |
4472 | int *source, *source_end; |
4473 | int i = 0; | |
4474 | ||
4475 | if (multibytep) | |
4476 | while (i < 1024 && p < src_end) | |
4477 | { | |
4478 | source_byteidx[i] = p - src; | |
4479 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
4480 | } | |
4481 | else | |
4482 | while (i < 1024 && p < src_end) | |
4483 | source_charbuf[i++] = *p++; | |
8f924df7 | 4484 | |
df7492f9 KH |
4485 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
4486 | ccl.last_block = 1; | |
4487 | ||
4488 | source = source_charbuf; | |
4489 | source_end = source + i; | |
4490 | while (source < source_end) | |
4491 | { | |
4492 | ccl_driver (&ccl, source, charbuf, | |
8dcbea82 KH |
4493 | source_end - source, charbuf_end - charbuf, |
4494 | charset_list); | |
df7492f9 KH |
4495 | source += ccl.consumed; |
4496 | charbuf += ccl.produced; | |
4497 | if (ccl.status != CCL_STAT_SUSPEND_BY_DST) | |
4498 | break; | |
4499 | } | |
4500 | if (source < source_end) | |
4501 | src += source_byteidx[source - source_charbuf]; | |
4502 | else | |
4503 | src = p; | |
4504 | consumed_chars += source - source_charbuf; | |
4505 | ||
4506 | if (ccl.status != CCL_STAT_SUSPEND_BY_SRC | |
4507 | && ccl.status != CODING_RESULT_INSUFFICIENT_SRC) | |
4508 | break; | |
4509 | } | |
4510 | ||
4511 | switch (ccl.status) | |
4512 | { | |
4513 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4514 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4515 | break; |
4516 | case CCL_STAT_SUSPEND_BY_DST: | |
4517 | break; | |
4518 | case CCL_STAT_QUIT: | |
4519 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4520 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4521 | break; |
4522 | default: | |
065e3595 | 4523 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4524 | break; |
4525 | } | |
4526 | coding->consumed_char += consumed_chars; | |
4527 | coding->consumed = src - coding->source; | |
4528 | coding->charbuf_used = charbuf - coding->charbuf; | |
4529 | } | |
4530 | ||
4531 | static int | |
4532 | encode_coding_ccl (coding) | |
4533 | struct coding_system *coding; | |
4534 | { | |
4535 | struct ccl_program ccl; | |
4536 | int multibytep = coding->dst_multibyte; | |
4537 | int *charbuf = coding->charbuf; | |
4538 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4539 | unsigned char *dst = coding->destination + coding->produced; | |
4540 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4541 | unsigned char *adjusted_dst_end = dst_end - 1; | |
4542 | int destination_charbuf[1024]; | |
4543 | int i, produced_chars = 0; | |
24a73b0a | 4544 | Lisp_Object attrs, charset_list; |
df7492f9 | 4545 | |
24a73b0a | 4546 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4547 | setup_ccl_program (&ccl, CODING_CCL_ENCODER (coding)); |
4548 | ||
4549 | ccl.last_block = coding->mode & CODING_MODE_LAST_BLOCK; | |
4550 | ccl.dst_multibyte = coding->dst_multibyte; | |
4551 | ||
4552 | while (charbuf < charbuf_end && dst < adjusted_dst_end) | |
4553 | { | |
4554 | int dst_bytes = dst_end - dst; | |
4555 | if (dst_bytes > 1024) | |
4556 | dst_bytes = 1024; | |
4557 | ||
4558 | ccl_driver (&ccl, charbuf, destination_charbuf, | |
8dcbea82 | 4559 | charbuf_end - charbuf, dst_bytes, charset_list); |
df7492f9 KH |
4560 | charbuf += ccl.consumed; |
4561 | if (multibytep) | |
4562 | for (i = 0; i < ccl.produced; i++) | |
4563 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); | |
4564 | else | |
4565 | { | |
4566 | for (i = 0; i < ccl.produced; i++) | |
4567 | *dst++ = destination_charbuf[i] & 0xFF; | |
4568 | produced_chars += ccl.produced; | |
4569 | } | |
4570 | } | |
4571 | ||
4572 | switch (ccl.status) | |
4573 | { | |
4574 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4575 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4576 | break; |
4577 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 4578 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
4579 | break; |
4580 | case CCL_STAT_QUIT: | |
4581 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4582 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4583 | break; |
4584 | default: | |
065e3595 | 4585 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 4586 | break; |
1397dc18 | 4587 | } |
df7492f9 KH |
4588 | |
4589 | coding->produced_char += produced_chars; | |
4590 | coding->produced = dst - coding->destination; | |
4591 | return 0; | |
1397dc18 KH |
4592 | } |
4593 | ||
df7492f9 | 4594 | |
1397dc18 | 4595 | \f |
df7492f9 | 4596 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 4597 | |
b73bfc1c | 4598 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 4599 | |
b73bfc1c | 4600 | static void |
df7492f9 | 4601 | decode_coding_raw_text (coding) |
4ed46869 | 4602 | struct coding_system *coding; |
4ed46869 | 4603 | { |
df7492f9 | 4604 | coding->chars_at_source = 1; |
2c78b7e1 KH |
4605 | coding->consumed_char = 0; |
4606 | coding->consumed = 0; | |
065e3595 | 4607 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 4608 | } |
4ed46869 | 4609 | |
df7492f9 KH |
4610 | static int |
4611 | encode_coding_raw_text (coding) | |
4612 | struct coding_system *coding; | |
4613 | { | |
4614 | int multibytep = coding->dst_multibyte; | |
4615 | int *charbuf = coding->charbuf; | |
4616 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
4617 | unsigned char *dst = coding->destination + coding->produced; | |
4618 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4619 | int produced_chars = 0; | |
b73bfc1c KH |
4620 | int c; |
4621 | ||
df7492f9 | 4622 | if (multibytep) |
b73bfc1c | 4623 | { |
df7492f9 | 4624 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 4625 | |
df7492f9 KH |
4626 | if (coding->src_multibyte) |
4627 | while (charbuf < charbuf_end) | |
4628 | { | |
4629 | ASSURE_DESTINATION (safe_room); | |
4630 | c = *charbuf++; | |
4631 | if (ASCII_CHAR_P (c)) | |
4632 | EMIT_ONE_ASCII_BYTE (c); | |
4633 | else if (CHAR_BYTE8_P (c)) | |
4634 | { | |
4635 | c = CHAR_TO_BYTE8 (c); | |
4636 | EMIT_ONE_BYTE (c); | |
4637 | } | |
4638 | else | |
4639 | { | |
4640 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 4641 | |
df7492f9 KH |
4642 | CHAR_STRING_ADVANCE (c, p1); |
4643 | while (p0 < p1) | |
9d123124 KH |
4644 | { |
4645 | EMIT_ONE_BYTE (*p0); | |
4646 | p0++; | |
4647 | } | |
df7492f9 KH |
4648 | } |
4649 | } | |
b73bfc1c | 4650 | else |
df7492f9 KH |
4651 | while (charbuf < charbuf_end) |
4652 | { | |
4653 | ASSURE_DESTINATION (safe_room); | |
4654 | c = *charbuf++; | |
4655 | EMIT_ONE_BYTE (c); | |
4656 | } | |
4657 | } | |
4658 | else | |
4ed46869 | 4659 | { |
df7492f9 | 4660 | if (coding->src_multibyte) |
d46c5b12 | 4661 | { |
df7492f9 KH |
4662 | int safe_room = MAX_MULTIBYTE_LENGTH; |
4663 | ||
4664 | while (charbuf < charbuf_end) | |
d46c5b12 | 4665 | { |
df7492f9 KH |
4666 | ASSURE_DESTINATION (safe_room); |
4667 | c = *charbuf++; | |
4668 | if (ASCII_CHAR_P (c)) | |
4669 | *dst++ = c; | |
4670 | else if (CHAR_BYTE8_P (c)) | |
4671 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 4672 | else |
df7492f9 KH |
4673 | CHAR_STRING_ADVANCE (c, dst); |
4674 | produced_chars++; | |
d46c5b12 KH |
4675 | } |
4676 | } | |
df7492f9 KH |
4677 | else |
4678 | { | |
4679 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
4680 | while (charbuf < charbuf_end && dst < dst_end) | |
4681 | *dst++ = *charbuf++; | |
4682 | produced_chars = dst - (coding->destination + coding->dst_bytes); | |
8f924df7 | 4683 | } |
4ed46869 | 4684 | } |
065e3595 | 4685 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4686 | coding->produced_char += produced_chars; |
4687 | coding->produced = dst - coding->destination; | |
4688 | return 0; | |
4ed46869 KH |
4689 | } |
4690 | ||
ff0dacd7 KH |
4691 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
4692 | Check if a text is encoded in a charset-based coding system. If it | |
4693 | is, return 1, else return 0. */ | |
4694 | ||
0a28aafb | 4695 | static int |
ff0dacd7 | 4696 | detect_coding_charset (coding, detect_info) |
df7492f9 | 4697 | struct coding_system *coding; |
ff0dacd7 | 4698 | struct coding_detection_info *detect_info; |
1397dc18 | 4699 | { |
065e3595 | 4700 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4701 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4702 | int multibytep = coding->src_multibyte; |
4703 | int consumed_chars = 0; | |
4704 | Lisp_Object attrs, valids; | |
584948ac | 4705 | int found = 0; |
1397dc18 | 4706 | |
ff0dacd7 KH |
4707 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
4708 | ||
df7492f9 KH |
4709 | coding = &coding_categories[coding_category_charset]; |
4710 | attrs = CODING_ID_ATTRS (coding->id); | |
4711 | valids = AREF (attrs, coding_attr_charset_valids); | |
4712 | ||
4713 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4714 | src += coding->head_ascii; | |
1397dc18 | 4715 | |
b73bfc1c | 4716 | while (1) |
1397dc18 | 4717 | { |
df7492f9 | 4718 | int c; |
1397dc18 | 4719 | |
065e3595 | 4720 | src_base = src; |
df7492f9 | 4721 | ONE_MORE_BYTE (c); |
065e3595 KH |
4722 | if (c < 0) |
4723 | continue; | |
df7492f9 KH |
4724 | if (NILP (AREF (valids, c))) |
4725 | break; | |
584948ac | 4726 | if (c >= 0x80) |
ff0dacd7 | 4727 | found = CATEGORY_MASK_CHARSET; |
df7492f9 | 4728 | } |
ff0dacd7 | 4729 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 4730 | return 0; |
4ed46869 | 4731 | |
df7492f9 | 4732 | no_more_source: |
ff0dacd7 KH |
4733 | detect_info->found |= found; |
4734 | return 1; | |
df7492f9 | 4735 | } |
b73bfc1c | 4736 | |
b73bfc1c | 4737 | static void |
df7492f9 | 4738 | decode_coding_charset (coding) |
4ed46869 | 4739 | struct coding_system *coding; |
4ed46869 | 4740 | { |
8f924df7 KH |
4741 | const unsigned char *src = coding->source + coding->consumed; |
4742 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4743 | const unsigned char *src_base; | |
69a80ea3 KH |
4744 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4745 | int *charbuf_end | |
4746 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4747 | int consumed_chars = 0, consumed_chars_base; |
4748 | int multibytep = coding->src_multibyte; | |
24a73b0a | 4749 | Lisp_Object attrs, charset_list, valids; |
ff0dacd7 KH |
4750 | int char_offset = coding->produced_char; |
4751 | int last_offset = char_offset; | |
4752 | int last_id = charset_ascii; | |
df7492f9 | 4753 | |
24a73b0a | 4754 | CODING_GET_INFO (coding, attrs, charset_list); |
4eb6d3f1 | 4755 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 4756 | |
df7492f9 | 4757 | while (1) |
4ed46869 | 4758 | { |
4eb6d3f1 | 4759 | int c; |
24a73b0a KH |
4760 | Lisp_Object val; |
4761 | struct charset *charset; | |
4762 | int dim; | |
4763 | int len = 1; | |
4764 | unsigned code; | |
df7492f9 KH |
4765 | |
4766 | src_base = src; | |
4767 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 4768 | |
df7492f9 KH |
4769 | if (charbuf >= charbuf_end) |
4770 | break; | |
4771 | ||
4eb6d3f1 | 4772 | ONE_MORE_BYTE (c); |
065e3595 KH |
4773 | if (c < 0) |
4774 | goto invalid_code; | |
24a73b0a KH |
4775 | code = c; |
4776 | ||
4777 | val = AREF (valids, c); | |
4778 | if (NILP (val)) | |
4779 | goto invalid_code; | |
4780 | if (INTEGERP (val)) | |
d46c5b12 | 4781 | { |
24a73b0a KH |
4782 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
4783 | dim = CHARSET_DIMENSION (charset); | |
4784 | while (len < dim) | |
b73bfc1c | 4785 | { |
24a73b0a KH |
4786 | ONE_MORE_BYTE (c); |
4787 | code = (code << 8) | c; | |
4788 | len++; | |
b73bfc1c | 4789 | } |
24a73b0a KH |
4790 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
4791 | charset, code, c); | |
d46c5b12 | 4792 | } |
df7492f9 | 4793 | else |
d46c5b12 | 4794 | { |
24a73b0a KH |
4795 | /* VAL is a list of charset IDs. It is assured that the |
4796 | list is sorted by charset dimensions (smaller one | |
4797 | comes first). */ | |
4798 | while (CONSP (val)) | |
4eb6d3f1 | 4799 | { |
24a73b0a | 4800 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 4801 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 4802 | while (len < dim) |
4eb6d3f1 | 4803 | { |
acb2a965 KH |
4804 | ONE_MORE_BYTE (c); |
4805 | code = (code << 8) | c; | |
f9d71dcd | 4806 | len++; |
4eb6d3f1 | 4807 | } |
24a73b0a KH |
4808 | CODING_DECODE_CHAR (coding, src, src_base, |
4809 | src_end, charset, code, c); | |
4810 | if (c >= 0) | |
4811 | break; | |
4812 | val = XCDR (val); | |
ff0dacd7 | 4813 | } |
d46c5b12 | 4814 | } |
24a73b0a KH |
4815 | if (c < 0) |
4816 | goto invalid_code; | |
4817 | if (charset->id != charset_ascii | |
4818 | && last_id != charset->id) | |
4819 | { | |
4820 | if (last_id != charset_ascii) | |
69a80ea3 | 4821 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4822 | last_id = charset->id; |
4823 | last_offset = char_offset; | |
4824 | } | |
4825 | ||
df7492f9 | 4826 | *charbuf++ = c; |
ff0dacd7 | 4827 | char_offset++; |
df7492f9 KH |
4828 | continue; |
4829 | ||
4830 | invalid_code: | |
4831 | src = src_base; | |
4832 | consumed_chars = consumed_chars_base; | |
4833 | ONE_MORE_BYTE (c); | |
065e3595 | 4834 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4835 | char_offset++; |
df7492f9 | 4836 | coding->errors++; |
4ed46869 KH |
4837 | } |
4838 | ||
df7492f9 | 4839 | no_more_source: |
ff0dacd7 | 4840 | if (last_id != charset_ascii) |
69a80ea3 | 4841 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4842 | coding->consumed_char += consumed_chars_base; |
4843 | coding->consumed = src_base - coding->source; | |
4844 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4845 | } |
4846 | ||
df7492f9 KH |
4847 | static int |
4848 | encode_coding_charset (coding) | |
4ed46869 | 4849 | struct coding_system *coding; |
4ed46869 | 4850 | { |
df7492f9 KH |
4851 | int multibytep = coding->dst_multibyte; |
4852 | int *charbuf = coding->charbuf; | |
4853 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4854 | unsigned char *dst = coding->destination + coding->produced; | |
4855 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4856 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
4857 | int produced_chars = 0; | |
24a73b0a | 4858 | Lisp_Object attrs, charset_list; |
df7492f9 | 4859 | int ascii_compatible; |
b73bfc1c | 4860 | int c; |
b73bfc1c | 4861 | |
24a73b0a | 4862 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 4863 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 4864 | |
df7492f9 | 4865 | while (charbuf < charbuf_end) |
4ed46869 | 4866 | { |
4eb6d3f1 | 4867 | struct charset *charset; |
df7492f9 | 4868 | unsigned code; |
8f924df7 | 4869 | |
df7492f9 KH |
4870 | ASSURE_DESTINATION (safe_room); |
4871 | c = *charbuf++; | |
4872 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
4873 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 4874 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 4875 | { |
16eafb5d KH |
4876 | c = CHAR_TO_BYTE8 (c); |
4877 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 4878 | } |
d46c5b12 | 4879 | else |
b73bfc1c | 4880 | { |
4eb6d3f1 KH |
4881 | charset = char_charset (c, charset_list, &code); |
4882 | if (charset) | |
4883 | { | |
4884 | if (CHARSET_DIMENSION (charset) == 1) | |
4885 | EMIT_ONE_BYTE (code); | |
4886 | else if (CHARSET_DIMENSION (charset) == 2) | |
4887 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
4888 | else if (CHARSET_DIMENSION (charset) == 3) | |
4889 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
4890 | else | |
4891 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
4892 | (code >> 8) & 0xFF, code & 0xFF); | |
4893 | } | |
4894 | else | |
41cbe562 KH |
4895 | { |
4896 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
4897 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4898 | else | |
4899 | c = coding->default_char; | |
4900 | EMIT_ONE_BYTE (c); | |
4901 | } | |
4ed46869 | 4902 | } |
4ed46869 KH |
4903 | } |
4904 | ||
065e3595 | 4905 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4906 | coding->produced_char += produced_chars; |
4907 | coding->produced = dst - coding->destination; | |
4908 | return 0; | |
4ed46869 KH |
4909 | } |
4910 | ||
4911 | \f | |
1397dc18 | 4912 | /*** 7. C library functions ***/ |
4ed46869 | 4913 | |
df7492f9 KH |
4914 | /* Setup coding context CODING from information about CODING_SYSTEM. |
4915 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
4916 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 4917 | |
ec6d2bb8 | 4918 | void |
e0e989f6 KH |
4919 | setup_coding_system (coding_system, coding) |
4920 | Lisp_Object coding_system; | |
4ed46869 KH |
4921 | struct coding_system *coding; |
4922 | { | |
df7492f9 KH |
4923 | Lisp_Object attrs; |
4924 | Lisp_Object eol_type; | |
4925 | Lisp_Object coding_type; | |
4608c386 | 4926 | Lisp_Object val; |
4ed46869 | 4927 | |
df7492f9 | 4928 | if (NILP (coding_system)) |
ae6f73fa | 4929 | coding_system = Qundecided; |
c07c8e12 | 4930 | |
df7492f9 | 4931 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 4932 | |
df7492f9 KH |
4933 | attrs = CODING_ID_ATTRS (coding->id); |
4934 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
1f5dbf34 | 4935 | |
df7492f9 KH |
4936 | coding->mode = 0; |
4937 | coding->head_ascii = -1; | |
4938 | coding->common_flags | |
4939 | = (VECTORP (eol_type) ? CODING_REQUIRE_DETECTION_MASK : 0); | |
5e5c78be KH |
4940 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
4941 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
4942 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
4943 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
4944 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
4945 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 4946 | |
df7492f9 | 4947 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 KH |
4948 | coding->max_charset_id = SCHARS (val) - 1; |
4949 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 | 4950 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
4608c386 | 4951 | |
df7492f9 KH |
4952 | coding_type = CODING_ATTR_TYPE (attrs); |
4953 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 4954 | { |
df7492f9 KH |
4955 | coding->detector = NULL; |
4956 | coding->decoder = decode_coding_raw_text; | |
4957 | coding->encoder = encode_coding_raw_text; | |
4958 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 4959 | } |
df7492f9 | 4960 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 4961 | { |
df7492f9 KH |
4962 | int i; |
4963 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
4964 | ||
4965 | /* Invoke graphic register 0 to plane 0. */ | |
4966 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
4967 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
4968 | CODING_ISO_INVOCATION (coding, 1) | |
4969 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
4970 | /* Setup the initial status of designation. */ | |
4971 | for (i = 0; i < 4; i++) | |
4972 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
4973 | /* Not single shifting initially. */ | |
4974 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
4975 | /* Beginning of buffer should also be regarded as bol. */ | |
4976 | CODING_ISO_BOL (coding) = 1; | |
4977 | coding->detector = detect_coding_iso_2022; | |
4978 | coding->decoder = decode_coding_iso_2022; | |
4979 | coding->encoder = encode_coding_iso_2022; | |
4980 | if (flags & CODING_ISO_FLAG_SAFE) | |
4981 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 4982 | coding->common_flags |
df7492f9 KH |
4983 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
4984 | | CODING_REQUIRE_FLUSHING_MASK); | |
4985 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
4986 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
4987 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
4988 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
4989 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
4990 | { | |
4991 | setup_iso_safe_charsets (attrs); | |
4992 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
4993 | coding->max_charset_id = SCHARS (val) - 1; |
4994 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
4995 | } |
4996 | CODING_ISO_FLAGS (coding) = flags; | |
d46c5b12 | 4997 | } |
df7492f9 | 4998 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 4999 | { |
df7492f9 KH |
5000 | coding->detector = detect_coding_charset; |
5001 | coding->decoder = decode_coding_charset; | |
5002 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5003 | coding->common_flags |
df7492f9 | 5004 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5005 | } |
df7492f9 | 5006 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5007 | { |
df7492f9 KH |
5008 | coding->detector = detect_coding_utf_8; |
5009 | coding->decoder = decode_coding_utf_8; | |
5010 | coding->encoder = encode_coding_utf_8; | |
5011 | coding->common_flags | |
5012 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
5013 | } | |
5014 | else if (EQ (coding_type, Qutf_16)) | |
5015 | { | |
5016 | val = AREF (attrs, coding_attr_utf_16_bom); | |
5017 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_16_detect_bom | |
5018 | : EQ (val, Qt) ? utf_16_with_bom | |
5019 | : utf_16_without_bom); | |
5020 | val = AREF (attrs, coding_attr_utf_16_endian); | |
b49a1807 | 5021 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5022 | : utf_16_little_endian); |
e19c3639 | 5023 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5024 | coding->detector = detect_coding_utf_16; |
5025 | coding->decoder = decode_coding_utf_16; | |
5026 | coding->encoder = encode_coding_utf_16; | |
5027 | coding->common_flags | |
5028 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
b49a1807 KH |
5029 | if (CODING_UTF_16_BOM (coding) == utf_16_detect_bom) |
5030 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5031 | } |
df7492f9 | 5032 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5033 | { |
df7492f9 KH |
5034 | coding->detector = detect_coding_ccl; |
5035 | coding->decoder = decode_coding_ccl; | |
5036 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5037 | coding->common_flags |
df7492f9 KH |
5038 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5039 | | CODING_REQUIRE_FLUSHING_MASK); | |
5040 | } | |
5041 | else if (EQ (coding_type, Qemacs_mule)) | |
5042 | { | |
5043 | coding->detector = detect_coding_emacs_mule; | |
5044 | coding->decoder = decode_coding_emacs_mule; | |
5045 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5046 | coding->common_flags |
df7492f9 KH |
5047 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5048 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
5049 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5050 | { | |
5051 | Lisp_Object tail, safe_charsets; | |
5052 | int max_charset_id = 0; | |
5053 | ||
5054 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5055 | tail = XCDR (tail)) | |
5056 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5057 | max_charset_id = XFASTINT (XCAR (tail)); | |
5058 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), | |
5059 | make_number (255)); | |
5060 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5061 | tail = XCDR (tail)) | |
8f924df7 | 5062 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5063 | coding->max_charset_id = max_charset_id; |
8f924df7 | 5064 | coding->safe_charsets = (char *) SDATA (safe_charsets); |
df7492f9 KH |
5065 | } |
5066 | } | |
5067 | else if (EQ (coding_type, Qshift_jis)) | |
5068 | { | |
5069 | coding->detector = detect_coding_sjis; | |
5070 | coding->decoder = decode_coding_sjis; | |
5071 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5072 | coding->common_flags |
df7492f9 KH |
5073 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5074 | } | |
5075 | else if (EQ (coding_type, Qbig5)) | |
5076 | { | |
5077 | coding->detector = detect_coding_big5; | |
5078 | coding->decoder = decode_coding_big5; | |
5079 | coding->encoder = encode_coding_big5; | |
c952af22 | 5080 | coding->common_flags |
df7492f9 KH |
5081 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5082 | } | |
5083 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5084 | { |
df7492f9 KH |
5085 | coding->detector = NULL; |
5086 | coding->decoder = decode_coding_raw_text; | |
5087 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5088 | if (! EQ (eol_type, Qunix)) |
5089 | { | |
5090 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5091 | if (! VECTORP (eol_type)) | |
5092 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5093 | } | |
5094 | ||
4ed46869 | 5095 | } |
4ed46869 | 5096 | |
df7492f9 | 5097 | return; |
4ed46869 KH |
5098 | } |
5099 | ||
0ff61e78 KH |
5100 | /* Return a list of charsets supported by CODING. */ |
5101 | ||
5102 | Lisp_Object | |
5103 | coding_charset_list (coding) | |
5104 | struct coding_system *coding; | |
5105 | { | |
35befdaa | 5106 | Lisp_Object attrs, charset_list; |
0ff61e78 KH |
5107 | |
5108 | CODING_GET_INFO (coding, attrs, charset_list); | |
5109 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5110 | { | |
5111 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5112 | ||
5113 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5114 | charset_list = Viso_2022_charset_list; | |
5115 | } | |
5116 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5117 | { | |
5118 | charset_list = Vemacs_mule_charset_list; | |
5119 | } | |
5120 | return charset_list; | |
5121 | } | |
5122 | ||
5123 | ||
df7492f9 KH |
5124 | /* Return raw-text or one of its subsidiaries that has the same |
5125 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5126 | |
df7492f9 KH |
5127 | Lisp_Object |
5128 | raw_text_coding_system (coding_system) | |
5129 | Lisp_Object coding_system; | |
ec6d2bb8 | 5130 | { |
0be8721c | 5131 | Lisp_Object spec, attrs; |
df7492f9 | 5132 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5133 | |
d3e4cb56 KH |
5134 | if (NILP (coding_system)) |
5135 | return Qraw_text; | |
df7492f9 KH |
5136 | spec = CODING_SYSTEM_SPEC (coding_system); |
5137 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5138 | |
df7492f9 KH |
5139 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5140 | return coding_system; | |
ec6d2bb8 | 5141 | |
df7492f9 KH |
5142 | eol_type = AREF (spec, 2); |
5143 | if (VECTORP (eol_type)) | |
5144 | return Qraw_text; | |
5145 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5146 | raw_text_eol_type = AREF (spec, 2); | |
5147 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5148 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5149 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5150 | } |
5151 | ||
54f78171 | 5152 | |
df7492f9 KH |
5153 | /* If CODING_SYSTEM doesn't specify end-of-line format but PARENT |
5154 | does, return one of the subsidiary that has the same eol-spec as | |
5155 | PARENT. Otherwise, return CODING_SYSTEM. */ | |
5156 | ||
5157 | Lisp_Object | |
