Commit | Line | Data |
---|---|---|
9542cb1f | 1 | /* Coding system handler (conversion, detection, etc). |
aaef169d | 2 | Copyright (C) 2001, 2002, 2003, 2004, 2005, |
114f9c96 | 3 | 2006, 2007, 2008, 2009, 2010 Free Software Foundation, Inc. |
7976eda0 | 4 | Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, |
114f9c96 | 5 | 2005, 2006, 2007, 2008, 2009, 2010 |
ce03bf76 KH |
6 | National Institute of Advanced Industrial Science and Technology (AIST) |
7 | Registration Number H14PRO021 | |
8f924df7 | 8 | Copyright (C) 2003 |
df7492f9 KH |
9 | National Institute of Advanced Industrial Science and Technology (AIST) |
10 | Registration Number H13PRO009 | |
4ed46869 | 11 | |
369314dc KH |
12 | This file is part of GNU Emacs. |
13 | ||
9ec0b715 | 14 | GNU Emacs is free software: you can redistribute it and/or modify |
369314dc | 15 | it under the terms of the GNU General Public License as published by |
9ec0b715 GM |
16 | the Free Software Foundation, either version 3 of the License, or |
17 | (at your option) any later version. | |
4ed46869 | 18 | |
369314dc KH |
19 | GNU Emacs is distributed in the hope that it will be useful, |
20 | but WITHOUT ANY WARRANTY; without even the implied warranty of | |
21 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
22 | GNU General Public License for more details. | |
4ed46869 | 23 | |
369314dc | 24 | You should have received a copy of the GNU General Public License |
9ec0b715 | 25 | along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */ |
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 | 291 | #include <stdio.h> |
d7306fe6 | 292 | #include <setjmp.h> |
4ed46869 | 293 | |
4ed46869 KH |
294 | #include "lisp.h" |
295 | #include "buffer.h" | |
df7492f9 | 296 | #include "character.h" |
4ed46869 KH |
297 | #include "charset.h" |
298 | #include "ccl.h" | |
df7492f9 | 299 | #include "composite.h" |
4ed46869 KH |
300 | #include "coding.h" |
301 | #include "window.h" | |
b8299c66 KL |
302 | #include "frame.h" |
303 | #include "termhooks.h" | |
4ed46869 | 304 | |
df7492f9 | 305 | Lisp_Object Vcoding_system_hash_table; |
4ed46869 | 306 | |
df7492f9 | 307 | Lisp_Object Qcoding_system, Qcoding_aliases, Qeol_type; |
1965cb73 DL |
308 | Lisp_Object Qunix, Qdos; |
309 | extern Lisp_Object Qmac; /* frame.c */ | |
4ed46869 KH |
310 | Lisp_Object Qbuffer_file_coding_system; |
311 | Lisp_Object Qpost_read_conversion, Qpre_write_conversion; | |
df7492f9 | 312 | Lisp_Object Qdefault_char; |
27901516 | 313 | Lisp_Object Qno_conversion, Qundecided; |
df7492f9 | 314 | Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5; |
b49a1807 | 315 | Lisp_Object Qbig, Qlittle; |
bb0115a2 | 316 | Lisp_Object Qcoding_system_history; |
1397dc18 | 317 | Lisp_Object Qvalid_codes; |
2133e2d1 | 318 | Lisp_Object QCcategory, QCmnemonic, QCdefault_char; |
a6f87d34 KH |
319 | Lisp_Object QCdecode_translation_table, QCencode_translation_table; |
320 | Lisp_Object QCpost_read_conversion, QCpre_write_conversion; | |
35befdaa | 321 | Lisp_Object QCascii_compatible_p; |
4ed46869 KH |
322 | |
323 | extern Lisp_Object Qinsert_file_contents, Qwrite_region; | |
387f6ba5 | 324 | Lisp_Object Qcall_process, Qcall_process_region; |
4ed46869 KH |
325 | Lisp_Object Qstart_process, Qopen_network_stream; |
326 | Lisp_Object Qtarget_idx; | |
327 | ||
065e3595 KH |
328 | Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source; |
329 | Lisp_Object Qinterrupted, Qinsufficient_memory; | |
330 | ||
c7183fb8 GM |
331 | extern Lisp_Object Qcompletion_ignore_case; |
332 | ||
44e8490d KH |
333 | /* If a symbol has this property, evaluate the value to define the |
334 | symbol as a coding system. */ | |
335 | static Lisp_Object Qcoding_system_define_form; | |
336 | ||
5d5bf4d8 KH |
337 | int coding_system_require_warning; |
338 | ||
d46c5b12 KH |
339 | Lisp_Object Vselect_safe_coding_system_function; |
340 | ||
7722baf9 EZ |
341 | /* Mnemonic string for each format of end-of-line. */ |
342 | Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; | |
343 | /* Mnemonic string to indicate format of end-of-line is not yet | |
4ed46869 | 344 | decided. */ |
7722baf9 | 345 | Lisp_Object eol_mnemonic_undecided; |
4ed46869 | 346 | |
fcbcfb64 KH |
347 | /* Format of end-of-line decided by system. This is Qunix on |
348 | Unix and Mac, Qdos on DOS/Windows. | |
349 | This has an effect only for external encoding (i.e. for output to | |
350 | file and process), not for in-buffer or Lisp string encoding. */ | |
351 | static Lisp_Object system_eol_type; | |
352 | ||
4ed46869 KH |
353 | #ifdef emacs |
354 | ||
4608c386 KH |
355 | Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
356 | ||
357 | Lisp_Object Qcoding_system_p, Qcoding_system_error; | |
4ed46869 | 358 | |
d46c5b12 KH |
359 | /* Coding system emacs-mule and raw-text are for converting only |
360 | end-of-line format. */ | |
361 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 362 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 363 | |
4ed46869 KH |
364 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
365 | routines by the following three variables. */ | |
366 | /* Coding-system for reading files and receiving data from process. */ | |
367 | Lisp_Object Vcoding_system_for_read; | |
368 | /* Coding-system for writing files and sending data to process. */ | |
369 | Lisp_Object Vcoding_system_for_write; | |
370 | /* Coding-system actually used in the latest I/O. */ | |
371 | Lisp_Object Vlast_coding_system_used; | |
065e3595 KH |
372 | /* Set to non-nil when an error is detected while code conversion. */ |
373 | Lisp_Object Vlast_code_conversion_error; | |
c4825358 | 374 | /* A vector of length 256 which contains information about special |
94487c4e | 375 | Latin codes (especially for dealing with Microsoft codes). */ |
3f003981 | 376 | Lisp_Object Vlatin_extra_code_table; |
c4825358 | 377 | |
9ce27fde KH |
378 | /* Flag to inhibit code conversion of end-of-line format. */ |
379 | int inhibit_eol_conversion; | |
380 | ||
74383408 KH |
381 | /* Flag to inhibit ISO2022 escape sequence detection. */ |
382 | int inhibit_iso_escape_detection; | |
383 | ||
97b1b294 EZ |
384 | /* Flag to inhibit detection of binary files through null bytes. */ |
385 | int inhibit_null_byte_detection; | |
386 | ||
ed29121d EZ |
387 | /* Flag to make buffer-file-coding-system inherit from process-coding. */ |
388 | int inherit_process_coding_system; | |
389 | ||
c4825358 KH |
390 | /* Coding system to be used to encode text for terminal display when |
391 | terminal coding system is nil. */ | |
392 | struct coding_system safe_terminal_coding; | |
393 | ||
02ba4723 KH |
394 | Lisp_Object Vfile_coding_system_alist; |
395 | Lisp_Object Vprocess_coding_system_alist; | |
396 | Lisp_Object Vnetwork_coding_system_alist; | |
4ed46869 | 397 | |
68c45bf0 PE |
398 | Lisp_Object Vlocale_coding_system; |
399 | ||
4ed46869 KH |
400 | #endif /* emacs */ |
401 | ||
f967223b KH |
402 | /* Flag to tell if we look up translation table on character code |
403 | conversion. */ | |
84fbb8a0 | 404 | Lisp_Object Venable_character_translation; |
f967223b KH |
405 | /* Standard translation table to look up on decoding (reading). */ |
406 | Lisp_Object Vstandard_translation_table_for_decode; | |
407 | /* Standard translation table to look up on encoding (writing). */ | |
408 | Lisp_Object Vstandard_translation_table_for_encode; | |
84fbb8a0 | 409 | |
f967223b KH |
410 | Lisp_Object Qtranslation_table; |
411 | Lisp_Object Qtranslation_table_id; | |
412 | Lisp_Object Qtranslation_table_for_decode; | |
413 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 KH |
414 | |
415 | /* Alist of charsets vs revision number. */ | |
df7492f9 | 416 | static Lisp_Object Vcharset_revision_table; |
4ed46869 | 417 | |
02ba4723 KH |
418 | /* Default coding systems used for process I/O. */ |
419 | Lisp_Object Vdefault_process_coding_system; | |
420 | ||
002fdb44 DL |
421 | /* Char table for translating Quail and self-inserting input. */ |
422 | Lisp_Object Vtranslation_table_for_input; | |
423 | ||
df7492f9 KH |
424 | /* Two special coding systems. */ |
425 | Lisp_Object Vsjis_coding_system; | |
426 | Lisp_Object Vbig5_coding_system; | |
427 | ||
df7492f9 KH |
428 | /* ISO2022 section */ |
429 | ||
430 | #define CODING_ISO_INITIAL(coding, reg) \ | |
431 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
432 | coding_attr_iso_initial), \ | |
433 | reg))) | |
434 | ||
435 | ||
1b3b981b AS |
436 | #define CODING_ISO_REQUEST(coding, charset_id) \ |
437 | (((charset_id) <= (coding)->max_charset_id \ | |
438 | ? ((coding)->safe_charsets[charset_id] != 255 \ | |
439 | ? (coding)->safe_charsets[charset_id] \ | |
440 | : -1) \ | |
df7492f9 KH |
441 | : -1)) |
442 | ||
443 | ||
444 | #define CODING_ISO_FLAGS(coding) \ | |
445 | ((coding)->spec.iso_2022.flags) | |
446 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
447 | ((coding)->spec.iso_2022.current_designation[reg]) | |
448 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
449 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
450 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
451 | ((coding)->spec.iso_2022.single_shifting) | |
452 | #define CODING_ISO_BOL(coding) \ | |
453 | ((coding)->spec.iso_2022.bol) | |
454 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
455 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
e951386e KH |
456 | #define CODING_ISO_CMP_STATUS(coding) \ |
457 | (&(coding)->spec.iso_2022.cmp_status) | |
458 | #define CODING_ISO_EXTSEGMENT_LEN(coding) \ | |
459 | ((coding)->spec.iso_2022.ctext_extended_segment_len) | |
460 | #define CODING_ISO_EMBEDDED_UTF_8(coding) \ | |
461 | ((coding)->spec.iso_2022.embedded_utf_8) | |
df7492f9 KH |
462 | |
463 | /* Control characters of ISO2022. */ | |
464 | /* code */ /* function */ | |
465 | #define ISO_CODE_LF 0x0A /* line-feed */ | |
466 | #define ISO_CODE_CR 0x0D /* carriage-return */ | |
467 | #define ISO_CODE_SO 0x0E /* shift-out */ | |
468 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
469 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
470 | #define ISO_CODE_ESC 0x1B /* escape */ | |
471 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
472 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
473 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
474 | ||
475 | /* All code (1-byte) of ISO2022 is classified into one of the | |
476 | followings. */ | |
477 | enum iso_code_class_type | |
478 | { | |
479 | ISO_control_0, /* Control codes in the range | |
480 | 0x00..0x1F and 0x7F, except for the | |
481 | following 5 codes. */ | |
df7492f9 KH |
482 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
483 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
484 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
485 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
486 | ISO_control_1, /* Control codes in the range | |
487 | 0x80..0x9F, except for the | |
488 | following 3 codes. */ | |
489 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
490 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
491 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
492 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
493 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
494 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
495 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
496 | }; | |
05e6f5dc | 497 | |
df7492f9 KH |
498 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
499 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 500 | |
df7492f9 KH |
501 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
502 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
503 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 504 | |
df7492f9 KH |
505 | /* If set, reset graphic planes and registers at end-of-line to the |
506 | initial state. */ | |
507 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 508 | |
df7492f9 KH |
509 | /* If set, reset graphic planes and registers before any control |
510 | characters to the initial state. */ | |
511 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 512 | |
df7492f9 KH |
513 | /* If set, encode by 7-bit environment. */ |
514 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 515 | |
df7492f9 KH |
516 | /* If set, use locking-shift function. */ |
517 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 518 | |
df7492f9 KH |
519 | /* If set, use single-shift function. Overwrite |
520 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
521 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 522 | |
df7492f9 KH |
523 | /* If set, use designation escape sequence. */ |
524 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 525 | |
df7492f9 KH |
526 | /* If set, produce revision number sequence. */ |
527 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 528 | |
df7492f9 KH |
529 | /* If set, produce ISO6429's direction specifying sequence. */ |
530 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 531 | |
df7492f9 KH |
532 | /* If set, assume designation states are reset at beginning of line on |
533 | output. */ | |
534 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 535 | |
df7492f9 KH |
536 | /* If set, designation sequence should be placed at beginning of line |
537 | on output. */ | |
538 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 539 | |
df7492f9 KH |
540 | /* If set, do not encode unsafe charactes on output. */ |
541 | #define CODING_ISO_FLAG_SAFE 0x0800 | |
aa72b389 | 542 | |
df7492f9 KH |
543 | /* If set, extra latin codes (128..159) are accepted as a valid code |
544 | on input. */ | |
545 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 546 | |
df7492f9 | 547 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 548 | |
df7492f9 | 549 | #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 |
aa72b389 | 550 | |
bf16eb23 | 551 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 552 | |
bf16eb23 | 553 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 554 | |
bf16eb23 | 555 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 556 | |
df7492f9 KH |
557 | /* A character to be produced on output if encoding of the original |
558 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
559 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 560 | |
a470d443 KH |
561 | /* UTF-8 section */ |
562 | #define CODING_UTF_8_BOM(coding) \ | |
563 | ((coding)->spec.utf_8_bom) | |
4ed46869 | 564 | |
df7492f9 KH |
565 | /* UTF-16 section */ |
566 | #define CODING_UTF_16_BOM(coding) \ | |
567 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 568 | |
df7492f9 KH |
569 | #define CODING_UTF_16_ENDIAN(coding) \ |
570 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 571 | |
df7492f9 KH |
572 | #define CODING_UTF_16_SURROGATE(coding) \ |
573 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 574 | |
4ed46869 | 575 | |
df7492f9 KH |
576 | /* CCL section */ |
577 | #define CODING_CCL_DECODER(coding) \ | |
578 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
579 | #define CODING_CCL_ENCODER(coding) \ | |
580 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
581 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 582 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 583 | |
5a936b46 | 584 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 585 | |
df7492f9 KH |
586 | enum coding_category |
587 | { | |
588 | coding_category_iso_7, | |
589 | coding_category_iso_7_tight, | |
590 | coding_category_iso_8_1, | |
591 | coding_category_iso_8_2, | |
592 | coding_category_iso_7_else, | |
593 | coding_category_iso_8_else, | |
a470d443 KH |
594 | coding_category_utf_8_auto, |
595 | coding_category_utf_8_nosig, | |
596 | coding_category_utf_8_sig, | |
df7492f9 KH |
597 | coding_category_utf_16_auto, |
598 | coding_category_utf_16_be, | |
599 | coding_category_utf_16_le, | |
600 | coding_category_utf_16_be_nosig, | |
601 | coding_category_utf_16_le_nosig, | |
602 | coding_category_charset, | |
603 | coding_category_sjis, | |
604 | coding_category_big5, | |
605 | coding_category_ccl, | |
606 | coding_category_emacs_mule, | |
607 | /* All above are targets of code detection. */ | |
608 | coding_category_raw_text, | |
609 | coding_category_undecided, | |
610 | coding_category_max | |
611 | }; | |
612 | ||
613 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
614 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
615 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
616 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
617 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
618 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
619 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
a470d443 KH |
620 | #define CATEGORY_MASK_UTF_8_AUTO (1 << coding_category_utf_8_auto) |
621 | #define CATEGORY_MASK_UTF_8_NOSIG (1 << coding_category_utf_8_nosig) | |
622 | #define CATEGORY_MASK_UTF_8_SIG (1 << coding_category_utf_8_sig) | |
b49a1807 | 623 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
624 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
625 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
626 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
627 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
628 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
629 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
630 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
631 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
632 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 633 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
634 | |
635 | /* This value is returned if detect_coding_mask () find nothing other | |
636 | than ASCII characters. */ | |
637 | #define CATEGORY_MASK_ANY \ | |
638 | (CATEGORY_MASK_ISO_7 \ | |
639 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
640 | | CATEGORY_MASK_ISO_8_1 \ | |
641 | | CATEGORY_MASK_ISO_8_2 \ | |
642 | | CATEGORY_MASK_ISO_7_ELSE \ | |
643 | | CATEGORY_MASK_ISO_8_ELSE \ | |
a470d443 KH |
644 | | CATEGORY_MASK_UTF_8_AUTO \ |
645 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
646 | | CATEGORY_MASK_UTF_8_SIG \ | |
2f3cbb32 | 647 | | CATEGORY_MASK_UTF_16_AUTO \ |
df7492f9 KH |
648 | | CATEGORY_MASK_UTF_16_BE \ |
649 | | CATEGORY_MASK_UTF_16_LE \ | |
650 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
651 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
652 | | CATEGORY_MASK_CHARSET \ | |
653 | | CATEGORY_MASK_SJIS \ | |
654 | | CATEGORY_MASK_BIG5 \ | |
655 | | CATEGORY_MASK_CCL \ | |
656 | | CATEGORY_MASK_EMACS_MULE) | |
657 | ||
658 | ||
659 | #define CATEGORY_MASK_ISO_7BIT \ | |
660 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
661 | ||
662 | #define CATEGORY_MASK_ISO_8BIT \ | |
663 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
664 | ||
665 | #define CATEGORY_MASK_ISO_ELSE \ | |
666 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
667 | ||
668 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
669 | (CATEGORY_MASK_ISO_7 \ | |
670 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
671 | | CATEGORY_MASK_ISO_7_ELSE \ | |
672 | | CATEGORY_MASK_ISO_8_ELSE) | |
673 | ||
674 | #define CATEGORY_MASK_ISO \ | |
675 | ( CATEGORY_MASK_ISO_7BIT \ | |
676 | | CATEGORY_MASK_ISO_8BIT \ | |
677 | | CATEGORY_MASK_ISO_ELSE) | |
678 | ||
679 | #define CATEGORY_MASK_UTF_16 \ | |
2f3cbb32 KH |
680 | (CATEGORY_MASK_UTF_16_AUTO \ |
681 | | CATEGORY_MASK_UTF_16_BE \ | |
df7492f9 KH |
682 | | CATEGORY_MASK_UTF_16_LE \ |
683 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
684 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
685 | ||
a470d443 KH |
686 | #define CATEGORY_MASK_UTF_8 \ |
687 | (CATEGORY_MASK_UTF_8_AUTO \ | |
688 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
689 | | CATEGORY_MASK_UTF_8_SIG) | |
df7492f9 KH |
690 | |
691 | /* List of symbols `coding-category-xxx' ordered by priority. This | |
692 | variable is exposed to Emacs Lisp. */ | |
693 | static Lisp_Object Vcoding_category_list; | |
694 | ||
695 | /* Table of coding categories (Lisp symbols). This variable is for | |
696 | internal use oly. */ | |
697 | static Lisp_Object Vcoding_category_table; | |
698 | ||
699 | /* Table of coding-categories ordered by priority. */ | |
700 | static enum coding_category coding_priorities[coding_category_max]; | |
701 | ||
702 | /* Nth element is a coding context for the coding system bound to the | |
703 | Nth coding category. */ | |
704 | static struct coding_system coding_categories[coding_category_max]; | |
705 | ||
df7492f9 KH |
706 | /*** Commonly used macros and functions ***/ |
707 | ||
708 | #ifndef min | |
709 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
710 | #endif | |
711 | #ifndef max | |
712 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
713 | #endif | |
4ed46869 | 714 | |
24a73b0a KH |
715 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
716 | do { \ | |
717 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
718 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 719 | } while (0) |
4ed46869 | 720 | |
4ed46869 | 721 | |
df7492f9 KH |
722 | /* Safely get one byte from the source text pointed by SRC which ends |
723 | at SRC_END, and set C to that byte. If there are not enough bytes | |
065e3595 KH |
724 | in the source, it jumps to `no_more_source'. If multibytep is |
725 | nonzero, and a multibyte character is found at SRC, set C to the | |
726 | negative value of the character code. The caller should declare | |
727 | and set these variables appropriately in advance: | |
728 | src, src_end, multibytep */ | |
aa72b389 | 729 | |
065e3595 KH |
730 | #define ONE_MORE_BYTE(c) \ |
731 | do { \ | |
732 | if (src == src_end) \ | |
733 | { \ | |
734 | if (src_base < src) \ | |
735 | record_conversion_result \ | |
736 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
737 | goto no_more_source; \ | |
738 | } \ | |
739 | c = *src++; \ | |
740 | if (multibytep && (c & 0x80)) \ | |
741 | { \ | |
742 | if ((c & 0xFE) == 0xC0) \ | |
743 | c = ((c & 1) << 6) | *src++; \ | |
744 | else \ | |
745 | { \ | |
35befdaa KH |
746 | src--; \ |
747 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
748 | record_conversion_result \ |
749 | (coding, CODING_RESULT_INVALID_SRC); \ | |
750 | } \ | |
751 | } \ | |
752 | consumed_chars++; \ | |
aa72b389 KH |
753 | } while (0) |
754 | ||
f56a4450 | 755 | /* Safely get two bytes from the source text pointed by SRC which ends |
220eeac9 KH |
756 | at SRC_END, and set C1 and C2 to those bytes while skipping the |
757 | heading multibyte characters. If there are not enough bytes in the | |
758 | source, it jumps to `no_more_source'. If multibytep is nonzero and | |
759 | a multibyte character is found for C2, set C2 to the negative value | |
760 | of the character code. The caller should declare and set these | |
761 | variables appropriately in advance: | |
f56a4450 KH |
762 | src, src_end, multibytep |
763 | It is intended that this macro is used in detect_coding_utf_16. */ | |
764 | ||
220eeac9 KH |
765 | #define TWO_MORE_BYTES(c1, c2) \ |
766 | do { \ | |
767 | do { \ | |
768 | if (src == src_end) \ | |
769 | goto no_more_source; \ | |
770 | c1 = *src++; \ | |
771 | if (multibytep && (c1 & 0x80)) \ | |
772 | { \ | |
773 | if ((c1 & 0xFE) == 0xC0) \ | |
774 | c1 = ((c1 & 1) << 6) | *src++; \ | |
775 | else \ | |
776 | { \ | |
777 | src += BYTES_BY_CHAR_HEAD (c1) - 1; \ | |
778 | c1 = -1; \ | |
779 | } \ | |
780 | } \ | |
781 | } while (c1 < 0); \ | |
782 | if (src == src_end) \ | |
783 | goto no_more_source; \ | |
784 | c2 = *src++; \ | |
785 | if (multibytep && (c2 & 0x80)) \ | |
786 | { \ | |
787 | if ((c2 & 0xFE) == 0xC0) \ | |
788 | c2 = ((c2 & 1) << 6) | *src++; \ | |
789 | else \ | |
790 | c2 = -1; \ | |
791 | } \ | |
f56a4450 KH |
792 | } while (0) |
793 | ||
aa72b389 | 794 | |
065e3595 KH |
795 | #define ONE_MORE_BYTE_NO_CHECK(c) \ |
796 | do { \ | |
797 | c = *src++; \ | |
798 | if (multibytep && (c & 0x80)) \ | |
799 | { \ | |
800 | if ((c & 0xFE) == 0xC0) \ | |
801 | c = ((c & 1) << 6) | *src++; \ | |
802 | else \ | |
803 | { \ | |
35befdaa KH |
804 | src--; \ |
805 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
806 | record_conversion_result \ |
807 | (coding, CODING_RESULT_INVALID_SRC); \ | |
808 | } \ | |
809 | } \ | |
810 | consumed_chars++; \ | |
aa72b389 KH |
811 | } while (0) |
812 | ||
aa72b389 | 813 | |
df7492f9 KH |
814 | /* Store a byte C in the place pointed by DST and increment DST to the |
815 | next free point, and increment PRODUCED_CHARS. The caller should | |
816 | assure that C is 0..127, and declare and set the variable `dst' | |
817 | appropriately in advance. | |
818 | */ | |
aa72b389 KH |
819 | |
820 | ||
df7492f9 KH |
821 | #define EMIT_ONE_ASCII_BYTE(c) \ |
822 | do { \ | |
823 | produced_chars++; \ | |
824 | *dst++ = (c); \ | |
b6871cc7 | 825 | } while (0) |
aa72b389 KH |
826 | |
827 | ||
df7492f9 | 828 | /* Like EMIT_ONE_ASCII_BYTE byt store two bytes; C1 and C2. */ |
aa72b389 | 829 | |
df7492f9 KH |
830 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
831 | do { \ | |
832 | produced_chars += 2; \ | |
833 | *dst++ = (c1), *dst++ = (c2); \ | |
834 | } while (0) | |
aa72b389 KH |
835 | |
836 | ||
df7492f9 KH |
837 | /* Store a byte C in the place pointed by DST and increment DST to the |
838 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is | |
839 | nonzero, store in an appropriate multibyte from. The caller should | |
840 | declare and set the variables `dst' and `multibytep' appropriately | |
841 | in advance. */ | |
842 | ||
843 | #define EMIT_ONE_BYTE(c) \ | |
844 | do { \ | |
845 | produced_chars++; \ | |
846 | if (multibytep) \ | |
847 | { \ | |
848 | int ch = (c); \ | |
849 | if (ch >= 0x80) \ | |
850 | ch = BYTE8_TO_CHAR (ch); \ | |
851 | CHAR_STRING_ADVANCE (ch, dst); \ | |
852 | } \ | |
853 | else \ | |
854 | *dst++ = (c); \ | |
aa72b389 | 855 | } while (0) |
aa72b389 | 856 | |
aa72b389 | 857 | |
df7492f9 | 858 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 859 | |
e19c3639 KH |
860 | #define EMIT_TWO_BYTES(c1, c2) \ |
861 | do { \ | |
862 | produced_chars += 2; \ | |
863 | if (multibytep) \ | |
864 | { \ | |
865 | int ch; \ | |
866 | \ | |
867 | ch = (c1); \ | |
868 | if (ch >= 0x80) \ | |
869 | ch = BYTE8_TO_CHAR (ch); \ | |
870 | CHAR_STRING_ADVANCE (ch, dst); \ | |
871 | ch = (c2); \ | |
872 | if (ch >= 0x80) \ | |
873 | ch = BYTE8_TO_CHAR (ch); \ | |
874 | CHAR_STRING_ADVANCE (ch, dst); \ | |
875 | } \ | |
876 | else \ | |
877 | { \ | |
878 | *dst++ = (c1); \ | |
879 | *dst++ = (c2); \ | |
880 | } \ | |
aa72b389 KH |
881 | } while (0) |
882 | ||
883 | ||
df7492f9 KH |
884 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
885 | do { \ | |
886 | EMIT_ONE_BYTE (c1); \ | |
887 | EMIT_TWO_BYTES (c2, c3); \ | |
888 | } while (0) | |
aa72b389 | 889 | |
aa72b389 | 890 | |
df7492f9 KH |
891 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
892 | do { \ | |
893 | EMIT_TWO_BYTES (c1, c2); \ | |
894 | EMIT_TWO_BYTES (c3, c4); \ | |
895 | } while (0) | |
aa72b389 | 896 | |
aa72b389 | 897 | |
f6cbaf43 | 898 | /* Prototypes for static functions. */ |
f57e2426 J |
899 | static void record_conversion_result (struct coding_system *coding, |
900 | enum coding_result_code result); | |
901 | static int detect_coding_utf_8 (struct coding_system *, | |
902 | struct coding_detection_info *info); | |
903 | static void decode_coding_utf_8 (struct coding_system *); | |
904 | static int encode_coding_utf_8 (struct coding_system *); | |
905 | ||
906 | static int detect_coding_utf_16 (struct coding_system *, | |
907 | struct coding_detection_info *info); | |
908 | static void decode_coding_utf_16 (struct coding_system *); | |
909 | static int encode_coding_utf_16 (struct coding_system *); | |
910 | ||
911 | static int detect_coding_iso_2022 (struct coding_system *, | |
912 | struct coding_detection_info *info); | |
913 | static void decode_coding_iso_2022 (struct coding_system *); | |
914 | static int encode_coding_iso_2022 (struct coding_system *); | |
915 | ||
916 | static int detect_coding_emacs_mule (struct coding_system *, | |
917 | struct coding_detection_info *info); | |
918 | static void decode_coding_emacs_mule (struct coding_system *); | |
919 | static int encode_coding_emacs_mule (struct coding_system *); | |
920 | ||
921 | static int detect_coding_sjis (struct coding_system *, | |
922 | struct coding_detection_info *info); | |
923 | static void decode_coding_sjis (struct coding_system *); | |
924 | static int encode_coding_sjis (struct coding_system *); | |
925 | ||
926 | static int detect_coding_big5 (struct coding_system *, | |
927 | struct coding_detection_info *info); | |
928 | static void decode_coding_big5 (struct coding_system *); | |
929 | static int encode_coding_big5 (struct coding_system *); | |
930 | ||
931 | static int detect_coding_ccl (struct coding_system *, | |
932 | struct coding_detection_info *info); | |
933 | static void decode_coding_ccl (struct coding_system *); | |
934 | static int encode_coding_ccl (struct coding_system *); | |
935 | ||
936 | static void decode_coding_raw_text (struct coding_system *); | |
937 | static int encode_coding_raw_text (struct coding_system *); | |
938 | ||
939 | static void coding_set_source (struct coding_system *); | |
940 | static void coding_set_destination (struct coding_system *); | |
941 | static void coding_alloc_by_realloc (struct coding_system *, EMACS_INT); | |
942 | static void coding_alloc_by_making_gap (struct coding_system *, | |
943 | EMACS_INT, EMACS_INT); | |
944 | static unsigned char *alloc_destination (struct coding_system *, | |
945 | EMACS_INT, unsigned char *); | |
946 | static void setup_iso_safe_charsets (Lisp_Object); | |
947 | static unsigned char *encode_designation_at_bol (struct coding_system *, | |
948 | int *, int *, | |
949 | unsigned char *); | |
950 | static int detect_eol (const unsigned char *, | |
951 | EMACS_INT, enum coding_category); | |
952 | static Lisp_Object adjust_coding_eol_type (struct coding_system *, int); | |
953 | static void decode_eol (struct coding_system *); | |
954 | static Lisp_Object get_translation_table (Lisp_Object, int, int *); | |
955 | static Lisp_Object get_translation (Lisp_Object, int *, int *); | |
956 | static int produce_chars (struct coding_system *, Lisp_Object, int); | |
957 | static INLINE void produce_charset (struct coding_system *, int *, | |
958 | EMACS_INT); | |
959 | static void produce_annotation (struct coding_system *, EMACS_INT); | |
960 | static int decode_coding (struct coding_system *); | |
961 | static INLINE int *handle_composition_annotation (EMACS_INT, EMACS_INT, | |
962 | struct coding_system *, | |
963 | int *, EMACS_INT *); | |
964 | static INLINE int *handle_charset_annotation (EMACS_INT, EMACS_INT, | |
965 | struct coding_system *, | |
966 | int *, EMACS_INT *); | |
967 | static void consume_chars (struct coding_system *, Lisp_Object, int); | |
968 | static int encode_coding (struct coding_system *); | |
969 | static Lisp_Object make_conversion_work_buffer (int); | |
970 | static Lisp_Object code_conversion_restore (Lisp_Object); | |
971 | static INLINE int char_encodable_p (int, Lisp_Object); | |
972 | static Lisp_Object make_subsidiaries (Lisp_Object); | |
f6cbaf43 | 973 | |
065e3595 KH |
974 | static void |
975 | record_conversion_result (struct coding_system *coding, | |
976 | enum coding_result_code result) | |
977 | { | |
978 | coding->result = result; | |
979 | switch (result) | |
980 | { | |
981 | case CODING_RESULT_INSUFFICIENT_SRC: | |
982 | Vlast_code_conversion_error = Qinsufficient_source; | |
983 | break; | |
984 | case CODING_RESULT_INCONSISTENT_EOL: | |
985 | Vlast_code_conversion_error = Qinconsistent_eol; | |
986 | break; | |
987 | case CODING_RESULT_INVALID_SRC: | |
988 | Vlast_code_conversion_error = Qinvalid_source; | |
989 | break; | |
990 | case CODING_RESULT_INTERRUPT: | |
991 | Vlast_code_conversion_error = Qinterrupted; | |
992 | break; | |
993 | case CODING_RESULT_INSUFFICIENT_MEM: | |
994 | Vlast_code_conversion_error = Qinsufficient_memory; | |
995 | break; | |
ebaf11b6 KH |
996 | case CODING_RESULT_INSUFFICIENT_DST: |
997 | /* Don't record this error in Vlast_code_conversion_error | |
998 | because it happens just temporarily and is resolved when the | |
999 | whole conversion is finished. */ | |
1000 | break; | |
409ea3a1 AS |
1001 | case CODING_RESULT_SUCCESS: |
1002 | break; | |
35befdaa KH |
1003 | default: |
1004 | Vlast_code_conversion_error = intern ("Unknown error"); | |
065e3595 KH |
1005 | } |
1006 | } | |
1007 | ||
75f80e63 EZ |
1008 | /* This wrapper macro is used to preserve validity of pointers into |
1009 | buffer text across calls to decode_char, which could cause | |
1010 | relocation of buffers if it loads a charset map, because loading a | |
1011 | charset map allocates large structures. */ | |
df7492f9 KH |
1012 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
1013 | do { \ | |
1014 | charset_map_loaded = 0; \ | |
1015 | c = DECODE_CHAR (charset, code); \ | |
1016 | if (charset_map_loaded) \ | |
1017 | { \ | |
8f924df7 | 1018 | const unsigned char *orig = coding->source; \ |
df7492f9 KH |
1019 | EMACS_INT offset; \ |
1020 | \ | |
1021 | coding_set_source (coding); \ | |
1022 | offset = coding->source - orig; \ | |
1023 | src += offset; \ | |
1024 | src_base += offset; \ | |
1025 | src_end += offset; \ | |
1026 | } \ | |
aa72b389 KH |
1027 | } while (0) |
1028 | ||
1029 | ||
119852e7 KH |
1030 | /* If there are at least BYTES length of room at dst, allocate memory |
1031 | for coding->destination and update dst and dst_end. We don't have | |
1032 | to take care of coding->source which will be relocated. It is | |
1033 | handled by calling coding_set_source in encode_coding. */ | |
1034 | ||
df7492f9 KH |
1035 | #define ASSURE_DESTINATION(bytes) \ |
1036 | do { \ | |
1037 | if (dst + (bytes) >= dst_end) \ | |
1038 | { \ | |
1039 | int more_bytes = charbuf_end - charbuf + (bytes); \ | |
1040 | \ | |
1041 | dst = alloc_destination (coding, more_bytes, dst); \ | |
1042 | dst_end = coding->destination + coding->dst_bytes; \ | |
1043 | } \ | |
1044 | } while (0) | |
aa72b389 | 1045 | |
aa72b389 | 1046 | |
db274c7a KH |
1047 | /* Store multibyte form of the character C in P, and advance P to the |
1048 | end of the multibyte form. This is like CHAR_STRING_ADVANCE but it | |
1049 | never calls MAYBE_UNIFY_CHAR. */ | |
1050 | ||
1051 | #define CHAR_STRING_ADVANCE_NO_UNIFY(c, p) \ | |
1052 | do { \ | |
1053 | if ((c) <= MAX_1_BYTE_CHAR) \ | |
1054 | *(p)++ = (c); \ | |
1055 | else if ((c) <= MAX_2_BYTE_CHAR) \ | |
1056 | *(p)++ = (0xC0 | ((c) >> 6)), \ | |
1057 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
1058 | else if ((c) <= MAX_3_BYTE_CHAR) \ | |
1059 | *(p)++ = (0xE0 | ((c) >> 12)), \ | |
1060 | *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \ | |
1061 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
1062 | else if ((c) <= MAX_4_BYTE_CHAR) \ | |
1063 | *(p)++ = (0xF0 | (c >> 18)), \ | |
1064 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
1065 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
1066 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
1067 | else if ((c) <= MAX_5_BYTE_CHAR) \ | |
1068 | *(p)++ = 0xF8, \ | |
1069 | *(p)++ = (0x80 | ((c >> 18) & 0x0F)), \ | |
1070 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
1071 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
1072 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
1073 | else \ | |
1074 | (p) += BYTE8_STRING ((c) - 0x3FFF80, p); \ | |
1075 | } while (0) | |
1076 | ||
1077 | ||
1078 | /* Return the character code of character whose multibyte form is at | |
1079 | P, and advance P to the end of the multibyte form. This is like | |
1080 | STRING_CHAR_ADVANCE, but it never calls MAYBE_UNIFY_CHAR. */ | |
1081 | ||
1082 | #define STRING_CHAR_ADVANCE_NO_UNIFY(p) \ | |
1083 | (!((p)[0] & 0x80) \ | |
1084 | ? *(p)++ \ | |
1085 | : ! ((p)[0] & 0x20) \ | |
1086 | ? ((p) += 2, \ | |
1087 | ((((p)[-2] & 0x1F) << 6) \ | |
1088 | | ((p)[-1] & 0x3F) \ | |
1089 | | ((unsigned char) ((p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \ | |
1090 | : ! ((p)[0] & 0x10) \ | |
1091 | ? ((p) += 3, \ | |
1092 | ((((p)[-3] & 0x0F) << 12) \ | |
1093 | | (((p)[-2] & 0x3F) << 6) \ | |
1094 | | ((p)[-1] & 0x3F))) \ | |
1095 | : ! ((p)[0] & 0x08) \ | |
1096 | ? ((p) += 4, \ | |
1097 | ((((p)[-4] & 0xF) << 18) \ | |
1098 | | (((p)[-3] & 0x3F) << 12) \ | |
1099 | | (((p)[-2] & 0x3F) << 6) \ | |
1100 | | ((p)[-1] & 0x3F))) \ | |
1101 | : ((p) += 5, \ | |
1102 | ((((p)[-4] & 0x3F) << 18) \ | |
1103 | | (((p)[-3] & 0x3F) << 12) \ | |
1104 | | (((p)[-2] & 0x3F) << 6) \ | |
1105 | | ((p)[-1] & 0x3F)))) | |
1106 | ||
aa72b389 | 1107 | |
df7492f9 KH |
1108 | static void |
1109 | coding_set_source (coding) | |
aa72b389 | 1110 | struct coding_system *coding; |
aa72b389 | 1111 | { |
df7492f9 KH |
1112 | if (BUFFERP (coding->src_object)) |
1113 | { | |
2cb26057 | 1114 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 1115 | |
df7492f9 | 1116 | if (coding->src_pos < 0) |
2cb26057 | 1117 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 1118 | else |
2cb26057 | 1119 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 1120 | } |
df7492f9 | 1121 | else if (STRINGP (coding->src_object)) |
aa72b389 | 1122 | { |
8f924df7 | 1123 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 1124 | } |
df7492f9 KH |
1125 | else |
1126 | /* Otherwise, the source is C string and is never relocated | |
1127 | automatically. Thus we don't have to update anything. */ | |
1128 | ; | |
1129 | } | |
aa72b389 | 1130 | |
df7492f9 KH |
1131 | static void |
1132 | coding_set_destination (coding) | |
1133 | struct coding_system *coding; | |
1134 | { | |
1135 | if (BUFFERP (coding->dst_object)) | |
aa72b389 | 1136 | { |
df7492f9 | 1137 | if (coding->src_pos < 0) |
aa72b389 | 1138 | { |
13818c30 | 1139 | coding->destination = BEG_ADDR + coding->dst_pos_byte - BEG_BYTE; |
28f67a95 KH |
1140 | coding->dst_bytes = (GAP_END_ADDR |
1141 | - (coding->src_bytes - coding->consumed) | |
1142 | - coding->destination); | |
aa72b389 | 1143 | } |
df7492f9 | 1144 | else |
28f67a95 KH |
1145 | { |
1146 | /* We are sure that coding->dst_pos_byte is before the gap | |
1147 | of the buffer. */ | |
1148 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
13818c30 | 1149 | + coding->dst_pos_byte - BEG_BYTE); |
28f67a95 KH |
1150 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) |
1151 | - coding->destination); | |
1152 | } | |
df7492f9 KH |
1153 | } |
1154 | else | |
1155 | /* Otherwise, the destination is C string and is never relocated | |
1156 | automatically. Thus we don't have to update anything. */ | |
1157 | ; | |
1158 | } | |
1159 | ||
1160 | ||
1161 | static void | |
1162 | coding_alloc_by_realloc (coding, bytes) | |
1163 | struct coding_system *coding; | |
1164 | EMACS_INT bytes; | |
1165 | { | |
1166 | coding->destination = (unsigned char *) xrealloc (coding->destination, | |
1167 | coding->dst_bytes + bytes); | |
1168 | coding->dst_bytes += bytes; | |
1169 | } | |
1170 | ||
1171 | static void | |
db274c7a | 1172 | coding_alloc_by_making_gap (coding, gap_head_used, bytes) |
df7492f9 | 1173 | struct coding_system *coding; |
db274c7a | 1174 | EMACS_INT gap_head_used, bytes; |
df7492f9 | 1175 | { |
db274c7a | 1176 | if (EQ (coding->src_object, coding->dst_object)) |
df7492f9 | 1177 | { |
db274c7a KH |
1178 | /* The gap may contain the produced data at the head and not-yet |
1179 | consumed data at the tail. To preserve those data, we at | |
1180 | first make the gap size to zero, then increase the gap | |
1181 | size. */ | |
1182 | EMACS_INT add = GAP_SIZE; | |
1183 | ||
1184 | GPT += gap_head_used, GPT_BYTE += gap_head_used; | |
1185 | GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
df7492f9 KH |
1186 | make_gap (bytes); |
1187 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
db274c7a | 1188 | GPT -= gap_head_used, GPT_BYTE -= gap_head_used; |
df7492f9 | 1189 | } |
730fff51 | 1190 | else |
df7492f9 | 1191 | { |
2c78b7e1 KH |
1192 | Lisp_Object this_buffer; |
1193 | ||
1194 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
1195 | set_buffer_internal (XBUFFER (coding->dst_object)); |
1196 | make_gap (bytes); | |
1197 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 1198 | } |
df7492f9 | 1199 | } |
8f924df7 | 1200 | |
df7492f9 KH |
1201 | |
1202 | static unsigned char * | |
1203 | alloc_destination (coding, nbytes, dst) | |
1204 | struct coding_system *coding; | |
3e139625 | 1205 | EMACS_INT nbytes; |
df7492f9 KH |
1206 | unsigned char *dst; |
1207 | { | |
1208 | EMACS_INT offset = dst - coding->destination; | |
1209 | ||
1210 | if (BUFFERP (coding->dst_object)) | |
db274c7a KH |
1211 | { |
1212 | struct buffer *buf = XBUFFER (coding->dst_object); | |
1213 | ||
1214 | coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes); | |
1215 | } | |
aa72b389 | 1216 | else |
df7492f9 | 1217 | coding_alloc_by_realloc (coding, nbytes); |
df7492f9 KH |
1218 | coding_set_destination (coding); |
1219 | dst = coding->destination + offset; | |
1220 | return dst; | |
1221 | } | |
aa72b389 | 1222 | |
ff0dacd7 KH |
1223 | /** Macros for annotations. */ |
1224 | ||
ff0dacd7 KH |
1225 | /* An annotation data is stored in the array coding->charbuf in this |
1226 | format: | |
69a80ea3 | 1227 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1228 | LENGTH is the number of elements in the annotation. |
1229 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1230 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1231 | |
1232 | The format of the following elements depend on ANNOTATION_MASK. | |
1233 | ||
1234 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1235 | follows: | |
e951386e KH |
1236 | ... NBYTES METHOD [ COMPOSITION-COMPONENTS ... ] |
1237 | ||
1238 | NBYTES is the number of bytes specified in the header part of | |
1239 | old-style emacs-mule encoding, or 0 for the other kind of | |
1240 | composition. | |
1241 | ||
ff0dacd7 | 1242 | METHOD is one of enum composition_method. |
e951386e | 1243 | |
ff0dacd7 KH |
1244 | Optionnal COMPOSITION-COMPONENTS are characters and composition |
1245 | rules. | |
1246 | ||
1247 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
e951386e KH |
1248 | follows. |
1249 | ||
1250 | If ANNOTATION_MASK is 0, this annotation is just a space holder to | |
1251 | recover from an invalid annotation, and should be skipped by | |
1252 | produce_annotation. */ | |
1253 | ||
1254 | /* Maximum length of the header of annotation data. */ | |
1255 | #define MAX_ANNOTATION_LENGTH 5 | |
ff0dacd7 | 1256 | |
69a80ea3 | 1257 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1258 | do { \ |
1259 | *(buf)++ = -(len); \ | |
1260 | *(buf)++ = (mask); \ | |
69a80ea3 | 1261 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1262 | coding->annotated = 1; \ |
1263 | } while (0); | |
1264 | ||
e951386e | 1265 | #define ADD_COMPOSITION_DATA(buf, nchars, nbytes, method) \ |
69a80ea3 | 1266 | do { \ |
e951386e KH |
1267 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ |
1268 | *buf++ = nbytes; \ | |
69a80ea3 | 1269 | *buf++ = method; \ |
ff0dacd7 KH |
1270 | } while (0) |
1271 | ||
1272 | ||
69a80ea3 KH |
1273 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1274 | do { \ | |
1275 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1276 | *buf++ = id; \ | |
ff0dacd7 KH |
1277 | } while (0) |
1278 | ||
df7492f9 KH |
1279 | \f |
1280 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1281 | ||
1282 | ||
1283 | ||
1284 | \f | |
1285 | /*** 3. UTF-8 ***/ | |
1286 | ||
1287 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1288 | Check if a text is encoded in UTF-8. If it is, return 1, else |
1289 | return 0. */ | |
df7492f9 KH |
1290 | |
1291 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1292 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1293 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1294 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1295 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1296 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1297 | ||
a470d443 KH |
1298 | #define UTF_BOM 0xFEFF |
1299 | #define UTF_8_BOM_1 0xEF | |
1300 | #define UTF_8_BOM_2 0xBB | |
1301 | #define UTF_8_BOM_3 0xBF | |
1302 | ||
df7492f9 | 1303 | static int |
ff0dacd7 | 1304 | detect_coding_utf_8 (coding, detect_info) |
df7492f9 | 1305 | struct coding_system *coding; |
ff0dacd7 | 1306 | struct coding_detection_info *detect_info; |
df7492f9 | 1307 | { |
065e3595 | 1308 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1309 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1310 | int multibytep = coding->src_multibyte; |
1311 | int consumed_chars = 0; | |
a470d443 | 1312 | int bom_found = 0; |
df7492f9 KH |
1313 | int found = 0; |
1314 | ||
ff0dacd7 | 1315 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1316 | /* A coding system of this category is always ASCII compatible. */ |
1317 | src += coding->head_ascii; | |
1318 | ||
1319 | while (1) | |
aa72b389 | 1320 | { |
df7492f9 | 1321 | int c, c1, c2, c3, c4; |
aa72b389 | 1322 | |
065e3595 | 1323 | src_base = src; |
df7492f9 | 1324 | ONE_MORE_BYTE (c); |
065e3595 | 1325 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1326 | continue; |
1327 | ONE_MORE_BYTE (c1); | |
065e3595 | 1328 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1329 | break; |
1330 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1331 | { |
a470d443 | 1332 | found = 1; |
df7492f9 | 1333 | continue; |
aa72b389 | 1334 | } |
df7492f9 | 1335 | ONE_MORE_BYTE (c2); |
065e3595 | 1336 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1337 | break; |
1338 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1339 | { |
a470d443 KH |
1340 | found = 1; |
1341 | if (src_base == coding->source | |
1342 | && c == UTF_8_BOM_1 && c1 == UTF_8_BOM_2 && c2 == UTF_8_BOM_3) | |
1343 | bom_found = 1; | |
df7492f9 | 1344 | continue; |
aa72b389 | 1345 | } |
df7492f9 | 1346 | ONE_MORE_BYTE (c3); |
065e3595 | 1347 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1348 | break; |
1349 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1350 | { |
a470d443 | 1351 | found = 1; |
df7492f9 KH |
1352 | continue; |
1353 | } | |
1354 | ONE_MORE_BYTE (c4); | |
065e3595 | 1355 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1356 | break; |
1357 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1358 | { | |
a470d443 | 1359 | found = 1; |
df7492f9 KH |
1360 | continue; |
1361 | } | |
1362 | break; | |
aa72b389 | 1363 | } |
ff0dacd7 | 1364 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1365 | return 0; |
aa72b389 | 1366 | |
df7492f9 | 1367 | no_more_source: |
065e3595 | 1368 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1369 | { |
ff0dacd7 | 1370 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1371 | return 0; |
aa72b389 | 1372 | } |
a470d443 KH |
1373 | if (bom_found) |
1374 | { | |
1375 | /* The first character 0xFFFE doesn't necessarily mean a BOM. */ | |
1376 | detect_info->found |= CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG; | |
1377 | } | |
1378 | else | |
1379 | { | |
1380 | detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG; | |
0e17387a KH |
1381 | if (found) |
1382 | detect_info->found |= CATEGORY_MASK_UTF_8_NOSIG; | |
a470d443 | 1383 | } |
ff0dacd7 | 1384 | return 1; |
aa72b389 KH |
1385 | } |
1386 | ||