5158 | coding_inherit_eol_type (coding_system, parent) | |
b74e4686 | 5159 | Lisp_Object coding_system, parent; |
54f78171 | 5160 | { |
3e139625 | 5161 | Lisp_Object spec, eol_type; |
54f78171 | 5162 | |
d3e4cb56 KH |
5163 | if (NILP (coding_system)) |
5164 | coding_system = Qraw_text; | |
df7492f9 | 5165 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5166 | eol_type = AREF (spec, 2); |
d3e4cb56 KH |
5167 | if (VECTORP (eol_type) |
5168 | && ! NILP (parent)) | |
df7492f9 KH |
5169 | { |
5170 | Lisp_Object parent_spec; | |
df7492f9 KH |
5171 | Lisp_Object parent_eol_type; |
5172 | ||
5173 | parent_spec | |
5174 | = CODING_SYSTEM_SPEC (buffer_defaults.buffer_file_coding_system); | |
5175 | parent_eol_type = AREF (parent_spec, 2); | |
5176 | if (EQ (parent_eol_type, Qunix)) | |
5177 | coding_system = AREF (eol_type, 0); | |
5178 | else if (EQ (parent_eol_type, Qdos)) | |
5179 | coding_system = AREF (eol_type, 1); | |
5180 | else if (EQ (parent_eol_type, Qmac)) | |
5181 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5182 | } |
df7492f9 | 5183 | return coding_system; |
54f78171 KH |
5184 | } |
5185 | ||
4ed46869 KH |
5186 | /* Emacs has a mechanism to automatically detect a coding system if it |
5187 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
5188 | it's impossible to distinguish some coding systems accurately | |
5189 | because they use the same range of codes. So, at first, coding | |
5190 | systems are categorized into 7, those are: | |
5191 | ||
0ef69138 | 5192 | o coding-category-emacs-mule |
4ed46869 KH |
5193 | |
5194 | The category for a coding system which has the same code range | |
5195 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 5196 | symbol) `emacs-mule' by default. |
4ed46869 KH |
5197 | |
5198 | o coding-category-sjis | |
5199 | ||
5200 | The category for a coding system which has the same code range | |
5201 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 5202 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
5203 | |
5204 | o coding-category-iso-7 | |
5205 | ||
5206 | The category for a coding system which has the same code range | |
7717c392 | 5207 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
5208 | shift and single shift functions. This can encode/decode all |
5209 | charsets. Assigned the coding-system (Lisp symbol) | |
5210 | `iso-2022-7bit' by default. | |
5211 | ||
5212 | o coding-category-iso-7-tight | |
5213 | ||
5214 | Same as coding-category-iso-7 except that this can | |
5215 | encode/decode only the specified charsets. | |
4ed46869 KH |
5216 | |
5217 | o coding-category-iso-8-1 | |
5218 | ||
5219 | The category for a coding system which has the same code range | |
5220 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5221 | for DIMENSION1 charset. This doesn't use any locking shift |
5222 | and single shift functions. Assigned the coding-system (Lisp | |
5223 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
5224 | |
5225 | o coding-category-iso-8-2 | |
5226 | ||
5227 | The category for a coding system which has the same code range | |
5228 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5229 | for DIMENSION2 charset. This doesn't use any locking shift |
5230 | and single shift functions. Assigned the coding-system (Lisp | |
5231 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 5232 | |
7717c392 | 5233 | o coding-category-iso-7-else |
4ed46869 KH |
5234 | |
5235 | The category for a coding system which has the same code range | |
df7492f9 | 5236 | as ISO2022 of 7-bit environemnt but uses locking shift or |
7717c392 KH |
5237 | single shift functions. Assigned the coding-system (Lisp |
5238 | symbol) `iso-2022-7bit-lock' by default. | |
5239 | ||
5240 | o coding-category-iso-8-else | |
5241 | ||
5242 | The category for a coding system which has the same code range | |
df7492f9 | 5243 | as ISO2022 of 8-bit environemnt but uses locking shift or |
7717c392 KH |
5244 | single shift functions. Assigned the coding-system (Lisp |
5245 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
5246 | |
5247 | o coding-category-big5 | |
5248 | ||
5249 | The category for a coding system which has the same code range | |
5250 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5251 | `cn-big5' by default. |
4ed46869 | 5252 | |
fa42c37f KH |
5253 | o coding-category-utf-8 |
5254 | ||
5255 | The category for a coding system which has the same code range | |
6e76ae91 | 5256 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
5257 | symbol) `utf-8' by default. |
5258 | ||
5259 | o coding-category-utf-16-be | |
5260 | ||
5261 | The category for a coding system in which a text has an | |
5262 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
5263 | endian at the head. Assigned the coding-system (Lisp symbol) | |
5264 | `utf-16-be' by default. | |
5265 | ||
5266 | o coding-category-utf-16-le | |
5267 | ||
5268 | The category for a coding system in which a text has an | |
5269 | Unicode signature (cf. Unicode Standard) in the order of | |
5270 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
5271 | symbol) `utf-16-le' by default. | |
5272 | ||
1397dc18 KH |
5273 | o coding-category-ccl |
5274 | ||
5275 | The category for a coding system of which encoder/decoder is | |
5276 | written in CCL programs. The default value is nil, i.e., no | |
5277 | coding system is assigned. | |
5278 | ||
4ed46869 KH |
5279 | o coding-category-binary |
5280 | ||
5281 | The category for a coding system not categorized in any of the | |
5282 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5283 | `no-conversion' by default. |
4ed46869 KH |
5284 | |
5285 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 5286 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
5287 | What Emacs does actually is to detect a category of coding system. |
5288 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 5289 | decide only one possible category, it selects a category of the |
4ed46869 KH |
5290 | highest priority. Priorities of categories are also specified by a |
5291 | user in a Lisp variable `coding-category-list'. | |
5292 | ||
5293 | */ | |
5294 | ||
df7492f9 KH |
5295 | #define EOL_SEEN_NONE 0 |
5296 | #define EOL_SEEN_LF 1 | |
5297 | #define EOL_SEEN_CR 2 | |
5298 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 5299 | |
ff0dacd7 KH |
5300 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
5301 | SOURCE is encoded. If CATEGORY is one of | |
5302 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
5303 | two-byte, else they are encoded by one-byte. | |
5304 | ||
5305 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 5306 | |
bc4bc72a | 5307 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
5308 | |
5309 | static int | |
89528eb3 | 5310 | detect_eol (source, src_bytes, category) |
f6cbaf43 | 5311 | const unsigned char *source; |
df7492f9 | 5312 | EMACS_INT src_bytes; |
89528eb3 | 5313 | enum coding_category category; |
4ed46869 | 5314 | { |
f6cbaf43 | 5315 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 5316 | unsigned char c; |
df7492f9 KH |
5317 | int total = 0; |
5318 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 5319 | |
89528eb3 | 5320 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 5321 | { |
df7492f9 | 5322 | int msb, lsb; |
fa42c37f | 5323 | |
89528eb3 KH |
5324 | msb = category == (coding_category_utf_16_le |
5325 | | coding_category_utf_16_le_nosig); | |
df7492f9 | 5326 | lsb = 1 - msb; |
fa42c37f | 5327 | |
df7492f9 | 5328 | while (src + 1 < src_end) |
fa42c37f | 5329 | { |
df7492f9 KH |
5330 | c = src[lsb]; |
5331 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 5332 | { |
df7492f9 KH |
5333 | int this_eol; |
5334 | ||
5335 | if (c == '\n') | |
5336 | this_eol = EOL_SEEN_LF; | |
5337 | else if (src + 3 >= src_end | |
5338 | || src[msb + 2] != 0 | |
5339 | || src[lsb + 2] != '\n') | |
5340 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 5341 | else |
8f924df7 | 5342 | this_eol = EOL_SEEN_CRLF; |
df7492f9 KH |
5343 | |
5344 | if (eol_seen == EOL_SEEN_NONE) | |
5345 | /* This is the first end-of-line. */ | |
5346 | eol_seen = this_eol; | |
5347 | else if (eol_seen != this_eol) | |
fa42c37f | 5348 | { |
df7492f9 KH |
5349 | /* The found type is different from what found before. */ |
5350 | eol_seen = EOL_SEEN_LF; | |
5351 | break; | |
fa42c37f | 5352 | } |
df7492f9 KH |
5353 | if (++total == MAX_EOL_CHECK_COUNT) |
5354 | break; | |
fa42c37f | 5355 | } |
df7492f9 | 5356 | src += 2; |
fa42c37f | 5357 | } |
bcf26d6a | 5358 | } |
d46c5b12 | 5359 | else |
c4825358 | 5360 | { |
df7492f9 | 5361 | while (src < src_end) |
27901516 | 5362 | { |
df7492f9 KH |
5363 | c = *src++; |
5364 | if (c == '\n' || c == '\r') | |
5365 | { | |
5366 | int this_eol; | |
d46c5b12 | 5367 | |
df7492f9 KH |
5368 | if (c == '\n') |
5369 | this_eol = EOL_SEEN_LF; | |
5370 | else if (src >= src_end || *src != '\n') | |
5371 | this_eol = EOL_SEEN_CR; | |
5372 | else | |
5373 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 5374 | |
df7492f9 KH |
5375 | if (eol_seen == EOL_SEEN_NONE) |
5376 | /* This is the first end-of-line. */ | |
5377 | eol_seen = this_eol; | |
5378 | else if (eol_seen != this_eol) | |
5379 | { | |
5380 | /* The found type is different from what found before. */ | |
5381 | eol_seen = EOL_SEEN_LF; | |
5382 | break; | |
5383 | } | |
5384 | if (++total == MAX_EOL_CHECK_COUNT) | |
5385 | break; | |
5386 | } | |
5387 | } | |
73be902c | 5388 | } |
df7492f9 | 5389 | return eol_seen; |
73be902c KH |
5390 | } |
5391 | ||
df7492f9 | 5392 | |
24a73b0a | 5393 | static Lisp_Object |
df7492f9 KH |
5394 | adjust_coding_eol_type (coding, eol_seen) |
5395 | struct coding_system *coding; | |
5396 | int eol_seen; | |
73be902c | 5397 | { |
0be8721c | 5398 | Lisp_Object eol_type; |
8f924df7 | 5399 | |
df7492f9 KH |
5400 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
5401 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
5402 | { |
5403 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
5404 | eol_type = Qunix; | |
5405 | } | |
6f197c07 | 5406 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
5407 | { |
5408 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
5409 | eol_type = Qdos; | |
5410 | } | |
6f197c07 | 5411 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
5412 | { |
5413 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
5414 | eol_type = Qmac; | |
5415 | } | |
5416 | return eol_type; | |
d46c5b12 | 5417 | } |
4ed46869 | 5418 | |
df7492f9 KH |
5419 | /* Detect how a text specified in CODING is encoded. If a coding |
5420 | system is detected, update fields of CODING by the detected coding | |
5421 | system. */ | |
0a28aafb | 5422 | |
df7492f9 KH |
5423 | void |
5424 | detect_coding (coding) | |
d46c5b12 | 5425 | struct coding_system *coding; |
d46c5b12 | 5426 | { |
8f924df7 | 5427 | const unsigned char *src, *src_end; |
d46c5b12 | 5428 | |
df7492f9 KH |
5429 | coding->consumed = coding->consumed_char = 0; |
5430 | coding->produced = coding->produced_char = 0; | |
5431 | coding_set_source (coding); | |
1c3478b0 | 5432 | |
df7492f9 | 5433 | src_end = coding->source + coding->src_bytes; |
1c3478b0 | 5434 | |
df7492f9 KH |
5435 | /* If we have not yet decided the text encoding type, detect it |
5436 | now. */ | |
5437 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 5438 | { |
df7492f9 | 5439 | int c, i; |
6cb21a4f | 5440 | struct coding_detection_info detect_info; |
df7492f9 | 5441 | |
6cb21a4f | 5442 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
24a73b0a | 5443 | for (i = 0, src = coding->source; src < src_end; i++, src++) |
d46c5b12 | 5444 | { |
df7492f9 | 5445 | c = *src; |
6cb21a4f | 5446 | if (c & 0x80) |
df7492f9 | 5447 | break; |
6cb21a4f KH |
5448 | if (c < 0x20 |
5449 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
5450 | && ! inhibit_iso_escape_detection | |
5451 | && ! detect_info.checked) | |
5452 | { | |
5453 | coding->head_ascii = src - (coding->source + coding->consumed); | |
5454 | if (detect_coding_iso_2022 (coding, &detect_info)) | |
5455 | { | |
5456 | /* We have scanned the whole data. */ | |
5457 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
5458 | /* We didn't find an 8-bit code. */ | |
5459 | src = src_end; | |
5460 | break; | |
5461 | } | |
5462 | } | |
d46c5b12 | 5463 | } |
df7492f9 KH |
5464 | coding->head_ascii = src - (coding->source + coding->consumed); |
5465 | ||
3aef54f3 | 5466 | if (coding->head_ascii < coding->src_bytes |
6cb21a4f | 5467 | || detect_info.found) |
d46c5b12 | 5468 | { |
ff0dacd7 KH |
5469 | enum coding_category category; |
5470 | struct coding_system *this; | |
df7492f9 | 5471 | |
6cb21a4f KH |
5472 | if (coding->head_ascii == coding->src_bytes) |
5473 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
5474 | for (i = 0; i < coding_category_raw_text; i++) | |
5475 | { | |
5476 | category = coding_priorities[i]; | |
5477 | this = coding_categories + category; | |
5478 | if (detect_info.found & (1 << category)) | |
24a73b0a | 5479 | break; |
6cb21a4f KH |
5480 | } |
5481 | else | |
5482 | for (i = 0; i < coding_category_raw_text; i++) | |
5483 | { | |
5484 | category = coding_priorities[i]; | |
5485 | this = coding_categories + category; | |
5486 | if (this->id < 0) | |
5487 | { | |
5488 | /* No coding system of this category is defined. */ | |
5489 | detect_info.rejected |= (1 << category); | |
5490 | } | |
5491 | else if (category >= coding_category_raw_text) | |
5492 | continue; | |
5493 | else if (detect_info.checked & (1 << category)) | |
5494 | { | |
5495 | if (detect_info.found & (1 << category)) | |
5496 | break; | |
5497 | } | |
5498 | else if ((*(this->detector)) (coding, &detect_info) | |
5499 | && detect_info.found & (1 << category)) | |
5500 | { | |
5501 | if (category == coding_category_utf_16_auto) | |
5502 | { | |
5503 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
5504 | category = coding_category_utf_16_le; | |
5505 | else | |
5506 | category = coding_category_utf_16_be; | |
5507 | } | |
5508 | break; | |
5509 | } | |
5510 | } | |
5511 | ||
ff0dacd7 KH |
5512 | if (i < coding_category_raw_text) |
5513 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5514 | else if (detect_info.rejected == CATEGORY_MASK_ANY) | |
df7492f9 | 5515 | setup_coding_system (Qraw_text, coding); |
ff0dacd7 | 5516 | else if (detect_info.rejected) |
df7492f9 | 5517 | for (i = 0; i < coding_category_raw_text; i++) |
ff0dacd7 KH |
5518 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) |
5519 | { | |
5520 | this = coding_categories + coding_priorities[i]; | |
5521 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5522 | break; | |
5523 | } | |
d46c5b12 | 5524 | } |
b73bfc1c | 5525 | } |
24a73b0a KH |
5526 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
5527 | == coding_category_utf_16_auto) | |
b49a1807 KH |
5528 | { |
5529 | Lisp_Object coding_systems; | |
5530 | struct coding_detection_info detect_info; | |
5531 | ||
5532 | coding_systems | |
5533 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_16_bom); | |
5534 | detect_info.found = detect_info.rejected = 0; | |
5535 | if (CONSP (coding_systems) | |
24a73b0a | 5536 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
5537 | { |
5538 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
5539 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 5540 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
5541 | setup_coding_system (XCDR (coding_systems), coding); |
5542 | } | |
5543 | } | |
4ed46869 | 5544 | } |
4ed46869 | 5545 | |
d46c5b12 | 5546 | |
aaaf0b1e | 5547 | static void |
df7492f9 | 5548 | decode_eol (coding) |
aaaf0b1e | 5549 | struct coding_system *coding; |
aaaf0b1e | 5550 | { |
24a73b0a KH |
5551 | Lisp_Object eol_type; |
5552 | unsigned char *p, *pbeg, *pend; | |
5553 | ||
5554 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
5555 | if (EQ (eol_type, Qunix)) | |
5556 | return; | |
5557 | ||
5558 | if (NILP (coding->dst_object)) | |
5559 | pbeg = coding->destination; | |
5560 | else | |
5561 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
5562 | pend = pbeg + coding->produced; | |
5563 | ||
5564 | if (VECTORP (eol_type)) | |
aaaf0b1e | 5565 | { |
df7492f9 | 5566 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 5567 | |
24a73b0a | 5568 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 5569 | { |
df7492f9 KH |
5570 | if (*p == '\n') |
5571 | eol_seen |= EOL_SEEN_LF; | |
5572 | else if (*p == '\r') | |
aaaf0b1e | 5573 | { |
df7492f9 | 5574 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 5575 | { |
df7492f9 KH |
5576 | eol_seen |= EOL_SEEN_CRLF; |
5577 | p++; | |
aaaf0b1e | 5578 | } |
aaaf0b1e | 5579 | else |
df7492f9 | 5580 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 5581 | } |
aaaf0b1e | 5582 | } |
24a73b0a KH |
5583 | if (eol_seen != EOL_SEEN_NONE |
5584 | && eol_seen != EOL_SEEN_LF | |
5585 | && eol_seen != EOL_SEEN_CRLF | |
5586 | && eol_seen != EOL_SEEN_CR) | |
5587 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 5588 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 5589 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 5590 | } |
d46c5b12 | 5591 | |
24a73b0a | 5592 | if (EQ (eol_type, Qmac)) |
27901516 | 5593 | { |
24a73b0a | 5594 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
5595 | if (*p == '\r') |
5596 | *p = '\n'; | |
4ed46869 | 5597 | } |
24a73b0a | 5598 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 5599 | { |
24a73b0a | 5600 | int n = 0; |
b73bfc1c | 5601 | |
24a73b0a KH |
5602 | if (NILP (coding->dst_object)) |
5603 | { | |
5604 | for (p = pend - 2; p >= pbeg; p--) | |
5605 | if (*p == '\r') | |
5606 | { | |
5607 | safe_bcopy ((char *) (p + 1), (char *) p, pend-- - p - 1); | |
5608 | n++; | |
5609 | } | |
5610 | } | |
5611 | else | |
5612 | { | |
5613 | for (p = pend - 2; p >= pbeg; p--) | |
5614 | if (*p == '\r') | |
5615 | { | |
5616 | int pos_byte = coding->dst_pos_byte + (p - pbeg); | |
5617 | int pos = BYTE_TO_CHAR (pos_byte); | |
5618 | ||
5619 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
5620 | n++; | |
5621 | } | |
5622 | } | |
5623 | coding->produced -= n; | |
5624 | coding->produced_char -= n; | |
aaaf0b1e | 5625 | } |
4ed46869 KH |
5626 | } |
5627 | ||
7d64c6ad | 5628 | |
a6f87d34 KH |
5629 | /* Return a translation table (or list of them) from coding system |
5630 | attribute vector ATTRS for encoding (ENCODEP is nonzero) or | |
5631 | decoding (ENCODEP is zero). */ | |
7d64c6ad | 5632 | |
e6a54062 | 5633 | static Lisp_Object |
09ee6fdd KH |
5634 | get_translation_table (attrs, encodep, max_lookup) |
5635 | Lisp_Object attrs; | |
5636 | int encodep, *max_lookup; | |
7d64c6ad KH |
5637 | { |
5638 | Lisp_Object standard, translation_table; | |
09ee6fdd | 5639 | Lisp_Object val; |
7d64c6ad KH |
5640 | |
5641 | if (encodep) | |
5642 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
5643 | standard = Vstandard_translation_table_for_encode; | |
5644 | else | |
5645 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
5646 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 5647 | if (NILP (translation_table)) |
09ee6fdd KH |
5648 | translation_table = standard; |
5649 | else | |
a6f87d34 | 5650 | { |
09ee6fdd KH |
5651 | if (SYMBOLP (translation_table)) |
5652 | translation_table = Fget (translation_table, Qtranslation_table); | |
5653 | else if (CONSP (translation_table)) | |
5654 | { | |
5655 | translation_table = Fcopy_sequence (translation_table); | |
5656 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
5657 | if (SYMBOLP (XCAR (val))) | |
5658 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
5659 | } | |
5660 | if (CHAR_TABLE_P (standard)) | |
5661 | { | |
5662 | if (CONSP (translation_table)) | |
5663 | translation_table = nconc2 (translation_table, | |
5664 | Fcons (standard, Qnil)); | |
5665 | else | |
5666 | translation_table = Fcons (translation_table, | |
5667 | Fcons (standard, Qnil)); | |
5668 | } | |
a6f87d34 | 5669 | } |
2170c8f0 KH |
5670 | |
5671 | if (max_lookup) | |
09ee6fdd | 5672 | { |
2170c8f0 KH |
5673 | *max_lookup = 1; |
5674 | if (CHAR_TABLE_P (translation_table) | |
5675 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
5676 | { | |
5677 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
5678 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
5679 | *max_lookup = XFASTINT (val); | |
5680 | } | |
5681 | else if (CONSP (translation_table)) | |
5682 | { | |
5683 | Lisp_Object tail, val; | |
09ee6fdd | 5684 | |
2170c8f0 KH |
5685 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
5686 | if (CHAR_TABLE_P (XCAR (tail)) | |
5687 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
5688 | { | |
5689 | val = XCHAR_TABLE (XCAR (tail))->extras[1]; | |
5690 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
5691 | *max_lookup = XFASTINT (val); | |
5692 | } | |
5693 | } | |
a6f87d34 | 5694 | } |
7d64c6ad KH |
5695 | return translation_table; |
5696 | } | |
5697 | ||
09ee6fdd KH |
5698 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
5699 | do { \ | |
5700 | trans = Qnil; \ | |
5701 | if (CHAR_TABLE_P (table)) \ | |
5702 | { \ | |
5703 | trans = CHAR_TABLE_REF (table, c); \ | |
5704 | if (CHARACTERP (trans)) \ | |
5705 | c = XFASTINT (trans), trans = Qnil; \ | |
5706 | } \ | |
5707 | else if (CONSP (table)) \ | |
5708 | { \ | |
5709 | Lisp_Object tail; \ | |
5710 | \ | |
5711 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
5712 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
5713 | { \ | |
5714 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
5715 | if (CHARACTERP (trans)) \ | |
5716 | c = XFASTINT (trans), trans = Qnil; \ | |
5717 | else if (! NILP (trans)) \ | |
5718 | break; \ | |
5719 | } \ | |
5720 | } \ | |
e6a54062 KH |
5721 | } while (0) |
5722 | ||
7d64c6ad | 5723 | |
69a80ea3 KH |
5724 | static Lisp_Object |
5725 | get_translation (val, buf, buf_end, last_block, from_nchars, to_nchars) | |
5726 | Lisp_Object val; | |
5727 | int *buf, *buf_end; | |
5728 | int last_block; | |
5729 | int *from_nchars, *to_nchars; | |
5730 | { | |
433f7f87 KH |
5731 | /* VAL is TO or (([FROM-CHAR ...] . TO) ...) where TO is TO-CHAR or |
5732 | [TO-CHAR ...]. */ | |
69a80ea3 KH |
5733 | if (CONSP (val)) |
5734 | { | |
433f7f87 | 5735 | Lisp_Object from, tail; |
69a80ea3 KH |
5736 | int i, len; |
5737 | ||
433f7f87 | 5738 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
69a80ea3 | 5739 | { |
433f7f87 KH |
5740 | val = XCAR (tail); |
5741 | from = XCAR (val); | |
5742 | len = ASIZE (from); | |
5743 | for (i = 0; i < len; i++) | |
5744 | { | |
5745 | if (buf + i == buf_end) | |
5746 | { | |
5747 | if (! last_block) | |
5748 | return Qt; | |
5749 | break; | |
5750 | } | |
5751 | if (XINT (AREF (from, i)) != buf[i]) | |
5752 | break; | |
5753 | } | |
5754 | if (i == len) | |
5755 | { | |
5756 | val = XCDR (val); | |
5757 | *from_nchars = len; | |
5758 | break; | |
5759 | } | |
69a80ea3 | 5760 | } |
433f7f87 KH |
5761 | if (! CONSP (tail)) |
5762 | return Qnil; | |
69a80ea3 KH |
5763 | } |
5764 | if (VECTORP (val)) | |
5765 | *buf = XINT (AREF (val, 0)), *to_nchars = ASIZE (val); | |
5766 | else | |
5767 | *buf = XINT (val); | |
5768 | return val; | |
5769 | } | |
5770 | ||
5771 | ||
d46c5b12 | 5772 | static int |
69a80ea3 | 5773 | produce_chars (coding, translation_table, last_block) |
df7492f9 | 5774 | struct coding_system *coding; |
69a80ea3 KH |
5775 | Lisp_Object translation_table; |
5776 | int last_block; | |
4ed46869 | 5777 | { |
df7492f9 KH |
5778 | unsigned char *dst = coding->destination + coding->produced; |
5779 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5780 | int produced; | |
5781 | int produced_chars = 0; | |
69a80ea3 | 5782 | int carryover = 0; |
4ed46869 | 5783 | |
df7492f9 | 5784 | if (! coding->chars_at_source) |
4ed46869 | 5785 | { |
df7492f9 | 5786 | /* Characters are in coding->charbuf. */ |
fba4576f AS |
5787 | int *buf = coding->charbuf; |
5788 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 5789 | |
df7492f9 KH |
5790 | if (BUFFERP (coding->src_object) |
5791 | && EQ (coding->src_object, coding->dst_object)) | |
8f924df7 | 5792 | dst_end = ((unsigned char *) coding->source) + coding->consumed; |
4ed46869 | 5793 | |
df7492f9 | 5794 | while (buf < buf_end) |
4ed46869 | 5795 | { |
69a80ea3 | 5796 | int c = *buf, i; |
bc4bc72a | 5797 | |
df7492f9 KH |
5798 | if (c >= 0) |
5799 | { | |
69a80ea3 KH |
5800 | int from_nchars = 1, to_nchars = 1; |
5801 | Lisp_Object trans = Qnil; | |
5802 | ||
09ee6fdd | 5803 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 5804 | if (! NILP (trans)) |
69a80ea3 KH |
5805 | { |
5806 | trans = get_translation (trans, buf, buf_end, last_block, | |
5807 | &from_nchars, &to_nchars); | |
5808 | if (EQ (trans, Qt)) | |
5809 | break; | |
5810 | c = *buf; | |
5811 | } | |
5812 | ||
5813 | if (dst + MAX_MULTIBYTE_LENGTH * to_nchars > dst_end) | |
5814 | { | |
5815 | dst = alloc_destination (coding, | |
5816 | buf_end - buf | |
5817 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
5818 | dst); | |
5819 | dst_end = coding->destination + coding->dst_bytes; | |
5820 | } | |
5821 | ||
433f7f87 | 5822 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 5823 | { |
433f7f87 KH |
5824 | if (i > 0) |
5825 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
5826 | if (coding->dst_multibyte |
5827 | || ! CHAR_BYTE8_P (c)) | |
5828 | CHAR_STRING_ADVANCE (c, dst); | |
5829 | else | |
5830 | *dst++ = CHAR_TO_BYTE8 (c); | |
5831 | } | |
5832 | produced_chars += to_nchars; | |
5833 | *buf++ = to_nchars; | |
5834 | while (--from_nchars > 0) | |
5835 | *buf++ = 0; | |
d46c5b12 | 5836 | } |
df7492f9 | 5837 | else |
69a80ea3 KH |
5838 | /* This is an annotation datum. (-C) is the length. */ |
5839 | buf += -c; | |
4ed46869 | 5840 | } |
69a80ea3 | 5841 | carryover = buf_end - buf; |
4ed46869 | 5842 | } |
fa42c37f | 5843 | else |
fa42c37f | 5844 | { |
8f924df7 KH |
5845 | const unsigned char *src = coding->source; |
5846 | const unsigned char *src_end = src + coding->src_bytes; | |
df7492f9 | 5847 | Lisp_Object eol_type; |
fa42c37f | 5848 | |
df7492f9 | 5849 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
4ed46869 | 5850 | |
df7492f9 | 5851 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 5852 | { |
df7492f9 | 5853 | if (coding->src_multibyte) |
fa42c37f | 5854 | { |
71c81426 | 5855 | int multibytep = 1; |
df7492f9 | 5856 | int consumed_chars; |
d46c5b12 | 5857 | |
df7492f9 KH |
5858 | while (1) |
5859 | { | |
8f924df7 | 5860 | const unsigned char *src_base = src; |
df7492f9 | 5861 | int c; |
b73bfc1c | 5862 | |
df7492f9 KH |
5863 | ONE_MORE_BYTE (c); |
5864 | if (c == '\r') | |
5865 | { | |
5866 | if (EQ (eol_type, Qdos)) | |
5867 | { | |
98725083 KH |