4ed46869 | 1387 | |
b73bfc1c | 1388 | static void |
df7492f9 | 1389 | decode_coding_utf_8 (coding) |
b73bfc1c | 1390 | struct coding_system *coding; |
b73bfc1c | 1391 | { |
8f924df7 KH |
1392 | const unsigned char *src = coding->source + coding->consumed; |
1393 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1394 | const unsigned char *src_base; | |
69a80ea3 KH |
1395 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1396 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
453b38f0 | 1397 | int consumed_chars = 0, consumed_chars_base = 0; |
df7492f9 | 1398 | int multibytep = coding->src_multibyte; |
a470d443 | 1399 | enum utf_bom_type bom = CODING_UTF_8_BOM (coding); |
24a73b0a | 1400 | Lisp_Object attr, charset_list; |
0a9564cb EZ |
1401 | int eol_crlf = |
1402 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1403 | int byte_after_cr = -1; |
4ed46869 | 1404 | |
24a73b0a | 1405 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1406 | |
a470d443 KH |
1407 | if (bom != utf_without_bom) |
1408 | { | |
1409 | int c1, c2, c3; | |
1410 | ||
1411 | src_base = src; | |
1412 | ONE_MORE_BYTE (c1); | |
1413 | if (! UTF_8_3_OCTET_LEADING_P (c1)) | |
1414 | src = src_base; | |
1415 | else | |
1416 | { | |
159bd5a2 | 1417 | ONE_MORE_BYTE (c2); |
a470d443 KH |
1418 | if (! UTF_8_EXTRA_OCTET_P (c2)) |
1419 | src = src_base; | |
1420 | else | |
1421 | { | |
159bd5a2 | 1422 | ONE_MORE_BYTE (c3); |
a470d443 KH |
1423 | if (! UTF_8_EXTRA_OCTET_P (c3)) |
1424 | src = src_base; | |
1425 | else | |
1426 | { | |
1427 | if ((c1 != UTF_8_BOM_1) | |
1428 | || (c2 != UTF_8_BOM_2) || (c3 != UTF_8_BOM_3)) | |
1429 | src = src_base; | |
1430 | else | |
1431 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1432 | } | |
1433 | } | |
1434 | } | |
1435 | } | |
1436 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1437 | ||
1438 | ||
1439 | ||
df7492f9 | 1440 | while (1) |
b73bfc1c | 1441 | { |
df7492f9 | 1442 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1443 | |
df7492f9 KH |
1444 | src_base = src; |
1445 | consumed_chars_base = consumed_chars; | |
4af310db | 1446 | |
df7492f9 | 1447 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1448 | { |
1449 | if (byte_after_cr >= 0) | |
1450 | src_base--; | |
1451 | break; | |
1452 | } | |
df7492f9 | 1453 | |
119852e7 KH |
1454 | if (byte_after_cr >= 0) |
1455 | c1 = byte_after_cr, byte_after_cr = -1; | |
1456 | else | |
1457 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1458 | if (c1 < 0) |
1459 | { | |
1460 | c = - c1; | |
1461 | } | |
1462 | else if (UTF_8_1_OCTET_P(c1)) | |
df7492f9 | 1463 | { |
119852e7 KH |
1464 | if (eol_crlf && c1 == '\r') |
1465 | ONE_MORE_BYTE (byte_after_cr); | |
df7492f9 | 1466 | c = c1; |
4af310db | 1467 | } |
df7492f9 | 1468 | else |
4af310db | 1469 | { |
df7492f9 | 1470 | ONE_MORE_BYTE (c2); |
065e3595 | 1471 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1472 | goto invalid_code; |
1473 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1474 | { |
b0edb2c5 DL |
1475 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1476 | /* Reject overlong sequences here and below. Encoders | |
1477 | producing them are incorrect, they can be misleading, | |
1478 | and they mess up read/write invariance. */ | |
1479 | if (c < 128) | |
1480 | goto invalid_code; | |
4af310db | 1481 | } |
df7492f9 | 1482 | else |
aa72b389 | 1483 | { |
df7492f9 | 1484 | ONE_MORE_BYTE (c3); |
065e3595 | 1485 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1486 | goto invalid_code; |
1487 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1488 | { |
1489 | c = (((c1 & 0xF) << 12) | |
1490 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1491 | if (c < 0x800 |
1492 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1493 | goto invalid_code; |
1494 | } | |
df7492f9 KH |
1495 | else |
1496 | { | |
1497 | ONE_MORE_BYTE (c4); | |
065e3595 | 1498 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1499 | goto invalid_code; |
1500 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1501 | { |
df7492f9 KH |
1502 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1503 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1504 | if (c < 0x10000) |
1505 | goto invalid_code; | |
1506 | } | |
df7492f9 KH |
1507 | else |
1508 | { | |
1509 | ONE_MORE_BYTE (c5); | |
065e3595 | 1510 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1511 | goto invalid_code; |
1512 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1513 | { | |
1514 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1515 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1516 | | (c5 & 0x3F)); | |
b0edb2c5 | 1517 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1518 | goto invalid_code; |
1519 | } | |
1520 | else | |
1521 | goto invalid_code; | |
1522 | } | |
1523 | } | |
aa72b389 | 1524 | } |
b73bfc1c | 1525 | } |
df7492f9 KH |
1526 | |
1527 | *charbuf++ = c; | |
1528 | continue; | |
1529 | ||
1530 | invalid_code: | |
1531 | src = src_base; | |
1532 | consumed_chars = consumed_chars_base; | |
1533 | ONE_MORE_BYTE (c); | |
1534 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1535 | coding->errors++; | |
aa72b389 KH |
1536 | } |
1537 | ||
df7492f9 KH |
1538 | no_more_source: |
1539 | coding->consumed_char += consumed_chars_base; | |
1540 | coding->consumed = src_base - coding->source; | |
1541 | coding->charbuf_used = charbuf - coding->charbuf; | |
1542 | } | |
1543 | ||
1544 | ||
1545 | static int | |
1546 | encode_coding_utf_8 (coding) | |
1547 | struct coding_system *coding; | |
1548 | { | |
1549 | int multibytep = coding->dst_multibyte; | |
1550 | int *charbuf = coding->charbuf; | |
1551 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1552 | unsigned char *dst = coding->destination + coding->produced; | |
1553 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
e19c3639 | 1554 | int produced_chars = 0; |
df7492f9 KH |
1555 | int c; |
1556 | ||
a470d443 KH |
1557 | if (CODING_UTF_8_BOM (coding) == utf_with_bom) |
1558 | { | |
1559 | ASSURE_DESTINATION (3); | |
1560 | EMIT_THREE_BYTES (UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3); | |
1561 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1562 | } | |
1563 | ||
df7492f9 | 1564 | if (multibytep) |
aa72b389 | 1565 | { |
df7492f9 KH |
1566 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1567 | ||
1568 | while (charbuf < charbuf_end) | |
b73bfc1c | 1569 | { |
df7492f9 | 1570 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1571 | |
df7492f9 KH |
1572 | ASSURE_DESTINATION (safe_room); |
1573 | c = *charbuf++; | |
28f67a95 KH |
1574 | if (CHAR_BYTE8_P (c)) |
1575 | { | |
1576 | c = CHAR_TO_BYTE8 (c); | |
1577 | EMIT_ONE_BYTE (c); | |
1578 | } | |
1579 | else | |
1580 | { | |
db274c7a | 1581 | CHAR_STRING_ADVANCE_NO_UNIFY (c, pend); |
28f67a95 KH |
1582 | for (p = str; p < pend; p++) |
1583 | EMIT_ONE_BYTE (*p); | |
1584 | } | |
b73bfc1c | 1585 | } |
aa72b389 | 1586 | } |
df7492f9 KH |
1587 | else |
1588 | { | |
1589 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1590 | ||
1591 | while (charbuf < charbuf_end) | |
b73bfc1c | 1592 | { |
df7492f9 KH |
1593 | ASSURE_DESTINATION (safe_room); |
1594 | c = *charbuf++; | |
f03caae0 KH |
1595 | if (CHAR_BYTE8_P (c)) |
1596 | *dst++ = CHAR_TO_BYTE8 (c); | |
1597 | else | |
db274c7a | 1598 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
df7492f9 | 1599 | produced_chars++; |
4ed46869 KH |
1600 | } |
1601 | } | |
065e3595 | 1602 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1603 | coding->produced_char += produced_chars; |
1604 | coding->produced = dst - coding->destination; | |
1605 | return 0; | |
4ed46869 KH |
1606 | } |
1607 | ||
b73bfc1c | 1608 | |
df7492f9 | 1609 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
1610 | Check if a text is encoded in one of UTF-16 based coding systems. |
1611 | If it is, return 1, else return 0. */ | |
aa72b389 | 1612 | |
df7492f9 KH |
1613 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1614 | (((val) & 0xFC00) == 0xD800) | |
1615 | ||
1616 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1617 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1618 | |
df7492f9 KH |
1619 | #define UTF_16_INVALID_P(val) \ |
1620 | (((val) == 0xFFFE) \ | |
1621 | || ((val) == 0xFFFF) \ | |
1622 | || UTF_16_LOW_SURROGATE_P (val)) | |
aa72b389 | 1623 | |
aa72b389 | 1624 | |
df7492f9 | 1625 | static int |
ff0dacd7 | 1626 | detect_coding_utf_16 (coding, detect_info) |
aa72b389 | 1627 | struct coding_system *coding; |
ff0dacd7 | 1628 | struct coding_detection_info *detect_info; |
aa72b389 | 1629 | { |
8f924df7 KH |
1630 | const unsigned char *src = coding->source, *src_base = src; |
1631 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
1632 | int multibytep = coding->src_multibyte; |
1633 | int consumed_chars = 0; | |
1634 | int c1, c2; | |
aa72b389 | 1635 | |
ff0dacd7 | 1636 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1637 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1638 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1639 | { |
1640 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1641 | return 0; | |
1642 | } | |
24a73b0a | 1643 | |
f56a4450 | 1644 | TWO_MORE_BYTES (c1, c2); |
df7492f9 | 1645 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1646 | { |
b49a1807 KH |
1647 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1648 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1649 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1650 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1651 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1652 | } |
df7492f9 | 1653 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1654 | { |
b49a1807 KH |
1655 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1656 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1657 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1658 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1659 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1660 | } | |
220eeac9 | 1661 | else if (c2 < 0) |
f56a4450 KH |
1662 | { |
1663 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1664 | return 0; | |
1665 | } | |
2f3cbb32 | 1666 | else |
24a73b0a | 1667 | { |
2f3cbb32 KH |
1668 | /* We check the dispersion of Eth and Oth bytes where E is even and |
1669 | O is odd. If both are high, we assume binary data.*/ | |
1670 | unsigned char e[256], o[256]; | |
1671 | unsigned e_num = 1, o_num = 1; | |
1672 | ||
1673 | memset (e, 0, 256); | |
1674 | memset (o, 0, 256); | |
1675 | e[c1] = 1; | |
1676 | o[c2] = 1; | |
1677 | ||
cc13543e KH |
1678 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_AUTO |
1679 | |CATEGORY_MASK_UTF_16_BE | |
1680 | | CATEGORY_MASK_UTF_16_LE); | |
2f3cbb32 | 1681 | |
7f1faf1c KH |
1682 | while ((detect_info->rejected & CATEGORY_MASK_UTF_16) |
1683 | != CATEGORY_MASK_UTF_16) | |
2f3cbb32 | 1684 | { |
f56a4450 | 1685 | TWO_MORE_BYTES (c1, c2); |
220eeac9 | 1686 | if (c2 < 0) |
f56a4450 | 1687 | break; |
2f3cbb32 KH |
1688 | if (! e[c1]) |
1689 | { | |
1690 | e[c1] = 1; | |
1691 | e_num++; | |
cc13543e KH |
1692 | if (e_num >= 128) |
1693 | detect_info->rejected |= CATEGORY_MASK_UTF_16_BE_NOSIG; | |
2f3cbb32 KH |
1694 | } |
1695 | if (! o[c2]) | |
1696 | { | |
977b85f4 | 1697 | o[c2] = 1; |
2f3cbb32 | 1698 | o_num++; |
cc13543e KH |
1699 | if (o_num >= 128) |
1700 | detect_info->rejected |= CATEGORY_MASK_UTF_16_LE_NOSIG; | |
2f3cbb32 KH |
1701 | } |
1702 | } | |
2f3cbb32 | 1703 | return 0; |
ff0dacd7 | 1704 | } |
2f3cbb32 | 1705 | |
df7492f9 | 1706 | no_more_source: |
ff0dacd7 | 1707 | return 1; |
df7492f9 | 1708 | } |
aa72b389 | 1709 | |
df7492f9 KH |
1710 | static void |
1711 | decode_coding_utf_16 (coding) | |
1712 | struct coding_system *coding; | |
1713 | { | |
8f924df7 KH |
1714 | const unsigned char *src = coding->source + coding->consumed; |
1715 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1716 | const unsigned char *src_base; | |
69a80ea3 | 1717 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
1718 | /* We may produces at most 3 chars in one loop. */ |
1719 | int *charbuf_end = coding->charbuf + coding->charbuf_size - 2; | |
3a8406e1 | 1720 | int consumed_chars = 0, consumed_chars_base = 0; |
df7492f9 | 1721 | int multibytep = coding->src_multibyte; |
a470d443 | 1722 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1723 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); |
1724 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
24a73b0a | 1725 | Lisp_Object attr, charset_list; |
0a9564cb EZ |
1726 | int eol_crlf = |
1727 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1728 | int byte_after_cr1 = -1, byte_after_cr2 = -1; |
df7492f9 | 1729 | |
24a73b0a | 1730 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1731 | |
a470d443 | 1732 | if (bom == utf_with_bom) |
aa72b389 | 1733 | { |
df7492f9 | 1734 | int c, c1, c2; |
4af310db | 1735 | |
aa72b389 | 1736 | src_base = src; |
df7492f9 KH |
1737 | ONE_MORE_BYTE (c1); |
1738 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1739 | c = (c1 << 8) | c2; |
aa72b389 | 1740 | |
b49a1807 KH |
1741 | if (endian == utf_16_big_endian |
1742 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1743 | { |
b49a1807 KH |
1744 | /* The first two bytes are not BOM. Treat them as bytes |
1745 | for a normal character. */ | |
1746 | src = src_base; | |
1747 | coding->errors++; | |
aa72b389 | 1748 | } |
a470d443 | 1749 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
b49a1807 | 1750 | } |
a470d443 | 1751 | else if (bom == utf_detect_bom) |
b49a1807 KH |
1752 | { |
1753 | /* We have already tried to detect BOM and failed in | |
1754 | detect_coding. */ | |
a470d443 | 1755 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 | 1756 | } |
aa72b389 | 1757 | |
df7492f9 KH |
1758 | while (1) |
1759 | { | |
1760 | int c, c1, c2; | |
1761 | ||
1762 | src_base = src; | |
1763 | consumed_chars_base = consumed_chars; | |
1764 | ||
df80c7f0 | 1765 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1766 | { |
1767 | if (byte_after_cr1 >= 0) | |
1768 | src_base -= 2; | |
1769 | break; | |
1770 | } | |
df7492f9 | 1771 | |
119852e7 KH |
1772 | if (byte_after_cr1 >= 0) |
1773 | c1 = byte_after_cr1, byte_after_cr1 = -1; | |
1774 | else | |
1775 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1776 | if (c1 < 0) |
1777 | { | |
1778 | *charbuf++ = -c1; | |
1779 | continue; | |
1780 | } | |
119852e7 KH |
1781 | if (byte_after_cr2 >= 0) |
1782 | c2 = byte_after_cr2, byte_after_cr2 = -1; | |
1783 | else | |
1784 | ONE_MORE_BYTE (c2); | |
065e3595 KH |
1785 | if (c2 < 0) |
1786 | { | |
1787 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1788 | *charbuf++ = -c2; | |
1789 | continue; | |
1790 | } | |
df7492f9 | 1791 | c = (endian == utf_16_big_endian |
e19c3639 | 1792 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
119852e7 | 1793 | |
df7492f9 | 1794 | if (surrogate) |
fd3ae0b9 | 1795 | { |
df7492f9 | 1796 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1797 | { |
df7492f9 KH |
1798 | if (endian == utf_16_big_endian) |
1799 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1800 | else | |
1801 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1802 | *charbuf++ = c1; | |
1803 | *charbuf++ = c2; | |
1804 | coding->errors++; | |
1805 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1806 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1807 | else |
df7492f9 | 1808 | *charbuf++ = c; |
fd3ae0b9 KH |
1809 | } |
1810 | else | |
df7492f9 KH |
1811 | { |
1812 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1813 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1814 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1815 | } |
fd3ae0b9 | 1816 | } |
aa72b389 | 1817 | else |
df7492f9 KH |
1818 | { |
1819 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1820 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1821 | else | |
119852e7 KH |
1822 | { |
1823 | if (eol_crlf && c == '\r') | |
1824 | { | |
1825 | ONE_MORE_BYTE (byte_after_cr1); | |
1826 | ONE_MORE_BYTE (byte_after_cr2); | |
1827 | } | |
1828 | *charbuf++ = c; | |
1829 | } | |
8f924df7 | 1830 | } |
aa72b389 | 1831 | } |
df7492f9 KH |
1832 | |
1833 | no_more_source: | |
1834 | coding->consumed_char += consumed_chars_base; | |
1835 | coding->consumed = src_base - coding->source; | |
1836 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1837 | } |
b73bfc1c | 1838 | |
df7492f9 KH |
1839 | static int |
1840 | encode_coding_utf_16 (coding) | |
1841 | struct coding_system *coding; | |
1842 | { | |
1843 | int multibytep = coding->dst_multibyte; | |
1844 | int *charbuf = coding->charbuf; | |
1845 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1846 | unsigned char *dst = coding->destination + coding->produced; | |
1847 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1848 | int safe_room = 8; | |
a470d443 | 1849 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1850 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; |
1851 | int produced_chars = 0; | |
24a73b0a | 1852 | Lisp_Object attrs, charset_list; |
df7492f9 | 1853 | int c; |
4ed46869 | 1854 | |
24a73b0a | 1855 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 1856 | |
a470d443 | 1857 | if (bom != utf_without_bom) |
df7492f9 KH |
1858 | { |
1859 | ASSURE_DESTINATION (safe_room); | |
1860 | if (big_endian) | |
df7492f9 | 1861 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1862 | else |
1863 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
a470d443 | 1864 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 KH |
1865 | } |
1866 | ||
1867 | while (charbuf < charbuf_end) | |
1868 | { | |
1869 | ASSURE_DESTINATION (safe_room); | |
1870 | c = *charbuf++; | |
60afa08d | 1871 | if (c > MAX_UNICODE_CHAR) |
e19c3639 | 1872 | c = coding->default_char; |
df7492f9 KH |
1873 | |
1874 | if (c < 0x10000) | |
1875 | { | |
1876 | if (big_endian) | |
1877 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1878 | else | |
1879 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1880 | } | |
1881 | else | |
1882 | { | |
1883 | int c1, c2; | |
1884 | ||
1885 | c -= 0x10000; | |
1886 | c1 = (c >> 10) + 0xD800; | |
1887 | c2 = (c & 0x3FF) + 0xDC00; | |
1888 | if (big_endian) | |
1889 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1890 | else | |
1891 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1892 | } | |
1893 | } | |
065e3595 | 1894 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1895 | coding->produced = dst - coding->destination; |
1896 | coding->produced_char += produced_chars; | |
1897 | return 0; | |
1898 | } | |
1899 | ||
1900 | \f | |
1901 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1902 | ||
1903 | /* Emacs' internal format for representation of multiple character | |
1904 | sets is a kind of multi-byte encoding, i.e. characters are | |
1905 | represented by variable-length sequences of one-byte codes. | |
1906 | ||
1907 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1908 | represented by one-byte sequences which are their ASCII codes, in | |
1909 | the range 0x00 through 0x7F. | |
1910 | ||
1911 | 8-bit characters of the range 0x80..0x9F are represented by | |
1912 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1913 | code + 0x20). | |
1914 | ||
1915 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1916 | one-byte sequences which are their 8-bit code. | |
1917 | ||
1918 | The other characters are represented by a sequence of `base | |
1919 | leading-code', optional `extended leading-code', and one or two | |
1920 | `position-code's. The length of the sequence is determined by the | |
1921 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1922 | whereas extended leading-code and position-code take the range 0xA0 | |
1923 | through 0xFF. See `charset.h' for more details about leading-code | |
1924 | and position-code. | |
1925 | ||
1926 | --- CODE RANGE of Emacs' internal format --- | |
1927 | character set range | |
1928 | ------------- ----- | |
1929 | ascii 0x00..0x7F | |
1930 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1931 | eight-bit-graphic 0xA0..0xBF | |
1932 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1933 | --------------------------------------------- | |
1934 | ||
1935 | As this is the internal character representation, the format is | |
1936 | usually not used externally (i.e. in a file or in a data sent to a | |
1937 | process). But, it is possible to have a text externally in this | |
1938 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1939 | ||
1940 | In that case, a sequence of one-byte codes has a slightly different | |
1941 | form. | |
1942 | ||
1943 | At first, all characters in eight-bit-control are represented by | |
1944 | one-byte sequences which are their 8-bit code. | |
1945 | ||
1946 | Next, character composition data are represented by the byte | |
1947 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1948 | where, | |
e951386e | 1949 | METHOD is 0xF2 plus one of composition method (enum |
df7492f9 KH |
1950 | composition_method), |
1951 | ||
1952 | BYTES is 0xA0 plus a byte length of this composition data, | |
1953 | ||
e951386e | 1954 | CHARS is 0xA0 plus a number of characters composed by this |
df7492f9 KH |
1955 | data, |
1956 | ||
1957 | COMPONENTs are characters of multibye form or composition | |
1958 | rules encoded by two-byte of ASCII codes. | |
1959 | ||
1960 | In addition, for backward compatibility, the following formats are | |
1961 | also recognized as composition data on decoding. | |
1962 | ||
1963 | 0x80 MSEQ ... | |
1964 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1965 | ||
1966 | Here, | |
1967 | MSEQ is a multibyte form but in these special format: | |
1968 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1969 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1970 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1971 | represents a composition rule. | |
1972 | */ | |
1973 | ||
1974 | char emacs_mule_bytes[256]; | |
1975 | ||
e951386e KH |
1976 | |
1977 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
1978 | Check if a text is encoded in `emacs-mule'. If it is, return 1, | |
1979 | else return 0. */ | |
1980 | ||
1981 | static int | |
1982 | detect_coding_emacs_mule (coding, detect_info) | |
1983 | struct coding_system *coding; | |
1984 | struct coding_detection_info *detect_info; | |
1985 | { | |
1986 | const unsigned char *src = coding->source, *src_base; | |
1987 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1988 | int multibytep = coding->src_multibyte; | |
1989 | int consumed_chars = 0; | |
1990 | int c; | |
1991 | int found = 0; | |
1992 | ||
1993 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; | |
1994 | /* A coding system of this category is always ASCII compatible. */ | |
1995 | src += coding->head_ascii; | |
1996 | ||
1997 | while (1) | |
1998 | { | |
1999 | src_base = src; | |
2000 | ONE_MORE_BYTE (c); | |
2001 | if (c < 0) | |
2002 | continue; | |
2003 | if (c == 0x80) | |
2004 | { | |
2005 | /* Perhaps the start of composite character. We simply skip | |
2006 | it because analyzing it is too heavy for detecting. But, | |
2007 | at least, we check that the composite character | |
2008 | constitutes of more than 4 bytes. */ | |
2009 | const unsigned char *src_base; | |
2010 | ||
2011 | repeat: | |
2012 | src_base = src; | |
2013 | do | |
2014 | { | |
2015 | ONE_MORE_BYTE (c); | |
2016 | } | |
2017 | while (c >= 0xA0); | |
2018 | ||
2019 | if (src - src_base <= 4) | |
2020 | break; | |
2021 | found = CATEGORY_MASK_EMACS_MULE; | |
2022 | if (c == 0x80) | |
2023 | goto repeat; | |
2024 | } | |
2025 | ||
2026 | if (c < 0x80) | |
2027 | { | |
2028 | if (c < 0x20 | |
2029 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