5868 | if (src == src_end) |
5869 | { | |
065e3595 KH |
5870 | record_conversion_result |
5871 | (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
98725083 KH |
5872 | goto no_more_source; |
5873 | } | |
5874 | if (*src == '\n') | |
df7492f9 KH |
5875 | c = *src++; |
5876 | } | |
5877 | else if (EQ (eol_type, Qmac)) | |
5878 | c = '\n'; | |
5879 | } | |
5880 | if (dst == dst_end) | |
5881 | { | |
2c78b7e1 | 5882 | coding->consumed = src - coding->source; |
b73bfc1c | 5883 | |
2c78b7e1 | 5884 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5885 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5886 | if (dst == dst_end) |
5887 | { | |
5888 | dst = alloc_destination (coding, src_end - src + 1, | |
5889 | dst); | |
5890 | dst_end = coding->destination + coding->dst_bytes; | |
5891 | coding_set_source (coding); | |
5892 | src = coding->source + coding->consumed; | |
5893 | src_end = coding->source + coding->src_bytes; | |
5894 | } | |
df7492f9 KH |
5895 | } |
5896 | *dst++ = c; | |
5897 | produced_chars++; | |
5898 | } | |
5899 | no_more_source: | |
5900 | ; | |
fa42c37f KH |
5901 | } |
5902 | else | |
df7492f9 KH |
5903 | while (src < src_end) |
5904 | { | |
71c81426 | 5905 | int multibytep = 1; |
df7492f9 | 5906 | int c = *src++; |
b73bfc1c | 5907 | |
df7492f9 KH |
5908 | if (c == '\r') |
5909 | { | |
5910 | if (EQ (eol_type, Qdos)) | |
5911 | { | |
5912 | if (src < src_end | |
5913 | && *src == '\n') | |
5914 | c = *src++; | |
5915 | } | |
5916 | else if (EQ (eol_type, Qmac)) | |
5917 | c = '\n'; | |
5918 | } | |
5919 | if (dst >= dst_end - 1) | |
5920 | { | |
2c78b7e1 | 5921 | coding->consumed = src - coding->source; |
df7492f9 | 5922 | |
2c78b7e1 | 5923 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5924 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5925 | if (dst >= dst_end - 1) |
5926 | { | |
5927 | dst = alloc_destination (coding, src_end - src + 2, | |
5928 | dst); | |
5929 | dst_end = coding->destination + coding->dst_bytes; | |
5930 | coding_set_source (coding); | |
5931 | src = coding->source + coding->consumed; | |
5932 | src_end = coding->source + coding->src_bytes; | |
5933 | } | |
df7492f9 KH |
5934 | } |
5935 | EMIT_ONE_BYTE (c); | |
5936 | } | |
d46c5b12 | 5937 | } |
df7492f9 KH |
5938 | else |
5939 | { | |
5940 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 5941 | { |
df7492f9 | 5942 | int require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 5943 | |
df7492f9 | 5944 | if (require > 0) |
fa42c37f | 5945 | { |
df7492f9 KH |
5946 | EMACS_INT offset = src - coding->source; |
5947 | ||
5948 | dst = alloc_destination (coding, require, dst); | |
5949 | coding_set_source (coding); | |
5950 | src = coding->source + offset; | |
5951 | src_end = coding->source + coding->src_bytes; | |
fa42c37f KH |
5952 | } |
5953 | } | |
df7492f9 KH |
5954 | produced_chars = coding->src_chars; |
5955 | while (src < src_end) | |
fa42c37f | 5956 | { |
df7492f9 KH |
5957 | int c = *src++; |
5958 | ||
5959 | if (c == '\r') | |
5960 | { | |
5961 | if (EQ (eol_type, Qdos)) | |
5962 | { | |
5963 | if (src < src_end | |
5964 | && *src == '\n') | |
5965 | c = *src++; | |
5966 | produced_chars--; | |
5967 | } | |
5968 | else if (EQ (eol_type, Qmac)) | |
5969 | c = '\n'; | |
5970 | } | |
5971 | *dst++ = c; | |
fa42c37f KH |
5972 | } |
5973 | } | |
2c78b7e1 KH |
5974 | coding->consumed = coding->src_bytes; |
5975 | coding->consumed_char = coding->src_chars; | |
fa42c37f KH |
5976 | } |
5977 | ||
df7492f9 KH |
5978 | produced = dst - (coding->destination + coding->produced); |
5979 | if (BUFFERP (coding->dst_object)) | |
5980 | insert_from_gap (produced_chars, produced); | |
5981 | coding->produced += produced; | |
5982 | coding->produced_char += produced_chars; | |
69a80ea3 | 5983 | return carryover; |
fa42c37f KH |
5984 | } |
5985 | ||
ff0dacd7 KH |
5986 | /* Compose text in CODING->object according to the annotation data at |
5987 | CHARBUF. CHARBUF is an array: | |
5988 | [ -LENGTH ANNOTATION_MASK FROM TO METHOD COMP_LEN [ COMPONENTS... ] ] | |
df7492f9 | 5989 | */ |
4ed46869 | 5990 | |
df7492f9 | 5991 | static INLINE void |
69a80ea3 | 5992 | produce_composition (coding, charbuf, pos) |
4ed46869 | 5993 | struct coding_system *coding; |
df7492f9 | 5994 | int *charbuf; |
69a80ea3 | 5995 | EMACS_INT pos; |
4ed46869 | 5996 | { |
df7492f9 | 5997 | int len; |
69a80ea3 | 5998 | EMACS_INT to; |
df7492f9 | 5999 | enum composition_method method; |
df7492f9 | 6000 | Lisp_Object components; |
fa42c37f | 6001 | |
df7492f9 | 6002 | len = -charbuf[0]; |
69a80ea3 | 6003 | to = pos + charbuf[2]; |
9ffd559c KH |
6004 | if (to <= pos) |
6005 | return; | |
69a80ea3 | 6006 | method = (enum composition_method) (charbuf[3]); |
d46c5b12 | 6007 | |
df7492f9 KH |
6008 | if (method == COMPOSITION_RELATIVE) |
6009 | components = Qnil; | |
9ffd559c KH |
6010 | else if (method >= COMPOSITION_WITH_RULE |
6011 | && method <= COMPOSITION_WITH_RULE_ALTCHARS) | |
d46c5b12 | 6012 | { |
df7492f9 KH |
6013 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
6014 | int i; | |
b73bfc1c | 6015 | |
69a80ea3 KH |
6016 | len -= 4; |
6017 | charbuf += 4; | |
df7492f9 | 6018 | for (i = 0; i < len; i++) |
9ffd559c KH |
6019 | { |
6020 | args[i] = make_number (charbuf[i]); | |
6021 | if (args[i] < 0) | |
6022 | return; | |
6023 | } | |
df7492f9 KH |
6024 | components = (method == COMPOSITION_WITH_ALTCHARS |
6025 | ? Fstring (len, args) : Fvector (len, args)); | |
d46c5b12 | 6026 | } |
9ffd559c KH |
6027 | else |
6028 | return; | |
69a80ea3 | 6029 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
6030 | } |
6031 | ||
d46c5b12 | 6032 | |
ff0dacd7 KH |
6033 | /* Put `charset' property on text in CODING->object according to |
6034 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 6035 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 6036 | */ |
d46c5b12 | 6037 | |
ff0dacd7 | 6038 | static INLINE void |
69a80ea3 | 6039 | produce_charset (coding, charbuf, pos) |
d46c5b12 | 6040 | struct coding_system *coding; |
ff0dacd7 | 6041 | int *charbuf; |
69a80ea3 | 6042 | EMACS_INT pos; |
d46c5b12 | 6043 | { |
69a80ea3 KH |
6044 | EMACS_INT from = pos - charbuf[2]; |
6045 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); | |
b73bfc1c | 6046 | |
69a80ea3 | 6047 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
6048 | Qcharset, CHARSET_NAME (charset), |
6049 | coding->dst_object); | |
d46c5b12 KH |
6050 | } |
6051 | ||
d46c5b12 | 6052 | |
df7492f9 KH |
6053 | #define CHARBUF_SIZE 0x4000 |
6054 | ||
6055 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
6056 | do { \ | |
6057 | int size = CHARBUF_SIZE;; \ | |
6058 | \ | |
6059 | coding->charbuf = NULL; \ | |
6060 | while (size > 1024) \ | |
6061 | { \ | |
6062 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
6063 | if (coding->charbuf) \ | |
6064 | break; \ | |
6065 | size >>= 1; \ | |
6066 | } \ | |
6067 | if (! coding->charbuf) \ | |
6068 | { \ | |
065e3595 | 6069 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
df7492f9 KH |
6070 | return coding->result; \ |
6071 | } \ | |
6072 | coding->charbuf_size = size; \ | |
6073 | } while (0) | |
4ed46869 | 6074 | |
d46c5b12 KH |
6075 | |
6076 | static void | |
69a80ea3 | 6077 | produce_annotation (coding, pos) |
d46c5b12 | 6078 | struct coding_system *coding; |
69a80ea3 | 6079 | EMACS_INT pos; |
d46c5b12 | 6080 | { |
df7492f9 KH |
6081 | int *charbuf = coding->charbuf; |
6082 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 6083 | |
ff0dacd7 KH |
6084 | if (NILP (coding->dst_object)) |
6085 | return; | |
d46c5b12 | 6086 | |
df7492f9 | 6087 | while (charbuf < charbuf_end) |
a84f1519 | 6088 | { |
df7492f9 | 6089 | if (*charbuf >= 0) |
69a80ea3 | 6090 | pos += *charbuf++; |
d46c5b12 | 6091 | else |
d46c5b12 | 6092 | { |
df7492f9 | 6093 | int len = -*charbuf; |
ff0dacd7 | 6094 | switch (charbuf[1]) |
df7492f9 KH |
6095 | { |
6096 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
69a80ea3 | 6097 | produce_composition (coding, charbuf, pos); |
df7492f9 | 6098 | break; |
ff0dacd7 | 6099 | case CODING_ANNOTATE_CHARSET_MASK: |
69a80ea3 | 6100 | produce_charset (coding, charbuf, pos); |
ff0dacd7 | 6101 | break; |
df7492f9 KH |
6102 | default: |
6103 | abort (); | |
6104 | } | |
6105 | charbuf += len; | |
d46c5b12 | 6106 | } |
a84f1519 | 6107 | } |
d46c5b12 KH |
6108 | } |
6109 | ||
df7492f9 KH |
6110 | /* Decode the data at CODING->src_object into CODING->dst_object. |
6111 | CODING->src_object is a buffer, a string, or nil. | |
6112 | CODING->dst_object is a buffer. | |
d46c5b12 | 6113 | |
df7492f9 KH |
6114 | If CODING->src_object is a buffer, it must be the current buffer. |
6115 | In this case, if CODING->src_pos is positive, it is a position of | |
6116 | the source text in the buffer, otherwise, the source text is in the | |
6117 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
6118 | the text from GPT (which must be the same as PT). If this is the | |
6119 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6120 | negative. | |
d46c5b12 | 6121 | |
df7492f9 KH |
6122 | If CODING->src_object is a string, CODING->src_pos in an index to |
6123 | that string. | |
d46c5b12 | 6124 | |
df7492f9 KH |
6125 | If CODING->src_object is nil, CODING->source must already point to |
6126 | the non-relocatable memory area. In this case, CODING->src_pos is | |
6127 | an offset from CODING->source. | |
73be902c | 6128 | |
df7492f9 KH |
6129 | The decoded data is inserted at the current point of the buffer |
6130 | CODING->dst_object. | |
6131 | */ | |
d46c5b12 | 6132 | |
df7492f9 KH |
6133 | static int |
6134 | decode_coding (coding) | |
d46c5b12 | 6135 | struct coding_system *coding; |
d46c5b12 | 6136 | { |
df7492f9 | 6137 | Lisp_Object attrs; |
24a73b0a | 6138 | Lisp_Object undo_list; |
7d64c6ad | 6139 | Lisp_Object translation_table; |
69a80ea3 KH |
6140 | int carryover; |
6141 | int i; | |
d46c5b12 | 6142 | |
df7492f9 KH |
6143 | if (BUFFERP (coding->src_object) |
6144 | && coding->src_pos > 0 | |
6145 | && coding->src_pos < GPT | |
6146 | && coding->src_pos + coding->src_chars > GPT) | |
6147 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 6148 | |
24a73b0a | 6149 | undo_list = Qt; |
df7492f9 | 6150 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 6151 | { |
df7492f9 KH |
6152 | if (current_buffer != XBUFFER (coding->dst_object)) |
6153 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6154 | if (GPT != PT) | |
6155 | move_gap_both (PT, PT_BYTE); | |
24a73b0a KH |
6156 | undo_list = current_buffer->undo_list; |
6157 | current_buffer->undo_list = Qt; | |
1c3478b0 KH |
6158 | } |
6159 | ||
df7492f9 KH |
6160 | coding->consumed = coding->consumed_char = 0; |
6161 | coding->produced = coding->produced_char = 0; | |
6162 | coding->chars_at_source = 0; | |
065e3595 | 6163 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 6164 | coding->errors = 0; |
1c3478b0 | 6165 | |
df7492f9 KH |
6166 | ALLOC_CONVERSION_WORK_AREA (coding); |
6167 | ||
6168 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 6169 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 6170 | |
69a80ea3 | 6171 | carryover = 0; |
df7492f9 | 6172 | do |
b73bfc1c | 6173 | { |
69a80ea3 KH |
6174 | EMACS_INT pos = coding->dst_pos + coding->produced_char; |
6175 | ||
df7492f9 KH |
6176 | coding_set_source (coding); |
6177 | coding->annotated = 0; | |
69a80ea3 | 6178 | coding->charbuf_used = carryover; |
df7492f9 | 6179 | (*(coding->decoder)) (coding); |
df7492f9 | 6180 | coding_set_destination (coding); |
69a80ea3 | 6181 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 6182 | if (coding->annotated) |
69a80ea3 KH |
6183 | produce_annotation (coding, pos); |
6184 | for (i = 0; i < carryover; i++) | |
6185 | coding->charbuf[i] | |
6186 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 6187 | } |
df7492f9 KH |
6188 | while (coding->consumed < coding->src_bytes |
6189 | && ! coding->result); | |
d46c5b12 | 6190 | |
69a80ea3 KH |
6191 | if (carryover > 0) |
6192 | { | |
6193 | coding_set_destination (coding); | |
6194 | coding->charbuf_used = carryover; | |
6195 | produce_chars (coding, translation_table, 1); | |
6196 | } | |
6197 | ||
df7492f9 KH |
6198 | coding->carryover_bytes = 0; |
6199 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 6200 | { |
df7492f9 | 6201 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 6202 | const unsigned char *src; |
df7492f9 KH |
6203 | |
6204 | coding_set_source (coding); | |
6205 | coding_set_destination (coding); | |
6206 | src = coding->source + coding->consumed; | |
6207 | ||
6208 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 6209 | { |
df7492f9 KH |
6210 | /* Flush out unprocessed data as binary chars. We are sure |
6211 | that the number of data is less than the size of | |
6212 | coding->charbuf. */ | |
065e3595 | 6213 | coding->charbuf_used = 0; |
df7492f9 | 6214 | while (nbytes-- > 0) |
1c3478b0 | 6215 | { |
df7492f9 | 6216 | int c = *src++; |
98725083 | 6217 | |
1c91457d KH |
6218 | if (c & 0x80) |
6219 | c = BYTE8_TO_CHAR (c); | |
6220 | coding->charbuf[coding->charbuf_used++] = c; | |
1c3478b0 | 6221 | } |
f6cbaf43 | 6222 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 6223 | } |
d46c5b12 | 6224 | else |
df7492f9 KH |
6225 | { |
6226 | /* Record unprocessed bytes in coding->carryover. We are | |
6227 | sure that the number of data is less than the size of | |
6228 | coding->carryover. */ | |
6229 | unsigned char *p = coding->carryover; | |
6230 | ||
6231 | coding->carryover_bytes = nbytes; | |
6232 | while (nbytes-- > 0) | |
6233 | *p++ = *src++; | |
1c3478b0 | 6234 | } |
df7492f9 | 6235 | coding->consumed = coding->src_bytes; |
b73bfc1c | 6236 | } |
69f76525 | 6237 | |
24a73b0a KH |
6238 | if (BUFFERP (coding->dst_object)) |
6239 | { | |
6240 | current_buffer->undo_list = undo_list; | |
6241 | record_insert (coding->dst_pos, coding->produced_char); | |
6242 | } | |
6243 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix)) | |
6244 | decode_eol (coding); | |
73be902c | 6245 | return coding->result; |
4ed46869 KH |
6246 | } |
6247 | ||
aaaf0b1e | 6248 | |
e1c23804 | 6249 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
6250 | ending before LIMIT of CODING->src_object (buffer or string), store |
6251 | the data in BUF, set *STOP to a starting position of the next | |
6252 | composition (if any) or to LIMIT, and return the address of the | |
6253 | next element of BUF. | |
6254 | ||
6255 | If such an annotation is not found, set *STOP to a starting | |
6256 | position of a composition after POS (if any) or to LIMIT, and | |
6257 | return BUF. */ | |
6258 | ||
6259 | static INLINE int * | |
6260 | handle_composition_annotation (pos, limit, coding, buf, stop) | |
6261 | EMACS_INT pos, limit; | |
aaaf0b1e | 6262 | struct coding_system *coding; |
ff0dacd7 KH |
6263 | int *buf; |
6264 | EMACS_INT *stop; | |
aaaf0b1e | 6265 | { |
ff0dacd7 KH |
6266 | EMACS_INT start, end; |
6267 | Lisp_Object prop; | |
aaaf0b1e | 6268 | |
ff0dacd7 KH |
6269 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
6270 | || end > limit) | |
6271 | *stop = limit; | |
6272 | else if (start > pos) | |
6273 | *stop = start; | |
6274 | else | |
aaaf0b1e | 6275 | { |
ff0dacd7 | 6276 | if (start == pos) |
aaaf0b1e | 6277 | { |
ff0dacd7 KH |
6278 | /* We found a composition. Store the corresponding |
6279 | annotation data in BUF. */ | |
6280 | int *head = buf; | |
6281 | enum composition_method method = COMPOSITION_METHOD (prop); | |
6282 | int nchars = COMPOSITION_LENGTH (prop); | |
6283 | ||
69a80ea3 | 6284 | ADD_COMPOSITION_DATA (buf, nchars, method); |
ff0dacd7 | 6285 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 6286 | { |
ff0dacd7 KH |
6287 | Lisp_Object components; |
6288 | int len, i, i_byte; | |
6289 | ||
6290 | components = COMPOSITION_COMPONENTS (prop); | |
6291 | if (VECTORP (components)) | |
aaaf0b1e | 6292 | { |
ff0dacd7 KH |
6293 | len = XVECTOR (components)->size; |
6294 | for (i = 0; i < len; i++) | |
6295 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 6296 | } |
ff0dacd7 | 6297 | else if (STRINGP (components)) |
aaaf0b1e | 6298 | { |
8f924df7 | 6299 | len = SCHARS (components); |
ff0dacd7 KH |
6300 | i = i_byte = 0; |
6301 | while (i < len) | |
6302 | { | |
6303 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
6304 | buf++; | |
6305 | } | |
6306 | } | |
6307 | else if (INTEGERP (components)) | |
6308 | { | |
6309 | len = 1; | |
6310 | *buf++ = XINT (components); | |
6311 | } | |
6312 | else if (CONSP (components)) | |
6313 | { | |
6314 | for (len = 0; CONSP (components); | |
6315 | len++, components = XCDR (components)) | |
6316 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 6317 | } |
aaaf0b1e | 6318 | else |
ff0dacd7 KH |
6319 | abort (); |
6320 | *head -= len; | |
aaaf0b1e | 6321 | } |
aaaf0b1e | 6322 | } |
ff0dacd7 KH |
6323 | |
6324 | if (find_composition (end, limit, &start, &end, &prop, | |
6325 | coding->src_object) | |
6326 | && end <= limit) | |
6327 | *stop = start; | |
6328 | else | |
6329 | *stop = limit; | |
aaaf0b1e | 6330 | } |
ff0dacd7 KH |
6331 | return buf; |
6332 | } | |
6333 | ||
6334 | ||
e1c23804 | 6335 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
6336 | CODING->src_object (buffer of string), store the data in BUF, set |
6337 | *STOP to the position where the value of `charset' property changes | |
6338 | (limiting by LIMIT), and return the address of the next element of | |
6339 | BUF. | |
6340 | ||
6341 | If the property value is nil, set *STOP to the position where the | |
6342 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
6343 | ||
6344 | static INLINE int * | |
6345 | handle_charset_annotation (pos, limit, coding, buf, stop) | |
6346 | EMACS_INT pos, limit; | |
6347 | struct coding_system *coding; | |
6348 | int *buf; | |
6349 | EMACS_INT *stop; | |
6350 | { | |
6351 | Lisp_Object val, next; | |
6352 | int id; | |
6353 | ||
6354 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
6355 | if (! NILP (val) && CHARSETP (val)) | |
6356 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
6357 | else | |
6358 | id = -1; | |
69a80ea3 | 6359 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
6360 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
6361 | coding->src_object, | |
6362 | make_number (limit)); | |
6363 | *stop = XINT (next); | |
6364 | return buf; | |
6365 | } | |
6366 | ||
6367 | ||
df7492f9 | 6368 | static void |
09ee6fdd | 6369 | consume_chars (coding, translation_table, max_lookup) |
df7492f9 | 6370 | struct coding_system *coding; |
433f7f87 | 6371 | Lisp_Object translation_table; |
09ee6fdd | 6372 | int max_lookup; |
df7492f9 KH |
6373 | { |
6374 | int *buf = coding->charbuf; | |
ff0dacd7 | 6375 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 6376 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 6377 | const unsigned char *src_end = coding->source + coding->src_bytes; |
ff0dacd7 KH |
6378 | EMACS_INT pos = coding->src_pos + coding->consumed_char; |
6379 | EMACS_INT end_pos = coding->src_pos + coding->src_chars; | |
df7492f9 KH |
6380 | int multibytep = coding->src_multibyte; |
6381 | Lisp_Object eol_type; | |
6382 | int c; | |
ff0dacd7 | 6383 | EMACS_INT stop, stop_composition, stop_charset; |
09ee6fdd | 6384 | int *lookup_buf = NULL; |
433f7f87 KH |
6385 | |
6386 | if (! NILP (translation_table)) | |
09ee6fdd | 6387 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 6388 | |
df7492f9 KH |
6389 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6390 | if (VECTORP (eol_type)) | |
6391 | eol_type = Qunix; | |
88993dfd | 6392 | |
df7492f9 KH |
6393 | /* Note: composition handling is not yet implemented. */ |
6394 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 6395 | |
0b5670c9 KH |
6396 | if (NILP (coding->src_object)) |
6397 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 6398 | else |
0b5670c9 KH |
6399 | { |
6400 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
6401 | stop = stop_composition = pos; | |
6402 | else | |
6403 | stop = stop_composition = end_pos; | |
6404 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
6405 | stop = stop_charset = pos; | |
6406 | else | |
6407 | stop_charset = end_pos; | |
6408 | } | |
ec6d2bb8 | 6409 | |
24a73b0a | 6410 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 6411 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 6412 | while (buf < buf_end) |
aaaf0b1e | 6413 | { |
433f7f87 KH |
6414 | Lisp_Object trans; |
6415 | ||
df7492f9 | 6416 | if (pos == stop) |
ec6d2bb8 | 6417 | { |
df7492f9 KH |
6418 | if (pos == end_pos) |
6419 | break; | |
ff0dacd7 KH |
6420 | if (pos == stop_composition) |
6421 | buf = handle_composition_annotation (pos, end_pos, coding, | |
6422 | buf, &stop_composition); | |
6423 | if (pos == stop_charset) | |
6424 | buf = handle_charset_annotation (pos, end_pos, coding, | |
6425 | buf, &stop_charset); | |
6426 | stop = (stop_composition < stop_charset | |
6427 | ? stop_composition : stop_charset); | |
df7492f9 KH |
6428 | } |
6429 | ||
6430 | if (! multibytep) | |
4776e638 | 6431 | { |
d3e4cb56 | 6432 | EMACS_INT bytes; |
aaaf0b1e | 6433 | |
ea29edf2 KH |
6434 | if (coding->encoder == encode_coding_raw_text) |
6435 | c = *src++, pos++; | |
6436 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
4776e638 KH |
6437 | c = STRING_CHAR_ADVANCE (src), pos += bytes; |
6438 | else | |
f03caae0 | 6439 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 6440 | } |
df7492f9 | 6441 | else |
4776e638 | 6442 | c = STRING_CHAR_ADVANCE (src), pos++; |
df7492f9 KH |
6443 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
6444 | c = '\n'; | |
6445 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 6446 | { |
df7492f9 | 6447 | if (c == '\n') |
aaaf0b1e | 6448 | { |
df7492f9 KH |
6449 | if (EQ (eol_type, Qdos)) |
6450 | *buf++ = '\r'; | |
6451 | else | |
6452 | c = '\r'; | |
aaaf0b1e KH |
6453 | } |
6454 | } | |
433f7f87 | 6455 | |
e6a54062 | 6456 | trans = Qnil; |
09ee6fdd | 6457 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6458 | if (NILP (trans)) |
433f7f87 KH |
6459 | *buf++ = c; |
6460 | else | |
6461 | { | |
6462 | int from_nchars = 1, to_nchars = 1; | |
6463 | int *lookup_buf_end; | |
6464 | const unsigned char *p = src; | |
6465 | int i; | |
6466 | ||
6467 | lookup_buf[0] = c; | |
6468 | for (i = 1; i < max_lookup && p < src_end; i++) | |
6469 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
6470 | lookup_buf_end = lookup_buf + i; | |
6471 | trans = get_translation (trans, lookup_buf, lookup_buf_end, 1, | |
6472 | &from_nchars, &to_nchars); | |
6473 | if (EQ (trans, Qt) | |
6474 | || buf + to_nchars > buf_end) | |
6475 | break; | |
6476 | *buf++ = *lookup_buf; | |
6477 | for (i = 1; i < to_nchars; i++) | |
6478 | *buf++ = XINT (AREF (trans, i)); | |
6479 | for (i = 1; i < from_nchars; i++, pos++) | |
6480 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
6481 | } | |
aaaf0b1e | 6482 | } |
ec6d2bb8 | 6483 | |
df7492f9 KH |
6484 | coding->consumed = src - coding->source; |
6485 | coding->consumed_char = pos - coding->src_pos; | |
6486 | coding->charbuf_used = buf - coding->charbuf; | |
6487 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
6488 | } |
6489 | ||
4ed46869 | 6490 | |
df7492f9 KH |
6491 | /* Encode the text at CODING->src_object into CODING->dst_object. |
6492 | CODING->src_object is a buffer or a string. | |
6493 | CODING->dst_object is a buffer or nil. | |
6494 | ||
6495 | If CODING->src_object is a buffer, it must be the current buffer. | |
6496 | In this case, if CODING->src_pos is positive, it is a position of | |
6497 | the source text in the buffer, otherwise. the source text is in the | |
6498 | gap area of the buffer, and coding->src_pos specifies the offset of | |
6499 | the text from GPT (which must be the same as PT). If this is the | |
6500 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6501 | negative and CODING should not have `pre-write-conversion'. | |
6502 | ||
6503 | If CODING->src_object is a string, CODING should not have | |
6504 | `pre-write-conversion'. | |
6505 | ||
6506 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
6507 | the current point of that buffer. | |
6508 | ||
6509 | If CODING->dst_object is nil, the encoded data is placed at the | |
6510 | memory area specified by CODING->destination. */ | |
6511 | ||
6512 | static int | |
6513 | encode_coding (coding) | |
4ed46869 | 6514 | struct coding_system *coding; |
4ed46869 | 6515 | { |
df7492f9 | 6516 | Lisp_Object attrs; |
7d64c6ad | 6517 | Lisp_Object translation_table; |
09ee6fdd | 6518 | int max_lookup; |
9861e777 | 6519 | |
df7492f9 | 6520 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
6521 | if (coding->encoder == encode_coding_raw_text) |
6522 | translation_table = Qnil, max_lookup = 0; | |
6523 | else | |
6524 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 6525 | |
df7492f9 | 6526 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 6527 | { |
df7492f9 KH |
6528 | set_buffer_internal (XBUFFER (coding->dst_object)); |
6529 | coding->dst_multibyte | |
6530 | = ! NILP (current_buffer->enable_multibyte_characters); | |
8844fa83 | 6531 | } |
4ed46869 | 6532 | |
b73bfc1c | 6533 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 6534 | coding->produced = coding->produced_char = 0; |
065e3595 | 6535 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 6536 | coding->errors = 0; |
b73bfc1c | 6537 | |
df7492f9 | 6538 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 6539 | |
df7492f9 KH |
6540 | do { |
6541 | coding_set_source (coding); | |
09ee6fdd | 6542 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
6543 | coding_set_destination (coding); |
6544 | (*(coding->encoder)) (coding); | |
6545 | } while (coding->consumed_char < coding->src_chars); | |
6546 | ||
6547 | if (BUFFERP (coding->dst_object)) | |
6548 | insert_from_gap (coding->produced_char, coding->produced); | |
6549 | ||
6550 | return (coding->result); | |
ec6d2bb8 KH |
6551 | } |
6552 | ||
fb88bf2d | 6553 | |
24a73b0a KH |
6554 | /* Name (or base name) of work buffer for code conversion. */ |
6555 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 6556 | |
24a73b0a KH |
6557 | /* A working buffer used by the top level conversion. Once it is |
6558 | created, it is never destroyed. It has the name | |
6559 | Vcode_conversion_workbuf_name. The other working buffers are | |
6560 | destroyed after the use is finished, and their names are modified | |
6561 | versions of Vcode_conversion_workbuf_name. */ | |
6562 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 6563 | |
24a73b0a KH |
6564 | /* 1 iff Vcode_conversion_reused_workbuf is already in use. */ |
6565 | static int reused_workbuf_in_use; | |
4ed46869 | 6566 | |
24a73b0a KH |