2030 | break; | |
2031 | } | |
2032 | else | |
2033 | { | |
2034 | int more_bytes = emacs_mule_bytes[*src_base] - 1; | |
2035 | ||
2036 | while (more_bytes > 0) | |
2037 | { | |
2038 | ONE_MORE_BYTE (c); | |
2039 | if (c < 0xA0) | |
2040 | { | |
2041 | src--; /* Unread the last byte. */ | |
2042 | break; | |
2043 | } | |
2044 | more_bytes--; | |
2045 | } | |
2046 | if (more_bytes != 0) | |
2047 | break; | |
2048 | found = CATEGORY_MASK_EMACS_MULE; | |
2049 | } | |
2050 | } | |
2051 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
2052 | return 0; | |
2053 | ||
2054 | no_more_source: | |
2055 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) | |
2056 | { | |
2057 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
2058 | return 0; | |
2059 | } | |
2060 | detect_info->found |= found; | |
2061 | return 1; | |
2062 | } | |
2063 | ||
2064 | ||
2065 | /* Parse emacs-mule multibyte sequence at SRC and return the decoded | |
2066 | character. If CMP_STATUS indicates that we must expect MSEQ or | |
2067 | RULE described above, decode it and return the negative value of | |
685ebdc8 | 2068 | the decoded character or rule. If an invalid byte is found, return |
e951386e KH |
2069 | -1. If SRC is too short, return -2. */ |
2070 | ||
df7492f9 | 2071 | int |
e951386e | 2072 | emacs_mule_char (coding, src, nbytes, nchars, id, cmp_status) |
df7492f9 | 2073 | struct coding_system *coding; |
065e3595 | 2074 | const unsigned char *src; |
ff0dacd7 | 2075 | int *nbytes, *nchars, *id; |
e951386e | 2076 | struct composition_status *cmp_status; |
df7492f9 | 2077 | { |
8f924df7 KH |
2078 | const unsigned char *src_end = coding->source + coding->src_bytes; |
2079 | const unsigned char *src_base = src; | |
df7492f9 | 2080 | int multibytep = coding->src_multibyte; |
df7492f9 KH |
2081 | struct charset *charset; |
2082 | unsigned code; | |
2083 | int c; | |
2084 | int consumed_chars = 0; | |
e951386e | 2085 | int mseq_found = 0; |
df7492f9 KH |
2086 | |
2087 | ONE_MORE_BYTE (c); | |
065e3595 | 2088 | if (c < 0) |
df7492f9 | 2089 | { |
065e3595 KH |
2090 | c = -c; |
2091 | charset = emacs_mule_charset[0]; | |
2092 | } | |
2093 | else | |
2094 | { | |
4d41e8b7 KH |
2095 | if (c >= 0xA0) |
2096 | { | |
e951386e KH |
2097 | if (cmp_status->state != COMPOSING_NO |
2098 | && cmp_status->old_form) | |
4d41e8b7 | 2099 | { |
e951386e KH |
2100 | if (cmp_status->state == COMPOSING_CHAR) |
2101 | { | |
2102 | if (c == 0xA0) | |
2103 | { | |
2104 | ONE_MORE_BYTE (c); | |
2105 | c -= 0x80; | |
2106 | if (c < 0) | |
2107 | goto invalid_code; | |
2108 | } | |
2109 | else | |
2110 | c -= 0x20; | |
2111 | mseq_found = 1; | |
2112 | } | |
2113 | else | |
2114 | { | |
2115 | *nbytes = src - src_base; | |
2116 | *nchars = consumed_chars; | |
2117 | return -c; | |
2118 | } | |
4d41e8b7 KH |
2119 | } |
2120 | else | |
e951386e | 2121 | goto invalid_code; |
4d41e8b7 KH |
2122 | } |
2123 | ||
065e3595 | 2124 | switch (emacs_mule_bytes[c]) |
b73bfc1c | 2125 | { |
065e3595 | 2126 | case 2: |
df7492f9 KH |
2127 | if (! (charset = emacs_mule_charset[c])) |
2128 | goto invalid_code; | |
2129 | ONE_MORE_BYTE (c); | |
9ffd559c | 2130 | if (c < 0xA0) |
065e3595 | 2131 | goto invalid_code; |
df7492f9 | 2132 | code = c & 0x7F; |
065e3595 KH |
2133 | break; |
2134 | ||
2135 | case 3: | |
2136 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
2137 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
2138 | { | |
2139 | ONE_MORE_BYTE (c); | |
9ffd559c | 2140 | if (c < 0xA0 || ! (charset = emacs_mule_charset[c])) |
065e3595 KH |
2141 | goto invalid_code; |
2142 | ONE_MORE_BYTE (c); | |
9ffd559c | 2143 | if (c < 0xA0) |
065e3595 KH |
2144 | goto invalid_code; |
2145 | code = c & 0x7F; | |
2146 | } | |
2147 | else | |
2148 | { | |
2149 | if (! (charset = emacs_mule_charset[c])) | |
2150 | goto invalid_code; | |
2151 | ONE_MORE_BYTE (c); | |
9ffd559c | 2152 | if (c < 0xA0) |
065e3595 KH |
2153 | goto invalid_code; |
2154 | code = (c & 0x7F) << 8; | |
2155 | ONE_MORE_BYTE (c); | |
9ffd559c | 2156 | if (c < 0xA0) |
065e3595 KH |
2157 | goto invalid_code; |
2158 | code |= c & 0x7F; | |
2159 | } | |
2160 | break; | |
2161 | ||
2162 | case 4: | |
2163 | ONE_MORE_BYTE (c); | |
2164 | if (c < 0 || ! (charset = emacs_mule_charset[c])) | |
df7492f9 KH |
2165 | goto invalid_code; |
2166 | ONE_MORE_BYTE (c); | |
9ffd559c | 2167 | if (c < 0xA0) |
065e3595 | 2168 | goto invalid_code; |
781d7a48 | 2169 | code = (c & 0x7F) << 8; |
df7492f9 | 2170 | ONE_MORE_BYTE (c); |
9ffd559c | 2171 | if (c < 0xA0) |
065e3595 | 2172 | goto invalid_code; |
df7492f9 | 2173 | code |= c & 0x7F; |
065e3595 | 2174 | break; |
df7492f9 | 2175 | |
065e3595 KH |
2176 | case 1: |
2177 | code = c; | |
2178 | charset = CHARSET_FROM_ID (ASCII_BYTE_P (code) | |
2179 | ? charset_ascii : charset_eight_bit); | |
2180 | break; | |
df7492f9 | 2181 | |
065e3595 KH |
2182 | default: |
2183 | abort (); | |
2184 | } | |
75f80e63 | 2185 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, code, c); |
065e3595 KH |
2186 | if (c < 0) |
2187 | goto invalid_code; | |
df7492f9 | 2188 | } |
df7492f9 KH |
2189 | *nbytes = src - src_base; |
2190 | *nchars = consumed_chars; | |
ff0dacd7 KH |
2191 | if (id) |
2192 | *id = charset->id; | |
e951386e | 2193 | return (mseq_found ? -c : c); |
df7492f9 KH |
2194 | |
2195 | no_more_source: | |
2196 | return -2; | |
2197 | ||
2198 | invalid_code: | |
2199 | return -1; | |
2200 | } | |
2201 | ||
2202 | ||
e951386e | 2203 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
df7492f9 | 2204 | |
e951386e KH |
2205 | /* Handle these composition sequence ('|': the end of header elements, |
2206 | BYTES and CHARS >= 0xA0): | |
df7492f9 | 2207 | |
e951386e KH |
2208 | (1) relative composition: 0x80 0xF2 BYTES CHARS | CHAR ... |
2209 | (2) altchar composition: 0x80 0xF4 BYTES CHARS | ALT ... ALT CHAR ... | |
2210 | (3) alt&rule composition: 0x80 0xF5 BYTES CHARS | ALT RULE ... ALT CHAR ... | |
df7492f9 | 2211 | |
e951386e KH |
2212 | and these old form: |
2213 | ||
2214 | (4) relative composition: 0x80 | MSEQ ... MSEQ | |
2215 | (5) rulebase composition: 0x80 0xFF | MSEQ MRULE ... MSEQ | |
df7492f9 | 2216 | |
e951386e KH |
2217 | When the starter 0x80 and the following header elements are found, |
2218 | this annotation header is produced. | |
df7492f9 | 2219 | |
e951386e | 2220 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS NBYTES METHOD ] |
df7492f9 | 2221 | |
e951386e KH |
2222 | NCHARS is CHARS - 0xA0 for (1), (2), (3), and 0 for (4), (5). |
2223 | NBYTES is BYTES - 0xA0 for (1), (2), (3), and 0 for (4), (5). | |
df7492f9 | 2224 | |
e951386e KH |
2225 | Then, upon reading the following elements, these codes are produced |
2226 | until the composition end is found: | |
df7492f9 | 2227 | |
e951386e KH |
2228 | (1) CHAR ... CHAR |
2229 | (2) ALT ... ALT CHAR ... CHAR | |
2230 | (3) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT CHAR ... CHAR | |
2231 | (4) CHAR ... CHAR | |
2232 | (5) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
4ed46869 | 2233 | |
e951386e KH |
2234 | When the composition end is found, LENGTH and NCHARS in the |
2235 | annotation header is updated as below: | |
b73bfc1c | 2236 | |
e951386e KH |
2237 | (1) LENGTH: unchanged, NCHARS: unchanged |
2238 | (2) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2239 | (3) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2240 | (4) LENGTH: unchanged, NCHARS: number of CHARs | |
2241 | (5) LENGTH: unchanged, NCHARS: number of CHARs | |
df7492f9 | 2242 | |
e951386e KH |
2243 | If an error is found while composing, the annotation header is |
2244 | changed to the original composition header (plus filler -1s) as | |
2245 | below: | |
2246 | ||
2247 | (1),(2),(3) [ 0x80 0xF2+METHOD BYTES CHARS -1 ] | |
2248 | (5) [ 0x80 0xFF -1 -1- -1 ] | |
2249 | ||
2250 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
2251 | byte sequence as below: | |
2252 | o the original byte sequence is B: [ B -1 ] | |
2253 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
2254 | ||
2255 | Most of the routines are implemented by macros because many | |
2256 | variables and labels in the caller decode_coding_emacs_mule must be | |
2257 | accessible, and they are usually called just once (thus doesn't | |
2258 | increase the size of compiled object). */ | |
2259 | ||
2260 | /* Decode a composition rule represented by C as a component of | |
2261 | composition sequence of Emacs 20 style. Set RULE to the decoded | |
2262 | rule. */ | |
2263 | ||
2264 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(c, rule) \ | |
df7492f9 | 2265 | do { \ |
e951386e KH |
2266 | int gref, nref; \ |
2267 | \ | |
4d41e8b7 | 2268 | c -= 0xA0; \ |
df7492f9 KH |
2269 | if (c < 0 || c >= 81) \ |
2270 | goto invalid_code; \ | |
df7492f9 | 2271 | gref = c / 9, nref = c % 9; \ |
e951386e KH |
2272 | if (gref == 4) gref = 10; \ |
2273 | if (nref == 4) nref = 10; \ | |
2274 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
df7492f9 KH |
2275 | } while (0) |
2276 | ||
2277 | ||
e951386e KH |
2278 | /* Decode a composition rule represented by C and the following byte |
2279 | at SRC as a component of composition sequence of Emacs 21 style. | |
2280 | Set RULE to the decoded rule. */ | |
781d7a48 | 2281 | |
e951386e | 2282 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(c, rule) \ |
781d7a48 KH |
2283 | do { \ |
2284 | int gref, nref; \ | |
e951386e KH |
2285 | \ |
2286 | gref = c - 0x20; \ | |
2287 | if (gref < 0 || gref >= 81) \ | |
781d7a48 | 2288 | goto invalid_code; \ |
e951386e KH |
2289 | ONE_MORE_BYTE (c); \ |
2290 | nref = c - 0x20; \ | |
2291 | if (nref < 0 || nref >= 81) \ | |
781d7a48 | 2292 | goto invalid_code; \ |
e951386e | 2293 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ |
781d7a48 KH |
2294 | } while (0) |
2295 | ||
2296 | ||
e951386e KH |
2297 | /* Start of Emacs 21 style format. The first three bytes at SRC are |
2298 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is the | |
2299 | byte length of this composition information, CHARS is the number of | |
2300 | characters composed by this composition. */ | |
2301 | ||
2302 | #define DECODE_EMACS_MULE_21_COMPOSITION() \ | |
aa72b389 | 2303 | do { \ |
781d7a48 KH |
2304 | enum composition_method method = c - 0xF2; \ |
2305 | int *charbuf_base = charbuf; \ | |
df7492f9 | 2306 | int nbytes, nchars; \ |
e951386e | 2307 | \ |
df7492f9 | 2308 | ONE_MORE_BYTE (c); \ |
065e3595 KH |
2309 | if (c < 0) \ |
2310 | goto invalid_code; \ | |
df7492f9 | 2311 | nbytes = c - 0xA0; \ |
e951386e | 2312 | if (nbytes < 3 || (method == COMPOSITION_RELATIVE && nbytes != 4)) \ |
df7492f9 KH |
2313 | goto invalid_code; \ |
2314 | ONE_MORE_BYTE (c); \ | |
2315 | nchars = c - 0xA0; \ | |
e951386e KH |
2316 | if (nchars <= 0 || nchars >= MAX_COMPOSITION_COMPONENTS) \ |
2317 | goto invalid_code; \ | |
2318 | cmp_status->old_form = 0; \ | |
2319 | cmp_status->method = method; \ | |
2320 | if (method == COMPOSITION_RELATIVE) \ | |
2321 | cmp_status->state = COMPOSING_CHAR; \ | |
2322 | else \ | |
2323 | cmp_status->state = COMPOSING_COMPONENT_CHAR; \ | |
2324 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2325 | cmp_status->nchars = nchars; \ | |
2326 | cmp_status->ncomps = nbytes - 4; \ | |
2327 | ADD_COMPOSITION_DATA (charbuf, nchars, nbytes, method); \ | |
aa72b389 | 2328 | } while (0) |
93dec019 | 2329 | |
aa72b389 | 2330 | |
e951386e KH |
2331 | /* Start of Emacs 20 style format for relative composition. */ |
2332 | ||
2333 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION() \ | |
2334 | do { \ | |
2335 | cmp_status->old_form = 1; \ | |
2336 | cmp_status->method = COMPOSITION_RELATIVE; \ | |
2337 | cmp_status->state = COMPOSING_CHAR; \ | |
2338 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2339 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2340 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
2341 | } while (0) | |
2342 | ||
2343 | ||
2344 | /* Start of Emacs 20 style format for rule-base composition. */ | |
2345 | ||
2346 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION() \ | |
2347 | do { \ | |
2348 | cmp_status->old_form = 1; \ | |
2349 | cmp_status->method = COMPOSITION_WITH_RULE; \ | |
2350 | cmp_status->state = COMPOSING_CHAR; \ | |
2351 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2352 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2353 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
df7492f9 KH |
2354 | } while (0) |
2355 | ||
2356 | ||
e951386e KH |
2357 | #define DECODE_EMACS_MULE_COMPOSITION_START() \ |
2358 | do { \ | |
2359 | const unsigned char *current_src = src; \ | |
2360 | \ | |
2361 | ONE_MORE_BYTE (c); \ | |
2362 | if (c < 0) \ | |
2363 | goto invalid_code; \ | |
2364 | if (c - 0xF2 >= COMPOSITION_RELATIVE \ | |
2365 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) \ | |
2366 | DECODE_EMACS_MULE_21_COMPOSITION (); \ | |
2367 | else if (c < 0xA0) \ | |
2368 | goto invalid_code; \ | |
2369 | else if (c < 0xC0) \ | |
2370 | { \ | |
2371 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (); \ | |
2372 | /* Re-read C as a composition component. */ \ | |
2373 | src = current_src; \ | |
2374 | } \ | |
2375 | else if (c == 0xFF) \ | |
2376 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (); \ | |
2377 | else \ | |
2378 | goto invalid_code; \ | |
2379 | } while (0) | |
2380 | ||
2381 | #define EMACS_MULE_COMPOSITION_END() \ | |
df7492f9 | 2382 | do { \ |
e951386e | 2383 | int idx = - cmp_status->length; \ |
4d41e8b7 | 2384 | \ |
e951386e KH |
2385 | if (cmp_status->old_form) \ |
2386 | charbuf[idx + 2] = cmp_status->nchars; \ | |
2387 | else if (cmp_status->method > COMPOSITION_RELATIVE) \ | |
2388 | charbuf[idx] = charbuf[idx + 2] - cmp_status->length; \ | |
2389 | cmp_status->state = COMPOSING_NO; \ | |
2390 | } while (0) | |
2391 | ||
2392 | ||
2393 | static int | |
2394 | emacs_mule_finish_composition (charbuf, cmp_status) | |
2395 | int *charbuf; | |
2396 | struct composition_status *cmp_status; | |
2397 | { | |
2398 | int idx = - cmp_status->length; | |
2399 | int new_chars; | |
2400 | ||
2401 | if (cmp_status->old_form && cmp_status->nchars > 0) | |
2402 | { | |
2403 | charbuf[idx + 2] = cmp_status->nchars; | |
2404 | new_chars = 0; | |
2405 | if (cmp_status->method == COMPOSITION_WITH_RULE | |
2406 | && cmp_status->state == COMPOSING_CHAR) | |
2407 | { | |
2408 | /* The last rule was invalid. */ | |
2409 | int rule = charbuf[-1] + 0xA0; | |
2410 | ||
2411 | charbuf[-2] = BYTE8_TO_CHAR (rule); | |
2412 | charbuf[-1] = -1; | |
2413 | new_chars = 1; | |
2414 | } | |
2415 | } | |
2416 | else | |
2417 | { | |
2418 | charbuf[idx++] = BYTE8_TO_CHAR (0x80); | |
2419 | ||
2420 | if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2421 | { | |
2422 | charbuf[idx++] = BYTE8_TO_CHAR (0xFF); | |
2423 | charbuf[idx++] = -3; | |
2424 | charbuf[idx++] = 0; | |
2425 | new_chars = 1; | |
2426 | } | |
2427 | else | |
2428 | { | |
2429 | int nchars = charbuf[idx + 1] + 0xA0; | |
2430 | int nbytes = charbuf[idx + 2] + 0xA0; | |
2431 | ||
2432 | charbuf[idx++] = BYTE8_TO_CHAR (0xF2 + cmp_status->method); | |
2433 | charbuf[idx++] = BYTE8_TO_CHAR (nbytes); | |
2434 | charbuf[idx++] = BYTE8_TO_CHAR (nchars); | |
2435 | charbuf[idx++] = -1; | |
2436 | new_chars = 4; | |
2437 | } | |
2438 | } | |
2439 | cmp_status->state = COMPOSING_NO; | |
2440 | return new_chars; | |
2441 | } | |
2442 | ||
2443 | #define EMACS_MULE_MAYBE_FINISH_COMPOSITION() \ | |
2444 | do { \ | |
2445 | if (cmp_status->state != COMPOSING_NO) \ | |
2446 | char_offset += emacs_mule_finish_composition (charbuf, cmp_status); \ | |
df7492f9 KH |
2447 | } while (0) |
2448 | ||
aa72b389 KH |
2449 | |
2450 | static void | |
df7492f9 | 2451 | decode_coding_emacs_mule (coding) |
aa72b389 | 2452 | struct coding_system *coding; |
aa72b389 | 2453 | { |
8f924df7 KH |
2454 | const unsigned char *src = coding->source + coding->consumed; |
2455 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2456 | const unsigned char *src_base; | |
69a80ea3 | 2457 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
2458 | /* We may produce two annocations (charset and composition) in one |
2459 | loop and one more charset annocation at the end. */ | |
69a80ea3 | 2460 | int *charbuf_end |
df80c7f0 | 2461 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
df7492f9 | 2462 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2463 | int multibytep = coding->src_multibyte; |
24a73b0a | 2464 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2465 | int char_offset = coding->produced_char; |
2466 | int last_offset = char_offset; | |
2467 | int last_id = charset_ascii; | |
0a9564cb EZ |
2468 | int eol_crlf = |
2469 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 2470 | int byte_after_cr = -1; |
e951386e | 2471 | struct composition_status *cmp_status = &coding->spec.emacs_mule.cmp_status; |
aa72b389 | 2472 | |
24a73b0a | 2473 | CODING_GET_INFO (coding, attrs, charset_list); |
aa72b389 | 2474 | |
e951386e KH |
2475 | if (cmp_status->state != COMPOSING_NO) |
2476 | { | |
2477 | int i; | |
2478 | ||
2479 | for (i = 0; i < cmp_status->length; i++) | |
2480 | *charbuf++ = cmp_status->carryover[i]; | |
2481 | coding->annotated = 1; | |
2482 | } | |
2483 | ||
aa72b389 KH |
2484 | while (1) |
2485 | { | |
e951386e | 2486 | int c, id; |
df7492f9 | 2487 | |
aa72b389 | 2488 | src_base = src; |
df7492f9 KH |
2489 | consumed_chars_base = consumed_chars; |
2490 | ||
2491 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
2492 | { |
2493 | if (byte_after_cr >= 0) | |
2494 | src_base--; | |
2495 | break; | |
2496 | } | |
aa72b389 | 2497 | |
119852e7 KH |
2498 | if (byte_after_cr >= 0) |
2499 | c = byte_after_cr, byte_after_cr = -1; | |
2500 | else | |
2501 | ONE_MORE_BYTE (c); | |
e951386e KH |
2502 | |
2503 | if (c < 0 || c == 0x80) | |
065e3595 | 2504 | { |
e951386e KH |
2505 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
2506 | if (c < 0) | |
2507 | { | |
2508 | *charbuf++ = -c; | |
2509 | char_offset++; | |
2510 | } | |
2511 | else | |
2512 | DECODE_EMACS_MULE_COMPOSITION_START (); | |
2513 | continue; | |
065e3595 | 2514 | } |
e951386e KH |
2515 | |
2516 | if (c < 0x80) | |
aa72b389 | 2517 | { |
119852e7 KH |
2518 | if (eol_crlf && c == '\r') |
2519 | ONE_MORE_BYTE (byte_after_cr); | |
e951386e KH |
2520 | id = charset_ascii; |
2521 | if (cmp_status->state != COMPOSING_NO) | |
2522 | { | |
2523 | if (cmp_status->old_form) | |
2524 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2525 | else if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2526 | cmp_status->ncomps--; | |
2527 | } | |
2528 | } | |
2529 | else | |
2530 | { | |
2531 | int nchars, nbytes; | |
75f80e63 EZ |
2532 | /* emacs_mule_char can load a charset map from a file, which |
2533 | allocates a large structure and might cause buffer text | |
2534 | to be relocated as result. Thus, we need to remember the | |
2535 | original pointer to buffer text, and fixup all related | |
2536 | pointers after the call. */ | |
2537 | const unsigned char *orig = coding->source; | |
2538 | EMACS_INT offset; | |
e951386e KH |
2539 | |
2540 | c = emacs_mule_char (coding, src_base, &nbytes, &nchars, &id, | |
2541 | cmp_status); | |
75f80e63 EZ |
2542 | offset = coding->source - orig; |
2543 | if (offset) | |
2544 | { | |
2545 | src += offset; | |
2546 | src_base += offset; | |
2547 | src_end += offset; | |
2548 | } | |
e951386e KH |
2549 | if (c < 0) |
2550 | { | |
2551 | if (c == -1) | |
2552 | goto invalid_code; | |
2553 | if (c == -2) | |
2554 | break; | |
2555 | } | |
2556 | src = src_base + nbytes; | |
2557 | consumed_chars = consumed_chars_base + nchars; | |
2558 | if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2559 | cmp_status->ncomps -= nchars; | |
2560 | } | |
2561 | ||
2562 | /* Now if C >= 0, we found a normally encoded characer, if C < | |
2563 | 0, we found an old-style composition component character or | |
2564 | rule. */ | |
2565 | ||
2566 | if (cmp_status->state == COMPOSING_NO) | |
2567 | { | |
2568 | if (last_id != id) | |
2569 | { | |
2570 | if (last_id != charset_ascii) | |
2571 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, | |
2572 | last_id); | |
2573 | last_id = id; | |
2574 | last_offset = char_offset; | |
2575 | } | |
df7492f9 KH |
2576 | *charbuf++ = c; |
2577 | char_offset++; | |
aa72b389 | 2578 | } |
e951386e | 2579 | else if (cmp_status->state == COMPOSING_CHAR) |
df7492f9 | 2580 | { |
e951386e KH |
2581 | if (cmp_status->old_form) |
2582 | { | |
2583 | if (c >= 0) | |
2584 | { | |
2585 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2586 | *charbuf++ = c; | |
2587 | char_offset++; | |
2588 | } | |
2589 | else | |
2590 | { | |
2591 | *charbuf++ = -c; | |
2592 | cmp_status->nchars++; | |
2593 | cmp_status->length++; | |
2594 | if (cmp_status->nchars == MAX_COMPOSITION_COMPONENTS) | |
2595 | EMACS_MULE_COMPOSITION_END (); | |
2596 | else if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2597 | cmp_status->state = COMPOSING_RULE; | |
2598 | } | |
2599 | } | |
df7492f9 | 2600 | else |
e951386e KH |
2601 | { |
2602 | *charbuf++ = c; | |
2603 | cmp_status->length++; | |
2604 | cmp_status->nchars--; | |
2605 | if (cmp_status->nchars == 0) | |
2606 | EMACS_MULE_COMPOSITION_END (); | |
2607 | } | |
df7492f9 | 2608 | } |
e951386e | 2609 | else if (cmp_status->state == COMPOSING_RULE) |
df7492f9 | 2610 | { |
e951386e | 2611 | int rule; |
ff0dacd7 | 2612 | |
e951386e | 2613 | if (c >= 0) |
df7492f9 | 2614 | { |
e951386e KH |
2615 | EMACS_MULE_COMPOSITION_END (); |
2616 | *charbuf++ = c; | |
2617 | char_offset++; | |
df7492f9 | 2618 | } |
e951386e | 2619 | else |
ff0dacd7 | 2620 | { |
e951386e KH |
2621 | c = -c; |
2622 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (c, rule); | |
2623 | if (rule < 0) | |
2624 | goto invalid_code; | |
2625 | *charbuf++ = -2; | |
2626 | *charbuf++ = rule; | |
2627 | cmp_status->length += 2; | |
2628 | cmp_status->state = COMPOSING_CHAR; | |
ff0dacd7 | 2629 | } |
e951386e KH |
2630 | } |
2631 | else if (cmp_status->state == COMPOSING_COMPONENT_CHAR) | |
2632 | { | |
df7492f9 | 2633 | *charbuf++ = c; |
e951386e KH |
2634 | cmp_status->length++; |
2635 | if (cmp_status->ncomps == 0) | |
2636 | cmp_status->state = COMPOSING_CHAR; | |
2637 | else if (cmp_status->ncomps > 0) | |
2638 | { | |
2639 | if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) | |
2640 | cmp_status->state = COMPOSING_COMPONENT_RULE; | |
2641 | } | |
2642 | else | |
2643 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
df7492f9 | 2644 | } |
e951386e KH |
2645 | else /* COMPOSING_COMPONENT_RULE */ |
2646 | { | |
2647 | int rule; | |
2648 | ||
2649 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (c, rule); | |
2650 | if (rule < 0) | |
2651 | goto invalid_code; | |
2652 | *charbuf++ = -2; | |
2653 | *charbuf++ = rule; | |
2654 | cmp_status->length += 2; | |
2655 | cmp_status->ncomps--; | |
2656 | if (cmp_status->ncomps > 0) | |
2657 | cmp_status->state = COMPOSING_COMPONENT_CHAR; | |
2658 | else | |
2659 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2660 | } | |
2661 | continue; | |
2662 | ||
2663 | retry: | |
2664 | src = src_base; | |
2665 | consumed_chars = consumed_chars_base; | |
df7492f9 KH |
2666 | continue; |
2667 | ||
2668 | invalid_code: | |
e951386e | 2669 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
df7492f9 KH |
2670 | src = src_base; |
2671 | consumed_chars = consumed_chars_base; | |
2672 | ONE_MORE_BYTE (c); | |
2673 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2674 | char_offset++; |
df7492f9 KH |
2675 | coding->errors++; |
2676 | } | |
2677 | ||
2678 | no_more_source: | |
e951386e KH |
2679 | if (cmp_status->state != COMPOSING_NO) |
2680 | { | |