6567 | |
6568 | /* Return a working buffer of code convesion. MULTIBYTE specifies the | |
6569 | multibyteness of returning buffer. */ | |
b73bfc1c | 6570 | |
f6cbaf43 | 6571 | static Lisp_Object |
24a73b0a | 6572 | make_conversion_work_buffer (multibyte) |
f6cbaf43 | 6573 | int multibyte; |
df7492f9 | 6574 | { |
24a73b0a KH |
6575 | Lisp_Object name, workbuf; |
6576 | struct buffer *current; | |
4ed46869 | 6577 | |
24a73b0a | 6578 | if (reused_workbuf_in_use++) |
065e3595 KH |
6579 | { |
6580 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
6581 | workbuf = Fget_buffer_create (name); | |
6582 | } | |
df7492f9 | 6583 | else |
065e3595 KH |
6584 | { |
6585 | name = Vcode_conversion_workbuf_name; | |
6586 | workbuf = Fget_buffer_create (name); | |
6587 | if (NILP (Vcode_conversion_reused_workbuf)) | |
6588 | Vcode_conversion_reused_workbuf = workbuf; | |
6589 | } | |
24a73b0a KH |
6590 | current = current_buffer; |
6591 | set_buffer_internal (XBUFFER (workbuf)); | |
6592 | Ferase_buffer (); | |
df7492f9 | 6593 | current_buffer->undo_list = Qt; |
24a73b0a | 6594 | current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil; |
df7492f9 | 6595 | set_buffer_internal (current); |
24a73b0a | 6596 | return workbuf; |
df7492f9 | 6597 | } |
d46c5b12 | 6598 | |
24a73b0a | 6599 | |
4776e638 | 6600 | static Lisp_Object |
24a73b0a KH |
6601 | code_conversion_restore (arg) |
6602 | Lisp_Object arg; | |
4776e638 | 6603 | { |
24a73b0a | 6604 | Lisp_Object current, workbuf; |
948bdcf3 | 6605 | struct gcpro gcpro1; |
24a73b0a | 6606 | |
948bdcf3 | 6607 | GCPRO1 (arg); |
24a73b0a KH |
6608 | current = XCAR (arg); |
6609 | workbuf = XCDR (arg); | |
6610 | if (! NILP (workbuf)) | |
6611 | { | |
6612 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
6613 | reused_workbuf_in_use = 0; | |
6614 | else if (! NILP (Fbuffer_live_p (workbuf))) | |
6615 | Fkill_buffer (workbuf); | |
6616 | } | |
6617 | set_buffer_internal (XBUFFER (current)); | |
948bdcf3 | 6618 | UNGCPRO; |
4776e638 KH |
6619 | return Qnil; |
6620 | } | |
b73bfc1c | 6621 | |
24a73b0a KH |
6622 | Lisp_Object |
6623 | code_conversion_save (with_work_buf, multibyte) | |
4776e638 | 6624 | int with_work_buf, multibyte; |
df7492f9 | 6625 | { |
24a73b0a | 6626 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 6627 | |
4776e638 | 6628 | if (with_work_buf) |
24a73b0a KH |
6629 | workbuf = make_conversion_work_buffer (multibyte); |
6630 | record_unwind_protect (code_conversion_restore, | |
6631 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 6632 | return workbuf; |
df7492f9 | 6633 | } |
d46c5b12 | 6634 | |
df7492f9 KH |
6635 | int |
6636 | decode_coding_gap (coding, chars, bytes) | |
6637 | struct coding_system *coding; | |
6638 | EMACS_INT chars, bytes; | |
6639 | { | |
6640 | int count = specpdl_ptr - specpdl; | |
5e5c78be | 6641 | Lisp_Object attrs; |
fb88bf2d | 6642 | |
24a73b0a | 6643 | code_conversion_save (0, 0); |
ec6d2bb8 | 6644 | |
24a73b0a | 6645 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6646 | coding->src_chars = chars; |
6647 | coding->src_bytes = bytes; | |
6648 | coding->src_pos = -chars; | |
6649 | coding->src_pos_byte = -bytes; | |
6650 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 6651 | coding->dst_object = coding->src_object; |
df7492f9 KH |
6652 | coding->dst_pos = PT; |
6653 | coding->dst_pos_byte = PT_BYTE; | |
71c81426 | 6654 | coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters); |
98725083 | 6655 | coding->mode |= CODING_MODE_LAST_BLOCK; |
4ed46869 | 6656 | |
df7492f9 KH |
6657 | if (CODING_REQUIRE_DETECTION (coding)) |
6658 | detect_coding (coding); | |
8f924df7 | 6659 | |
df7492f9 | 6660 | decode_coding (coding); |
d46c5b12 | 6661 | |
5e5c78be KH |
6662 | attrs = CODING_ID_ATTRS (coding->id); |
6663 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 6664 | { |
5e5c78be KH |
6665 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
6666 | Lisp_Object val; | |
6667 | ||
6668 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
6669 | val = call1 (CODING_ATTR_POST_READ (attrs), |
6670 | make_number (coding->produced_char)); | |
5e5c78be KH |
6671 | CHECK_NATNUM (val); |
6672 | coding->produced_char += Z - prev_Z; | |
6673 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 6674 | } |
4ed46869 | 6675 | |
df7492f9 | 6676 | unbind_to (count, Qnil); |
b73bfc1c KH |
6677 | return coding->result; |
6678 | } | |
52d41803 | 6679 | |
4ed46869 | 6680 | int |
df7492f9 | 6681 | encode_coding_gap (coding, chars, bytes) |
4ed46869 | 6682 | struct coding_system *coding; |
df7492f9 | 6683 | EMACS_INT chars, bytes; |
4ed46869 | 6684 | { |
df7492f9 | 6685 | int count = specpdl_ptr - specpdl; |
4ed46869 | 6686 | |
24a73b0a | 6687 | code_conversion_save (0, 0); |
4ed46869 | 6688 | |
24a73b0a | 6689 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6690 | coding->src_chars = chars; |
6691 | coding->src_bytes = bytes; | |
6692 | coding->src_pos = -chars; | |
6693 | coding->src_pos_byte = -bytes; | |
6694 | coding->src_multibyte = chars < bytes; | |
6695 | coding->dst_object = coding->src_object; | |
6696 | coding->dst_pos = PT; | |
6697 | coding->dst_pos_byte = PT_BYTE; | |
4ed46869 | 6698 | |
df7492f9 | 6699 | encode_coding (coding); |
b73bfc1c | 6700 | |
df7492f9 KH |
6701 | unbind_to (count, Qnil); |
6702 | return coding->result; | |
6703 | } | |
4ed46869 | 6704 | |
d46c5b12 | 6705 | |
df7492f9 KH |
6706 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
6707 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 6708 | |
df7492f9 | 6709 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 6710 | |
df7492f9 KH |
6711 | If it is a buffer, the text is at point of the buffer. FROM and TO |
6712 | are positions in the buffer. | |
b73bfc1c | 6713 | |
df7492f9 KH |
6714 | If it is a string, the text is at the beginning of the string. |
6715 | FROM and TO are indices to the string. | |
4ed46869 | 6716 | |
df7492f9 KH |
6717 | If it is nil, the text is at coding->source. FROM and TO are |
6718 | indices to coding->source. | |
bb10be8b | 6719 | |
df7492f9 | 6720 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 6721 | |
df7492f9 KH |
6722 | If it is a buffer, the decoded text is inserted at point of the |
6723 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
6724 | is deleted. | |
4ed46869 | 6725 | |
df7492f9 KH |
6726 | If it is Qt, a string is made from the decoded text, and |
6727 | set in CODING->dst_object. | |
d46c5b12 | 6728 | |
df7492f9 | 6729 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 6730 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
6731 | CODING->destination by xmalloc. If the decoded text is longer than |
6732 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
6733 | */ | |
d46c5b12 | 6734 | |
df7492f9 KH |
6735 | void |
6736 | decode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6737 | dst_object) | |
d46c5b12 | 6738 | struct coding_system *coding; |
df7492f9 KH |
6739 | Lisp_Object src_object; |
6740 | EMACS_INT from, from_byte, to, to_byte; | |
6741 | Lisp_Object dst_object; | |
d46c5b12 | 6742 | { |
df7492f9 KH |
6743 | int count = specpdl_ptr - specpdl; |
6744 | unsigned char *destination; | |
6745 | EMACS_INT dst_bytes; | |
6746 | EMACS_INT chars = to - from; | |
6747 | EMACS_INT bytes = to_byte - from_byte; | |
6748 | Lisp_Object attrs; | |
4776e638 KH |
6749 | Lisp_Object buffer; |
6750 | int saved_pt = -1, saved_pt_byte; | |
d46c5b12 | 6751 | |
4776e638 | 6752 | buffer = Fcurrent_buffer (); |
93dec019 | 6753 | |
df7492f9 | 6754 | if (NILP (dst_object)) |
d46c5b12 | 6755 | { |
df7492f9 KH |
6756 | destination = coding->destination; |
6757 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 6758 | } |
93dec019 | 6759 | |
df7492f9 KH |
6760 | coding->src_object = src_object; |
6761 | coding->src_chars = chars; | |
6762 | coding->src_bytes = bytes; | |
6763 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 6764 | |
df7492f9 | 6765 | if (STRINGP (src_object)) |
d46c5b12 | 6766 | { |
df7492f9 KH |
6767 | coding->src_pos = from; |
6768 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6769 | } |
df7492f9 | 6770 | else if (BUFFERP (src_object)) |
88993dfd | 6771 | { |
df7492f9 KH |
6772 | set_buffer_internal (XBUFFER (src_object)); |
6773 | if (from != GPT) | |
6774 | move_gap_both (from, from_byte); | |
6775 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 6776 | { |
4776e638 | 6777 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6778 | TEMP_SET_PT_BOTH (from, from_byte); |
6779 | del_range_both (from, from_byte, to, to_byte, 1); | |
6780 | coding->src_pos = -chars; | |
6781 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 6782 | } |
df7492f9 | 6783 | else |
fb88bf2d | 6784 | { |
df7492f9 KH |
6785 | coding->src_pos = from; |
6786 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 6787 | } |
88993dfd KH |
6788 | } |
6789 | ||
df7492f9 KH |
6790 | if (CODING_REQUIRE_DETECTION (coding)) |
6791 | detect_coding (coding); | |
6792 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 6793 | |
2cb26057 KH |
6794 | if (EQ (dst_object, Qt) |
6795 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
6796 | && NILP (dst_object))) | |
b73bfc1c | 6797 | { |
24a73b0a | 6798 | coding->dst_object = code_conversion_save (1, 1); |
df7492f9 KH |
6799 | coding->dst_pos = BEG; |
6800 | coding->dst_pos_byte = BEG_BYTE; | |
6801 | coding->dst_multibyte = 1; | |
b73bfc1c | 6802 | } |
df7492f9 | 6803 | else if (BUFFERP (dst_object)) |
d46c5b12 | 6804 | { |
24a73b0a | 6805 | code_conversion_save (0, 0); |
df7492f9 KH |
6806 | coding->dst_object = dst_object; |
6807 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6808 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6809 | coding->dst_multibyte | |
6810 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
d46c5b12 KH |
6811 | } |
6812 | else | |
6813 | { | |
24a73b0a | 6814 | code_conversion_save (0, 0); |
df7492f9 KH |
6815 | coding->dst_object = Qnil; |
6816 | coding->dst_multibyte = 1; | |
d46c5b12 KH |
6817 | } |
6818 | ||
df7492f9 | 6819 | decode_coding (coding); |
fa46990e | 6820 | |
df7492f9 KH |
6821 | if (BUFFERP (coding->dst_object)) |
6822 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 6823 | |
df7492f9 | 6824 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 6825 | { |
df7492f9 KH |
6826 | struct gcpro gcpro1, gcpro2; |
6827 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; | |
2b4f9037 | 6828 | Lisp_Object val; |
d46c5b12 | 6829 | |
c0cc7f7f | 6830 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
df7492f9 | 6831 | GCPRO2 (coding->src_object, coding->dst_object); |
d4850d67 KH |
6832 | val = safe_call1 (CODING_ATTR_POST_READ (attrs), |
6833 | make_number (coding->produced_char)); | |
df7492f9 KH |
6834 | UNGCPRO; |
6835 | CHECK_NATNUM (val); | |
6836 | coding->produced_char += Z - prev_Z; | |
6837 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 6838 | } |
de79a6a5 | 6839 | |
df7492f9 | 6840 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 6841 | { |
df7492f9 KH |
6842 | coding->dst_object = Fbuffer_string (); |
6843 | } | |
6844 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
6845 | { | |
6846 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6847 | if (dst_bytes < coding->produced) | |
6848 | { | |
6849 | destination | |
6850 | = (unsigned char *) xrealloc (destination, coding->produced); | |
6851 | if (! destination) | |
6852 | { | |
065e3595 KH |
6853 | record_conversion_result (coding, |
6854 | CODING_RESULT_INSUFFICIENT_DST); | |
df7492f9 KH |
6855 | unbind_to (count, Qnil); |
6856 | return; | |
6857 | } | |
6858 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
6859 | move_gap_both (BEGV, BEGV_BYTE); | |
6860 | bcopy (BEGV_ADDR, destination, coding->produced); | |
6861 | coding->destination = destination; | |
d46c5b12 | 6862 | } |
ec6d2bb8 | 6863 | } |
b73bfc1c | 6864 | |
4776e638 KH |
6865 | if (saved_pt >= 0) |
6866 | { | |
6867 | /* This is the case of: | |
6868 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
6869 | As we have moved PT while replacing the original buffer | |
6870 | contents, we must recover it now. */ | |
6871 | set_buffer_internal (XBUFFER (src_object)); | |
6872 | if (saved_pt < from) | |
6873 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
6874 | else if (saved_pt < from + chars) | |
6875 | TEMP_SET_PT_BOTH (from, from_byte); | |
6876 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
6877 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
6878 | saved_pt_byte + (coding->produced - bytes)); | |
6879 | else | |
6880 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
6881 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 6882 | } |
4776e638 | 6883 | |
065e3595 | 6884 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
6885 | } |
6886 | ||
d46c5b12 | 6887 | |
df7492f9 KH |
6888 | void |
6889 | encode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6890 | dst_object) | |
d46c5b12 | 6891 | struct coding_system *coding; |
df7492f9 KH |
6892 | Lisp_Object src_object; |
6893 | EMACS_INT from, from_byte, to, to_byte; | |
6894 | Lisp_Object dst_object; | |
d46c5b12 | 6895 | { |
b73bfc1c | 6896 | int count = specpdl_ptr - specpdl; |
df7492f9 KH |
6897 | EMACS_INT chars = to - from; |
6898 | EMACS_INT bytes = to_byte - from_byte; | |
6899 | Lisp_Object attrs; | |
4776e638 KH |
6900 | Lisp_Object buffer; |
6901 | int saved_pt = -1, saved_pt_byte; | |
c02d943b | 6902 | int kill_src_buffer = 0; |
df7492f9 | 6903 | |
4776e638 | 6904 | buffer = Fcurrent_buffer (); |
df7492f9 KH |
6905 | |
6906 | coding->src_object = src_object; | |
6907 | coding->src_chars = chars; | |
6908 | coding->src_bytes = bytes; | |
6909 | coding->src_multibyte = chars < bytes; | |
6910 | ||
6911 | attrs = CODING_ID_ATTRS (coding->id); | |
6912 | ||
6913 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
6bac5b12 | 6914 | { |
24a73b0a | 6915 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
6916 | set_buffer_internal (XBUFFER (coding->src_object)); |
6917 | if (STRINGP (src_object)) | |
6918 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
6919 | else if (BUFFERP (src_object)) | |
6920 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
6921 | else | |
6922 | insert_1_both (coding->source + from, chars, bytes, 0, 0, 0); | |
d46c5b12 | 6923 | |
df7492f9 KH |
6924 | if (EQ (src_object, dst_object)) |
6925 | { | |
6926 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 6927 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6928 | del_range_both (from, from_byte, to, to_byte, 1); |
6929 | set_buffer_internal (XBUFFER (coding->src_object)); | |
6930 | } | |
6931 | ||
d4850d67 KH |
6932 | { |
6933 | Lisp_Object args[3]; | |
6934 | ||
6935 | args[0] = CODING_ATTR_PRE_WRITE (attrs); | |
6936 | args[1] = make_number (BEG); | |
6937 | args[2] = make_number (Z); | |
6938 | safe_call (3, args); | |
6939 | } | |
c02d943b KH |
6940 | if (XBUFFER (coding->src_object) != current_buffer) |
6941 | kill_src_buffer = 1; | |
ac87bbef | 6942 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6943 | if (BEG != GPT) |
6944 | move_gap_both (BEG, BEG_BYTE); | |
6945 | coding->src_chars = Z - BEG; | |
6946 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
6947 | coding->src_pos = BEG; | |
6948 | coding->src_pos_byte = BEG_BYTE; | |
6949 | coding->src_multibyte = Z < Z_BYTE; | |
6950 | } | |
6951 | else if (STRINGP (src_object)) | |
d46c5b12 | 6952 | { |
24a73b0a | 6953 | code_conversion_save (0, 0); |
df7492f9 KH |
6954 | coding->src_pos = from; |
6955 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 6956 | } |
df7492f9 | 6957 | else if (BUFFERP (src_object)) |
b73bfc1c | 6958 | { |
24a73b0a | 6959 | code_conversion_save (0, 0); |
df7492f9 | 6960 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 6961 | if (EQ (src_object, dst_object)) |
d46c5b12 | 6962 | { |
4776e638 | 6963 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
6964 | coding->src_object = del_range_1 (from, to, 1, 1); |
6965 | coding->src_pos = 0; | |
6966 | coding->src_pos_byte = 0; | |
d46c5b12 | 6967 | } |
df7492f9 | 6968 | else |
d46c5b12 | 6969 | { |
ff0dacd7 KH |
6970 | if (from < GPT && to >= GPT) |
6971 | move_gap_both (from, from_byte); | |
df7492f9 KH |
6972 | coding->src_pos = from; |
6973 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6974 | } |
d46c5b12 | 6975 | } |
4776e638 | 6976 | else |
24a73b0a | 6977 | code_conversion_save (0, 0); |
d46c5b12 | 6978 | |
df7492f9 | 6979 | if (BUFFERP (dst_object)) |
88993dfd | 6980 | { |
df7492f9 | 6981 | coding->dst_object = dst_object; |
28f67a95 KH |
6982 | if (EQ (src_object, dst_object)) |
6983 | { | |
6984 | coding->dst_pos = from; | |
6985 | coding->dst_pos_byte = from_byte; | |
6986 | } | |
6987 | else | |
6988 | { | |
6989 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6990 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6991 | } | |
df7492f9 KH |
6992 | coding->dst_multibyte |
6993 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
88993dfd | 6994 | } |
df7492f9 | 6995 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 6996 | { |
df7492f9 | 6997 | coding->dst_object = Qnil; |
df7492f9 | 6998 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
6999 | if (coding->dst_bytes == 0) |
7000 | coding->dst_bytes = 1; | |
7001 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 7002 | coding->dst_multibyte = 0; |
d46c5b12 KH |
7003 | } |
7004 | else | |
7005 | { | |
df7492f9 KH |
7006 | coding->dst_object = Qnil; |
7007 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
7008 | } |
7009 | ||
df7492f9 | 7010 | encode_coding (coding); |
d46c5b12 | 7011 | |
df7492f9 | 7012 | if (EQ (dst_object, Qt)) |
d46c5b12 | 7013 | { |
df7492f9 KH |
7014 | if (BUFFERP (coding->dst_object)) |
7015 | coding->dst_object = Fbuffer_string (); | |
7016 | else | |
d46c5b12 | 7017 | { |
df7492f9 KH |
7018 | coding->dst_object |
7019 | = make_unibyte_string ((char *) coding->destination, | |
7020 | coding->produced); | |
7021 | xfree (coding->destination); | |
d46c5b12 | 7022 | } |
4ed46869 | 7023 | } |
d46c5b12 | 7024 | |
4776e638 KH |
7025 | if (saved_pt >= 0) |
7026 | { | |
7027 | /* This is the case of: | |
7028 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7029 | As we have moved PT while replacing the original buffer | |
7030 | contents, we must recover it now. */ | |
7031 | set_buffer_internal (XBUFFER (src_object)); | |
7032 | if (saved_pt < from) | |
7033 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7034 | else if (saved_pt < from + chars) | |
7035 | TEMP_SET_PT_BOTH (from, from_byte); | |
7036 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
7037 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
7038 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 7039 | else |
4776e638 KH |
7040 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
7041 | saved_pt_byte + (coding->produced - bytes)); | |
7042 | } | |
7043 | ||
c02d943b KH |
7044 | if (kill_src_buffer) |
7045 | Fkill_buffer (coding->src_object); | |
df7492f9 | 7046 | unbind_to (count, Qnil); |
b73bfc1c KH |
7047 | } |
7048 | ||
df7492f9 | 7049 | |
b73bfc1c | 7050 | Lisp_Object |
df7492f9 | 7051 | preferred_coding_system () |
b73bfc1c | 7052 | { |
df7492f9 | 7053 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 7054 | |
df7492f9 | 7055 | return CODING_ID_NAME (id); |
4ed46869 KH |
7056 | } |
7057 | ||
7058 | \f | |
7059 | #ifdef emacs | |
1397dc18 | 7060 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 7061 | |
4ed46869 | 7062 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 7063 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 7064 | See the documentation of `define-coding-system' for information |
48b0f3ae PJ |
7065 | about coding-system objects. */) |
7066 | (obj) | |
4ed46869 KH |
7067 | Lisp_Object obj; |
7068 | { | |
44e8490d KH |
7069 | if (NILP (obj) |
7070 | || CODING_SYSTEM_ID (obj) >= 0) | |
7071 | return Qt; | |
7072 | if (! SYMBOLP (obj) | |
7073 | || NILP (Fget (obj, Qcoding_system_define_form))) | |
7074 | return Qnil; | |
7075 | return Qt; | |
4ed46869 KH |
7076 | } |
7077 | ||
9d991de8 RS |
7078 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
7079 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae PJ |
7080 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
7081 | (prompt) | |
4ed46869 KH |
7082 | Lisp_Object prompt; |
7083 | { | |
e0e989f6 | 7084 | Lisp_Object val; |
9d991de8 RS |
7085 | do |
7086 | { | |
4608c386 KH |
7087 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
7088 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 7089 | } |
8f924df7 | 7090 | while (SCHARS (val) == 0); |
e0e989f6 | 7091 | return (Fintern (val, Qnil)); |
4ed46869 KH |
7092 | } |
7093 | ||
9b787f3e | 7094 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae PJ |
7095 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
7096 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. */) | |
7097 | (prompt, default_coding_system) | |
9b787f3e | 7098 | Lisp_Object prompt, default_coding_system; |
4ed46869 | 7099 | { |
f44d27ce | 7100 | Lisp_Object val; |
9b787f3e | 7101 | if (SYMBOLP (default_coding_system)) |
a3181084 | 7102 | XSETSTRING (default_coding_system, XPNTR (SYMBOL_NAME (default_coding_system))); |
4608c386 | 7103 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
7104 | Qt, Qnil, Qcoding_system_history, |
7105 | default_coding_system, Qnil); | |
8f924df7 | 7106 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
7107 | } |
7108 | ||
7109 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
7110 | 1, 1, 0, | |
48b0f3ae | 7111 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
7112 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
7113 | It is valid if it is nil or a symbol defined as a coding system by the | |
7114 | function `define-coding-system'. */) | |
df7492f9 | 7115 | (coding_system) |
4ed46869 KH |
7116 | Lisp_Object coding_system; |
7117 | { | |
44e8490d KH |
7118 | Lisp_Object define_form; |
7119 | ||
7120 | define_form = Fget (coding_system, Qcoding_system_define_form); | |
7121 | if (! NILP (define_form)) | |
7122 | { | |
7123 | Fput (coding_system, Qcoding_system_define_form, Qnil); | |
7124 | safe_eval (define_form); | |
7125 | } | |
4ed46869 KH |
7126 | if (!NILP (Fcoding_system_p (coding_system))) |
7127 | return coding_system; | |
7128 | while (1) | |
02ba4723 | 7129 | Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil)); |
4ed46869 | 7130 | } |
df7492f9 | 7131 | |
3a73fa5d | 7132 | \f |
89528eb3 KH |
7133 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
7134 | HIGHEST is nonzero, return the coding system of the highest | |
7135 | priority among the detected coding systems. Otherwize return a | |
7136 | list of detected coding systems sorted by their priorities. If | |
7137 | MULTIBYTEP is nonzero, it is assumed that the bytes are in correct | |
7138 | multibyte form but contains only ASCII and eight-bit chars. | |
7139 | Otherwise, the bytes are raw bytes. | |
7140 | ||
7141 | CODING-SYSTEM controls the detection as below: | |
7142 | ||
7143 | If it is nil, detect both text-format and eol-format. If the | |
7144 | text-format part of CODING-SYSTEM is already specified | |
7145 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
7146 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
7147 | detect only text-format. */ | |
7148 | ||
d46c5b12 | 7149 | Lisp_Object |
24a73b0a KH |
7150 | detect_coding_system (src, src_chars, src_bytes, highest, multibytep, |
7151 | coding_system) | |
8f924df7 | 7152 | const unsigned char *src; |
24a73b0a | 7153 | int src_chars, src_bytes, highest; |
0a28aafb | 7154 | int multibytep; |
df7492f9 | 7155 | Lisp_Object coding_system; |
4ed46869 | 7156 | { |
8f924df7 | 7157 | const unsigned char *src_end = src + src_bytes; |
df7492f9 KH |
7158 | Lisp_Object attrs, eol_type; |
7159 | Lisp_Object val; | |
7160 | struct coding_system coding; | |
89528eb3 | 7161 | int id; |
ff0dacd7 | 7162 | struct coding_detection_info detect_info; |
24a73b0a | 7163 | enum coding_category base_category; |
b73bfc1c | 7164 | |
df7492f9 KH |
7165 | if (NILP (coding_system)) |
7166 | coding_system = Qundecided; | |
7167 | setup_coding_system (coding_system, &coding); | |
7168 | attrs = CODING_ID_ATTRS (coding.id); | |
7169 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 7170 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 7171 | |
df7492f9 | 7172 | coding.source = src; |
24a73b0a | 7173 | coding.src_chars = src_chars; |
df7492f9 KH |
7174 | coding.src_bytes = src_bytes; |
7175 | coding.src_multibyte = multibytep; | |
7176 | coding.consumed = 0; | |
89528eb3 | 7177 | coding.mode |= CODING_MODE_LAST_BLOCK; |
d46c5b12 | 7178 | |
ff0dacd7 | 7179 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 7180 | |
89528eb3 | 7181 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
7182 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
7183 | if (base_category == coding_category_undecided) | |
4ed46869 | 7184 | { |
ff0dacd7 KH |
7185 | enum coding_category category; |
7186 | struct coding_system *this; | |
7187 | int c, i; | |
88993dfd | 7188 | |
24a73b0a KH |
7189 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
7190 | for (i = 0; src < src_end; i++, src++) | |
4ed46869 | 7191 | { |
df7492f9 | 7192 | c = *src; |
6cb21a4f | 7193 | if (c & 0x80) |
d46c5b12 | 7194 | break; |
6cb21a4f KH |
7195 | if (c < 0x20 |
7196 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
7197 | && inhibit_iso_escape_detection) | |
7198 | { | |
7199 | coding.head_ascii = src - coding.source; | |
7200 | if (detect_coding_iso_2022 (&coding, &detect_info)) | |
7201 | { | |
7202 | /* We have scanned the whole data. */ | |
7203 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
7204 | /* We didn't find an 8-bit code. */ | |
7205 | src = src_end; | |
7206 | break; | |
7207 | } | |
7208 | } | |
4ed46869 | 7209 | } |
df7492f9 | 7210 | coding.head_ascii = src - coding.source; |
88993dfd | 7211 | |
6cb21a4f KH |
7212 | if (src < src_end |
7213 | || detect_info.found) | |
7214 | { | |
7215 | if (src == src_end) | |
7216 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
7217 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 7218 | { |
6cb21a4f KH |
7219 | category = coding_priorities[i]; |
7220 | if (detect_info.found & (1 << category)) | |
ff0dacd7 KH |
7221 | break; |
7222 | } | |
6cb21a4f KH |
7223 | else |
7224 | for (i = 0; i < coding_category_raw_text; i++) | |
df7492f9 | 7225 | { |
6cb21a4f KH |
7226 | category = coding_priorities[i]; |
7227 | this = coding_categories + category; | |
7228 | ||
7229 | if (this->id < 0) | |
24a73b0a | 7230 | { |
6cb21a4f KH |
7231 | /* No coding system of this category is defined. */ |
7232 | detect_info.rejected |= (1 << category); | |
7233 | } | |
7234 | else if (category >= coding_category_raw_text) | |
7235 | continue; | |
7236 | else if (detect_info.checked & (1 << category)) | |
7237 | { | |
7238 | if (highest | |
7239 | && (detect_info.found & (1 << category))) | |
7240 | break; | |
7241 | } | |
7242 | else | |
7243 | { | |
7244 | if ((*(this->detector)) (&coding, &detect_info) | |
7245 | && highest | |
7246 | && (detect_info.found & (1 << category))) | |
24a73b0a | 7247 | { |
6cb21a4f KH |
7248 | if (category == coding_category_utf_16_auto) |
7249 | { | |
7250 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
7251 | category = coding_category_utf_16_le; | |
7252 | else | |
7253 | category = coding_category_utf_16_be; | |
7254 | } | |
7255 | break; | |
24a73b0a | 7256 | } |
24a73b0a | 7257 | } |
df7492f9 | 7258 | } |
6cb21a4f | 7259 | } |
ec6d2bb8 | 7260 | |
ff0dacd7 | 7261 | if (detect_info.rejected == CATEGORY_MASK_ANY) |
ec6d2bb8 | 7262 | { |
ff0dacd7 | 7263 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
89528eb3 KH |
7264 | id = coding_categories[coding_category_raw_text].id; |
7265 | val = Fcons (make_number (id), Qnil); | |
7266 | } | |
ff0dacd7 | 7267 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 7268 | { |
ff0dacd7 | 7269 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
7270 | id = coding_categories[coding_category_undecided].id; |
7271 | val = Fcons (make_number (id), Qnil); | |
7272 | } | |
7273 | else if (highest) | |
7274 | { | |
ff0dacd7 | 7275 | if (detect_info.found) |
ec6d2bb8 | 7276 | { |
ff0dacd7 KH |
7277 | detect_info.found = 1 << category; |
7278 | val = Fcons (make_number (this->id), Qnil); | |
7279 | } | |
7280 | else | |
7281 | for (i = 0; i < coding_category_raw_text; i++) | |
7282 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
7283 | { | |
7284 | detect_info.found = 1 << coding_priorities[i]; | |
7285 | id = coding_categories[coding_priorities[i]].id; | |
7286 | val = Fcons (make_number (id), Qnil); | |
7287 | break; | |
7288 | } | |
7289 | } | |
89528eb3 KH |
7290 | else |
7291 | { | |
ff0dacd7 KH |
7292 | int mask = detect_info.rejected | detect_info.found; |
7293 | int found = 0; | |
89528eb3 | 7294 | val = Qnil; |
ec6d2bb8 | 7295 | |
89528eb3 | 7296 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
7297 | { |
7298 | category = coding_priorities[i]; | |
7299 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 7300 | { |
ff0dacd7 KH |
7301 | found |= 1 << category; |
7302 | id = coding_categories[category].id; | |
7303 | val = Fcons (make_number (id), val); | |
7304 | } | |
7305 | } | |
7306 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
7307 | { | |
7308 | category = coding_priorities[i]; | |
7309 | if (detect_info.found & (1 << category)) | |
7310 | { | |
7311 | id = coding_categories[category].id; | |
7312 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 7313 | } |
ec6d2bb8 | 7314 | } |
ff0dacd7 | 7315 | detect_info.found |= found; |
ec6d2bb8 | 7316 | } |
ec6d2bb8 | 7317 | } |
24a73b0a KH |
7318 | else if (base_category == coding_category_utf_16_auto) |
7319 | { | |
7320 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
7321 | { | |
24a73b0a KH |
7322 | struct coding_system *this; |
7323 | ||
7324 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
7325 | this = coding_categories + coding_category_utf_16_le; | |
7326 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
7327 | this = coding_categories + coding_category_utf_16_be; | |
7328 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
7329 | this = coding_categories + coding_category_utf_16_be_nosig; | |
7330 | else | |
7331 | this = coding_categories + coding_category_utf_16_le_nosig; | |
7332 | val = Fcons (make_number (this->id), Qnil); | |
7333 | } | |
7334 | } | |
df7492f9 KH |
7335 | else |
7336 | { | |
ff0dacd7 | 7337 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 7338 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 7339 | } |
df7492f9 | 7340 | |
89528eb3 | 7341 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 7342 | { |
89528eb3 | 7343 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol; |
df7492f9 KH |
7344 | Lisp_Object tail; |
7345 | ||
89528eb3 KH |
7346 | if (VECTORP (eol_type)) |
7347 | { | |
ff0dacd7 | 7348 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
89528eb3 KH |
7349 | normal_eol = detect_eol (coding.source, src_bytes, |
7350 | coding_category_raw_text); | |
ff0dacd7 KH |
7351 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
7352 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
7353 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
7354 | coding_category_utf_16_be); | |
ff0dacd7 KH |
7355 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
7356 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
7357 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
7358 | coding_category_utf_16_le); | |
7359 | } | |
7360 | else | |
7361 | { | |
7362 | if (EQ (eol_type, Qunix)) | |
7363 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
7364 | else if (EQ (eol_type, Qdos)) | |
7365 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
7366 | else | |
7367 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
7368 | } | |
7369 | ||
df7492f9 KH |
7370 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
7371 | { | |
89528eb3 | 7372 | enum coding_category category; |
df7492f9 | 7373 | int this_eol; |
89528eb3 KH |
7374 | |
7375 | id = XINT (XCAR (tail)); | |
7376 | attrs = CODING_ID_ATTRS (id); | |
7377 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
7378 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
7379 | if (VECTORP (eol_type)) |
7380 | { | |
89528eb3 KH |
7381 | if (category == coding_category_utf_16_be |
7382 | || category == coding_category_utf_16_be_nosig) | |
7383 | this_eol = utf_16_be_eol; | |
7384 | else if (category == coding_category_utf_16_le | |
7385 | || category == coding_category_utf_16_le_nosig) | |
7386 | this_eol = utf_16_le_eol; | |
df7492f9 | 7387 | else |
89528eb3 KH |
7388 | this_eol = normal_eol; |
7389 | ||
df7492f9 KH |
7390 | if (this_eol == EOL_SEEN_LF) |
7391 | XSETCAR (tail, AREF (eol_type, 0)); | |
7392 | else if (this_eol == EOL_SEEN_CRLF) | |
7393 | XSETCAR (tail, AREF (eol_type, 1)); | |
7394 | else if (this_eol == EOL_SEEN_CR) | |
7395 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
7396 | else |
7397 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 7398 | } |
89528eb3 KH |
7399 | else |
7400 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
7401 | } |
7402 | } | |
ec6d2bb8 | 7403 | |
03699b14 | 7404 | return (highest ? XCAR (val) : val); |
ec6d2bb8 KH |
7405 | } |
7406 | ||
ec6d2bb8 | 7407 | |
d46c5b12 KH |
7408 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
7409 | 2, 3, 0, | |
48b0f3ae PJ |
7410 | doc: /* Detect coding system of the text in the region between START and END. |
7411 | Return a list of possible coding systems ordered by priority. | |
ec6d2bb8 | 7412 | |
48b0f3ae PJ |
7413 | If only ASCII characters are found, it returns a list of single element |
7414 | `undecided' or its subsidiary coding system according to a detected | |
7415 | end-of-line format. | |
ec6d2bb8 | 7416 | |
48b0f3ae PJ |
7417 | If optional argument HIGHEST is non-nil, return the coding system of |
7418 | highest priority. */) | |
7419 | (start, end, highest) | |
d46c5b12 KH |
7420 | Lisp_Object start, end, highest; |
7421 | { | |
7422 | int from, to; | |
7423 | int from_byte, to_byte; | |
ec6d2bb8 | 7424 | |
b7826503 PJ |
7425 | CHECK_NUMBER_COERCE_MARKER (start); |
7426 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 7427 | |
d46c5b12 KH |
7428 | validate_region (&start, &end); |
7429 | from = XINT (start), to = XINT (end); | |
7430 | from_byte = CHAR_TO_BYTE (from); | |
7431 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 7432 | |
d46c5b12 KH |
7433 | if (from < GPT && to >= GPT) |
7434 | move_gap_both (to, to_byte); | |
c210f766 | 7435 | |
d46c5b12 | 7436 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 7437 | to - from, to_byte - from_byte, |
0a28aafb KH |
7438 | !NILP (highest), |
7439 | !NILP (current_buffer | |
df7492f9 KH |
7440 | ->enable_multibyte_characters), |
7441 | Qnil); | |
ec6d2bb8 KH |
7442 | } |
7443 | ||
d46c5b12 KH |
7444 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
7445 | 1, 2, 0, | |
48b0f3ae PJ |
7446 | doc: /* Detect coding system of the text in STRING. |
7447 | Return a list of possible coding systems ordered by priority. | |
fb88bf2d | 7448 | |
48b0f3ae PJ |
7449 | If only ASCII characters are found, it returns a list of single element |
7450 | `undecided' or its subsidiary coding system according to a detected | |
7451 | end-of-line format. | |
d46c5b12 | 7452 | |
48b0f3ae PJ |
7453 | If optional argument HIGHEST is non-nil, return the coding system of |
7454 | highest priority. */) | |
7455 | (string, highest) | |
d46c5b12 KH |
7456 | Lisp_Object string, highest; |
7457 | { | |
b7826503 | 7458 | CHECK_STRING (string); |
b73bfc1c | 7459 | |
24a73b0a KH |
7460 | return detect_coding_system (SDATA (string), |
7461 | SCHARS (string), SBYTES (string), | |
8f924df7 | 7462 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 7463 | Qnil); |
4ed46869 | 7464 | } |
4ed46869 | 7465 | |
b73bfc1c | 7466 | |
df7492f9 KH |
7467 | static INLINE int |
7468 | char_encodable_p (c, attrs) | |
7469 | int c; | |
7470 | Lisp_Object attrs; | |
05e6f5dc | 7471 | { |
df7492f9 | 7472 | Lisp_Object tail; |
df7492f9 | 7473 | struct charset *charset; |
7d64c6ad | 7474 | Lisp_Object translation_table; |
d46c5b12 | 7475 | |
7d64c6ad | 7476 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 7477 | if (! NILP (translation_table)) |
7d64c6ad | 7478 | c = translate_char (translation_table, c); |
df7492f9 KH |
7479 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
7480 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 7481 | { |
df7492f9 KH |
7482 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
7483 | if (CHAR_CHARSET_P (c, charset)) | |
7484 | break; | |
e133c8fa | 7485 | } |
df7492f9 | 7486 | return (! NILP (tail)); |
05e6f5dc | 7487 | } |
83fa074f | 7488 | |
fb88bf2d | 7489 | |
df7492f9 KH |
7490 | /* Return a list of coding systems that safely encode the text between |
7491 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
7492 | systems not to check. The returned list doesn't contain any such | |
48468dac | 7493 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 7494 | unibyte, return t. */ |
e077cc80 | 7495 | |
df7492f9 KH |
7496 | DEFUN ("find-coding-systems-region-internal", |
7497 | Ffind_coding_systems_region_internal, | |
7498 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
7499 | doc: /* Internal use only. */) | |
7500 | (start, end, exclude) | |
7501 | Lisp_Object start, end, exclude; | |
7502 | { | |
7503 | Lisp_Object coding_attrs_list, safe_codings; | |
7504 | EMACS_INT start_byte, end_byte; | |
7c78e542 | 7505 | const unsigned char *p, *pbeg, *pend; |
df7492f9 KH |
7506 | int c; |
7507 | Lisp_Object tail, elt; | |
d46c5b12 | 7508 | |
df7492f9 KH |
7509 | if (STRINGP (start)) |
7510 | { | |
7511 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 7512 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
7513 | return Qt; |
7514 | start_byte = 0; | |
8f924df7 | 7515 | end_byte = SBYTES (start); |
df7492f9 KH |
7516 | } |
7517 | else | |
d46c5b12 | 7518 | { |
df7492f9 KH |
7519 | CHECK_NUMBER_COERCE_MARKER (start); |
7520 | CHECK_NUMBER_COERCE_MARKER (end); | |
7521 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
7522 | args_out_of_range (start, end); | |
7523 | if (NILP (current_buffer->enable_multibyte_characters)) | |
7524 | return Qt; | |
7525 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7526 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7527 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
7528 | return Qt; | |
d46c5b12 | 7529 | |
e1c23804 | 7530 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 7531 | { |
e1c23804 DL |
7532 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7533 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7534 | else |
e1c23804 | 7535 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
7536 | } |
7537 | } | |
7538 | ||
df7492f9 KH |
7539 | coding_attrs_list = Qnil; |
7540 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
7541 | if (NILP (exclude) | |
7542 | || NILP (Fmemq (XCAR (tail), exclude))) | |
7543 | { | |
7544 | Lisp_Object attrs; | |
d46c5b12 | 7545 | |
df7492f9 KH |
7546 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
7547 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
7548 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
7549 | { |
7550 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 7551 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
7552 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
7553 | } | |
df7492f9 | 7554 | } |
d46c5b12 | 7555 | |
df7492f9 | 7556 | if (STRINGP (start)) |
8f924df7 | 7557 | p = pbeg = SDATA (start); |
df7492f9 KH |
7558 | else |
7559 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
7560 | pend = p + (end_byte - start_byte); | |
b843d1ae | 7561 | |
df7492f9 KH |
7562 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
7563 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 7564 | |
05e6f5dc | 7565 | while (p < pend) |
72d1a715 | 7566 | { |
df7492f9 KH |
7567 | if (ASCII_BYTE_P (*p)) |
7568 | p++; | |
72d1a715 RS |
7569 | else |
7570 | { | |
df7492f9 | 7571 | c = STRING_CHAR_ADVANCE (p); |
12410ef1 | 7572 | |
df7492f9 KH |
7573 | charset_map_loaded = 0; |
7574 | for (tail = coding_attrs_list; CONSP (tail);) | |
7575 | { | |
7576 | elt = XCAR (tail); | |
7577 | if (NILP (elt)) | |
7578 | tail = XCDR (tail); | |
7579 | else if (char_encodable_p (c, elt)) | |
7580 | tail = XCDR (tail); | |
7581 | else if (CONSP (XCDR (tail))) | |
7582 | { | |
7583 | XSETCAR (tail, XCAR (XCDR (tail))); | |
7584 | XSETCDR (tail, XCDR (XCDR (tail))); | |
7585 | } | |
7586 | else | |
7587 | { | |
7588 | XSETCAR (tail, Qnil); | |
7589 | tail = XCDR (tail); | |
7590 | } | |
7591 | } | |
7592 | if (charset_map_loaded) | |
7593 | { | |
7594 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 7595 | |
df7492f9 | 7596 | if (STRINGP (start)) |
8f924df7 | 7597 | pbeg = SDATA (start); |
df7492f9 KH |
7598 | else |
7599 | pbeg = BYTE_POS_ADDR (start_byte); | |
7600 | p = pbeg + p_offset; | |
7601 | pend = pbeg + pend_offset; | |
7602 | } | |
7603 | } | |
ec6d2bb8 | 7604 | } |
fb88bf2d | 7605 | |
988b3759 | 7606 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
7607 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
7608 | if (! NILP (XCAR (tail))) | |
7609 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 7610 | |
05e6f5dc KH |
7611 | return safe_codings; |
7612 | } | |
4956c225 | 7613 | |
d46c5b12 | 7614 | |
8f924df7 KH |
7615 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
7616 | Sunencodable_char_position, 3, 5, 0, | |
7617 | doc: /* | |
7618 | Return position of first un-encodable character in a region. | |
7619 | START and END specfiy the region and CODING-SYSTEM specifies the | |
7620 | encoding to check. Return nil if CODING-SYSTEM does encode the region. | |
d46c5b12 | 7621 | |
8f924df7 KH |
7622 | If optional 4th argument COUNT is non-nil, it specifies at most how |
7623 | many un-encodable characters to search. In this case, the value is a | |
7624 | list of positions. | |
d46c5b12 | 7625 | |
8f924df7 KH |
7626 | If optional 5th argument STRING is non-nil, it is a string to search |
7627 | for un-encodable characters. In that case, START and END are indexes | |
7628 | to the string. */) | |
7629 | (start, end, coding_system, count, string) | |
7630 | Lisp_Object start, end, coding_system, count, string; | |
7631 | { | |
7632 | int n; | |
7633 | struct coding_system coding; | |
7d64c6ad | 7634 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 KH |
7635 | Lisp_Object positions; |
7636 | int from, to; | |
7637 | const unsigned char *p, *stop, *pend; | |
7638 | int ascii_compatible; | |
fb88bf2d | 7639 | |
8f924df7 KH |
7640 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
7641 | attrs = CODING_ID_ATTRS (coding.id); | |
7642 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
7643 | return Qnil; | |
7644 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
7645 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 7646 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 7647 | |
8f924df7 KH |
7648 | if (NILP (string)) |
7649 | { | |
7650 | validate_region (&start, &end); | |
7651 | from = XINT (start); | |
7652 | to = XINT (end); | |
7653 | if (NILP (current_buffer->enable_multibyte_characters) | |
7654 | || (ascii_compatible | |
7655 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
7656 | return Qnil; | |
7657 | p = CHAR_POS_ADDR (from); | |
7658 | pend = CHAR_POS_ADDR (to); | |
7659 | if (from < GPT && to >= GPT) | |
7660 | stop = GPT_ADDR; | |
7661 | else | |
7662 | stop = pend; | |
7663 | } | |
7664 | else | |
7665 | { | |
7666 | CHECK_STRING (string); | |
7667 | CHECK_NATNUM (start); | |
7668 | CHECK_NATNUM (end); | |
7669 | from = XINT (start); | |
7670 | to = XINT (end); | |
7671 | if (from > to | |
7672 | || to > SCHARS (string)) | |
7673 | args_out_of_range_3 (string, start, end); | |
7674 | if (! STRING_MULTIBYTE (string)) | |
7675 | return Qnil; | |
7676 | p = SDATA (string) + string_char_to_byte (string, from); | |
7677 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
7678 | if (ascii_compatible && (to - from) == (pend - p)) | |
7679 | return Qnil; | |
7680 | } | |
f2558efd | 7681 | |
8f924df7 KH |
7682 | if (NILP (count)) |
7683 | n = 1; | |
7684 | else | |
b73bfc1c | 7685 | { |
8f924df7 KH |
7686 | CHECK_NATNUM (count); |
7687 | n = XINT (count); | |
b73bfc1c KH |
7688 | } |
7689 | ||
8f924df7 KH |
7690 | positions = Qnil; |
7691 | while (1) | |
d46c5b12 | 7692 | { |
8f924df7 | 7693 | int c; |
ec6d2bb8 | 7694 | |
8f924df7 KH |
7695 | if (ascii_compatible) |
7696 | while (p < stop && ASCII_BYTE_P (*p)) | |
7697 | p++, from++; | |
7698 | if (p >= stop) | |
0e79d667 | 7699 | { |
8f924df7 KH |
7700 | if (p >= pend) |
7701 | break; | |
7702 | stop = pend; | |
7703 | p = GAP_END_ADDR; | |
0e79d667 | 7704 | } |
ec6d2bb8 | 7705 | |
8f924df7 KH |
7706 | c = STRING_CHAR_ADVANCE (p); |
7707 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
7708 | && ! char_charset (translate_char (translation_table, c), |
7709 | charset_list, NULL)) | |
ec6d2bb8 | 7710 | { |
8f924df7 KH |
7711 | positions = Fcons (make_number (from), positions); |
7712 | n--; | |
7713 | if (n == 0) | |
7714 | break; | |
ec6d2bb8 KH |
7715 | } |
7716 | ||
8f924df7 KH |
7717 | from++; |
7718 | } | |
d46c5b12 | 7719 | |
8f924df7 KH |
7720 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
7721 | } | |
d46c5b12 | 7722 | |
d46c5b12 | 7723 | |
df7492f9 KH |
7724 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
7725 | Scheck_coding_systems_region, 3, 3, 0, | |
7726 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 7727 | |
df7492f9 KH |
7728 | START and END are buffer positions specifying the region. |
7729 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 7730 | |
df7492f9 KH |
7731 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
7732 | CODING-SYSTEM is a member of CODING-SYSTEM-LIst and can't encode the | |
7733 | whole region, POS0, POS1, ... are buffer positions where non-encodable | |
7734 | characters are found. | |
93dec019 | 7735 | |
df7492f9 KH |
7736 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
7737 | value is nil. | |
93dec019 | 7738 | |
df7492f9 KH |
7739 | START may be a string. In that case, check if the string is |
7740 | encodable, and the value contains indices to the string instead of | |
7741 | buffer positions. END is ignored. */) | |
7742 | (start, end, coding_system_list) | |
7743 | Lisp_Object start, end, coding_system_list; | |
05e6f5dc | 7744 | { |
df7492f9 KH |
7745 | Lisp_Object list; |
7746 | EMACS_INT start_byte, end_byte; | |
7747 | int pos; | |
7c78e542 | 7748 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 7749 | int c; |
7d64c6ad | 7750 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 7751 | |
05e6f5dc KH |
7752 | if (STRINGP (start)) |
7753 | { | |
df7492f9 | 7754 | if (!STRING_MULTIBYTE (start) |
8f924df7 | 7755 | && SCHARS (start) != SBYTES (start)) |
df7492f9 KH |
7756 | return Qnil; |
7757 | start_byte = 0; | |
8f924df7 | 7758 | end_byte = SBYTES (start); |
df7492f9 | 7759 | pos = 0; |
d46c5b12 | 7760 | } |
05e6f5dc | 7761 | else |
b73bfc1c | 7762 | { |
b7826503 PJ |
7763 | CHECK_NUMBER_COERCE_MARKER (start); |
7764 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
7765 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
7766 | args_out_of_range (start, end); | |
7767 | if (NILP (current_buffer->enable_multibyte_characters)) | |
df7492f9 KH |
7768 | return Qnil; |
7769 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7770 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7771 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
05e6f5dc | 7772 | return Qt; |
df7492f9 | 7773 | |
e1c23804 | 7774 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 7775 | { |
e1c23804 DL |
7776 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7777 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7778 | else |
e1c23804 | 7779 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 7780 | } |
e1c23804 | 7781 | pos = XINT (start); |
b73bfc1c | 7782 | } |
7553d0e1 | 7783 | |
df7492f9 KH |
7784 | list = Qnil; |
7785 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 7786 | { |
df7492f9 | 7787 | elt = XCAR (tail); |
7d64c6ad | 7788 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
7789 | ASET (attrs, coding_attr_trans_tbl, |
7790 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 7791 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
7792 | } |
7793 | ||
df7492f9 | 7794 | if (STRINGP (start)) |
8f924df7 | 7795 | p = pbeg = SDATA (start); |
72d1a715 | 7796 | else |
df7492f9 KH |
7797 | p = pbeg = BYTE_POS_ADDR (start_byte); |
7798 | pend = p + (end_byte - start_byte); | |
4ed46869 | 7799 | |
df7492f9 KH |
7800 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
7801 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 7802 | |
df7492f9 | 7803 | while (p < pend) |
d46c5b12 | 7804 | { |
df7492f9 KH |
7805 | if (ASCII_BYTE_P (*p)) |
7806 | p++; | |
e133c8fa | 7807 | else |
05e6f5dc | 7808 | { |
df7492f9 KH |
7809 | c = STRING_CHAR_ADVANCE (p); |
7810 | ||
7811 | charset_map_loaded = 0; | |
7812 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
7813 | { | |
7814 | elt = XCDR (XCAR (tail)); | |
7815 | if (! char_encodable_p (c, XCAR (elt))) | |
7816 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
7817 | } | |
7818 | if (charset_map_loaded) | |
7819 | { | |
7820 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
7821 | ||
7822 | if (STRINGP (start)) | |
8f924df7 | 7823 | pbeg = SDATA (start); |
df7492f9 KH |
7824 | else |
7825 | pbeg = BYTE_POS_ADDR (start_byte); | |
7826 | p = pbeg + p_offset; | |
7827 | pend = pbeg + pend_offset; | |
7828 | } | |
05e6f5dc | 7829 | } |
df7492f9 | 7830 | pos++; |
d46c5b12 | 7831 | } |
4ed46869 | 7832 | |
df7492f9 KH |
7833 | tail = list; |
7834 | list = Qnil; | |
7835 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 7836 | { |
df7492f9 KH |
7837 | elt = XCAR (tail); |
7838 | if (CONSP (XCDR (XCDR (elt)))) | |
7839 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
7840 | list); | |
ec6d2bb8 | 7841 | } |
2b4f9037 | 7842 | |
df7492f9 | 7843 | return list; |
d46c5b12 KH |
7844 | } |
7845 | ||
3fd9494b | 7846 | |
b73bfc1c | 7847 | Lisp_Object |
df7492f9 KH |
7848 | code_convert_region (start, end, coding_system, dst_object, encodep, norecord) |
7849 | Lisp_Object start, end, coding_system, dst_object; | |
7850 | int encodep, norecord; | |
4ed46869 | 7851 | { |
3a73fa5d | 7852 | struct coding_system coding; |
df7492f9 KH |
7853 | EMACS_INT from, from_byte, to, to_byte; |
7854 | Lisp_Object src_object; | |
4ed46869 | 7855 | |
b7826503 PJ |
7856 | CHECK_NUMBER_COERCE_MARKER (start); |
7857 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
7858 | if (NILP (coding_system)) |
7859 | coding_system = Qno_conversion; | |
7860 | else | |
7861 | CHECK_CODING_SYSTEM (coding_system); | |
7862 | src_object = Fcurrent_buffer (); | |
7863 | if (NILP (dst_object)) | |
7864 | dst_object = src_object; | |
7865 | else if (! EQ (dst_object, Qt)) | |
7866 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 7867 | |
d46c5b12 KH |
7868 | validate_region (&start, &end); |
7869 | from = XFASTINT (start); | |
df7492f9 | 7870 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 7871 | to = XFASTINT (end); |
df7492f9 | 7872 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 7873 | |
df7492f9 KH |
7874 | setup_coding_system (coding_system, &coding); |
7875 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 7876 | |
df7492f9 KH |
7877 | if (encodep) |
7878 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7879 | dst_object); | |
7880 | else | |
7881 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7882 | dst_object); | |
7883 | if (! norecord) | |
7884 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 7885 | |
df7492f9 KH |
7886 | return (BUFFERP (dst_object) |
7887 | ? make_number (coding.produced_char) | |
7888 | : coding.dst_object); | |
4031e2bf | 7889 | } |
78108bcd | 7890 | |
4ed46869 | 7891 | |
4031e2bf | 7892 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 7893 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 7894 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
7895 | When called from a program, takes four arguments: |
7896 | START, END, CODING-SYSTEM, and DESTINATION. | |
7897 | START and END are buffer positions. | |
8844fa83 | 7898 | |
df7492f9 KH |
7899 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
7900 | If nil, the region between START and END is replace by the decoded text. | |
7901 | If buffer, the decoded text is inserted in the buffer. | |
7902 | If t, the decoded text is returned. | |
8844fa83 | 7903 | |
48b0f3ae PJ |
7904 | This function sets `last-coding-system-used' to the precise coding system |
7905 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7906 | not fully specified.) | |
7907 | It returns the length of the decoded text. */) | |
df7492f9 KH |
7908 | (start, end, coding_system, destination) |
7909 | Lisp_Object start, end, coding_system, destination; | |
4031e2bf | 7910 | { |
df7492f9 | 7911 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 7912 | } |