2681 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
2682 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2683 | else | |
2684 | { | |
2685 | int i; | |
2686 | ||
2687 | charbuf -= cmp_status->length; | |
2688 | for (i = 0; i < cmp_status->length; i++) | |
2689 | cmp_status->carryover[i] = charbuf[i]; | |
2690 | } | |
2691 | } | |
ff0dacd7 | 2692 | if (last_id != charset_ascii) |
69a80ea3 | 2693 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2694 | coding->consumed_char += consumed_chars_base; |
2695 | coding->consumed = src_base - coding->source; | |
2696 | coding->charbuf_used = charbuf - coding->charbuf; | |
2697 | } | |
2698 | ||
2699 | ||
2700 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2701 | do { \ | |
2702 | if (id < 0xA0) \ | |
2703 | codes[0] = id, codes[1] = 0; \ | |
2704 | else if (id < 0xE0) \ | |
2705 | codes[0] = 0x9A, codes[1] = id; \ | |
2706 | else if (id < 0xF0) \ | |
2707 | codes[0] = 0x9B, codes[1] = id; \ | |
2708 | else if (id < 0xF5) \ | |
2709 | codes[0] = 0x9C, codes[1] = id; \ | |
2710 | else \ | |
2711 | codes[0] = 0x9D, codes[1] = id; \ | |
2712 | } while (0); | |
2713 | ||
aa72b389 | 2714 | |
df7492f9 KH |
2715 | static int |
2716 | encode_coding_emacs_mule (coding) | |
2717 | struct coding_system *coding; | |
2718 | { | |
2719 | int multibytep = coding->dst_multibyte; | |
2720 | int *charbuf = coding->charbuf; | |
2721 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2722 | unsigned char *dst = coding->destination + coding->produced; | |
2723 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2724 | int safe_room = 8; | |
df7492f9 | 2725 | int produced_chars = 0; |
24a73b0a | 2726 | Lisp_Object attrs, charset_list; |
df7492f9 | 2727 | int c; |
ff0dacd7 | 2728 | int preferred_charset_id = -1; |
df7492f9 | 2729 | |
24a73b0a | 2730 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2731 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2732 | { | |
2733 | CODING_ATTR_CHARSET_LIST (attrs) | |
2734 | = charset_list = Vemacs_mule_charset_list; | |
2735 | } | |
df7492f9 KH |
2736 | |
2737 | while (charbuf < charbuf_end) | |
2738 | { | |
2739 | ASSURE_DESTINATION (safe_room); | |
2740 | c = *charbuf++; | |
ff0dacd7 KH |
2741 | |
2742 | if (c < 0) | |
2743 | { | |
2744 | /* Handle an annotation. */ | |
2745 | switch (*charbuf) | |
2746 | { | |
2747 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2748 | /* Not yet implemented. */ | |
2749 | break; | |
2750 | case CODING_ANNOTATE_CHARSET_MASK: | |
2751 | preferred_charset_id = charbuf[3]; | |
2752 | if (preferred_charset_id >= 0 | |
2753 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2754 | charset_list))) | |
2755 | preferred_charset_id = -1; | |
2756 | break; | |
2757 | default: | |
2758 | abort (); | |
2759 | } | |
2760 | charbuf += -c - 1; | |
2761 | continue; | |
2762 | } | |
2763 | ||
df7492f9 KH |
2764 | if (ASCII_CHAR_P (c)) |
2765 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2766 | else if (CHAR_BYTE8_P (c)) |
2767 | { | |
2768 | c = CHAR_TO_BYTE8 (c); | |
2769 | EMIT_ONE_BYTE (c); | |
2770 | } | |
df7492f9 | 2771 | else |
aa72b389 | 2772 | { |
df7492f9 KH |
2773 | struct charset *charset; |
2774 | unsigned code; | |
2775 | int dimension; | |
2776 | int emacs_mule_id; | |
2777 | unsigned char leading_codes[2]; | |
2778 | ||
ff0dacd7 KH |
2779 | if (preferred_charset_id >= 0) |
2780 | { | |
2781 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
905ca9d2 KH |
2782 | if (CHAR_CHARSET_P (c, charset)) |
2783 | code = ENCODE_CHAR (charset, c); | |
2784 | else | |
2785 | charset = char_charset (c, charset_list, &code); | |
ff0dacd7 KH |
2786 | } |
2787 | else | |
2788 | charset = char_charset (c, charset_list, &code); | |
df7492f9 KH |
2789 | if (! charset) |
2790 | { | |
2791 | c = coding->default_char; | |
2792 | if (ASCII_CHAR_P (c)) | |
2793 | { | |
2794 | EMIT_ONE_ASCII_BYTE (c); | |
2795 | continue; | |
2796 | } | |
2797 | charset = char_charset (c, charset_list, &code); | |
2798 | } | |
2799 | dimension = CHARSET_DIMENSION (charset); | |
2800 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2801 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2802 | EMIT_ONE_BYTE (leading_codes[0]); | |
2803 | if (leading_codes[1]) | |
2804 | EMIT_ONE_BYTE (leading_codes[1]); | |
2805 | if (dimension == 1) | |
1fa663f9 | 2806 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2807 | else |
df7492f9 | 2808 | { |
1fa663f9 | 2809 | code |= 0x8080; |
df7492f9 KH |
2810 | EMIT_ONE_BYTE (code >> 8); |
2811 | EMIT_ONE_BYTE (code & 0xFF); | |
2812 | } | |
aa72b389 | 2813 | } |
aa72b389 | 2814 | } |
065e3595 | 2815 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2816 | coding->produced_char += produced_chars; |
2817 | coding->produced = dst - coding->destination; | |
2818 | return 0; | |
aa72b389 | 2819 | } |
b73bfc1c | 2820 | |
4ed46869 | 2821 | \f |
df7492f9 | 2822 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2823 | |
2824 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2825 | Since the intention of this note is to help understand the |
5a936b46 | 2826 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2827 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2828 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2829 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2830 | |
2831 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2832 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2833 | is encoded using bytes less than 128. This may make the encoded |
2834 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2835 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2836 | Significant Bit). |
b73bfc1c | 2837 | |
cfb43547 DL |
2838 | There are two kinds of character sets: control character sets and |
2839 | graphic character sets. The former contain control characters such | |
4ed46869 | 2840 | as `newline' and `escape' to provide control functions (control |
39787efd | 2841 | functions are also provided by escape sequences). The latter |
cfb43547 | 2842 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2843 | two control character sets and many graphic character sets. |
2844 | ||
2845 | Graphic character sets are classified into one of the following | |
39787efd KH |
2846 | four classes, according to the number of bytes (DIMENSION) and |
2847 | number of characters in one dimension (CHARS) of the set: | |
2848 | - DIMENSION1_CHARS94 | |
2849 | - DIMENSION1_CHARS96 | |
2850 | - DIMENSION2_CHARS94 | |
2851 | - DIMENSION2_CHARS96 | |
2852 | ||
2853 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2854 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2855 | hereafter). The <F> of each character set is decided by ECMA(*) |
2856 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2857 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2858 | |
2859 | Note (*): ECMA = European Computer Manufacturers Association | |
2860 | ||
cfb43547 | 2861 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2862 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2863 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2864 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2865 | o DIMENSION2_CHARS96 -- none for the moment | |
2866 | ||
39787efd | 2867 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2868 | C0 [0x00..0x1F] -- control character plane 0 |
2869 | GL [0x20..0x7F] -- graphic character plane 0 | |
2870 | C1 [0x80..0x9F] -- control character plane 1 | |
2871 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2872 | ||
2873 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2874 | C1 by an escape sequence. The most common case is that: |
2875 | - ISO646's control character set is designated/invoked to C0, and | |
2876 | - ISO6429's control character set is designated/invoked to C1, | |
2877 | and usually these designations/invocations are omitted in encoded | |
2878 | text. In a 7-bit environment, only C0 can be used, and a control | |
2879 | character for C1 is encoded by an appropriate escape sequence to | |
2880 | fit into the environment. All control characters for C1 are | |
2881 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2882 | |
2883 | A graphic character set is at first designated to one of four | |
2884 | graphic registers (G0 through G3), then these graphic registers are | |
2885 | invoked to GL or GR. These designations and invocations can be | |
2886 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2887 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2888 | these invocations and designations are omitted in encoded text. | |
2889 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2890 | |
39787efd KH |
2891 | When a graphic character set of CHARS94 is invoked to GL, codes |
2892 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2893 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2894 | be used. | |
4ed46869 KH |
2895 | |
2896 | There are two ways of invocation: locking-shift and single-shift. | |
2897 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2898 | invocation, whereas with single-shift, the invocation affects the |
2899 | following character only and doesn't affect the locking-shift | |
2900 | state. Invocations are done by the following control characters or | |
2901 | escape sequences: | |
4ed46869 KH |
2902 | |
2903 | ---------------------------------------------------------------------- | |
39787efd | 2904 | abbrev function cntrl escape seq description |
4ed46869 | 2905 | ---------------------------------------------------------------------- |
39787efd KH |
2906 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2907 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2908 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2909 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2910 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2911 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2912 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2913 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2914 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2915 | ---------------------------------------------------------------------- |
39787efd KH |
2916 | (*) These are not used by any known coding system. |
2917 | ||
2918 | Control characters for these functions are defined by macros | |
2919 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2920 | |
39787efd | 2921 | Designations are done by the following escape sequences: |
4ed46869 KH |
2922 | ---------------------------------------------------------------------- |
2923 | escape sequence description | |
2924 | ---------------------------------------------------------------------- | |
2925 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2926 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2927 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2928 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2929 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2930 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2931 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2932 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2933 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2934 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2935 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2936 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2937 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2938 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2939 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2940 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2941 | ---------------------------------------------------------------------- | |
2942 | ||
2943 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2944 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2945 | |
2946 | Note (*): Although these designations are not allowed in ISO2022, | |
2947 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2948 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2949 | 7-bit environment, non-locking-shift, and non-single-shift. |
2950 | ||
2951 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2952 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2953 | |
cfb43547 | 2954 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2955 | same multilingual text in ISO2022. Actually, there exist many |
2956 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2957 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2958 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2959 | localized platforms), and all of these are variants of ISO2022. |
2960 | ||
2961 | In addition to the above, Emacs handles two more kinds of escape | |
2962 | sequences: ISO6429's direction specification and Emacs' private | |
2963 | sequence for specifying character composition. | |
2964 | ||
39787efd | 2965 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2966 | o CSI ']' -- end of the current direction |
2967 | o CSI '0' ']' -- end of the current direction | |
2968 | o CSI '1' ']' -- start of left-to-right text | |
2969 | o CSI '2' ']' -- start of right-to-left text | |
2970 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2971 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2972 | ||
2973 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2974 | o ESC '0' -- start relative composition |
2975 | o ESC '1' -- end composition | |
2976 | o ESC '2' -- start rule-base composition (*) | |
2977 | o ESC '3' -- start relative composition with alternate chars (**) | |
2978 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2979 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2980 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2981 | |
5a936b46 DL |
2982 | (*) This form is used only in Emacs 20.7 and older versions, |
2983 | but newer versions can safely decode it. | |
cfb43547 | 2984 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2985 | and older versions can't decode it. |
ec6d2bb8 | 2986 | |
cfb43547 | 2987 | Here's a list of example usages of these composition escape |
b73bfc1c | 2988 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2989 | |
b73bfc1c | 2990 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2991 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2992 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2993 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2994 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2995 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2996 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2997 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2998 | |
2999 | enum iso_code_class_type iso_code_class[256]; | |
3000 | ||
df7492f9 KH |
3001 | #define SAFE_CHARSET_P(coding, id) \ |
3002 | ((id) <= (coding)->max_charset_id \ | |
1b3b981b | 3003 | && (coding)->safe_charsets[id] != 255) |
df7492f9 KH |
3004 | |
3005 | ||
3006 | #define SHIFT_OUT_OK(category) \ | |
3007 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
3008 | ||
3009 | static void | |
f0064e1f DL |
3010 | setup_iso_safe_charsets (attrs) |
3011 | Lisp_Object attrs; | |
df7492f9 KH |
3012 | { |
3013 | Lisp_Object charset_list, safe_charsets; | |
3014 | Lisp_Object request; | |
3015 | Lisp_Object reg_usage; | |
3016 | Lisp_Object tail; | |
3017 | int reg94, reg96; | |
3018 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
3019 | int max_charset_id; | |
3020 | ||
3021 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
3022 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
3023 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
3024 | { | |
3025 | CODING_ATTR_CHARSET_LIST (attrs) | |
3026 | = charset_list = Viso_2022_charset_list; | |
3027 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
3028 | } | |
3029 | ||
3030 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
3031 | return; | |
3032 | ||
3033 | max_charset_id = 0; | |
3034 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
3035 | { | |
3036 | int id = XINT (XCAR (tail)); | |
3037 | if (max_charset_id < id) | |
3038 | max_charset_id = id; | |
3039 | } | |
d46c5b12 | 3040 | |
1b3b981b AS |
3041 | safe_charsets = make_uninit_string (max_charset_id + 1); |
3042 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
3043 | request = AREF (attrs, coding_attr_iso_request); |
3044 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
3045 | reg94 = XINT (XCAR (reg_usage)); | |
3046 | reg96 = XINT (XCDR (reg_usage)); | |
3047 | ||
3048 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
3049 | { | |
3050 | Lisp_Object id; | |
3051 | Lisp_Object reg; | |
3052 | struct charset *charset; | |
3053 | ||
3054 | id = XCAR (tail); | |
3055 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 3056 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 3057 | if (! NILP (reg)) |
8f924df7 | 3058 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
3059 | else if (charset->iso_chars_96) |
3060 | { | |
3061 | if (reg96 < 4) | |
8f924df7 | 3062 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
3063 | } |
3064 | else | |
3065 | { | |
3066 | if (reg94 < 4) | |
8f924df7 | 3067 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
3068 | } |
3069 | } | |
3070 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
3071 | } | |
d46c5b12 | 3072 | |
b6871cc7 | 3073 | |
4ed46869 | 3074 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
3075 | Check if a text is encoded in one of ISO-2022 based codig systems. |
3076 | If it is, return 1, else return 0. */ | |
4ed46869 | 3077 | |
0a28aafb | 3078 | static int |
ff0dacd7 | 3079 | detect_coding_iso_2022 (coding, detect_info) |
df7492f9 | 3080 | struct coding_system *coding; |
ff0dacd7 | 3081 | struct coding_detection_info *detect_info; |
4ed46869 | 3082 | { |
8f924df7 KH |
3083 | const unsigned char *src = coding->source, *src_base = src; |
3084 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 3085 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 3086 | int single_shifting = 0; |
df7492f9 KH |
3087 | int id; |
3088 | int c, c1; | |
3089 | int consumed_chars = 0; | |
3090 | int i; | |
ff0dacd7 KH |
3091 | int rejected = 0; |
3092 | int found = 0; | |
cee53ed4 | 3093 | int composition_count = -1; |
ff0dacd7 KH |
3094 | |
3095 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
3096 | |
3097 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
3098 | { | |
3099 | struct coding_system *this = &(coding_categories[i]); | |
3100 | Lisp_Object attrs, val; | |
3101 | ||
c6b278e7 KH |
3102 | if (this->id < 0) |
3103 | continue; | |
df7492f9 KH |
3104 | attrs = CODING_ID_ATTRS (this->id); |
3105 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
1b3b981b | 3106 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Viso_2022_charset_list)) |
df7492f9 KH |
3107 | setup_iso_safe_charsets (attrs); |
3108 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 3109 | this->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 3110 | this->safe_charsets = SDATA (val); |
df7492f9 KH |
3111 | } |
3112 | ||
3113 | /* A coding system of this category is always ASCII compatible. */ | |
3114 | src += coding->head_ascii; | |
3f003981 | 3115 | |
ff0dacd7 | 3116 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 3117 | { |
065e3595 | 3118 | src_base = src; |
df7492f9 | 3119 | ONE_MORE_BYTE (c); |
4ed46869 KH |
3120 | switch (c) |
3121 | { | |
3122 | case ISO_CODE_ESC: | |
74383408 KH |
3123 | if (inhibit_iso_escape_detection) |
3124 | break; | |
f46869e4 | 3125 | single_shifting = 0; |
df7492f9 | 3126 | ONE_MORE_BYTE (c); |
d46c5b12 | 3127 | if (c >= '(' && c <= '/') |
4ed46869 | 3128 | { |
bf9cdd4e | 3129 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 3130 | ONE_MORE_BYTE (c1); |
d46c5b12 | 3131 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 3132 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
3133 | /* Invalid designation sequence. Just ignore. */ |
3134 | break; | |
bf9cdd4e KH |
3135 | } |
3136 | else if (c == '$') | |
3137 | { | |
3138 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 3139 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
3140 | if (c >= '@' && c <= 'B') |
3141 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
ff0dacd7 | 3142 | id = iso_charset_table[1][0][c]; |
bf9cdd4e | 3143 | else if (c >= '(' && c <= '/') |
bcf26d6a | 3144 | { |
df7492f9 | 3145 | ONE_MORE_BYTE (c1); |
d46c5b12 | 3146 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 3147 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
3148 | /* Invalid designation sequence. Just ignore. */ |
3149 | break; | |
bcf26d6a | 3150 | } |
bf9cdd4e | 3151 | else |
ff0dacd7 | 3152 | /* Invalid designation sequence. Just ignore it. */ |
d46c5b12 KH |
3153 | break; |
3154 | } | |
ae9ff118 | 3155 | else if (c == 'N' || c == 'O') |
d46c5b12 | 3156 | { |
ae9ff118 | 3157 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
3158 | single_shifting = 1; |
3159 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
d46c5b12 | 3160 | break; |
4ed46869 | 3161 | } |
cee53ed4 KH |
3162 | else if (c == '1') |
3163 | { | |
3164 | /* End of composition. */ | |
3165 | if (composition_count < 0 | |
3166 | || composition_count > MAX_COMPOSITION_COMPONENTS) | |
3167 | /* Invalid */ | |
3168 | break; | |
3169 | composition_count = -1; | |
3170 | found |= CATEGORY_MASK_ISO; | |
3171 | } | |
ec6d2bb8 KH |
3172 | else if (c >= '0' && c <= '4') |
3173 | { | |
3174 | /* ESC <Fp> for start/end composition. */ | |
cee53ed4 | 3175 | composition_count = 0; |
ec6d2bb8 KH |
3176 | break; |
3177 | } | |
bf9cdd4e | 3178 | else |
df7492f9 | 3179 | { |
ff0dacd7 | 3180 | /* Invalid escape sequence. Just ignore it. */ |
df7492f9 KH |
3181 | break; |
3182 | } | |
d46c5b12 KH |
3183 | |
3184 | /* We found a valid designation sequence for CHARSET. */ | |
ff0dacd7 | 3185 | rejected |= CATEGORY_MASK_ISO_8BIT; |
df7492f9 KH |
3186 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], |
3187 | id)) | |
ff0dacd7 | 3188 | found |= CATEGORY_MASK_ISO_7; |
d46c5b12 | 3189 | else |
ff0dacd7 | 3190 | rejected |= CATEGORY_MASK_ISO_7; |
df7492f9 KH |
3191 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], |
3192 | id)) | |
ff0dacd7 | 3193 | found |= CATEGORY_MASK_ISO_7_TIGHT; |
d46c5b12 | 3194 | else |
ff0dacd7 | 3195 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; |
df7492f9 KH |
3196 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], |
3197 | id)) | |
ff0dacd7 | 3198 | found |= CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 | 3199 | else |
ff0dacd7 | 3200 | rejected |= CATEGORY_MASK_ISO_7_ELSE; |
df7492f9 KH |
3201 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], |
3202 | id)) | |
ff0dacd7 | 3203 | found |= CATEGORY_MASK_ISO_8_ELSE; |
ae9ff118 | 3204 | else |
ff0dacd7 | 3205 | rejected |= CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
3206 | break; |
3207 | ||
4ed46869 | 3208 | case ISO_CODE_SO: |
d46c5b12 | 3209 | case ISO_CODE_SI: |
ff0dacd7 | 3210 | /* Locking shift out/in. */ |
74383408 KH |
3211 | if (inhibit_iso_escape_detection) |
3212 | break; | |
f46869e4 | 3213 | single_shifting = 0; |
ff0dacd7 | 3214 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
d46c5b12 KH |
3215 | break; |
3216 | ||
4ed46869 | 3217 | case ISO_CODE_CSI: |
ff0dacd7 | 3218 | /* Control sequence introducer. */ |
f46869e4 | 3219 | single_shifting = 0; |
ff0dacd7 KH |
3220 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3221 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3222 | goto check_extra_latin; | |
3223 | ||
4ed46869 KH |
3224 | case ISO_CODE_SS2: |
3225 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
3226 | /* Single shift. */ |
3227 | if (inhibit_iso_escape_detection) | |
3228 | break; | |
75e2a253 | 3229 | single_shifting = 0; |
ff0dacd7 KH |
3230 | rejected |= CATEGORY_MASK_ISO_7BIT; |
3231 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3232 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 | 3233 | found |= CATEGORY_MASK_ISO_8_1, single_shifting = 1; |
ff0dacd7 KH |
3234 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
3235 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 KH |
3236 | found |= CATEGORY_MASK_ISO_8_2, single_shifting = 1; |
3237 | if (single_shifting) | |
3238 | break; | |
ff0dacd7 | 3239 | goto check_extra_latin; |
4ed46869 KH |
3240 | |
3241 | default: | |
065e3595 KH |
3242 | if (c < 0) |
3243 | continue; | |
4ed46869 | 3244 | if (c < 0x80) |
f46869e4 | 3245 | { |
cee53ed4 KH |
3246 | if (composition_count >= 0) |
3247 | composition_count++; | |
f46869e4 KH |
3248 | single_shifting = 0; |
3249 | break; | |
3250 | } | |
ff0dacd7 | 3251 | if (c >= 0xA0) |
c4825358 | 3252 | { |
ff0dacd7 KH |
3253 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3254 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 3255 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
3256 | 0xA0..0FF. If the byte length is even, we include |
3257 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
3258 | only when we are not single shifting. */ | |
3259 | if (! single_shifting | |
3260 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 3261 | { |
e17de821 | 3262 | int i = 1; |
b73bfc1c KH |
3263 | while (src < src_end) |
3264 | { | |
d12bd917 | 3265 | src_base = src; |
df7492f9 | 3266 | ONE_MORE_BYTE (c); |
b73bfc1c | 3267 | if (c < 0xA0) |
d12bd917 KH |
3268 | { |
3269 | src = src_base; | |
3270 | break; | |
3271 | } | |
b73bfc1c KH |
3272 | i++; |
3273 | } | |
3274 | ||
3275 | if (i & 1 && src < src_end) | |
cee53ed4 KH |
3276 | { |
3277 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3278 | if (composition_count >= 0) | |
3279 | composition_count += i; | |
3280 | } | |
f46869e4 | 3281 | else |
cee53ed4 KH |
3282 | { |
3283 | found |= CATEGORY_MASK_ISO_8_2; | |
3284 | if (composition_count >= 0) | |
3285 | composition_count += i / 2; | |
3286 | } | |
f46869e4 | 3287 | } |
ff0dacd7 | 3288 | break; |
4ed46869 | 3289 | } |
ff0dacd7 KH |
3290 | check_extra_latin: |
3291 | single_shifting = 0; | |
3292 | if (! VECTORP (Vlatin_extra_code_table) | |
3293 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
3294 | { | |
3295 | rejected = CATEGORY_MASK_ISO; | |
3296 | break; | |
3297 | } | |
3298 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3299 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
3300 | found |= CATEGORY_MASK_ISO_8_1; | |
3301 | else | |
3302 | rejected |= CATEGORY_MASK_ISO_8_1; | |
75e2a253 | 3303 | rejected |= CATEGORY_MASK_ISO_8_2; |
4ed46869 KH |
3304 | } |
3305 | } | |
ff0dacd7 KH |
3306 | detect_info->rejected |= CATEGORY_MASK_ISO; |
3307 | return 0; | |
4ed46869 | 3308 | |
df7492f9 | 3309 | no_more_source: |
ff0dacd7 KH |
3310 | detect_info->rejected |= rejected; |
3311 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 3312 | return 1; |
4ed46869 | 3313 | } |
ec6d2bb8 | 3314 | |
4ed46869 | 3315 | |
134b9549 KH |
3316 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
3317 | escape sequence should be kept. */ | |
df7492f9 KH |
3318 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
3319 | do { \ | |
3320 | int id, prev; \ | |
3321 | \ | |
3322 | if (final < '0' || final >= 128 \ | |
3323 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
3324 | || !SAFE_CHARSET_P (coding, id)) \ | |
3325 | { \ | |
3326 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
3327 | chars_96 = -1; \ |
3328 | break; \ | |
df7492f9 KH |
3329 | } \ |
3330 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
3331 | if (id == charset_jisx0201_roman) \ |
3332 | { \ | |
3333 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3334 | id = charset_ascii; \ | |
3335 | } \ | |
3336 | else if (id == charset_jisx0208_1978) \ | |
3337 | { \ | |
3338 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3339 | id = charset_jisx0208; \ | |
3340 | } \ | |
df7492f9 KH |
3341 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
3342 | /* If there was an invalid designation to REG previously, and this \ | |
3343 | designation is ASCII to REG, we should keep this designation \ | |
3344 | sequence. */ \ | |
3345 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 3346 | chars_96 = -1; \ |
4ed46869 KH |
3347 | } while (0) |
3348 | ||
d46c5b12 | 3349 | |
e951386e KH |
3350 | /* Handle these composition sequence (ALT: alternate char): |
3351 | ||
3352 | (1) relative composition: ESC 0 CHAR ... ESC 1 | |
3353 | (2) rulebase composition: ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
3354 | (3) altchar composition: ESC 3 ALT ... ALT ESC 0 CHAR ... ESC 1 | |
3355 | (4) alt&rule composition: ESC 4 ALT RULE ... ALT ESC 0 CHAR ... ESC 1 | |
3356 | ||
3357 | When the start sequence (ESC 0/2/3/4) is found, this annotation | |
3358 | header is produced. | |
3359 | ||
3360 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) 0 METHOD ] | |
3361 | ||
3362 | Then, upon reading CHAR or RULE (one or two bytes), these codes are | |
3363 | produced until the end sequence (ESC 1) is found: | |
3364 | ||
3365 | (1) CHAR ... CHAR | |
3366 | (2) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
3367 | (3) ALT ... ALT -1 -1 CHAR ... CHAR | |
3368 | (4) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT -1 -1 CHAR ... CHAR | |
3369 | ||
3370 | When the end sequence (ESC 1) is found, LENGTH and NCHARS in the | |
3371 | annotation header is updated as below: | |
3372 | ||
3373 | (1) LENGTH: unchanged, NCHARS: number of CHARs | |
3374 | (2) LENGTH: unchanged, NCHARS: number of CHARs | |
3375 | (3) LENGTH: += number of ALTs + 2, NCHARS: number of CHARs | |
3376 | (4) LENGTH: += number of ALTs * 3, NCHARS: number of CHARs | |
3377 | ||
3378 | If an error is found while composing, the annotation header is | |
3379 | changed to: | |
3380 | ||
3381 | [ ESC '0'/'2'/'3'/'4' -2 0 ] | |
3382 | ||
3383 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
3384 | byte sequence as below: | |
3385 | o the original byte sequence is B: [ B -1 ] | |
3386 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
3387 | and the sequence [ -1 -1 ] is changed to the original byte | |
3388 | sequence: | |
3389 | [ ESC '0' ] | |
3390 | */ | |
3391 | ||
3392 | /* Decode a composition rule C1 and maybe one more byte from the | |
3393 | source, and set RULE to the encoded composition rule, NBYTES to the | |
3394 | length of the composition rule. If the rule is invalid, set RULE | |
3395 | to some negative value. */ | |
3396 | ||
3397 | #define DECODE_COMPOSITION_RULE(rule, nbytes) \ | |
3398 | do { \ | |
3399 | rule = c1 - 32; \ | |
3400 | if (rule < 0) \ | |
3401 | break; \ | |
3402 | if (rule < 81) /* old format (before ver.21) */ \ | |
3403 | { \ | |
3404 | int gref = (rule) / 9; \ | |
3405 | int nref = (rule) % 9; \ | |
3406 | if (gref == 4) gref = 10; \ | |
3407 | if (nref == 4) nref = 10; \ | |
3408 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
3409 | nbytes = 1; \ | |
3410 | } \ | |
3411 | else /* new format (after ver.21) */ \ | |
3412 | { \ | |
3413 | int c; \ | |
3414 | \ | |
3415 | ONE_MORE_BYTE (c); \ | |
3416 | rule = COMPOSITION_ENCODE_RULE (rule - 81, c - 32); \ | |
3417 | if (rule >= 0) \ | |
3418 | rule += 0x100; /* to destinguish it from the old format */ \ | |
3419 | nbytes = 2; \ | |
3420 | } \ | |
3421 | } while (0) | |
3422 | ||
3423 | #define ENCODE_COMPOSITION_RULE(rule) \ | |
df7492f9 | 3424 | do { \ |
e951386e KH |
3425 | int gref = (rule % 0x100) / 12, nref = (rule % 0x100) % 12; \ |
3426 | \ | |
3427 | if (rule < 0x100) /* old format */ \ | |
df7492f9 | 3428 | { \ |
e951386e KH |
3429 | if (gref == 10) gref = 4; \ |
3430 | if (nref == 10) nref = 4; \ | |
3431 | charbuf[idx] = 32 + gref * 9 + nref; \ | |
3432 | charbuf[idx + 1] = -1; \ | |
3433 | new_chars++; \ | |
df7492f9 | 3434 | } \ |
e951386e | 3435 | else /* new format */ \ |
df7492f9 | 3436 | { \ |
e951386e KH |
3437 | charbuf[idx] = 32 + 81 + gref; \ |
3438 | charbuf[idx + 1] = 32 + nref; \ | |
3439 | new_chars += 2; \ | |
df7492f9 KH |
3440 | } \ |
3441 | } while (0) | |
3442 | ||
e951386e KH |
3443 | /* Finish the current composition as invalid. */ |
3444 | ||
f57e2426 | 3445 | static int finish_composition (int *, struct composition_status *); |
e951386e KH |
3446 | |
3447 | static int | |
3448 | finish_composition (charbuf, cmp_status) | |
3449 | int *charbuf; | |
3450 | struct composition_status *cmp_status; | |
3451 | { | |
3452 | int idx = - cmp_status->length; | |
3453 | int new_chars; | |
3454 | ||
3455 | /* Recover the original ESC sequence */ | |
3456 | charbuf[idx++] = ISO_CODE_ESC; | |
3457 | charbuf[idx++] = (cmp_status->method == COMPOSITION_RELATIVE ? '0' | |
3458 | : cmp_status->method == COMPOSITION_WITH_RULE ? '2' | |
3459 | : cmp_status->method == COMPOSITION_WITH_ALTCHARS ? '3' | |
3460 | /* cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS */ | |
3461 | : '4'); | |
3462 | charbuf[idx++] = -2; | |
3463 | charbuf[idx++] = 0; | |
3464 | charbuf[idx++] = -1; | |
3465 | new_chars = cmp_status->nchars; | |
3466 | if (cmp_status->method >= COMPOSITION_WITH_RULE) | |
3467 | for (; idx < 0; idx++) | |
3468 | { | |
3469 | int elt = charbuf[idx]; | |
3470 | ||
3471 | if (elt == -2) | |
3472 | { | |
3473 | ENCODE_COMPOSITION_RULE (charbuf[idx + 1]); | |
3474 | idx++; | |
3475 | } | |
3476 | else if (elt == -1) | |
3477 | { | |
3478 | charbuf[idx++] = ISO_CODE_ESC; | |
3479 | charbuf[idx] = '0'; | |
3480 | new_chars += 2; | |
3481 | } | |
3482 | } | |
3483 | cmp_status->state = COMPOSING_NO; | |
3484 | return new_chars; | |
3485 | } | |
3486 | ||
3487 | /* If characers are under composition, finish the composition. */ | |
3488 | #define MAYBE_FINISH_COMPOSITION() \ | |
3489 | do { \ | |
3490 | if (cmp_status->state != COMPOSING_NO) \ | |
3491 | char_offset += finish_composition (charbuf, cmp_status); \ | |
3492 | } while (0) | |
d46c5b12 | 3493 | |
aa72b389 | 3494 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
e951386e | 3495 | |
aa72b389 KH |
3496 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 |
3497 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
3498 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
3499 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
ec6d2bb8 | 3500 | |
e951386e KH |
3501 | Produce this annotation sequence now: |
3502 | ||
3503 | [ -LENGTH(==-4) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) METHOD ] | |
3504 | */ | |
3505 | ||
3506 | #define DECODE_COMPOSITION_START(c1) \ | |
3507 | do { \ | |
3508 | if (c1 == '0' \ | |
3509 | && ((cmp_status->state == COMPOSING_COMPONENT_CHAR \ | |
3510 | && cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ | |
3511 | || (cmp_status->state == COMPOSING_COMPONENT_RULE \ | |
3512 | && cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS))) \ | |
3513 | { \ | |
3514 | *charbuf++ = -1; \ | |
3515 | *charbuf++= -1; \ | |
3516 | cmp_status->state = COMPOSING_CHAR; \ | |
3517 | cmp_status->length += 2; \ | |
3518 | } \ | |
3519 | else \ | |
3520 | { \ | |
3521 | MAYBE_FINISH_COMPOSITION (); \ | |
3522 | cmp_status->method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
3523 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
3524 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
3525 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
3526 | cmp_status->state \ | |
3527 | = (c1 <= '2' ? COMPOSING_CHAR : COMPOSING_COMPONENT_CHAR); \ | |
3528 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
3529 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
3530 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
3531 | coding->annotated = 1; \ | |
3532 | } \ | |
ec6d2bb8 KH |
3533 | } while (0) |
3534 | ||
ec6d2bb8 | 3535 | |
e951386e | 3536 | /* Handle composition end sequence ESC 1. */ |
df7492f9 KH |
3537 | |
3538 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 3539 | do { \ |
e951386e KH |
3540 | if (cmp_status->nchars == 0 \ |
3541 | || ((cmp_status->state == COMPOSING_CHAR) \ | |
3542 | == (cmp_status->method == COMPOSITION_WITH_RULE))) \ | |
ec6d2bb8 | 3543 | { \ |
e951386e KH |
3544 | MAYBE_FINISH_COMPOSITION (); \ |
3545 | goto invalid_code; \ | |
ec6d2bb8 | 3546 | } \ |
e951386e KH |
3547 | if (cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ |
3548 | charbuf[- cmp_status->length] -= cmp_status->ncomps + 2; \ | |
3549 | else if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) \ | |
3550 | charbuf[- cmp_status->length] -= cmp_status->ncomps * 3; \ | |
3551 | charbuf[- cmp_status->length + 2] = cmp_status->nchars; \ | |
3552 | char_offset += cmp_status->nchars; \ | |
3553 | cmp_status->state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
3554 | } while (0) |
3555 | ||
e951386e | 3556 | /* Store a composition rule RULE in charbuf, and update cmp_status. */ |
df7492f9 | 3557 | |
e951386e KH |
3558 | #define STORE_COMPOSITION_RULE(rule) \ |
3559 | do { \ | |
3560 | *charbuf++ = -2; \ | |
3561 | *charbuf++ = rule; \ | |
3562 | cmp_status->length += 2; \ | |
3563 | cmp_status->state--; \ | |
3564 | } while (0) | |
ec6d2bb8 | 3565 | |
e951386e KH |
3566 | /* Store a composed char or a component char C in charbuf, and update |
3567 | cmp_status. */ | |
3568 | ||
3569 | #define STORE_COMPOSITION_CHAR(c) \ | |
ec6d2bb8 | 3570 | do { \ |
e951386e KH |
3571 | *charbuf++ = (c); \ |
3572 | cmp_status->length++; \ | |
3573 | if (cmp_status->state == COMPOSING_CHAR) \ | |
3574 | cmp_status->nchars++; \ | |
df7492f9 | 3575 | else \ |
e951386e KH |
3576 | cmp_status->ncomps++; \ |
3577 | if (cmp_status->method == COMPOSITION_WITH_RULE \ | |
3578 | || (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS \ | |
3579 | && cmp_status->state == COMPOSING_COMPONENT_CHAR)) \ | |
3580 | cmp_status->state++; \ | |
ec6d2bb8 | 3581 | } while (0) |
88993dfd | 3582 | |
d46c5b12 | 3583 | |
4ed46869 KH |
3584 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
3585 | ||
b73bfc1c | 3586 | static void |
df7492f9 | 3587 | decode_coding_iso_2022 (coding) |
4ed46869 | 3588 | struct coding_system *coding; |
4ed46869 | 3589 | { |
8f924df7 KH |
3590 | const unsigned char *src = coding->source + coding->consumed; |
3591 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
3592 | const unsigned char *src_base; | |
69a80ea3 | 3593 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
3594 | /* We may produce two annocations (charset and composition) in one |
3595 | loop and one more charset annocation at the end. */ | |
ff0dacd7 | 3596 | int *charbuf_end |
df80c7f0 | 3597 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
df7492f9 | 3598 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 3599 | int multibytep = coding->src_multibyte; |
4ed46869 | 3600 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
3601 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3602 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 3603 | int charset_id_2, charset_id_3; |
df7492f9 KH |
3604 | struct charset *charset; |
3605 | int c; | |
e951386e | 3606 | struct composition_status *cmp_status = CODING_ISO_CMP_STATUS (coding); |
24a73b0a | 3607 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
3608 | int char_offset = coding->produced_char; |
3609 | int last_offset = char_offset; | |
3610 | int last_id = charset_ascii; | |
0a9564cb EZ |
3611 | int eol_crlf = |
3612 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 3613 | int byte_after_cr = -1; |
e951386e | 3614 | int i; |
df7492f9 | 3615 | |
24a73b0a | 3616 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 3617 | setup_iso_safe_charsets (attrs); |
287c57d7 KH |
3618 | /* Charset list may have been changed. */ |
3619 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
1b3b981b | 3620 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
b73bfc1c | 3621 | |
e951386e KH |
3622 | if (cmp_status->state != COMPOSING_NO) |
3623 | { | |
3624 | for (i = 0; i < cmp_status->length; i++) | |
3625 | *charbuf++ = cmp_status->carryover[i]; | |
3626 | coding->annotated = 1; | |
3627 | } | |
3628 | ||
b73bfc1c | 3629 | while (1) |
4ed46869 | 3630 | { |
cf299835 | 3631 | int c1, c2, c3; |
b73bfc1c KH |
3632 | |
3633 | src_base = src; | |
df7492f9 KH |
3634 | consumed_chars_base = consumed_chars; |
3635 | ||
3636 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
3637 | { |
3638 | if (byte_after_cr >= 0) | |
3639 | src_base--; | |
3640 | break; | |
3641 | } | |
df7492f9 | 3642 | |
119852e7 KH |
3643 | if (byte_after_cr >= 0) |
3644 | c1 = byte_after_cr, byte_after_cr = -1; | |
3645 | else | |
3646 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
3647 | if (c1 < 0) |
3648 | goto invalid_code; | |
4ed46869 | 3649 | |
e951386e | 3650 | if (CODING_ISO_EXTSEGMENT_LEN (coding) > 0) |
4ed46869 | 3651 | { |
e951386e KH |
3652 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
3653 | char_offset++; | |
3654 | CODING_ISO_EXTSEGMENT_LEN (coding)--; | |
3655 | continue; | |
3656 | } | |
3657 | ||
3658 | if (CODING_ISO_EMBEDDED_UTF_8 (coding)) | |
3659 | { | |
3660 | if (c1 == ISO_CODE_ESC) | |
ec6d2bb8 | 3661 | { |
e951386e KH |
3662 | if (src + 1 >= src_end) |
3663 | goto no_more_source; | |
3664 | *charbuf++ = ISO_CODE_ESC; | |
3665 | char_offset++; | |
3666 | if (src[0] == '%' && src[1] == '@') | |
df7492f9 | 3667 | { |
e951386e KH |
3668 | src += 2; |
3669 | consumed_chars += 2; | |
3670 | char_offset += 2; | |
3671 | /* We are sure charbuf can contain two more chars. */ | |
3672 | *charbuf++ = '%'; | |
3673 | *charbuf++ = '@'; | |
3674 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
df7492f9 | 3675 | } |
4ed46869 | 3676 | } |
e951386e KH |
3677 | else |
3678 | { | |
3679 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
3680 | char_offset++; | |
3681 | } | |
3682 | continue; | |
3683 | } | |
3684 | ||
3685 | if ((cmp_status->state == COMPOSING_RULE | |
3686 | || cmp_status->state == COMPOSING_COMPONENT_RULE) | |
3687 | && c1 != ISO_CODE_ESC) | |
3688 | { | |
3689 | int rule, nbytes; | |
3690 | ||
3691 | DECODE_COMPOSITION_RULE (rule, nbytes); | |
3692 | if (rule < 0) | |
3693 | goto invalid_code; | |
3694 | STORE_COMPOSITION_RULE (rule); | |
3695 | continue; | |
3696 | } | |
3697 | ||
3698 | /* We produce at most one character. */ | |
3699 | switch (iso_code_class [c1]) | |
3700 | { | |
3701 | case ISO_0x20_or_0x7F: | |
df7492f9 KH |
3702 | if (charset_id_0 < 0 |
3703 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
3704 | /* This is SPACE or DEL. */ |
3705 | charset = CHARSET_FROM_ID (charset_ascii); | |
3706 | else | |
3707 | charset = CHARSET_FROM_ID (charset_id_0); | |
3708 | break; | |
4ed46869 KH |
3709 | |
3710 | case ISO_graphic_plane_0: | |
134b9549 KH |
3711 | if (charset_id_0 < 0) |
3712 | charset = CHARSET_FROM_ID (charset_ascii); | |
3713 | else | |
3714 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
3715 | break; |
3716 | ||
3717 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
3718 | if (charset_id_1 < 0 |
3719 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
3720 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
3721 | goto invalid_code; | |
4ed46869 KH |
3722 | /* This is a graphic character, we fall down ... */ |
3723 | ||
3724 | case ISO_graphic_plane_1: | |
df7492f9 KH |
3725 | if (charset_id_1 < 0) |
3726 | goto invalid_code; | |
3727 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
3728 | break; |
3729 | ||
df7492f9 | 3730 | case ISO_control_0: |
119852e7 KH |
3731 | if (eol_crlf && c1 == '\r') |
3732 | ONE_MORE_BYTE (byte_after_cr); | |
df7492f9 KH |
3733 | MAYBE_FINISH_COMPOSITION (); |
3734 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
3735 | break; |
3736 | ||
df7492f9 | 3737 | case ISO_control_1: |
df7492f9 KH |
3738 | goto invalid_code; |
3739 | ||
4ed46869 | 3740 | case ISO_shift_out: |
df7492f9 KH |
3741 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3742 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3743 | goto invalid_code; | |
3744 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3745 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3746 | continue; |
4ed46869 KH |
3747 | |
3748 | case ISO_shift_in: | |
df7492f9 KH |
3749 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3750 | goto invalid_code; | |
3751 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3752 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3753 | continue; |
4ed46869 KH |
3754 | |
3755 | case ISO_single_shift_2_7: | |
a63dba42 KH |
3756 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)) |
3757 | goto invalid_code; | |
4ed46869 | 3758 | case ISO_single_shift_2: |
df7492f9 KH |
3759 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3760 | goto invalid_code; | |
4ed46869 KH |
3761 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3762 | c1 = 'N'; | |
3763 | goto label_escape_sequence; | |
3764 | ||
3765 | case ISO_single_shift_3: | |
df7492f9 KH |
3766 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3767 | goto invalid_code; | |
4ed46869 KH |
3768 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3769 | c1 = 'O'; | |
3770 | goto label_escape_sequence; | |
3771 | ||
3772 | case ISO_control_sequence_introducer: | |
3773 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3774 | c1 = '['; | |
3775 | goto label_escape_sequence; | |
3776 | ||
3777 | case ISO_escape: | |
3778 | ONE_MORE_BYTE (c1); | |
3779 | label_escape_sequence: | |
df7492f9 | 3780 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3781 | designation, direction specification, and character |
3782 | composition specification. */ | |
3783 | switch (c1) | |
3784 | { | |
3785 | case '&': /* revision of following character set */ | |
3786 | ONE_MORE_BYTE (c1); | |
3787 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3788 | goto invalid_code; |
4ed46869 KH |
3789 | ONE_MORE_BYTE (c1); |
3790 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3791 | goto invalid_code; |
4ed46869 KH |
3792 | ONE_MORE_BYTE (c1); |
3793 | goto label_escape_sequence; | |
3794 | ||
3795 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3796 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3797 | goto invalid_code; | |
134b9549 KH |
3798 | { |
3799 | int reg, chars96; | |
3800 | ||
3801 | ONE_MORE_BYTE (c1); | |
3802 | if (c1 >= '@' && c1 <= 'B') | |
3803 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3804 | or JISX0208.1980 */ |
134b9549 KH |
3805 | reg = 0, chars96 = 0; |
3806 | } | |
3807 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3808 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3809 | reg = c1 - 0x28, chars96 = 0; | |
3810 | ONE_MORE_BYTE (c1); | |
3811 | } | |
3812 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3813 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3814 | reg = c1 - 0x2C, chars96 = 1; | |
3815 | ONE_MORE_BYTE (c1); | |
3816 | } | |
3817 | else | |
3818 | goto invalid_code; | |
3819 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3820 | /* We must update these variables now. */ | |
3821 | if (reg == 0) | |
3822 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3823 | else if (reg == 1) | |
3824 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3825 | if (chars96 < 0) | |
3826 | goto invalid_code; | |
3827 | } | |
b73bfc1c | 3828 | continue; |
4ed46869 KH |
3829 | |
3830 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3831 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3832 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3833 | goto invalid_code; | |
3834 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3835 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3836 | continue; |