8844fa83 | 7913 | |
3a73fa5d | 7914 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
7915 | 3, 4, "r\nzCoding system: ", |
7916 | doc: /* Encode the current region by specified coding system. | |
48b0f3ae PJ |
7917 | When called from a program, takes three arguments: |
7918 | START, END, and CODING-SYSTEM. START and END are buffer positions. | |
d46c5b12 | 7919 | |
df7492f9 KH |
7920 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
7921 | If nil, the region between START and END is replace by the encoded text. | |
7922 | If buffer, the encoded text is inserted in the buffer. | |
7923 | If t, the encoded text is returned. | |
2391eaa4 | 7924 | |
48b0f3ae PJ |
7925 | This function sets `last-coding-system-used' to the precise coding system |
7926 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7927 | not fully specified.) | |
7928 | It returns the length of the encoded text. */) | |
df7492f9 KH |
7929 | (start, end, coding_system, destination) |
7930 | Lisp_Object start, end, coding_system, destination; | |
3a73fa5d | 7931 | { |
df7492f9 | 7932 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
7933 | } |
7934 | ||
7935 | Lisp_Object | |
df7492f9 KH |
7936 | code_convert_string (string, coding_system, dst_object, |
7937 | encodep, nocopy, norecord) | |
7938 | Lisp_Object string, coding_system, dst_object; | |
7939 | int encodep, nocopy, norecord; | |
b73bfc1c | 7940 | { |
4031e2bf | 7941 | struct coding_system coding; |
df7492f9 | 7942 | EMACS_INT chars, bytes; |
ec6d2bb8 | 7943 | |
b7826503 | 7944 | CHECK_STRING (string); |
d46c5b12 | 7945 | if (NILP (coding_system)) |
4956c225 | 7946 | { |
df7492f9 KH |
7947 | if (! norecord) |
7948 | Vlast_coding_system_used = Qno_conversion; | |
7949 | if (NILP (dst_object)) | |
7950 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 7951 | } |
b73bfc1c | 7952 | |
df7492f9 KH |
7953 | if (NILP (coding_system)) |
7954 | coding_system = Qno_conversion; | |
7955 | else | |
7956 | CHECK_CODING_SYSTEM (coding_system); | |
7957 | if (NILP (dst_object)) | |
7958 | dst_object = Qt; | |
7959 | else if (! EQ (dst_object, Qt)) | |
7960 | CHECK_BUFFER (dst_object); | |
73be902c | 7961 | |
df7492f9 | 7962 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 7963 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
7964 | chars = SCHARS (string); |
7965 | bytes = SBYTES (string); | |
df7492f9 KH |
7966 | if (encodep) |
7967 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7968 | else | |
7969 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7970 | if (! norecord) | |
7971 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 7972 | |
df7492f9 KH |
7973 | return (BUFFERP (dst_object) |
7974 | ? make_number (coding.produced_char) | |
7975 | : coding.dst_object); | |
4ed46869 | 7976 | } |
73be902c | 7977 | |
b73bfc1c | 7978 | |
ecec61c1 | 7979 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 7980 | Do not set Vlast_coding_system_used. |
4ed46869 | 7981 | |
ec6d2bb8 KH |
7982 | This function is called only from macros DECODE_FILE and |
7983 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 7984 | |
ecec61c1 KH |
7985 | Lisp_Object |
7986 | code_convert_string_norecord (string, coding_system, encodep) | |
7987 | Lisp_Object string, coding_system; | |
7988 | int encodep; | |
4ed46869 | 7989 | { |
0be8721c | 7990 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
7991 | } |
7992 | ||
4ed46869 | 7993 | |
df7492f9 KH |
7994 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
7995 | 2, 4, 0, | |
7996 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
7997 | ||
7998 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
7999 | if the decoding operation is trivial. | |
ecec61c1 | 8000 | |
df7492f9 | 8001 | Optional fourth arg BUFFER non-nil meant that the decoded text is |
a3f6ee6d | 8002 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 | 8003 | the return value is BUFFER. |
ecec61c1 | 8004 | |
df7492f9 KH |
8005 | This function sets `last-coding-system-used' to the precise coding system |
8006 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
8007 | not fully specified. */) | |
8008 | (string, coding_system, nocopy, buffer) | |
8009 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 8010 | { |
df7492f9 KH |
8011 | return code_convert_string (string, coding_system, buffer, |
8012 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
8013 | } |
8014 | ||
df7492f9 KH |
8015 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
8016 | 2, 4, 0, | |
8017 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
8018 | ||
8019 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
8020 | itself if the encoding operation is trivial. | |
8021 | ||
8022 | Optional fourth arg BUFFER non-nil meant that the encoded text is | |
a3f6ee6d | 8023 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 KH |
8024 | the return value is BUFFER. |
8025 | ||
8026 | This function sets `last-coding-system-used' to the precise coding system | |
8027 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
8028 | not fully specified.) */) | |
8029 | (string, coding_system, nocopy, buffer) | |
8030 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 8031 | { |
df7492f9 | 8032 | return code_convert_string (string, coding_system, buffer, |
c197f191 | 8033 | 1, ! NILP (nocopy), 1); |
4ed46869 | 8034 | } |
df7492f9 | 8035 | |
3a73fa5d | 8036 | \f |
4ed46869 | 8037 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
8038 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
8039 | Return the corresponding character. */) | |
8040 | (code) | |
4ed46869 | 8041 | Lisp_Object code; |
4ed46869 | 8042 | { |
df7492f9 KH |
8043 | Lisp_Object spec, attrs, val; |
8044 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
8045 | int c; | |
4ed46869 | 8046 | |
df7492f9 KH |
8047 | CHECK_NATNUM (code); |
8048 | c = XFASTINT (code); | |
8049 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
8050 | attrs = AREF (spec, 0); | |
4ed46869 | 8051 | |
df7492f9 KH |
8052 | if (ASCII_BYTE_P (c) |
8053 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8054 | return code; | |
4ed46869 | 8055 | |
df7492f9 KH |
8056 | val = CODING_ATTR_CHARSET_LIST (attrs); |
8057 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
8058 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
8059 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 8060 | |
df7492f9 KH |
8061 | if (c <= 0x7F) |
8062 | charset = charset_roman; | |
8063 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 8064 | { |
df7492f9 KH |
8065 | charset = charset_kana; |
8066 | c -= 0x80; | |
4ed46869 | 8067 | } |
55ab7be3 | 8068 | else |
4ed46869 | 8069 | { |
004068e4 | 8070 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
8071 | |
8072 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
8073 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
8074 | error ("Invalid code: %d", code); | |
8075 | SJIS_TO_JIS (c); | |
8076 | charset = charset_kanji; | |
4ed46869 | 8077 | } |
df7492f9 KH |
8078 | c = DECODE_CHAR (charset, c); |
8079 | if (c < 0) | |
8080 | error ("Invalid code: %d", code); | |
8081 | return make_number (c); | |
93dec019 | 8082 | } |
4ed46869 | 8083 | |
48b0f3ae | 8084 | |
4ed46869 | 8085 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
8086 | doc: /* Encode a Japanese character CHAR to shift_jis encoding. |
8087 | Return the corresponding code in SJIS. */) | |
8088 | (ch) | |
df7492f9 | 8089 | Lisp_Object ch; |
4ed46869 | 8090 | { |
df7492f9 KH |
8091 | Lisp_Object spec, attrs, charset_list; |
8092 | int c; | |
8093 | struct charset *charset; | |
8094 | unsigned code; | |
48b0f3ae | 8095 | |
df7492f9 KH |
8096 | CHECK_CHARACTER (ch); |
8097 | c = XFASTINT (ch); | |
8098 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
8099 | attrs = AREF (spec, 0); | |
8100 | ||
8101 | if (ASCII_CHAR_P (c) | |
8102 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8103 | return ch; | |
8104 | ||
8105 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
8106 | charset = char_charset (c, charset_list, &code); | |
8107 | if (code == CHARSET_INVALID_CODE (charset)) | |
8108 | error ("Can't encode by shift_jis encoding: %d", c); | |
8109 | JIS_TO_SJIS (code); | |
8110 | ||
8111 | return make_number (code); | |
4ed46869 KH |
8112 | } |
8113 | ||
8114 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
8115 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
8116 | Return the corresponding character. */) | |
8117 | (code) | |
4ed46869 | 8118 | Lisp_Object code; |
d46c5b12 | 8119 | { |
df7492f9 KH |
8120 | Lisp_Object spec, attrs, val; |
8121 | struct charset *charset_roman, *charset_big5, *charset; | |
8122 | int c; | |
6289dd10 | 8123 | |
df7492f9 KH |
8124 | CHECK_NATNUM (code); |
8125 | c = XFASTINT (code); | |
8126 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
8127 | attrs = AREF (spec, 0); | |
4ed46869 | 8128 | |
df7492f9 KH |
8129 | if (ASCII_BYTE_P (c) |
8130 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8131 | return code; | |
6289dd10 | 8132 | |
df7492f9 KH |
8133 | val = CODING_ATTR_CHARSET_LIST (attrs); |
8134 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
8135 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 8136 | |
df7492f9 KH |
8137 | if (c <= 0x7F) |
8138 | charset = charset_roman; | |
c28a9453 KH |
8139 | else |
8140 | { | |
df7492f9 KH |
8141 | int b1 = c >> 8, b2 = c & 0x7F; |
8142 | if (b1 < 0xA1 || b1 > 0xFE | |
8143 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
8144 | error ("Invalid code: %d", code); | |
8145 | charset = charset_big5; | |
c28a9453 | 8146 | } |
df7492f9 KH |
8147 | c = DECODE_CHAR (charset, (unsigned )c); |
8148 | if (c < 0) | |
8149 | error ("Invalid code: %d", code); | |
8150 | return make_number (c); | |
d46c5b12 | 8151 | } |
6289dd10 | 8152 | |
4ed46869 | 8153 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
48b0f3ae PJ |
8154 | doc: /* Encode the Big5 character CHAR to BIG5 coding system. |
8155 | Return the corresponding character code in Big5. */) | |
8156 | (ch) | |
4ed46869 KH |
8157 | Lisp_Object ch; |
8158 | { | |
df7492f9 KH |
8159 | Lisp_Object spec, attrs, charset_list; |
8160 | struct charset *charset; | |
8161 | int c; | |
8162 | unsigned code; | |
8163 | ||
8164 | CHECK_CHARACTER (ch); | |
8165 | c = XFASTINT (ch); | |
8166 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
8167 | attrs = AREF (spec, 0); | |
8168 | if (ASCII_CHAR_P (c) | |
8169 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8170 | return ch; | |
8171 | ||
8172 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
8173 | charset = char_charset (c, charset_list, &code); | |
8174 | if (code == CHARSET_INVALID_CODE (charset)) | |
8175 | error ("Can't encode by Big5 encoding: %d", c); | |
8176 | ||
8177 | return make_number (code); | |
4ed46869 | 8178 | } |
48b0f3ae | 8179 | |
3a73fa5d | 8180 | \f |
1ba9e4ab KH |
8181 | DEFUN ("set-terminal-coding-system-internal", |
8182 | Fset_terminal_coding_system_internal, | |
48b0f3ae PJ |
8183 | Sset_terminal_coding_system_internal, 1, 1, 0, |
8184 | doc: /* Internal use only. */) | |
8185 | (coding_system) | |
b74e4686 | 8186 | Lisp_Object coding_system; |
4ed46869 | 8187 | { |
b7826503 | 8188 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
8189 | setup_coding_system (Fcheck_coding_system (coding_system), |
8190 | &terminal_coding); | |
48b0f3ae | 8191 | |
70c22245 | 8192 | /* We had better not send unsafe characters to terminal. */ |
df7492f9 KH |
8193 | terminal_coding.mode |= CODING_MODE_SAFE_ENCODING; |
8194 | /* Characer composition should be disabled. */ | |
8195 | terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
8196 | terminal_coding.src_multibyte = 1; |
8197 | terminal_coding.dst_multibyte = 0; | |
4ed46869 KH |
8198 | return Qnil; |
8199 | } | |
8200 | ||
c4825358 KH |
8201 | DEFUN ("set-safe-terminal-coding-system-internal", |
8202 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 8203 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 8204 | doc: /* Internal use only. */) |
48b0f3ae | 8205 | (coding_system) |
b74e4686 | 8206 | Lisp_Object coding_system; |
d46c5b12 | 8207 | { |
b7826503 | 8208 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
8209 | setup_coding_system (Fcheck_coding_system (coding_system), |
8210 | &safe_terminal_coding); | |
df7492f9 KH |
8211 | /* Characer composition should be disabled. */ |
8212 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
8213 | safe_terminal_coding.src_multibyte = 1; |
8214 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
8215 | return Qnil; |
8216 | } | |
4ed46869 | 8217 | |
4ed46869 KH |
8218 | DEFUN ("terminal-coding-system", |
8219 | Fterminal_coding_system, Sterminal_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
8220 | doc: /* Return coding system specified for terminal output. */) |
8221 | () | |
4ed46869 | 8222 | { |
ae6f73fa KH |
8223 | Lisp_Object coding_system; |
8224 | ||
8225 | coding_system = CODING_ID_NAME (terminal_coding.id); | |
8226 | /* For backward compatibility, return nil if it is `undecided'. */ | |
8227 | return (coding_system != Qundecided ? coding_system : Qnil); | |
4ed46869 KH |
8228 | } |
8229 | ||
1ba9e4ab KH |
8230 | DEFUN ("set-keyboard-coding-system-internal", |
8231 | Fset_keyboard_coding_system_internal, | |
48b0f3ae PJ |
8232 | Sset_keyboard_coding_system_internal, 1, 1, 0, |
8233 | doc: /* Internal use only. */) | |
8234 | (coding_system) | |
4ed46869 KH |
8235 | Lisp_Object coding_system; |
8236 | { | |
b7826503 | 8237 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
8238 | setup_coding_system (Fcheck_coding_system (coding_system), |
8239 | &keyboard_coding); | |
8240 | /* Characer composition should be disabled. */ | |
8241 | keyboard_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
8242 | return Qnil; |
8243 | } | |
8244 | ||
8245 | DEFUN ("keyboard-coding-system", | |
8246 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
8247 | doc: /* Return coding system specified for decoding keyboard input. */) |
8248 | () | |
4ed46869 | 8249 | { |
df7492f9 | 8250 | return CODING_ID_NAME (keyboard_coding.id); |
4ed46869 KH |
8251 | } |
8252 | ||
4ed46869 | 8253 | \f |
a5d301df KH |
8254 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
8255 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
8256 | doc: /* Choose a coding system for an operation based on the target name. |
8257 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
8258 | DECODING-SYSTEM is the coding system to use for decoding | |
8259 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
8260 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 8261 | |
48b0f3ae PJ |
8262 | The first argument OPERATION specifies an I/O primitive: |
8263 | For file I/O, `insert-file-contents' or `write-region'. | |
8264 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
8265 | For network I/O, `open-network-stream'. | |
05e6f5dc | 8266 | |
48b0f3ae PJ |
8267 | The remaining arguments should be the same arguments that were passed |
8268 | to the primitive. Depending on which primitive, one of those arguments | |
8269 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
8270 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 8271 | |
48b0f3ae PJ |
8272 | TARGET has a meaning which depends on OPERATION: |
8273 | For file I/O, TARGET is a file name. | |
8274 | For process I/O, TARGET is a process name. | |
8275 | For network I/O, TARGET is a service name or a port number | |
05e6f5dc | 8276 | |
48b0f3ae PJ |
8277 | This function looks up what specified for TARGET in, |
8278 | `file-coding-system-alist', `process-coding-system-alist', | |
8279 | or `network-coding-system-alist' depending on OPERATION. | |
8280 | They may specify a coding system, a cons of coding systems, | |
8281 | or a function symbol to call. | |
8282 | In the last case, we call the function with one argument, | |
8283 | which is a list of all the arguments given to this function. | |
8284 | ||
8285 | usage: (find-operation-coding-system OPERATION ARGUMENTS ...) */) | |
8286 | (nargs, args) | |
4ed46869 KH |
8287 | int nargs; |
8288 | Lisp_Object *args; | |
6b89e3aa | 8289 | { |
4ed46869 KH |
8290 | Lisp_Object operation, target_idx, target, val; |
8291 | register Lisp_Object chain; | |
177c0ea7 | 8292 | |
4ed46869 KH |
8293 | if (nargs < 2) |
8294 | error ("Too few arguments"); | |
8295 | operation = args[0]; | |
8296 | if (!SYMBOLP (operation) | |
8297 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
df7492f9 | 8298 | error ("Invalid first arguement"); |
4ed46869 KH |
8299 | if (nargs < 1 + XINT (target_idx)) |
8300 | error ("Too few arguments for operation: %s", | |
8f924df7 | 8301 | SDATA (SYMBOL_NAME (operation))); |
4ed46869 KH |
8302 | target = args[XINT (target_idx) + 1]; |
8303 | if (!(STRINGP (target) | |
8304 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) | |
df7492f9 | 8305 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
4ed46869 | 8306 | |
2e34157c RS |
8307 | chain = ((EQ (operation, Qinsert_file_contents) |
8308 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 8309 | ? Vfile_coding_system_alist |
2e34157c | 8310 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
8311 | ? Vnetwork_coding_system_alist |
8312 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
8313 | if (NILP (chain)) |
8314 | return Qnil; | |
8315 | ||
03699b14 | 8316 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 8317 | { |
f44d27ce | 8318 | Lisp_Object elt; |
6b89e3aa | 8319 | |
df7492f9 | 8320 | elt = XCAR (chain); |
4ed46869 KH |
8321 | if (CONSP (elt) |
8322 | && ((STRINGP (target) | |
03699b14 KR |
8323 | && STRINGP (XCAR (elt)) |
8324 | && fast_string_match (XCAR (elt), target) >= 0) | |
8325 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 8326 | { |
03699b14 | 8327 | val = XCDR (elt); |
b19fd4c5 KH |
8328 | /* Here, if VAL is both a valid coding system and a valid |
8329 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
8330 | if (CONSP (val)) |
8331 | return val; | |
8332 | if (! SYMBOLP (val)) | |
8333 | return Qnil; | |
8334 | if (! NILP (Fcoding_system_p (val))) | |
8335 | return Fcons (val, val); | |
b19fd4c5 | 8336 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 8337 | { |
b19fd4c5 KH |
8338 | val = call1 (val, Flist (nargs, args)); |
8339 | if (CONSP (val)) | |
8340 | return val; | |
8341 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
8342 | return Fcons (val, val); | |
6b89e3aa | 8343 | } |
02ba4723 | 8344 | return Qnil; |
6b89e3aa KH |
8345 | } |
8346 | } | |
4ed46869 | 8347 | return Qnil; |
6b89e3aa KH |
8348 | } |
8349 | ||
df7492f9 | 8350 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 8351 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 8352 | doc: /* Assign higher priority to the coding systems given as arguments. |
ff563fce | 8353 | If multiple coding systems belongs to the same category, |
a3181084 DL |
8354 | all but the first one are ignored. |
8355 | ||
8356 | usage: (set-coding-system-priority ...) */) | |
df7492f9 KH |
8357 | (nargs, args) |
8358 | int nargs; | |
8359 | Lisp_Object *args; | |
8360 | { | |
8361 | int i, j; | |
8362 | int changed[coding_category_max]; | |
8363 | enum coding_category priorities[coding_category_max]; | |
8364 | ||
8365 | bzero (changed, sizeof changed); | |
6b89e3aa | 8366 | |
df7492f9 | 8367 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 8368 | { |
df7492f9 KH |
8369 | enum coding_category category; |
8370 | Lisp_Object spec, attrs; | |
6b89e3aa | 8371 | |
df7492f9 KH |
8372 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
8373 | attrs = AREF (spec, 0); | |
8374 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8375 | if (changed[category]) | |
8376 | /* Ignore this coding system because a coding system of the | |
8377 | same category already had a higher priority. */ | |
8378 | continue; | |
8379 | changed[category] = 1; | |
8380 | priorities[j++] = category; | |
8381 | if (coding_categories[category].id >= 0 | |
8382 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
8383 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 8384 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 8385 | } |
6b89e3aa | 8386 | |
df7492f9 KH |
8387 | /* Now we have decided top J priorities. Reflect the order of the |
8388 | original priorities to the remaining priorities. */ | |
6b89e3aa | 8389 | |
df7492f9 | 8390 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 8391 | { |
df7492f9 KH |
8392 | while (j < coding_category_max |
8393 | && changed[coding_priorities[j]]) | |
8394 | j++; | |
8395 | if (j == coding_category_max) | |
8396 | abort (); | |
8397 | priorities[i] = coding_priorities[j]; | |
8398 | } | |
6b89e3aa | 8399 | |
df7492f9 | 8400 | bcopy (priorities, coding_priorities, sizeof priorities); |
177c0ea7 | 8401 | |
ff563fce KH |
8402 | /* Update `coding-category-list'. */ |
8403 | Vcoding_category_list = Qnil; | |
8404 | for (i = coding_category_max - 1; i >= 0; i--) | |
8405 | Vcoding_category_list | |
8406 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
8407 | Vcoding_category_list); | |
6b89e3aa | 8408 | |
df7492f9 | 8409 | return Qnil; |
6b89e3aa KH |
8410 | } |
8411 | ||
df7492f9 KH |
8412 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
8413 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 DL |
8414 | doc: /* Return a list of coding systems ordered by their priorities. |
8415 | HIGHESTP non-nil means just return the highest priority one. */) | |
df7492f9 KH |
8416 | (highestp) |
8417 | Lisp_Object highestp; | |
d46c5b12 KH |
8418 | { |
8419 | int i; | |
df7492f9 | 8420 | Lisp_Object val; |
6b89e3aa | 8421 | |
df7492f9 | 8422 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 8423 | { |
df7492f9 KH |
8424 | enum coding_category category = coding_priorities[i]; |
8425 | int id = coding_categories[category].id; | |
8426 | Lisp_Object attrs; | |
068a9dbd | 8427 | |
df7492f9 KH |
8428 | if (id < 0) |
8429 | continue; | |
8430 | attrs = CODING_ID_ATTRS (id); | |
8431 | if (! NILP (highestp)) | |
8432 | return CODING_ATTR_BASE_NAME (attrs); | |
8433 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
8434 | } | |
8435 | return Fnreverse (val); | |
8436 | } | |
068a9dbd | 8437 | |
f0064e1f | 8438 | static char *suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
8439 | |
8440 | static Lisp_Object | |
df7492f9 KH |
8441 | make_subsidiaries (base) |
8442 | Lisp_Object base; | |
068a9dbd | 8443 | { |
df7492f9 | 8444 | Lisp_Object subsidiaries; |
8f924df7 | 8445 | int base_name_len = SBYTES (SYMBOL_NAME (base)); |
df7492f9 KH |
8446 | char *buf = (char *) alloca (base_name_len + 6); |
8447 | int i; | |
068a9dbd | 8448 | |
8f924df7 | 8449 | bcopy (SDATA (SYMBOL_NAME (base)), buf, base_name_len); |
df7492f9 KH |
8450 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
8451 | for (i = 0; i < 3; i++) | |
068a9dbd | 8452 | { |
df7492f9 KH |
8453 | bcopy (suffixes[i], buf + base_name_len, strlen (suffixes[i]) + 1); |
8454 | ASET (subsidiaries, i, intern (buf)); | |
068a9dbd | 8455 | } |
df7492f9 | 8456 | return subsidiaries; |
068a9dbd KH |
8457 | } |
8458 | ||
8459 | ||
df7492f9 KH |
8460 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
8461 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
8462 | doc: /* For internal use only. |
8463 | usage: (define-coding-system-internal ...) */) | |
df7492f9 KH |
8464 | (nargs, args) |
8465 | int nargs; | |
8466 | Lisp_Object *args; | |
068a9dbd | 8467 | { |
df7492f9 KH |
8468 | Lisp_Object name; |
8469 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
8470 | Lisp_Object attrs; /* Vector of attributes. */ | |
8471 | Lisp_Object eol_type; | |
8472 | Lisp_Object aliases; | |
8473 | Lisp_Object coding_type, charset_list, safe_charsets; | |
8474 | enum coding_category category; | |
8475 | Lisp_Object tail, val; | |
8476 | int max_charset_id = 0; | |
8477 | int i; | |
068a9dbd | 8478 | |
df7492f9 KH |
8479 | if (nargs < coding_arg_max) |
8480 | goto short_args; | |
068a9dbd | 8481 | |
df7492f9 | 8482 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 8483 | |
df7492f9 KH |
8484 | name = args[coding_arg_name]; |
8485 | CHECK_SYMBOL (name); | |
8486 | CODING_ATTR_BASE_NAME (attrs) = name; | |
068a9dbd | 8487 | |
df7492f9 KH |
8488 | val = args[coding_arg_mnemonic]; |
8489 | if (! STRINGP (val)) | |
8490 | CHECK_CHARACTER (val); | |
8491 | CODING_ATTR_MNEMONIC (attrs) = val; | |
068a9dbd | 8492 | |
df7492f9 KH |
8493 | coding_type = args[coding_arg_coding_type]; |
8494 | CHECK_SYMBOL (coding_type); | |
8495 | CODING_ATTR_TYPE (attrs) = coding_type; | |
068a9dbd | 8496 | |
df7492f9 KH |
8497 | charset_list = args[coding_arg_charset_list]; |
8498 | if (SYMBOLP (charset_list)) | |
8499 | { | |
8500 | if (EQ (charset_list, Qiso_2022)) | |
8501 | { | |
8502 | if (! EQ (coding_type, Qiso_2022)) | |
8503 | error ("Invalid charset-list"); | |
8504 | charset_list = Viso_2022_charset_list; | |
8505 | } | |
8506 | else if (EQ (charset_list, Qemacs_mule)) | |
8507 | { | |
8508 | if (! EQ (coding_type, Qemacs_mule)) | |
8509 | error ("Invalid charset-list"); | |
8510 | charset_list = Vemacs_mule_charset_list; | |
8511 | } | |
8512 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8513 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
8514 | max_charset_id = XFASTINT (XCAR (tail)); | |
8515 | } | |
068a9dbd KH |
8516 | else |
8517 | { | |
df7492f9 KH |
8518 | charset_list = Fcopy_sequence (charset_list); |
8519 | for (tail = charset_list; !NILP (tail); tail = Fcdr (tail)) | |
068a9dbd | 8520 | { |
df7492f9 KH |
8521 | struct charset *charset; |
8522 | ||
8523 | val = Fcar (tail); | |
8524 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8525 | if (EQ (coding_type, Qiso_2022) | |
8526 | ? CHARSET_ISO_FINAL (charset) < 0 | |
8527 | : EQ (coding_type, Qemacs_mule) | |
8528 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
8529 | : 0) | |
8530 | error ("Can't handle charset `%s'", | |
8f924df7 | 8531 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 8532 | |
8f924df7 | 8533 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
8534 | if (max_charset_id < charset->id) |
8535 | max_charset_id = charset->id; | |
068a9dbd KH |
8536 | } |
8537 | } | |
df7492f9 | 8538 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; |
068a9dbd | 8539 | |
df7492f9 KH |
8540 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
8541 | make_number (255)); | |
8542 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8f924df7 | 8543 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 8544 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; |
068a9dbd | 8545 | |