4ed46869 KH |
3837 | |
3838 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3839 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3840 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3841 | goto invalid_code; | |
3842 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3843 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3844 | continue; |
4ed46869 KH |
3845 | |
3846 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3847 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3848 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3849 | goto invalid_code; | |
134b9549 KH |
3850 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3851 | if (charset_id_2 < 0) | |
3852 | charset = CHARSET_FROM_ID (charset_ascii); | |
3853 | else | |
3854 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3855 | ONE_MORE_BYTE (c1); |
e7046a18 | 3856 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3857 | goto invalid_code; |
4ed46869 KH |
3858 | break; |
3859 | ||
3860 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3861 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3862 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3863 | goto invalid_code; | |
134b9549 KH |
3864 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3865 | if (charset_id_3 < 0) | |
3866 | charset = CHARSET_FROM_ID (charset_ascii); | |
3867 | else | |
3868 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3869 | ONE_MORE_BYTE (c1); |
e7046a18 | 3870 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3871 | goto invalid_code; |
4ed46869 KH |
3872 | break; |
3873 | ||
ec6d2bb8 | 3874 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3875 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3876 | goto invalid_code; | |
e951386e KH |
3877 | if (last_id != charset_ascii) |
3878 | { | |
3879 | ADD_CHARSET_DATA (charbuf, char_offset- last_offset, last_id); | |
3880 | last_id = charset_ascii; | |
3881 | last_offset = char_offset; | |
3882 | } | |
ec6d2bb8 | 3883 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3884 | continue; |
4ed46869 | 3885 | |
ec6d2bb8 | 3886 | case '1': /* end composition */ |
e951386e | 3887 | if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3888 | goto invalid_code; |
3889 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3890 | continue; |
4ed46869 KH |
3891 | |
3892 | case '[': /* specification of direction */ | |
de59072a | 3893 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION)) |
df7492f9 | 3894 | goto invalid_code; |
4ed46869 | 3895 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3896 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
df7492f9 | 3897 | left-to-right, and nozero means right-to-left. */ |
4ed46869 KH |
3898 | ONE_MORE_BYTE (c1); |
3899 | switch (c1) | |
3900 | { | |
3901 | case ']': /* end of the current direction */ | |
d46c5b12 | 3902 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3903 | |
3904 | case '0': /* end of the current direction */ | |
3905 | case '1': /* start of left-to-right direction */ | |
3906 | ONE_MORE_BYTE (c1); | |
3907 | if (c1 == ']') | |
d46c5b12 | 3908 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3909 | else |
df7492f9 | 3910 | goto invalid_code; |
4ed46869 KH |
3911 | break; |
3912 | ||
3913 | case '2': /* start of right-to-left direction */ | |
3914 | ONE_MORE_BYTE (c1); | |
3915 | if (c1 == ']') | |
d46c5b12 | 3916 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3917 | else |
df7492f9 | 3918 | goto invalid_code; |
4ed46869 KH |
3919 | break; |
3920 | ||
3921 | default: | |
df7492f9 | 3922 | goto invalid_code; |
4ed46869 | 3923 | } |
b73bfc1c | 3924 | continue; |
4ed46869 | 3925 | |
103e0180 | 3926 | case '%': |
103e0180 KH |
3927 | ONE_MORE_BYTE (c1); |
3928 | if (c1 == '/') | |
3929 | { | |
3930 | /* CTEXT extended segment: | |
3931 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3932 | We keep these bytes as is for the moment. | |
3933 | They may be decoded by post-read-conversion. */ | |
3934 | int dim, M, L; | |
4776e638 | 3935 | int size; |
8f924df7 | 3936 | |
103e0180 | 3937 | ONE_MORE_BYTE (dim); |
e951386e KH |
3938 | if (dim < 0 || dim > 4) |
3939 | goto invalid_code; | |
103e0180 | 3940 | ONE_MORE_BYTE (M); |
e951386e KH |
3941 | if (M < 128) |
3942 | goto invalid_code; | |
103e0180 | 3943 | ONE_MORE_BYTE (L); |
e951386e KH |
3944 | if (L < 128) |
3945 | goto invalid_code; | |
103e0180 | 3946 | size = ((M - 128) * 128) + (L - 128); |
e951386e | 3947 | if (charbuf + 6 > charbuf_end) |
4776e638 KH |
3948 | goto break_loop; |
3949 | *charbuf++ = ISO_CODE_ESC; | |
3950 | *charbuf++ = '%'; | |
3951 | *charbuf++ = '/'; | |
3952 | *charbuf++ = dim; | |
3953 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3954 | *charbuf++ = BYTE8_TO_CHAR (L); | |
e951386e | 3955 | CODING_ISO_EXTSEGMENT_LEN (coding) = size; |
103e0180 KH |
3956 | } |
3957 | else if (c1 == 'G') | |
3958 | { | |
103e0180 KH |
3959 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3960 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3961 | We keep these bytes as is for the moment. | |
3962 | They may be decoded by post-read-conversion. */ | |
e951386e | 3963 | if (charbuf + 3 > charbuf_end) |
4776e638 | 3964 | goto break_loop; |
e951386e KH |
3965 | *charbuf++ = ISO_CODE_ESC; |
3966 | *charbuf++ = '%'; | |
3967 | *charbuf++ = 'G'; | |
3968 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 1; | |
103e0180 KH |
3969 | } |
3970 | else | |
4776e638 | 3971 | goto invalid_code; |
103e0180 | 3972 | continue; |
4776e638 | 3973 | break; |
103e0180 | 3974 | |
4ed46869 | 3975 | default: |
df7492f9 KH |
3976 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3977 | goto invalid_code; | |
134b9549 KH |
3978 | { |
3979 | int reg, chars96; | |
3980 | ||
3981 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3982 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3983 | reg = c1 - 0x28, chars96 = 0; | |
3984 | ONE_MORE_BYTE (c1); | |
3985 | } | |
3986 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3987 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3988 | reg = c1 - 0x2C, chars96 = 1; | |
3989 | ONE_MORE_BYTE (c1); | |
3990 | } | |
3991 | else | |
3992 | goto invalid_code; | |
3993 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3994 | /* We must update these variables now. */ | |
3995 | if (reg == 0) | |
3996 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3997 | else if (reg == 1) | |
3998 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3999 | if (chars96 < 0) | |
4000 | goto invalid_code; | |
4001 | } | |
b73bfc1c | 4002 | continue; |
4ed46869 | 4003 | } |
b73bfc1c | 4004 | } |
4ed46869 | 4005 | |
e951386e KH |
4006 | if (cmp_status->state == COMPOSING_NO |
4007 | && charset->id != charset_ascii | |
ff0dacd7 KH |
4008 | && last_id != charset->id) |
4009 | { | |
4010 | if (last_id != charset_ascii) | |
69a80ea3 | 4011 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
4012 | last_id = charset->id; |
4013 | last_offset = char_offset; | |
4014 | } | |
4015 | ||
b73bfc1c | 4016 | /* Now we know CHARSET and 1st position code C1 of a character. |
cf299835 KH |
4017 | Produce a decoded character while getting 2nd and 3rd |
4018 | position codes C2, C3 if necessary. */ | |
df7492f9 | 4019 | if (CHARSET_DIMENSION (charset) > 1) |
b73bfc1c KH |
4020 | { |
4021 | ONE_MORE_BYTE (c2); | |
cf299835 KH |
4022 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0) |
4023 | || ((c1 & 0x80) != (c2 & 0x80))) | |
b73bfc1c | 4024 | /* C2 is not in a valid range. */ |
df7492f9 | 4025 | goto invalid_code; |
cf299835 KH |
4026 | if (CHARSET_DIMENSION (charset) == 2) |
4027 | c1 = (c1 << 8) | c2; | |
4028 | else | |
df7492f9 | 4029 | { |
cf299835 KH |
4030 | ONE_MORE_BYTE (c3); |
4031 | if (c3 < 0x20 || (c3 >= 0x80 && c3 < 0xA0) | |
4032 | || ((c1 & 0x80) != (c3 & 0x80))) | |
4033 | /* C3 is not in a valid range. */ | |
df7492f9 | 4034 | goto invalid_code; |
cf299835 | 4035 | c1 = (c1 << 16) | (c2 << 8) | c2; |
df7492f9 KH |
4036 | } |
4037 | } | |
cf299835 | 4038 | c1 &= 0x7F7F7F; |
df7492f9 KH |
4039 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); |
4040 | if (c < 0) | |
4041 | { | |
4042 | MAYBE_FINISH_COMPOSITION (); | |
4043 | for (; src_base < src; src_base++, char_offset++) | |
4044 | { | |
4045 | if (ASCII_BYTE_P (*src_base)) | |
4046 | *charbuf++ = *src_base; | |
4047 | else | |
4048 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
4049 | } | |
4050 | } | |
e951386e | 4051 | else if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
4052 | { |
4053 | *charbuf++ = c; | |
4054 | char_offset++; | |
4ed46869 | 4055 | } |
e951386e KH |
4056 | else if ((cmp_status->state == COMPOSING_CHAR |
4057 | ? cmp_status->nchars | |
4058 | : cmp_status->ncomps) | |
4059 | >= MAX_COMPOSITION_COMPONENTS) | |
781d7a48 | 4060 | { |
e951386e KH |
4061 | /* Too long composition. */ |
4062 | MAYBE_FINISH_COMPOSITION (); | |
4063 | *charbuf++ = c; | |
4064 | char_offset++; | |
4ed46869 | 4065 | } |
e951386e KH |
4066 | else |
4067 | STORE_COMPOSITION_CHAR (c); | |
4ed46869 KH |
4068 | continue; |
4069 | ||
df7492f9 KH |
4070 | invalid_code: |
4071 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 4072 | src = src_base; |
df7492f9 KH |
4073 | consumed_chars = consumed_chars_base; |
4074 | ONE_MORE_BYTE (c); | |
065e3595 | 4075 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4076 | char_offset++; |
df7492f9 | 4077 | coding->errors++; |
4776e638 KH |
4078 | continue; |
4079 | ||
4080 | break_loop: | |
4081 | break; | |
4ed46869 | 4082 | } |
fb88bf2d | 4083 | |
df7492f9 | 4084 | no_more_source: |
e951386e KH |
4085 | if (cmp_status->state != COMPOSING_NO) |
4086 | { | |
4087 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
4088 | MAYBE_FINISH_COMPOSITION (); | |
4089 | else | |
4090 | { | |
4091 | charbuf -= cmp_status->length; | |
4092 | for (i = 0; i < cmp_status->length; i++) | |
4093 | cmp_status->carryover[i] = charbuf[i]; | |
4094 | } | |
4095 | } | |
4096 | else if (last_id != charset_ascii) | |
69a80ea3 | 4097 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4098 | coding->consumed_char += consumed_chars_base; |
4099 | coding->consumed = src_base - coding->source; | |
4100 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4101 | } |
4102 | ||
b73bfc1c | 4103 | |
f4dee582 | 4104 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
4105 | |
4106 | /* | |
f4dee582 | 4107 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 4108 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 4109 | variant has the following specifications: |
df7492f9 | 4110 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
4111 | 2. Allows short-form designation? |
4112 | 3. ASCII should be designated to G0 before control characters? | |
4113 | 4. ASCII should be designated to G0 at end of line? | |
4114 | 5. 7-bit environment or 8-bit environment? | |
4115 | 6. Use locking-shift? | |
4116 | 7. Use Single-shift? | |
4117 | And the following two are only for Japanese: | |
4118 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
4119 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
4120 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
4121 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 4122 | details. |
4ed46869 KH |
4123 | */ |
4124 | ||
4125 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
4126 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
4127 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
4128 | designation sequence of short-form. */ | |
4ed46869 KH |
4129 | |
4130 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
4131 | do { \ | |
df7492f9 | 4132 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
4ed46869 KH |
4133 | char *intermediate_char_94 = "()*+"; \ |
4134 | char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
4135 | int revision = -1; \ |
4136 | int c; \ | |
4137 | \ | |
4138 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 4139 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
4140 | \ |
4141 | if (revision >= 0) \ | |
70c22245 | 4142 | { \ |
df7492f9 KH |
4143 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
4144 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 4145 | } \ |
df7492f9 | 4146 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
4147 | if (CHARSET_DIMENSION (charset) == 1) \ |
4148 | { \ | |
df7492f9 KH |
4149 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
4150 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 4151 | else \ |
df7492f9 KH |
4152 | c = intermediate_char_96[reg]; \ |
4153 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
4154 | } \ |
4155 | else \ | |
4156 | { \ | |
df7492f9 KH |
4157 | EMIT_ONE_ASCII_BYTE ('$'); \ |
4158 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 4159 | { \ |
df7492f9 | 4160 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
4161 | || reg != 0 \ |
4162 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 4163 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
4164 | } \ |
4165 | else \ | |
df7492f9 | 4166 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 4167 | } \ |
df7492f9 KH |
4168 | EMIT_ONE_ASCII_BYTE (final_char); \ |
4169 | \ | |
4170 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
4171 | } while (0) |
4172 | ||
df7492f9 | 4173 | |
4ed46869 KH |
4174 | /* The following two macros produce codes (control character or escape |
4175 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
4176 | single-shift-3). */ | |
4177 | ||
df7492f9 KH |
4178 | #define ENCODE_SINGLE_SHIFT_2 \ |
4179 | do { \ | |
4180 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4181 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
4182 | else \ | |
4183 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
4184 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4185 | } while (0) |
4186 | ||
df7492f9 KH |
4187 | |
4188 | #define ENCODE_SINGLE_SHIFT_3 \ | |
4189 | do { \ | |
4190 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4191 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
4192 | else \ | |
4193 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
4194 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4195 | } while (0) |
4196 | ||
df7492f9 | 4197 | |
4ed46869 KH |
4198 | /* The following four macros produce codes (control character or |
4199 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
4200 | shift-out, locking-shift-2, and locking-shift-3). */ | |
4201 | ||
df7492f9 KH |
4202 | #define ENCODE_SHIFT_IN \ |
4203 | do { \ | |
4204 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
4205 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
4206 | } while (0) |
4207 | ||
df7492f9 KH |
4208 | |
4209 | #define ENCODE_SHIFT_OUT \ | |
4210 | do { \ | |
4211 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
4212 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
4213 | } while (0) |
4214 | ||
df7492f9 KH |
4215 | |
4216 | #define ENCODE_LOCKING_SHIFT_2 \ | |
4217 | do { \ | |
4218 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4219 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
4220 | } while (0) |
4221 | ||
df7492f9 KH |
4222 | |
4223 | #define ENCODE_LOCKING_SHIFT_3 \ | |
4224 | do { \ | |
4225 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4226 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
4227 | } while (0) |
4228 | ||
df7492f9 | 4229 | |
f4dee582 RS |
4230 | /* Produce codes for a DIMENSION1 character whose character set is |
4231 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
4232 | sequences are also produced in advance if necessary. */ |
4233 | ||
6e85d753 KH |
4234 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
4235 | do { \ | |
df7492f9 | 4236 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4237 | \ |
4238 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
4239 | && id == charset_ascii) \ | |
4240 | { \ | |
4241 | id = charset_jisx0201_roman; \ | |
4242 | charset = CHARSET_FROM_ID (id); \ | |
4243 | } \ | |
4244 | \ | |
df7492f9 | 4245 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4246 | { \ |
df7492f9 KH |
4247 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4248 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 4249 | else \ |
df7492f9 KH |
4250 | EMIT_ONE_BYTE (c1 | 0x80); \ |
4251 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4252 | break; \ |
4253 | } \ | |
df7492f9 | 4254 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4255 | { \ |
df7492f9 | 4256 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
4257 | break; \ |
4258 | } \ | |
df7492f9 | 4259 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4260 | { \ |
df7492f9 | 4261 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
4262 | break; \ |
4263 | } \ | |
6e85d753 KH |
4264 | else \ |
4265 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4266 | must invoke it, or, at first, designate it to some graphic \ | |
4267 | register. Then repeat the loop to actually produce the \ | |
4268 | character. */ \ | |
df7492f9 KH |
4269 | dst = encode_invocation_designation (charset, coding, dst, \ |
4270 | &produced_chars); \ | |
4ed46869 KH |
4271 | } while (1) |
4272 | ||
df7492f9 | 4273 | |
f4dee582 RS |
4274 | /* Produce codes for a DIMENSION2 character whose character set is |
4275 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
4276 | invocation codes are also produced in advance if necessary. */ |
4277 | ||
6e85d753 KH |
4278 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
4279 | do { \ | |
df7492f9 | 4280 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4281 | \ |
4282 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
4283 | && id == charset_jisx0208) \ | |
4284 | { \ | |
4285 | id = charset_jisx0208_1978; \ | |
4286 | charset = CHARSET_FROM_ID (id); \ | |
4287 | } \ | |
4288 | \ | |
df7492f9 | 4289 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4290 | { \ |
df7492f9 KH |
4291 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4292 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 4293 | else \ |
df7492f9 KH |
4294 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
4295 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4296 | break; \ |
4297 | } \ | |
df7492f9 | 4298 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4299 | { \ |
df7492f9 | 4300 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
4301 | break; \ |
4302 | } \ | |
df7492f9 | 4303 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4304 | { \ |
df7492f9 | 4305 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
4306 | break; \ |
4307 | } \ | |
6e85d753 KH |
4308 | else \ |
4309 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4310 | must invoke it, or, at first, designate it to some graphic \ | |
4311 | register. Then repeat the loop to actually produce the \ | |
4312 | character. */ \ | |
df7492f9 KH |
4313 | dst = encode_invocation_designation (charset, coding, dst, \ |
4314 | &produced_chars); \ | |
4ed46869 KH |
4315 | } while (1) |
4316 | ||
05e6f5dc | 4317 | |
df7492f9 KH |
4318 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
4319 | do { \ | |
4320 | int code = ENCODE_CHAR ((charset),(c)); \ | |
4321 | \ | |
4322 | if (CHARSET_DIMENSION (charset) == 1) \ | |
4323 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
4324 | else \ | |
4325 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 4326 | } while (0) |
bdd9fb48 | 4327 | |
05e6f5dc | 4328 | |
4ed46869 | 4329 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 4330 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
4331 | Return new DST. */ |
4332 | ||
4333 | unsigned char * | |
df7492f9 KH |
4334 | encode_invocation_designation (charset, coding, dst, p_nchars) |
4335 | struct charset *charset; | |
4ed46869 KH |
4336 | struct coding_system *coding; |
4337 | unsigned char *dst; | |
df7492f9 | 4338 | int *p_nchars; |
4ed46869 | 4339 | { |
df7492f9 KH |
4340 | int multibytep = coding->dst_multibyte; |
4341 | int produced_chars = *p_nchars; | |
4ed46869 | 4342 | int reg; /* graphic register number */ |
df7492f9 | 4343 | int id = CHARSET_ID (charset); |
4ed46869 KH |
4344 | |
4345 | /* At first, check designations. */ | |
4346 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 4347 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
4348 | break; |
4349 | ||
4350 | if (reg >= 4) | |
4351 | { | |
4352 | /* CHARSET is not yet designated to any graphic registers. */ | |
4353 | /* At first check the requested designation. */ | |
df7492f9 KH |
4354 | reg = CODING_ISO_REQUEST (coding, id); |
4355 | if (reg < 0) | |
1ba9e4ab KH |
4356 | /* Since CHARSET requests no special designation, designate it |
4357 | to graphic register 0. */ | |
4ed46869 KH |
4358 | reg = 0; |
4359 | ||
4360 | ENCODE_DESIGNATION (charset, reg, coding); | |
4361 | } | |
4362 | ||
df7492f9 KH |
4363 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
4364 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
4365 | { |
4366 | /* Since the graphic register REG is not invoked to any graphic | |
4367 | planes, invoke it to graphic plane 0. */ | |
4368 | switch (reg) | |
4369 | { | |
4370 | case 0: /* graphic register 0 */ | |
4371 | ENCODE_SHIFT_IN; | |
4372 | break; | |
4373 | ||
4374 | case 1: /* graphic register 1 */ | |
4375 | ENCODE_SHIFT_OUT; | |
4376 | break; | |
4377 | ||
4378 | case 2: /* graphic register 2 */ | |
df7492f9 | 4379 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4380 | ENCODE_SINGLE_SHIFT_2; |
4381 | else | |
4382 | ENCODE_LOCKING_SHIFT_2; | |
4383 | break; | |
4384 | ||
4385 | case 3: /* graphic register 3 */ | |
df7492f9 | 4386 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4387 | ENCODE_SINGLE_SHIFT_3; |
4388 | else | |
4389 | ENCODE_LOCKING_SHIFT_3; | |
4390 | break; | |
4391 | } | |
4392 | } | |
b73bfc1c | 4393 | |
df7492f9 | 4394 | *p_nchars = produced_chars; |
4ed46869 KH |
4395 | return dst; |
4396 | } | |
4397 | ||
df7492f9 KH |
4398 | /* The following three macros produce codes for indicating direction |
4399 | of text. */ | |
4400 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 4401 | do { \ |
df7492f9 KH |
4402 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
4403 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 4404 | else \ |
df7492f9 | 4405 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
4406 | } while (0) |
4407 | ||
ec6d2bb8 | 4408 | |
df7492f9 KH |
4409 | #define ENCODE_DIRECTION_R2L() \ |
4410 | do { \ | |
4411 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
4412 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
4413 | } while (0) |
4414 | ||
ec6d2bb8 | 4415 | |
df7492f9 | 4416 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 4417 | do { \ |
df7492f9 KH |
4418 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
4419 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
ec6d2bb8 | 4420 | } while (0) |
4ed46869 | 4421 | |
4ed46869 KH |
4422 | |
4423 | /* Produce codes for designation and invocation to reset the graphic | |
4424 | planes and registers to initial state. */ | |
df7492f9 KH |
4425 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
4426 | do { \ | |
4427 | int reg; \ | |
4428 | struct charset *charset; \ | |
4429 | \ | |
4430 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
4431 | ENCODE_SHIFT_IN; \ | |
4432 | for (reg = 0; reg < 4; reg++) \ | |
4433 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
4434 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
4435 | != CODING_ISO_INITIAL (coding, reg))) \ | |
4436 | { \ | |
4437 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
4438 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
4439 | } \ | |
4ed46869 KH |
4440 | } while (0) |
4441 | ||
df7492f9 | 4442 | |