584948ac | 8546 | CODING_ATTR_ASCII_COMPAT (attrs) = args[coding_arg_ascii_compatible_p]; |
3a73fa5d | 8547 | |
df7492f9 | 8548 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 8549 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 8550 | CHECK_SYMBOL (val); |
df7492f9 | 8551 | CODING_ATTR_DECODE_TBL (attrs) = val; |
3a73fa5d | 8552 | |
df7492f9 | 8553 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 8554 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 8555 | CHECK_SYMBOL (val); |
df7492f9 | 8556 | CODING_ATTR_ENCODE_TBL (attrs) = val; |
d46c5b12 | 8557 | |
df7492f9 KH |
8558 | val = args[coding_arg_post_read_conversion]; |
8559 | CHECK_SYMBOL (val); | |
8560 | CODING_ATTR_POST_READ (attrs) = val; | |
d46c5b12 | 8561 | |
df7492f9 KH |
8562 | val = args[coding_arg_pre_write_conversion]; |
8563 | CHECK_SYMBOL (val); | |
8564 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
3a73fa5d | 8565 | |
df7492f9 KH |
8566 | val = args[coding_arg_default_char]; |
8567 | if (NILP (val)) | |
8568 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
8569 | else | |
8570 | { | |
8f924df7 | 8571 | CHECK_CHARACTER (val); |
df7492f9 KH |
8572 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; |
8573 | } | |
4031e2bf | 8574 | |
8f924df7 KH |
8575 | val = args[coding_arg_for_unibyte]; |
8576 | CODING_ATTR_FOR_UNIBYTE (attrs) = NILP (val) ? Qnil : Qt; | |
3a73fa5d | 8577 | |
df7492f9 KH |
8578 | val = args[coding_arg_plist]; |
8579 | CHECK_LIST (val); | |
8580 | CODING_ATTR_PLIST (attrs) = val; | |
3a73fa5d | 8581 | |
df7492f9 KH |
8582 | if (EQ (coding_type, Qcharset)) |
8583 | { | |
c7c66a95 KH |
8584 | /* Generate a lisp vector of 256 elements. Each element is nil, |
8585 | integer, or a list of charset IDs. | |
3a73fa5d | 8586 | |
c7c66a95 KH |
8587 | If Nth element is nil, the byte code N is invalid in this |
8588 | coding system. | |
4ed46869 | 8589 | |
c7c66a95 KH |
8590 | If Nth element is a number NUM, N is the first byte of a |
8591 | charset whose ID is NUM. | |
4ed46869 | 8592 | |
c7c66a95 KH |
8593 | If Nth element is a list of charset IDs, N is the first byte |
8594 | of one of them. The list is sorted by dimensions of the | |
2bc515e4 | 8595 | charsets. A charset of smaller dimension comes firtst. */ |
df7492f9 | 8596 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 8597 | |
5c99c2e6 | 8598 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 8599 | { |
c7c66a95 KH |
8600 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
8601 | int dim = CHARSET_DIMENSION (charset); | |
8602 | int idx = (dim - 1) * 4; | |
4ed46869 | 8603 | |
5c99c2e6 | 8604 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
584948ac | 8605 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
4031e2bf | 8606 | |
15d143f7 KH |
8607 | for (i = charset->code_space[idx]; |
8608 | i <= charset->code_space[idx + 1]; i++) | |
8609 | { | |
c7c66a95 KH |
8610 | Lisp_Object tmp, tmp2; |
8611 | int dim2; | |
ec6d2bb8 | 8612 | |
c7c66a95 KH |
8613 | tmp = AREF (val, i); |
8614 | if (NILP (tmp)) | |
8615 | tmp = XCAR (tail); | |
8616 | else if (NUMBERP (tmp)) | |
8617 | { | |
8618 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
8619 | if (dim < dim2) | |
c7c66a95 | 8620 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
8621 | else |
8622 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 8623 | } |
15d143f7 | 8624 | else |
c7c66a95 KH |
8625 | { |
8626 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
8627 | { | |
8628 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
8629 | if (dim < dim2) | |
8630 | break; | |
8631 | } | |
8632 | if (NILP (tmp2)) | |
8633 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
8634 | else | |
8635 | { | |
8636 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
8637 | XSETCAR (tmp2, XCAR (tail)); | |
8638 | } | |
8639 | } | |
8640 | ASET (val, i, tmp); | |
15d143f7 | 8641 | } |
df7492f9 KH |
8642 | } |
8643 | ASET (attrs, coding_attr_charset_valids, val); | |
8644 | category = coding_category_charset; | |
8645 | } | |
8646 | else if (EQ (coding_type, Qccl)) | |
8647 | { | |
8648 | Lisp_Object valids; | |
ecec61c1 | 8649 | |
df7492f9 KH |
8650 | if (nargs < coding_arg_ccl_max) |
8651 | goto short_args; | |
ecec61c1 | 8652 | |
df7492f9 KH |
8653 | val = args[coding_arg_ccl_decoder]; |
8654 | CHECK_CCL_PROGRAM (val); | |
8655 | if (VECTORP (val)) | |
8656 | val = Fcopy_sequence (val); | |
8657 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 8658 | |
df7492f9 KH |
8659 | val = args[coding_arg_ccl_encoder]; |
8660 | CHECK_CCL_PROGRAM (val); | |
8661 | if (VECTORP (val)) | |
8662 | val = Fcopy_sequence (val); | |
8663 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 8664 | |
df7492f9 KH |
8665 | val = args[coding_arg_ccl_valids]; |
8666 | valids = Fmake_string (make_number (256), make_number (0)); | |
8667 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
8668 | { | |
8dcbea82 | 8669 | int from, to; |
ecec61c1 | 8670 | |
df7492f9 KH |
8671 | val = Fcar (tail); |
8672 | if (INTEGERP (val)) | |
8dcbea82 KH |
8673 | { |
8674 | from = to = XINT (val); | |
8675 | if (from < 0 || from > 255) | |
8676 | args_out_of_range_3 (val, make_number (0), make_number (255)); | |
8677 | } | |
df7492f9 KH |
8678 | else |
8679 | { | |
df7492f9 | 8680 | CHECK_CONS (val); |
8f924df7 KH |
8681 | CHECK_NATNUM_CAR (val); |
8682 | CHECK_NATNUM_CDR (val); | |
df7492f9 | 8683 | from = XINT (XCAR (val)); |
8f924df7 | 8684 | if (from > 255) |
8dcbea82 KH |
8685 | args_out_of_range_3 (XCAR (val), |
8686 | make_number (0), make_number (255)); | |
df7492f9 | 8687 | to = XINT (XCDR (val)); |
8dcbea82 KH |
8688 | if (to < from || to > 255) |
8689 | args_out_of_range_3 (XCDR (val), | |
8690 | XCAR (val), make_number (255)); | |
df7492f9 | 8691 | } |
8dcbea82 | 8692 | for (i = from; i <= to; i++) |
8f924df7 | 8693 | SSET (valids, i, 1); |
df7492f9 KH |
8694 | } |
8695 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 8696 | |
df7492f9 | 8697 | category = coding_category_ccl; |
55ab7be3 | 8698 | } |
df7492f9 | 8699 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 8700 | { |
df7492f9 | 8701 | Lisp_Object bom, endian; |
4ed46869 | 8702 | |
584948ac | 8703 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; |
4ed46869 | 8704 | |
df7492f9 KH |
8705 | if (nargs < coding_arg_utf16_max) |
8706 | goto short_args; | |
4ed46869 | 8707 | |
df7492f9 KH |
8708 | bom = args[coding_arg_utf16_bom]; |
8709 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
8710 | { | |
8711 | CHECK_CONS (bom); | |
8f924df7 KH |
8712 | val = XCAR (bom); |
8713 | CHECK_CODING_SYSTEM (val); | |
8714 | val = XCDR (bom); | |
8715 | CHECK_CODING_SYSTEM (val); | |
df7492f9 KH |
8716 | } |
8717 | ASET (attrs, coding_attr_utf_16_bom, bom); | |
8718 | ||
8719 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
8720 | CHECK_SYMBOL (endian); |
8721 | if (NILP (endian)) | |
8722 | endian = Qbig; | |
8723 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 8724 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
8725 | ASET (attrs, coding_attr_utf_16_endian, endian); |
8726 | ||
8727 | category = (CONSP (bom) | |
8728 | ? coding_category_utf_16_auto | |
8729 | : NILP (bom) | |
b49a1807 | 8730 | ? (EQ (endian, Qbig) |
df7492f9 KH |
8731 | ? coding_category_utf_16_be_nosig |
8732 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 8733 | : (EQ (endian, Qbig) |
df7492f9 KH |
8734 | ? coding_category_utf_16_be |
8735 | : coding_category_utf_16_le)); | |
8736 | } | |
8737 | else if (EQ (coding_type, Qiso_2022)) | |
8738 | { | |
8739 | Lisp_Object initial, reg_usage, request, flags; | |
4776e638 | 8740 | int i; |
1397dc18 | 8741 | |
df7492f9 KH |
8742 | if (nargs < coding_arg_iso2022_max) |
8743 | goto short_args; | |
8744 | ||
8745 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
8746 | CHECK_VECTOR (initial); | |
8747 | for (i = 0; i < 4; i++) | |
8748 | { | |
8749 | val = Faref (initial, make_number (i)); | |
8750 | if (! NILP (val)) | |
8751 | { | |
584948ac KH |
8752 | struct charset *charset; |
8753 | ||
8754 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8755 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
8756 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
8757 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8758 | } |
8759 | else | |
8760 | ASET (initial, i, make_number (-1)); | |
8761 | } | |
8762 | ||
8763 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
8764 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
8765 | CHECK_NUMBER_CAR (reg_usage); |
8766 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
8767 | |
8768 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
8769 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 8770 | { |
df7492f9 | 8771 | int id; |
8f924df7 | 8772 | Lisp_Object tmp; |
df7492f9 KH |
8773 | |
8774 | val = Fcar (tail); | |
8775 | CHECK_CONS (val); | |
8f924df7 KH |
8776 | tmp = XCAR (val); |
8777 | CHECK_CHARSET_GET_ID (tmp, id); | |
8778 | CHECK_NATNUM_CDR (val); | |
df7492f9 KH |
8779 | if (XINT (XCDR (val)) >= 4) |
8780 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
8f924df7 | 8781 | XSETCAR (val, make_number (id)); |
1397dc18 | 8782 | } |
4ed46869 | 8783 | |
df7492f9 KH |
8784 | flags = args[coding_arg_iso2022_flags]; |
8785 | CHECK_NATNUM (flags); | |
8786 | i = XINT (flags); | |
8787 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
8788 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
8789 | ||
8790 | ASET (attrs, coding_attr_iso_initial, initial); | |
8791 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
8792 | ASET (attrs, coding_attr_iso_request, request); | |
8793 | ASET (attrs, coding_attr_iso_flags, flags); | |
8794 | setup_iso_safe_charsets (attrs); | |
8795 | ||
8796 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
8797 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
8798 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
8799 | ? coding_category_iso_7_else | |
8800 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
8801 | ? coding_category_iso_7 | |
8802 | : coding_category_iso_7_tight); | |
8803 | else | |
8804 | { | |
8805 | int id = XINT (AREF (initial, 1)); | |
8806 | ||
c6fb6e98 | 8807 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
8808 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
8809 | || id < 0) | |
8810 | ? coding_category_iso_8_else | |
8811 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
8812 | ? coding_category_iso_8_1 | |
8813 | : coding_category_iso_8_2); | |
8814 | } | |
0ce7886f KH |
8815 | if (category != coding_category_iso_8_1 |
8816 | && category != coding_category_iso_8_2) | |
8817 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; | |
df7492f9 KH |
8818 | } |
8819 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 8820 | { |
df7492f9 KH |
8821 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
8822 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
584948ac | 8823 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
df7492f9 | 8824 | category = coding_category_emacs_mule; |
c28a9453 | 8825 | } |
df7492f9 | 8826 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 8827 | { |
df7492f9 KH |
8828 | |
8829 | struct charset *charset; | |
8830 | ||
7d64c6ad | 8831 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 8832 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 8833 | error ("There should be three or four charsets"); |
df7492f9 KH |
8834 | |
8835 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8836 | if (CHARSET_DIMENSION (charset) != 1) | |
8837 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8838 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8839 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8840 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8841 | |
8842 | charset_list = XCDR (charset_list); | |
8843 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8844 | if (CHARSET_DIMENSION (charset) != 1) | |
8845 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8846 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
8847 | |
8848 | charset_list = XCDR (charset_list); | |
8849 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8850 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
8851 | error ("Dimension of charset %s is not two", |
8852 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
8853 | ||
8854 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
8855 | if (! NILP (charset_list)) |
8856 | { | |
8857 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8858 | if (CHARSET_DIMENSION (charset) != 2) | |
8859 | error ("Dimension of charset %s is not two", | |
8860 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
8861 | } | |
df7492f9 KH |
8862 | |
8863 | category = coding_category_sjis; | |
8864 | Vsjis_coding_system = name; | |
c28a9453 | 8865 | } |
df7492f9 KH |
8866 | else if (EQ (coding_type, Qbig5)) |
8867 | { | |
8868 | struct charset *charset; | |
4ed46869 | 8869 | |
df7492f9 KH |
8870 | if (XINT (Flength (charset_list)) != 2) |
8871 | error ("There should be just two charsets"); | |
8872 | ||
8873 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8874 | if (CHARSET_DIMENSION (charset) != 1) | |
8875 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8876 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8877 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8878 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8879 | |
8880 | charset_list = XCDR (charset_list); | |
8881 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8882 | if (CHARSET_DIMENSION (charset) != 2) | |
8883 | error ("Dimension of charset %s is not two", | |
8f924df7 | 8884 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 8885 | |
df7492f9 KH |
8886 | category = coding_category_big5; |
8887 | Vbig5_coding_system = name; | |
8888 | } | |
8889 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 8890 | { |
584948ac KH |
8891 | category = coding_category_raw_text; |
8892 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
c28a9453 | 8893 | } |
df7492f9 | 8894 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 8895 | { |
584948ac KH |
8896 | category = coding_category_utf_8; |
8897 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
4ed46869 | 8898 | } |
df7492f9 KH |
8899 | else if (EQ (coding_type, Qundecided)) |
8900 | category = coding_category_undecided; | |
4ed46869 | 8901 | else |
df7492f9 | 8902 | error ("Invalid coding system type: %s", |
8f924df7 | 8903 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 8904 | |
df7492f9 | 8905 | CODING_ATTR_CATEGORY (attrs) = make_number (category); |
01378f49 KH |
8906 | CODING_ATTR_PLIST (attrs) |
8907 | = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category), | |
8908 | CODING_ATTR_PLIST (attrs))); | |
35befdaa KH |
8909 | CODING_ATTR_PLIST (attrs) |
8910 | = Fcons (QCascii_compatible_p, | |
8911 | Fcons (CODING_ATTR_ASCII_COMPAT (attrs), | |
8912 | CODING_ATTR_PLIST (attrs))); | |
c4825358 | 8913 | |
df7492f9 KH |
8914 | eol_type = args[coding_arg_eol_type]; |
8915 | if (! NILP (eol_type) | |
8916 | && ! EQ (eol_type, Qunix) | |
8917 | && ! EQ (eol_type, Qdos) | |
8918 | && ! EQ (eol_type, Qmac)) | |
8919 | error ("Invalid eol-type"); | |
4ed46869 | 8920 | |
df7492f9 | 8921 | aliases = Fcons (name, Qnil); |
4ed46869 | 8922 | |
df7492f9 KH |
8923 | if (NILP (eol_type)) |
8924 | { | |
8925 | eol_type = make_subsidiaries (name); | |
8926 | for (i = 0; i < 3; i++) | |
1397dc18 | 8927 | { |
df7492f9 KH |
8928 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
8929 | ||
8930 | this_name = AREF (eol_type, i); | |
8931 | this_aliases = Fcons (this_name, Qnil); | |
8932 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
8933 | this_spec = Fmake_vector (make_number (3), attrs); | |
8934 | ASET (this_spec, 1, this_aliases); | |
8935 | ASET (this_spec, 2, this_eol_type); | |
8936 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
8937 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
583f71ca KH |
8938 | val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist); |
8939 | if (NILP (val)) | |
8940 | Vcoding_system_alist | |
8941 | = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
8942 | Vcoding_system_alist); | |
1397dc18 | 8943 | } |
d46c5b12 | 8944 | } |
4ed46869 | 8945 | |
df7492f9 KH |
8946 | spec_vec = Fmake_vector (make_number (3), attrs); |
8947 | ASET (spec_vec, 1, aliases); | |
8948 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 8949 | |
df7492f9 KH |
8950 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
8951 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
583f71ca KH |
8952 | val = Fassoc (Fsymbol_name (name), Vcoding_system_alist); |
8953 | if (NILP (val)) | |
8954 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
8955 | Vcoding_system_alist); | |
48b0f3ae | 8956 | |
df7492f9 KH |
8957 | { |
8958 | int id = coding_categories[category].id; | |
48b0f3ae | 8959 | |
df7492f9 KH |
8960 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
8961 | setup_coding_system (name, &coding_categories[category]); | |
8962 | } | |
48b0f3ae | 8963 | |
d46c5b12 | 8964 | return Qnil; |
48b0f3ae | 8965 | |
df7492f9 KH |
8966 | short_args: |
8967 | return Fsignal (Qwrong_number_of_arguments, | |
8968 | Fcons (intern ("define-coding-system-internal"), | |
8969 | make_number (nargs))); | |
d46c5b12 | 8970 | } |
4ed46869 | 8971 | |
d6925f38 | 8972 | |
a6f87d34 KH |
8973 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
8974 | 3, 3, 0, | |
8975 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
8976 | (coding_system, prop, val) | |
8977 | Lisp_Object coding_system, prop, val; | |
8978 | { | |
3dbe7859 | 8979 | Lisp_Object spec, attrs; |
a6f87d34 KH |
8980 | |
8981 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8982 | attrs = AREF (spec, 0); | |
8983 | if (EQ (prop, QCmnemonic)) | |
8984 | { | |
8985 | if (! STRINGP (val)) | |
8986 | CHECK_CHARACTER (val); | |
8987 | CODING_ATTR_MNEMONIC (attrs) = val; | |
8988 | } | |
8989 | else if (EQ (prop, QCdefalut_char)) | |
8990 | { | |
8991 | if (NILP (val)) | |
8992 | val = make_number (' '); | |
8993 | else | |
8994 | CHECK_CHARACTER (val); | |
8995 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; | |
8996 | } | |
8997 | else if (EQ (prop, QCdecode_translation_table)) | |
8998 | { | |
8999 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
9000 | CHECK_SYMBOL (val); | |
9001 | CODING_ATTR_DECODE_TBL (attrs) = val; | |
9002 | } | |
9003 | else if (EQ (prop, QCencode_translation_table)) | |
9004 | { | |
9005 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
9006 | CHECK_SYMBOL (val); | |
9007 | CODING_ATTR_ENCODE_TBL (attrs) = val; | |
9008 | } | |
9009 | else if (EQ (prop, QCpost_read_conversion)) | |
9010 | { | |
9011 | CHECK_SYMBOL (val); | |
9012 | CODING_ATTR_POST_READ (attrs) = val; | |
9013 | } | |
9014 | else if (EQ (prop, QCpre_write_conversion)) | |
9015 | { | |
9016 | CHECK_SYMBOL (val); | |
9017 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
9018 | } | |
35befdaa KH |
9019 | else if (EQ (prop, QCascii_compatible_p)) |
9020 | { | |
9021 | CODING_ATTR_ASCII_COMPAT (attrs) = val; | |
9022 | } | |
a6f87d34 KH |
9023 | |
9024 | CODING_ATTR_PLIST (attrs) | |
9025 | = Fplist_put (CODING_ATTR_PLIST (attrs), prop, val); | |
9026 | return val; | |
9027 | } | |
9028 | ||
9029 | ||
df7492f9 KH |
9030 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
9031 | Sdefine_coding_system_alias, 2, 2, 0, | |
9032 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
9033 | (alias, coding_system) | |
9034 | Lisp_Object alias, coding_system; | |
66cfb530 | 9035 | { |
583f71ca | 9036 | Lisp_Object spec, aliases, eol_type, val; |
4ed46869 | 9037 | |
df7492f9 KH |
9038 | CHECK_SYMBOL (alias); |
9039 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9040 | aliases = AREF (spec, 1); | |
d6925f38 KH |
9041 | /* ALISES should be a list of length more than zero, and the first |
9042 | element is a base coding system. Append ALIAS at the tail of the | |
9043 | list. */ | |
df7492f9 KH |
9044 | while (!NILP (XCDR (aliases))) |
9045 | aliases = XCDR (aliases); | |
8f924df7 | 9046 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 9047 | |
df7492f9 KH |
9048 | eol_type = AREF (spec, 2); |
9049 | if (VECTORP (eol_type)) | |
4ed46869 | 9050 | { |
df7492f9 KH |
9051 | Lisp_Object subsidiaries; |
9052 | int i; | |
4ed46869 | 9053 | |
df7492f9 KH |
9054 | subsidiaries = make_subsidiaries (alias); |
9055 | for (i = 0; i < 3; i++) | |
9056 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
9057 | AREF (eol_type, i)); | |
4ed46869 | 9058 | } |
df7492f9 KH |
9059 | |
9060 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 9061 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
583f71ca KH |
9062 | val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist); |
9063 | if (NILP (val)) | |
9064 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), | |
9065 | Vcoding_system_alist); | |
66cfb530 | 9066 | |
4ed46869 KH |
9067 | return Qnil; |
9068 | } | |
9069 | ||
df7492f9 KH |
9070 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
9071 | 1, 1, 0, | |
9072 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 9073 | Any alias or subsidiary coding system is not a base coding system. */) |
df7492f9 KH |
9074 | (coding_system) |
9075 | Lisp_Object coding_system; | |
d46c5b12 | 9076 | { |
df7492f9 | 9077 | Lisp_Object spec, attrs; |
d46c5b12 | 9078 | |
df7492f9 KH |
9079 | if (NILP (coding_system)) |
9080 | return (Qno_conversion); | |
9081 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9082 | attrs = AREF (spec, 0); | |
9083 | return CODING_ATTR_BASE_NAME (attrs); | |
9084 | } | |
1397dc18 | 9085 | |
df7492f9 KH |
9086 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
9087 | 1, 1, 0, | |
9088 | doc: "Return the property list of CODING-SYSTEM.") | |
9089 | (coding_system) | |
9090 | Lisp_Object coding_system; | |
9091 | { | |
9092 | Lisp_Object spec, attrs; | |
1397dc18 | 9093 | |
df7492f9 KH |
9094 | if (NILP (coding_system)) |
9095 | coding_system = Qno_conversion; | |
9096 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9097 | attrs = AREF (spec, 0); | |
9098 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
9099 | } |
9100 | ||
df7492f9 KH |
9101 | |
9102 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
9103 | 1, 1, 0, | |
da7db224 | 9104 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
df7492f9 KH |
9105 | (coding_system) |
9106 | Lisp_Object coding_system; | |
66cfb530 | 9107 | { |
df7492f9 | 9108 | Lisp_Object spec; |
84d60297 | 9109 | |
df7492f9 KH |
9110 | if (NILP (coding_system)) |
9111 | coding_system = Qno_conversion; | |
9112 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 9113 | return AREF (spec, 1); |
df7492f9 | 9114 | } |
66cfb530 | 9115 | |
df7492f9 KH |
9116 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
9117 | Scoding_system_eol_type, 1, 1, 0, | |
9118 | doc: /* Return eol-type of CODING-SYSTEM. | |
9119 | An eol-type is integer 0, 1, 2, or a vector of coding systems. | |
66cfb530 | 9120 | |
df7492f9 KH |
9121 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
9122 | and CR respectively. | |
66cfb530 | 9123 | |
df7492f9 KH |
9124 | A vector value indicates that a format of end-of-line should be |
9125 | detected automatically. Nth element of the vector is the subsidiary | |
9126 | coding system whose eol-type is N. */) | |
6b89e3aa KH |
9127 | (coding_system) |
9128 | Lisp_Object coding_system; | |
9129 | { | |
df7492f9 KH |
9130 | Lisp_Object spec, eol_type; |
9131 | int n; | |
6b89e3aa | 9132 | |
df7492f9 KH |
9133 | if (NILP (coding_system)) |
9134 | coding_system = Qno_conversion; | |
9135 | if (! CODING_SYSTEM_P (coding_system)) | |
9136 | return Qnil; | |
9137 | spec = CODING_SYSTEM_SPEC (coding_system); | |
9138 | eol_type = AREF (spec, 2); | |
9139 | if (VECTORP (eol_type)) | |
9140 | return Fcopy_sequence (eol_type); | |
9141 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
9142 | return make_number (n); | |
6b89e3aa KH |
9143 | } |
9144 | ||
4ed46869 KH |
9145 | #endif /* emacs */ |
9146 | ||
9147 | \f | |
1397dc18 | 9148 | /*** 9. Post-amble ***/ |
4ed46869 | 9149 | |
dfcf069d | 9150 | void |
4ed46869 KH |
9151 | init_coding_once () |
9152 | { | |
9153 | int i; | |
9154 | ||
df7492f9 KH |
9155 | for (i = 0; i < coding_category_max; i++) |
9156 | { | |
9157 | coding_categories[i].id = -1; | |
9158 | coding_priorities[i] = i; | |
9159 | } | |
4ed46869 KH |
9160 | |
9161 | /* ISO2022 specific initialize routine. */ | |
9162 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 9163 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
9164 | for (i = 0x21; i < 0x7F; i++) |
9165 | iso_code_class[i] = ISO_graphic_plane_0; | |
9166 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 9167 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
9168 | for (i = 0xA1; i < 0xFF; i++) |
9169 | iso_code_class[i] = ISO_graphic_plane_1; | |
9170 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
9171 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
9172 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
9173 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
9174 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
9175 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
9176 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
9177 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
9178 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
9179 | ||
df7492f9 KH |
9180 | for (i = 0; i < 256; i++) |
9181 | { | |
9182 | emacs_mule_bytes[i] = 1; | |
9183 | } | |
7c78e542 KH |
9184 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
9185 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
9186 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
9187 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
9188 | } |
9189 | ||
9190 | #ifdef emacs | |
9191 | ||
dfcf069d | 9192 | void |
e0e989f6 KH |
9193 | syms_of_coding () |
9194 | { | |
df7492f9 | 9195 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
9196 | { |
9197 | Lisp_Object args[2]; | |
9198 | args[0] = QCtest; | |
9199 | args[1] = Qeq; | |
9200 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
9201 | } | |
df7492f9 KH |
9202 | |
9203 | staticpro (&Vsjis_coding_system); | |
9204 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 9205 | |
df7492f9 KH |
9206 | staticpro (&Vbig5_coding_system); |
9207 | Vbig5_coding_system = Qnil; | |
9208 | ||
24a73b0a KH |
9209 | staticpro (&Vcode_conversion_reused_workbuf); |
9210 | Vcode_conversion_reused_workbuf = Qnil; | |
9211 | ||
9212 | staticpro (&Vcode_conversion_workbuf_name); | |
9213 | Vcode_conversion_workbuf_name = build_string (" *code-conversion-work*"); | |
e0e989f6 | 9214 | |
24a73b0a | 9215 | reused_workbuf_in_use = 0; |
df7492f9 KH |
9216 | |
9217 | DEFSYM (Qcharset, "charset"); | |
9218 | DEFSYM (Qtarget_idx, "target-idx"); | |
9219 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
9220 | Fset (Qcoding_system_history, Qnil); |
9221 | ||
9ce27fde | 9222 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 9223 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 9224 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
9225 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
9226 | ||
df7492f9 | 9227 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 9228 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
9229 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
9230 | ||
df7492f9 | 9231 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 9232 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
9233 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
9234 | ||
df7492f9 | 9235 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 9236 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
9237 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
9238 | ||
df7492f9 | 9239 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 9240 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
9241 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
9242 | ||
df7492f9 KH |
9243 | DEFSYM (Qcoding_system, "coding-system"); |
9244 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 9245 | |
df7492f9 KH |
9246 | DEFSYM (Qeol_type, "eol-type"); |
9247 | DEFSYM (Qunix, "unix"); | |
9248 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 9249 | |
df7492f9 KH |
9250 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
9251 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
9252 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
9253 | DEFSYM (Qdefault_char, "default-char"); | |
9254 | DEFSYM (Qundecided, "undecided"); | |
9255 | DEFSYM (Qno_conversion, "no-conversion"); | |
9256 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 9257 | |
df7492f9 | 9258 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 9259 | |
df7492f9 | 9260 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 9261 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 9262 | |
df7492f9 | 9263 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
9264 | DEFSYM (Qbig, "big"); |
9265 | DEFSYM (Qlittle, "little"); | |
27901516 | 9266 | |
df7492f9 KH |
9267 | DEFSYM (Qshift_jis, "shift-jis"); |
9268 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 9269 | |
df7492f9 | 9270 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 9271 | |
df7492f9 | 9272 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 KH |
9273 | Fput (Qcoding_system_error, Qerror_conditions, |
9274 | Fcons (Qcoding_system_error, Fcons (Qerror, Qnil))); | |
9275 | Fput (Qcoding_system_error, Qerror_message, | |
9ce27fde | 9276 | build_string ("Invalid coding system")); |
4ed46869 | 9277 | |
05e6f5dc KH |
9278 | /* Intern this now in case it isn't already done. |
9279 | Setting this variable twice is harmless. | |
9280 | But don't staticpro it here--that is done in alloc.c. */ | |
9281 | Qchar_table_extra_slots = intern ("char-table-extra-slots"); | |
70c22245 | 9282 | |
df7492f9 | 9283 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 9284 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
9285 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
9286 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
9287 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 9288 | |
df7492f9 | 9289 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 9290 | |
df7492f9 | 9291 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 9292 | |
01378f49 | 9293 | DEFSYM (QCcategory, ":category"); |
a6f87d34 KH |
9294 | DEFSYM (QCmnemonic, ":mnemonic"); |
9295 | DEFSYM (QCdefalut_char, ":default-char"); | |
9296 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); | |
9297 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
9298 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
9299 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
35befdaa | 9300 | DEFSYM (QCascii_compatible_p, ":ascii-compatible-p"); |
01378f49 | 9301 | |
df7492f9 KH |
9302 | Vcoding_category_table |
9303 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
9304 | staticpro (&Vcoding_category_table); | |
9305 | /* Followings are target of code detection. */ | |
9306 | ASET (Vcoding_category_table, coding_category_iso_7, | |
9307 | intern ("coding-category-iso-7")); | |
9308 | ASET (Vcoding_category_table, coding_category_iso_7_tight, | |
9309 | intern ("coding-category-iso-7-tight")); | |
9310 | ASET (Vcoding_category_table, coding_category_iso_8_1, | |
9311 | intern ("coding-category-iso-8-1")); | |
9312 | ASET (Vcoding_category_table, coding_category_iso_8_2, | |
9313 | intern ("coding-category-iso-8-2")); | |
9314 | ASET (Vcoding_category_table, coding_category_iso_7_else, | |
9315 | intern ("coding-category-iso-7-else")); | |
9316 | ASET (Vcoding_category_table, coding_category_iso_8_else, | |
9317 | intern ("coding-category-iso-8-else")); | |
9318 | ASET (Vcoding_category_table, coding_category_utf_8, | |
9319 | intern ("coding-category-utf-8")); | |
9320 | ASET (Vcoding_category_table, coding_category_utf_16_be, | |
9321 | intern ("coding-category-utf-16-be")); | |
ff563fce KH |
9322 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
9323 | intern ("coding-category-utf-16-auto")); | |
df7492f9 KH |
9324 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
9325 | intern ("coding-category-utf-16-le")); | |
9326 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, | |
9327 | intern ("coding-category-utf-16-be-nosig")); | |
9328 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, | |
9329 | intern ("coding-category-utf-16-le-nosig")); | |
9330 | ASET (Vcoding_category_table, coding_category_charset, | |
9331 | intern ("coding-category-charset")); | |
9332 | ASET (Vcoding_category_table, coding_category_sjis, | |
9333 | intern ("coding-category-sjis")); | |
9334 | ASET (Vcoding_category_table, coding_category_big5, | |
9335 | intern ("coding-category-big5")); | |
9336 | ASET (Vcoding_category_table, coding_category_ccl, | |
9337 | intern ("coding-category-ccl")); | |
9338 | ASET (Vcoding_category_table, coding_category_emacs_mule, | |
9339 | intern ("coding-category-emacs-mule")); | |
9340 | /* Followings are NOT target of code detection. */ | |
9341 | ASET (Vcoding_category_table, coding_category_raw_text, | |
9342 | intern ("coding-category-raw-text")); | |
9343 | ASET (Vcoding_category_table, coding_category_undecided, | |
9344 | intern ("coding-category-undecided")); | |
ecf488bc | 9345 | |
065e3595 KH |
9346 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
9347 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
9348 | DEFSYM (Qinvalid_source, "invalid-source"); | |
9349 | DEFSYM (Qinterrupted, "interrupted"); | |
9350 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
44e8490d | 9351 | DEFSYM (Qcoding_system_define_form, "coding-system-define-form"); |
065e3595 | 9352 | |
4ed46869 KH |
9353 | defsubr (&Scoding_system_p); |
9354 | defsubr (&Sread_coding_system); | |
9355 | defsubr (&Sread_non_nil_coding_system); | |
9356 | defsubr (&Scheck_coding_system); | |
9357 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 9358 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 9359 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 9360 | defsubr (&Sunencodable_char_position); |
df7492f9 | 9361 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
9362 | defsubr (&Sdecode_coding_region); |
9363 | defsubr (&Sencode_coding_region); | |
9364 | defsubr (&Sdecode_coding_string); | |
9365 | defsubr (&Sencode_coding_string); | |
9366 | defsubr (&Sdecode_sjis_char); | |
9367 | defsubr (&Sencode_sjis_char); | |
9368 | defsubr (&Sdecode_big5_char); | |
9369 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 9370 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 9371 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 9372 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 9373 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 9374 | defsubr (&Skeyboard_coding_system); |
a5d301df | 9375 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 9376 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 9377 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 9378 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 9379 | defsubr (&Scoding_system_put); |
df7492f9 KH |
9380 | defsubr (&Scoding_system_base); |
9381 | defsubr (&Scoding_system_plist); | |
9382 | defsubr (&Scoding_system_aliases); | |
9383 | defsubr (&Scoding_system_eol_type); | |
9384 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 9385 | |
4608c386 | 9386 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
48b0f3ae PJ |
9387 | doc: /* List of coding systems. |
9388 | ||
9389 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 9390 | updated by the functions `define-coding-system' and |
48b0f3ae | 9391 | `define-coding-system-alias'. */); |
4608c386 KH |
9392 | Vcoding_system_list = Qnil; |
9393 | ||
9394 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, | |
48b0f3ae PJ |
9395 | doc: /* Alist of coding system names. |
9396 | Each element is one element list of coding system name. | |
9397 | This variable is given to `completing-read' as TABLE argument. | |
9398 | ||
9399 | Do not alter the value of this variable manually. This variable should be | |
9400 | updated by the functions `make-coding-system' and | |
9401 | `define-coding-system-alias'. */); | |
4608c386 KH |
9402 | Vcoding_system_alist = Qnil; |
9403 | ||
4ed46869 | 9404 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
48b0f3ae PJ |
9405 | doc: /* List of coding-categories (symbols) ordered by priority. |
9406 | ||
9407 | On detecting a coding system, Emacs tries code detection algorithms | |
9408 | associated with each coding-category one by one in this order. When | |
9409 | one algorithm agrees with a byte sequence of source text, the coding | |
0ec31faf KH |
9410 | system bound to the corresponding coding-category is selected. |
9411 | ||
42205607 | 9412 | Don't modify this variable directly, but use `set-coding-priority'. */); |
4ed46869 KH |
9413 | { |
9414 | int i; | |
9415 | ||
9416 | Vcoding_category_list = Qnil; | |
df7492f9 | 9417 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 9418 | Vcoding_category_list |
d46c5b12 KH |
9419 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
9420 | Vcoding_category_list); | |
4ed46869 KH |
9421 | } |
9422 | ||
9423 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, | |
48b0f3ae PJ |
9424 | doc: /* Specify the coding system for read operations. |
9425 | It is useful to bind this variable with `let', but do not set it globally. | |
9426 | If the value is a coding system, it is used for decoding on read operation. | |
9427 | If not, an appropriate element is used from one of the coding system alists: | |
9428 | There are three such tables, `file-coding-system-alist', | |
9429 | `process-coding-system-alist', and `network-coding-system-alist'. */); | |
4ed46869 KH |
9430 | Vcoding_system_for_read = Qnil; |
9431 | ||
9432 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, | |
48b0f3ae PJ |
9433 | doc: /* Specify the coding system for write operations. |
9434 | Programs bind this variable with `let', but you should not set it globally. | |
9435 | If the value is a coding system, it is used for encoding of output, | |
9436 | when writing it to a file and when sending it to a file or subprocess. | |
9437 | ||
9438 | If this does not specify a coding system, an appropriate element | |
9439 | is used from one of the coding system alists: | |
9440 | There are three such tables, `file-coding-system-alist', | |
9441 | `process-coding-system-alist', and `network-coding-system-alist'. | |
9442 | For output to files, if the above procedure does not specify a coding system, | |
9443 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
9444 | Vcoding_system_for_write = Qnil; |
9445 | ||
9446 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, | |
df7492f9 KH |
9447 | doc: /* |
9448 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
9449 | Vlast_coding_system_used = Qnil; |
9450 | ||
065e3595 KH |
9451 | DEFVAR_LISP ("last-code-conversion-error", &Vlast_code_conversion_error, |
9452 | doc: /* | |
9453 | Error status of the last code conversion. | |
9454 | ||
9455 | When an error was detected in the last code conversion, this variable | |
9456 | is set to one of the following symbols. | |
9457 | `insufficient-source' | |
9458 | `inconsistent-eol' | |
9459 | `invalid-source' | |
9460 | `interrupted' | |
9461 | `insufficient-memory' | |
9462 | When no error was detected, the value doesn't change. So, to check | |
9463 | the error status of a code conversion by this variable, you must | |
9464 | explicitly set this variable to nil before performing code | |
9465 | conversion. */); | |
9466 | Vlast_code_conversion_error = Qnil; | |
9467 | ||
9ce27fde | 9468 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
df7492f9 KH |
9469 | doc: /* |
9470 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
9471 | See info node `Coding Systems' and info node `Text and Binary' concerning |
9472 | such conversion. */); | |
9ce27fde KH |
9473 | inhibit_eol_conversion = 0; |
9474 | ||
ed29121d | 9475 | DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
df7492f9 KH |
9476 | doc: /* |
9477 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
9478 | Bind it to t if the process output is to be treated as if it were a file |
9479 | read from some filesystem. */); | |
ed29121d EZ |
9480 | inherit_process_coding_system = 0; |
9481 | ||
02ba4723 | 9482 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
df7492f9 KH |
9483 | doc: /* |
9484 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
9485 | The format is ((PATTERN . VAL) ...), |
9486 | where PATTERN is a regular expression matching a file name, | |
9487 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9488 | If VAL is a coding system, it is used for both decoding and encoding | |
9489 | the file contents. | |
9490 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9491 | and the cdr part is used for encoding. | |
9492 | If VAL is a function symbol, the function must return a coding system | |
0192762c DL |
9493 | or a cons of coding systems which are used as above. The function gets |
9494 | the arguments with which `find-operation-coding-systems' was called. | |
48b0f3ae PJ |
9495 | |
9496 | See also the function `find-operation-coding-system' | |
9497 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
9498 | Vfile_coding_system_alist = Qnil; |
9499 | ||
9500 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, | |
df7492f9 KH |
9501 | doc: /* |
9502 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
9503 | The format is ((PATTERN . VAL) ...), |
9504 | where PATTERN is a regular expression matching a program name, | |
9505 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9506 | If VAL is a coding system, it is used for both decoding what received | |
9507 | from the program and encoding what sent to the program. | |
9508 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9509 | and the cdr part is used for encoding. | |
9510 | If VAL is a function symbol, the function must return a coding system | |
9511 | or a cons of coding systems which are used as above. | |
9512 | ||
9513 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
9514 | Vprocess_coding_system_alist = Qnil; |
9515 | ||
9516 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, | |
df7492f9 KH |
9517 | doc: /* |
9518 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
9519 | The format is ((PATTERN . VAL) ...), |
9520 | where PATTERN is a regular expression matching a network service name | |
9521 | or is a port number to connect to, | |
9522 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9523 | If VAL is a coding system, it is used for both decoding what received | |
9524 | from the network stream and encoding what sent to the network stream. | |
9525 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9526 | and the cdr part is used for encoding. | |
9527 | If VAL is a function symbol, the function must return a coding system | |
9528 | or a cons of coding systems which are used as above. | |
9529 | ||
9530 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 9531 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 9532 | |
68c45bf0 | 9533 | DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
75205970 RS |
9534 | doc: /* Coding system to use with system messages. |
9535 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
9536 | Vlocale_coding_system = Qnil; |
9537 | ||
005f0d35 | 9538 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
7722baf9 | 9539 | DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
df7492f9 KH |
9540 | doc: /* |
9541 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
7722baf9 | 9542 | eol_mnemonic_unix = build_string (":"); |
4ed46869 | 9543 | |
7722baf9 | 9544 | DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
df7492f9 KH |
9545 | doc: /* |
9546 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
7722baf9 | 9547 | eol_mnemonic_dos = build_string ("\\"); |
4ed46869 | 9548 | |
7722baf9 | 9549 | DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
df7492f9 KH |
9550 | doc: /* |
9551 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
7722baf9 | 9552 | eol_mnemonic_mac = build_string ("/"); |
4ed46869 | 9553 | |
7722baf9 | 9554 | DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
df7492f9 KH |
9555 | doc: /* |
9556 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
7722baf9 | 9557 | eol_mnemonic_undecided = build_string (":"); |
4ed46869 | 9558 | |
84fbb8a0 | 9559 | DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
df7492f9 KH |
9560 | doc: /* |
9561 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 9562 | Venable_character_translation = Qt; |
bdd9fb48 | 9563 | |
f967223b | 9564 | DEFVAR_LISP ("standard-translation-table-for-decode", |
48b0f3ae PJ |
9565 | &Vstandard_translation_table_for_decode, |
9566 | doc: /* Table for translating characters while decoding. */); | |
f967223b | 9567 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 9568 | |
f967223b | 9569 | DEFVAR_LISP ("standard-translation-table-for-encode", |
48b0f3ae PJ |
9570 | &Vstandard_translation_table_for_encode, |
9571 | doc: /* Table for translating characters while encoding. */); | |
f967223b | 9572 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 9573 | |
df7492f9 | 9574 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table, |
48b0f3ae PJ |
9575 | doc: /* Alist of charsets vs revision numbers. |
9576 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
9577 | designate it with the escape sequence identifying revision (cdr part |
9578 | of the element). */); | |
9579 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
9580 | |
9581 | DEFVAR_LISP ("default-process-coding-system", | |
9582 | &Vdefault_process_coding_system, | |
48b0f3ae PJ |
9583 | doc: /* Cons of coding systems used for process I/O by default. |
9584 | The car part is used for decoding a process output, | |
9585 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 9586 | Vdefault_process_coding_system = Qnil; |
c4825358 | 9587 | |
3f003981 | 9588 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
df7492f9 KH |
9589 | doc: /* |
9590 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
9591 | This is a vector of length 256. |
9592 | If Nth element is non-nil, the existence of code N in a file | |
9593 | \(or output of subprocess) doesn't prevent it to be detected as | |
9594 | a coding system of ISO 2022 variant which has a flag | |
9595 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
9596 | or reading output of a subprocess. | |
9597 | Only 128th through 159th elements has a meaning. */); | |
3f003981 | 9598 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
9599 | |
9600 | DEFVAR_LISP ("select-safe-coding-system-function", | |
9601 | &Vselect_safe_coding_system_function, | |
df7492f9 KH |
9602 | doc: /* |
9603 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
9604 | |
9605 | If set, this function is called to force a user to select a proper | |
9606 | coding system which can encode the text in the case that a default | |
9607 | coding system used in each operation can't encode the text. | |
9608 | ||
9609 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
9610 | Vselect_safe_coding_system_function = Qnil; |
9611 | ||
5d5bf4d8 KH |
9612 | DEFVAR_BOOL ("coding-system-require-warning", |
9613 | &coding_system_require_warning, | |
9614 | doc: /* Internal use only. | |
6b89e3aa KH |
9615 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
9616 | called even if `coding-system-for-write' is non-nil. The command | |
9617 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
9618 | coding_system_require_warning = 0; |
9619 | ||
9620 | ||
22ab2303 | 9621 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
74383408 | 9622 | &inhibit_iso_escape_detection, |
df7492f9 KH |
9623 | doc: /* |
9624 | If non-nil, Emacs ignores ISO2022's escape sequence on code detection. | |
48b0f3ae PJ |
9625 | |
9626 | By default, on reading a file, Emacs tries to detect how the text is | |
9627 | encoded. This code detection is sensitive to escape sequences. If | |
9628 | the sequence is valid as ISO2022, the code is determined as one of | |
9629 | the ISO2022 encodings, and the file is decoded by the corresponding | |
9630 | coding system (e.g. `iso-2022-7bit'). | |
9631 | ||
9632 | However, there may be a case that you want to read escape sequences in | |
9633 | a file as is. In such a case, you can set this variable to non-nil. | |
9634 | Then, as the code detection ignores any escape sequences, no file is | |
9635 | detected as encoded in some ISO2022 encoding. The result is that all | |
9636 | escape sequences become visible in a buffer. | |
9637 | ||
9638 | The default value is nil, and it is strongly recommended not to change | |
9639 | it. That is because many Emacs Lisp source files that contain | |
9640 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
9641 | in Emacs's distribution, and they won't be decoded correctly on | |
9642 | reading if you suppress escape sequence detection. | |
9643 | ||
9644 | The other way to read escape sequences in a file without decoding is | |
9645 | to explicitly specify some coding system that doesn't use ISO2022's | |
9646 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); | |
74383408 | 9647 | inhibit_iso_escape_detection = 0; |
002fdb44 DL |
9648 | |
9649 | DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input, | |
15c8f9d1 DL |
9650 | doc: /* Char table for translating self-inserting characters. |
9651 | This is applied to the result of input methods, not their input. See also | |
9652 | `keyboard-translate-table'. */); | |
002fdb44 | 9653 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 9654 | |
2c78b7e1 KH |
9655 | { |
9656 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 9657 | Lisp_Object plist[16]; |
2c78b7e1 KH |
9658 | int i; |
9659 | ||
9660 | for (i = 0; i < coding_arg_max; i++) | |
9661 | args[i] = Qnil; | |
9662 | ||
9663 | plist[0] = intern (":name"); | |
9664 | plist[1] = args[coding_arg_name] = Qno_conversion; | |
9665 | plist[2] = intern (":mnemonic"); | |
9666 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); | |
9667 | plist[4] = intern (":coding-type"); | |
9668 | plist[5] = args[coding_arg_coding_type] = Qraw_text; | |
9669 | plist[6] = intern (":ascii-compatible-p"); | |
9670 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; | |
9671 | plist[8] = intern (":default-char"); | |
9672 | plist[9] = args[coding_arg_default_char] = make_number (0); | |
8f924df7 KH |
9673 | plist[10] = intern (":for-unibyte"); |
9674 | plist[11] = args[coding_arg_for_unibyte] = Qt; | |
9675 | plist[12] = intern (":docstring"); | |
9676 | plist[13] = build_string ("Do no conversion.\n\ | |
2c78b7e1 KH |
9677 | \n\ |
9678 | When you visit a file with this coding, the file is read into a\n\ | |
9679 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
9680 | character."); | |
8f924df7 KH |
9681 | plist[14] = intern (":eol-type"); |
9682 | plist[15] = args[coding_arg_eol_type] = Qunix; | |
9683 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 | 9684 | Fdefine_coding_system_internal (coding_arg_max, args); |
ae6f73fa KH |
9685 | |
9686 | plist[1] = args[coding_arg_name] = Qundecided; | |
9687 | plist[3] = args[coding_arg_mnemonic] = make_number ('-'); | |
9688 | plist[5] = args[coding_arg_coding_type] = Qundecided; | |
9689 | /* This is already set. | |
35befdaa | 9690 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */ |
ae6f73fa KH |
9691 | plist[8] = intern (":charset-list"); |
9692 | plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil); | |
9693 | plist[11] = args[coding_arg_for_unibyte] = Qnil; | |
9694 | plist[13] = build_string ("No conversion on encoding, automatic conversion on decoding."); | |
9695 | plist[15] = args[coding_arg_eol_type] = Qnil; | |
9696 | args[coding_arg_plist] = Flist (16, plist); | |
9697 | Fdefine_coding_system_internal (coding_arg_max, args); | |
2c78b7e1 KH |
9698 | } |
9699 | ||
9700 | setup_coding_system (Qno_conversion, &keyboard_coding); | |
ae6f73fa | 9701 | setup_coding_system (Qundecided, &terminal_coding); |
2c78b7e1 | 9702 | setup_coding_system (Qno_conversion, &safe_terminal_coding); |
ff563fce KH |
9703 | |
9704 | { | |
9705 | int i; | |
9706 | ||
9707 | for (i = 0; i < coding_category_max; i++) | |
9708 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
9709 | } | |
4ed46869 KH |
9710 | } |
9711 | ||
68c45bf0 PE |
9712 | char * |
9713 | emacs_strerror (error_number) | |
9714 | int error_number; | |
9715 | { | |
9716 | char *str; | |
9717 | ||
ca9c0567 | 9718 | synchronize_system_messages_locale (); |
68c45bf0 PE |
9719 | str = strerror (error_number); |
9720 | ||
9721 | if (! NILP (Vlocale_coding_system)) | |
9722 | { | |
9723 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
9724 | Vlocale_coding_system, | |
9725 | 0); | |
d5db4077 | 9726 | str = (char *) SDATA (dec); |
68c45bf0 PE |
9727 | } |
9728 | ||
9729 | return str; | |
9730 | } | |
9731 | ||
4ed46869 | 9732 | #endif /* emacs */ |
9ffd559c KH |
9733 | |
9734 | /* arch-tag: 3a3a2b01-5ff6-4071-9afe-f5b808d9229d | |
9735 | (do not change this comment) */ |