bdd9fb48 | 4443 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 4444 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
4445 | |
4446 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
4447 | find all the necessary designations. */ |
4448 | ||
b73bfc1c | 4449 | static unsigned char * |
df7492f9 | 4450 | encode_designation_at_bol (coding, charbuf, charbuf_end, dst) |
e0e989f6 | 4451 | struct coding_system *coding; |
df7492f9 KH |
4452 | int *charbuf, *charbuf_end; |
4453 | unsigned char *dst; | |
e0e989f6 | 4454 | { |
df7492f9 | 4455 | struct charset *charset; |
bdd9fb48 KH |
4456 | /* Table of charsets to be designated to each graphic register. */ |
4457 | int r[4]; | |
df7492f9 KH |
4458 | int c, found = 0, reg; |
4459 | int produced_chars = 0; | |
4460 | int multibytep = coding->dst_multibyte; | |
4461 | Lisp_Object attrs; | |
4462 | Lisp_Object charset_list; | |
4463 | ||
4464 | attrs = CODING_ID_ATTRS (coding->id); | |
4465 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
4466 | if (EQ (charset_list, Qiso_2022)) | |
4467 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
4468 | |
4469 | for (reg = 0; reg < 4; reg++) | |
4470 | r[reg] = -1; | |
4471 | ||
b73bfc1c | 4472 | while (found < 4) |
e0e989f6 | 4473 | { |
df7492f9 KH |
4474 | int id; |
4475 | ||
4476 | c = *charbuf++; | |
b73bfc1c KH |
4477 | if (c == '\n') |
4478 | break; | |
df7492f9 KH |
4479 | charset = char_charset (c, charset_list, NULL); |
4480 | id = CHARSET_ID (charset); | |
4481 | reg = CODING_ISO_REQUEST (coding, id); | |
4482 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
4483 | { |
4484 | found++; | |
df7492f9 | 4485 | r[reg] = id; |
bdd9fb48 | 4486 | } |
bdd9fb48 KH |
4487 | } |
4488 | ||
4489 | if (found) | |
4490 | { | |
4491 | for (reg = 0; reg < 4; reg++) | |
4492 | if (r[reg] >= 0 | |
df7492f9 KH |
4493 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
4494 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 4495 | } |
b73bfc1c KH |
4496 | |
4497 | return dst; | |
e0e989f6 KH |
4498 | } |
4499 | ||
4ed46869 KH |
4500 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
4501 | ||
df7492f9 KH |
4502 | static int |
4503 | encode_coding_iso_2022 (coding) | |
4ed46869 | 4504 | struct coding_system *coding; |
4ed46869 | 4505 | { |
df7492f9 KH |
4506 | int multibytep = coding->dst_multibyte; |
4507 | int *charbuf = coding->charbuf; | |
4508 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4509 | unsigned char *dst = coding->destination + coding->produced; | |
4510 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4511 | int safe_room = 16; | |
4512 | int bol_designation | |
4513 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
4514 | && CODING_ISO_BOL (coding)); | |
4515 | int produced_chars = 0; | |
4516 | Lisp_Object attrs, eol_type, charset_list; | |
4517 | int ascii_compatible; | |
b73bfc1c | 4518 | int c; |
ff0dacd7 | 4519 | int preferred_charset_id = -1; |
05e6f5dc | 4520 | |
24a73b0a | 4521 | CODING_GET_INFO (coding, attrs, charset_list); |
0a9564cb | 4522 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
24a73b0a KH |
4523 | if (VECTORP (eol_type)) |
4524 | eol_type = Qunix; | |
4525 | ||
004068e4 | 4526 | setup_iso_safe_charsets (attrs); |
ff0dacd7 | 4527 | /* Charset list may have been changed. */ |
287c57d7 | 4528 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); |
1b3b981b | 4529 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
0eecad43 | 4530 | |
df7492f9 | 4531 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
bdd9fb48 | 4532 | |
df7492f9 | 4533 | while (charbuf < charbuf_end) |
4ed46869 | 4534 | { |
df7492f9 | 4535 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 4536 | |
df7492f9 | 4537 | if (bol_designation) |
b73bfc1c | 4538 | { |
df7492f9 | 4539 | unsigned char *dst_prev = dst; |
4ed46869 | 4540 | |
bdd9fb48 | 4541 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
4542 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
4543 | bol_designation = 0; | |
4544 | /* We are sure that designation sequences are all ASCII bytes. */ | |
4545 | produced_chars += dst - dst_prev; | |
e0e989f6 KH |
4546 | } |
4547 | ||
df7492f9 | 4548 | c = *charbuf++; |
ec6d2bb8 | 4549 | |
ff0dacd7 KH |
4550 | if (c < 0) |
4551 | { | |
4552 | /* Handle an annotation. */ | |
4553 | switch (*charbuf) | |
ec6d2bb8 | 4554 | { |
ff0dacd7 KH |
4555 | case CODING_ANNOTATE_COMPOSITION_MASK: |
4556 | /* Not yet implemented. */ | |
4557 | break; | |
4558 | case CODING_ANNOTATE_CHARSET_MASK: | |
cf7dfdf5 | 4559 | preferred_charset_id = charbuf[2]; |
ff0dacd7 KH |
4560 | if (preferred_charset_id >= 0 |
4561 | && NILP (Fmemq (make_number (preferred_charset_id), | |
4562 | charset_list))) | |
4563 | preferred_charset_id = -1; | |
4564 | break; | |
4565 | default: | |
4566 | abort (); | |
4ed46869 | 4567 | } |
ff0dacd7 KH |
4568 | charbuf += -c - 1; |
4569 | continue; | |
4ed46869 | 4570 | } |
ec6d2bb8 | 4571 | |
b73bfc1c KH |
4572 | /* Now encode the character C. */ |
4573 | if (c < 0x20 || c == 0x7F) | |
4574 | { | |
df7492f9 KH |
4575 | if (c == '\n' |
4576 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 4577 | { |
df7492f9 KH |
4578 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
4579 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4580 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 4581 | { |
df7492f9 KH |
4582 | int i; |
4583 | ||
4584 | for (i = 0; i < 4; i++) | |
4585 | CODING_ISO_DESIGNATION (coding, i) | |
4586 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 4587 | } |
df7492f9 KH |
4588 | bol_designation |
4589 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 4590 | } |
df7492f9 KH |
4591 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
4592 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4593 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 4594 | } |
df7492f9 | 4595 | else if (ASCII_CHAR_P (c)) |
88993dfd | 4596 | { |
df7492f9 KH |
4597 | if (ascii_compatible) |
4598 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 4599 | else |
19a8d9e0 | 4600 | { |
bf16eb23 KH |
4601 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
4602 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 4603 | } |
4ed46869 | 4604 | } |
16eafb5d | 4605 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 4606 | { |
16eafb5d KH |
4607 | c = CHAR_TO_BYTE8 (c); |
4608 | EMIT_ONE_BYTE (c); | |
88993dfd | 4609 | } |
b73bfc1c | 4610 | else |
df7492f9 | 4611 | { |
ff0dacd7 | 4612 | struct charset *charset; |
b73bfc1c | 4613 | |
ff0dacd7 KH |
4614 | if (preferred_charset_id >= 0) |
4615 | { | |
4616 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
4617 | if (! CHAR_CHARSET_P (c, charset)) | |
4618 | charset = char_charset (c, charset_list, NULL); | |
4619 | } | |
4620 | else | |
4621 | charset = char_charset (c, charset_list, NULL); | |
df7492f9 KH |
4622 | if (!charset) |
4623 | { | |
41cbe562 KH |
4624 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
4625 | { | |
4626 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4627 | charset = CHARSET_FROM_ID (charset_ascii); | |
4628 | } | |
4629 | else | |
4630 | { | |
4631 | c = coding->default_char; | |
4632 | charset = char_charset (c, charset_list, NULL); | |
4633 | } | |
df7492f9 KH |
4634 | } |
4635 | ENCODE_ISO_CHARACTER (charset, c); | |
4636 | } | |
84fbb8a0 | 4637 | } |
b73bfc1c | 4638 | |
df7492f9 KH |
4639 | if (coding->mode & CODING_MODE_LAST_BLOCK |
4640 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
4641 | { | |
4642 | ASSURE_DESTINATION (safe_room); | |
4643 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4644 | } | |
065e3595 | 4645 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4646 | CODING_ISO_BOL (coding) = bol_designation; |
4647 | coding->produced_char += produced_chars; | |
4648 | coding->produced = dst - coding->destination; | |
4649 | return 0; | |
4ed46869 KH |
4650 | } |
4651 | ||
4652 | \f | |
df7492f9 | 4653 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 4654 | |
df7492f9 | 4655 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
4656 | quite widely. So, for the moment, Emacs supports them in the bare |
4657 | C code. But, in the future, they may be supported only by CCL. */ | |
4658 | ||
4659 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
4660 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
4661 | as is. A character of charset katakana-jisx0201 is encoded by | |
4662 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
4663 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 4664 | so that it fit in the range below. |
4ed46869 KH |
4665 | |
4666 | --- CODE RANGE of SJIS --- | |
4667 | (character set) (range) | |
4668 | ASCII 0x00 .. 0x7F | |
df7492f9 | 4669 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 4670 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 4671 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
4672 | ------------------------------- |
4673 | ||
4674 | */ | |
4675 | ||
4676 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
4677 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 4678 | character set and is encoded in two-byte. |
4ed46869 KH |
4679 | |
4680 | --- CODE RANGE of BIG5 --- | |
4681 | (character set) (range) | |
4682 | ASCII 0x00 .. 0x7F | |
4683 | Big5 (1st byte) 0xA1 .. 0xFE | |
4684 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
4685 | -------------------------- | |
4686 | ||
df7492f9 | 4687 | */ |
4ed46869 KH |
4688 | |
4689 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4690 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 4691 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 4692 | |
0a28aafb | 4693 | static int |
ff0dacd7 | 4694 | detect_coding_sjis (coding, detect_info) |
df7492f9 | 4695 | struct coding_system *coding; |
ff0dacd7 | 4696 | struct coding_detection_info *detect_info; |
4ed46869 | 4697 | { |
065e3595 | 4698 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4699 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4700 | int multibytep = coding->src_multibyte; |
4701 | int consumed_chars = 0; | |
4702 | int found = 0; | |
b73bfc1c | 4703 | int c; |
f07190ca KH |
4704 | Lisp_Object attrs, charset_list; |
4705 | int max_first_byte_of_2_byte_code; | |
4706 | ||
4707 | CODING_GET_INFO (coding, attrs, charset_list); | |
4708 | max_first_byte_of_2_byte_code | |
4709 | = (XINT (Flength (charset_list)) > 3 ? 0xFC : 0xEF); | |
df7492f9 | 4710 | |
ff0dacd7 | 4711 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4712 | /* A coding system of this category is always ASCII compatible. */ |
4713 | src += coding->head_ascii; | |
4ed46869 | 4714 | |
b73bfc1c | 4715 | while (1) |
4ed46869 | 4716 | { |
065e3595 | 4717 | src_base = src; |
df7492f9 | 4718 | ONE_MORE_BYTE (c); |
682169fe KH |
4719 | if (c < 0x80) |
4720 | continue; | |
f07190ca KH |
4721 | if ((c >= 0x81 && c <= 0x9F) |
4722 | || (c >= 0xE0 && c <= max_first_byte_of_2_byte_code)) | |
4ed46869 | 4723 | { |
df7492f9 | 4724 | ONE_MORE_BYTE (c); |
682169fe | 4725 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 4726 | break; |
ff0dacd7 | 4727 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 4728 | } |
df7492f9 | 4729 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 4730 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
4731 | else |
4732 | break; | |
4ed46869 | 4733 | } |
ff0dacd7 | 4734 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4735 | return 0; |
4736 | ||
4737 | no_more_source: | |
065e3595 | 4738 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4739 | { |
ff0dacd7 | 4740 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 4741 | return 0; |
4ed46869 | 4742 | } |
ff0dacd7 KH |
4743 | detect_info->found |= found; |
4744 | return 1; | |
4ed46869 KH |
4745 | } |
4746 | ||
4747 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4748 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 4749 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 4750 | |
0a28aafb | 4751 | static int |
ff0dacd7 | 4752 | detect_coding_big5 (coding, detect_info) |
df7492f9 | 4753 | struct coding_system *coding; |
ff0dacd7 | 4754 | struct coding_detection_info *detect_info; |
4ed46869 | 4755 | { |
065e3595 | 4756 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4757 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4758 | int multibytep = coding->src_multibyte; |
4759 | int consumed_chars = 0; | |
4760 | int found = 0; | |
b73bfc1c | 4761 | int c; |
fa42c37f | 4762 | |
ff0dacd7 | 4763 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4764 | /* A coding system of this category is always ASCII compatible. */ |
4765 | src += coding->head_ascii; | |
fa42c37f | 4766 | |
b73bfc1c | 4767 | while (1) |
fa42c37f | 4768 | { |
065e3595 | 4769 | src_base = src; |
df7492f9 KH |
4770 | ONE_MORE_BYTE (c); |
4771 | if (c < 0x80) | |
fa42c37f | 4772 | continue; |
df7492f9 | 4773 | if (c >= 0xA1) |
fa42c37f | 4774 | { |
df7492f9 KH |
4775 | ONE_MORE_BYTE (c); |
4776 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4777 | return 0; |
ff0dacd7 | 4778 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4779 | } |
df7492f9 KH |
4780 | else |
4781 | break; | |
fa42c37f | 4782 | } |
ff0dacd7 | 4783 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4784 | return 0; |
fa42c37f | 4785 | |
df7492f9 | 4786 | no_more_source: |
065e3595 | 4787 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4788 | { |
ff0dacd7 | 4789 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4790 | return 0; |
4791 | } | |
ff0dacd7 KH |
4792 | detect_info->found |= found; |
4793 | return 1; | |
fa42c37f KH |
4794 | } |
4795 | ||
4ed46869 KH |
4796 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
4797 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
fa42c37f | 4798 | |
b73bfc1c | 4799 | static void |
df7492f9 | 4800 | decode_coding_sjis (coding) |
4ed46869 | 4801 | struct coding_system *coding; |
4ed46869 | 4802 | { |
8f924df7 KH |
4803 | const unsigned char *src = coding->source + coding->consumed; |
4804 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4805 | const unsigned char *src_base; | |
69a80ea3 | 4806 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
4807 | /* We may produce one charset annocation in one loop and one more at |
4808 | the end. */ | |
69a80ea3 | 4809 | int *charbuf_end |
df80c7f0 | 4810 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
4811 | int consumed_chars = 0, consumed_chars_base; |
4812 | int multibytep = coding->src_multibyte; | |
4813 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4814 | struct charset *charset_kanji2; |
24a73b0a | 4815 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4816 | int char_offset = coding->produced_char; |
4817 | int last_offset = char_offset; | |
4818 | int last_id = charset_ascii; | |
0a9564cb EZ |
4819 | int eol_crlf = |
4820 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4821 | int byte_after_cr = -1; |
a5d301df | 4822 | |
24a73b0a | 4823 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4824 | |
4825 | val = charset_list; | |
4826 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4827 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4828 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4829 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4830 | |
b73bfc1c | 4831 | while (1) |
4ed46869 | 4832 | { |
df7492f9 | 4833 | int c, c1; |
24a73b0a | 4834 | struct charset *charset; |
fa42c37f | 4835 | |
b73bfc1c | 4836 | src_base = src; |
df7492f9 | 4837 | consumed_chars_base = consumed_chars; |
fa42c37f | 4838 | |
df7492f9 | 4839 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
4840 | { |
4841 | if (byte_after_cr >= 0) | |
4842 | src_base--; | |
4843 | break; | |
4844 | } | |
df7492f9 | 4845 | |
119852e7 KH |
4846 | if (byte_after_cr >= 0) |
4847 | c = byte_after_cr, byte_after_cr = -1; | |
4848 | else | |
4849 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4850 | if (c < 0) |
4851 | goto invalid_code; | |
24a73b0a | 4852 | if (c < 0x80) |
119852e7 KH |
4853 | { |
4854 | if (eol_crlf && c == '\r') | |
4855 | ONE_MORE_BYTE (byte_after_cr); | |
4856 | charset = charset_roman; | |
4857 | } | |
57a47f8a | 4858 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4859 | goto invalid_code; |
57a47f8a KH |
4860 | else if (c >= 0xA1 && c <= 0xDF) |
4861 | { | |
4862 | /* SJIS -> JISX0201-Kana */ | |
4863 | c &= 0x7F; | |
4864 | charset = charset_kana; | |
4865 | } | |
4866 | else if (c <= 0xEF) | |
df7492f9 | 4867 | { |
57a47f8a KH |
4868 | /* SJIS -> JISX0208 */ |
4869 | ONE_MORE_BYTE (c1); | |
4870 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4871 | goto invalid_code; |
57a47f8a KH |
4872 | c = (c << 8) | c1; |
4873 | SJIS_TO_JIS (c); | |
4874 | charset = charset_kanji; | |
4875 | } | |
4876 | else if (c <= 0xFC && charset_kanji2) | |
4877 | { | |
c6876370 | 4878 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4879 | ONE_MORE_BYTE (c1); |
4880 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4881 | goto invalid_code; |
57a47f8a KH |
4882 | c = (c << 8) | c1; |
4883 | SJIS_TO_JIS2 (c); | |
4884 | charset = charset_kanji2; | |
df7492f9 | 4885 | } |
57a47f8a KH |
4886 | else |
4887 | goto invalid_code; | |
24a73b0a KH |
4888 | if (charset->id != charset_ascii |
4889 | && last_id != charset->id) | |
4890 | { | |
4891 | if (last_id != charset_ascii) | |
69a80ea3 | 4892 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4893 | last_id = charset->id; |
4894 | last_offset = char_offset; | |
4895 | } | |
4896 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4897 | *charbuf++ = c; |
ff0dacd7 | 4898 | char_offset++; |
df7492f9 | 4899 | continue; |
b73bfc1c | 4900 | |
df7492f9 KH |
4901 | invalid_code: |
4902 | src = src_base; | |
4903 | consumed_chars = consumed_chars_base; | |
4904 | ONE_MORE_BYTE (c); | |
065e3595 | 4905 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4906 | char_offset++; |
df7492f9 KH |
4907 | coding->errors++; |
4908 | } | |
fa42c37f | 4909 | |
df7492f9 | 4910 | no_more_source: |
ff0dacd7 | 4911 | if (last_id != charset_ascii) |
69a80ea3 | 4912 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4913 | coding->consumed_char += consumed_chars_base; |
4914 | coding->consumed = src_base - coding->source; | |
4915 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4916 | } |
4917 | ||
b73bfc1c | 4918 | static void |
df7492f9 | 4919 | decode_coding_big5 (coding) |
4ed46869 | 4920 | struct coding_system *coding; |
4ed46869 | 4921 | { |
8f924df7 KH |
4922 | const unsigned char *src = coding->source + coding->consumed; |
4923 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4924 | const unsigned char *src_base; | |
69a80ea3 | 4925 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
4926 | /* We may produce one charset annocation in one loop and one more at |
4927 | the end. */ | |
69a80ea3 | 4928 | int *charbuf_end |
df80c7f0 | 4929 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
4930 | int consumed_chars = 0, consumed_chars_base; |
4931 | int multibytep = coding->src_multibyte; | |
4932 | struct charset *charset_roman, *charset_big5; | |
24a73b0a | 4933 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4934 | int char_offset = coding->produced_char; |
4935 | int last_offset = char_offset; | |
4936 | int last_id = charset_ascii; | |
0a9564cb EZ |
4937 | int eol_crlf = |
4938 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4939 | int byte_after_cr = -1; |
df7492f9 | 4940 | |
24a73b0a | 4941 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4942 | val = charset_list; |
4943 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4944 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4945 | |
b73bfc1c | 4946 | while (1) |
4ed46869 | 4947 | { |
df7492f9 | 4948 | int c, c1; |
24a73b0a | 4949 | struct charset *charset; |
b73bfc1c KH |
4950 | |
4951 | src_base = src; | |
df7492f9 KH |
4952 | consumed_chars_base = consumed_chars; |
4953 | ||
4954 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
4955 | { |
4956 | if (byte_after_cr >= 0) | |
4957 | src_base--; | |
4958 | break; | |
4959 | } | |
df7492f9 | 4960 | |
119852e7 | 4961 | if (byte_after_cr >= 0) |
14daee73 | 4962 | c = byte_after_cr, byte_after_cr = -1; |
119852e7 KH |
4963 | else |
4964 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4965 | |
065e3595 KH |
4966 | if (c < 0) |
4967 | goto invalid_code; | |
24a73b0a | 4968 | if (c < 0x80) |
119852e7 | 4969 | { |
14daee73 | 4970 | if (eol_crlf && c == '\r') |
119852e7 KH |
4971 | ONE_MORE_BYTE (byte_after_cr); |
4972 | charset = charset_roman; | |
4973 | } | |
24a73b0a | 4974 | else |
4ed46869 | 4975 | { |
24a73b0a KH |
4976 | /* BIG5 -> Big5 */ |
4977 | if (c < 0xA1 || c > 0xFE) | |
4978 | goto invalid_code; | |
4979 | ONE_MORE_BYTE (c1); | |
4980 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4981 | goto invalid_code; | |
4982 | c = c << 8 | c1; | |
4983 | charset = charset_big5; | |
4ed46869 | 4984 | } |
24a73b0a KH |
4985 | if (charset->id != charset_ascii |
4986 | && last_id != charset->id) | |
df7492f9 | 4987 | { |
24a73b0a | 4988 | if (last_id != charset_ascii) |
69a80ea3 | 4989 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4990 | last_id = charset->id; |
4991 | last_offset = char_offset; | |
4ed46869 | 4992 | } |
24a73b0a | 4993 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4994 | *charbuf++ = c; |
ff0dacd7 | 4995 | char_offset++; |
fb88bf2d KH |
4996 | continue; |
4997 | ||
df7492f9 | 4998 | invalid_code: |
4ed46869 | 4999 | src = src_base; |
df7492f9 KH |
5000 | consumed_chars = consumed_chars_base; |
5001 | ONE_MORE_BYTE (c); | |
065e3595 | 5002 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 5003 | char_offset++; |
df7492f9 | 5004 | coding->errors++; |
fb88bf2d | 5005 | } |
d46c5b12 | 5006 | |
df7492f9 | 5007 | no_more_source: |
ff0dacd7 | 5008 | if (last_id != charset_ascii) |
69a80ea3 | 5009 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
5010 | coding->consumed_char += consumed_chars_base; |
5011 | coding->consumed = src_base - coding->source; | |
5012 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
5013 | } |
5014 | ||
5015 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
5016 | This function can encode charsets `ascii', `katakana-jisx0201', |
5017 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
5018 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
5019 | (i.e. do not have extended leading-codes). Characters of other |
5020 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
5021 | SJIS text, else encode BIG5 text. */ | |
5022 | ||
df7492f9 KH |
5023 | static int |
5024 | encode_coding_sjis (coding) | |
4ed46869 | 5025 | struct coding_system *coding; |
4ed46869 | 5026 | { |
df7492f9 KH |
5027 | int multibytep = coding->dst_multibyte; |
5028 | int *charbuf = coding->charbuf; | |
5029 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5030 | unsigned char *dst = coding->destination + coding->produced; | |
5031 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5032 | int safe_room = 4; | |
5033 | int produced_chars = 0; | |
24a73b0a | 5034 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
5035 | int ascii_compatible; |
5036 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 5037 | struct charset *charset_kanji2; |
df7492f9 | 5038 | int c; |
a5d301df | 5039 | |
24a73b0a | 5040 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
5041 | val = charset_list; |
5042 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
5043 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
57a47f8a KH |
5044 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
5045 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 5046 | |
df7492f9 | 5047 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 5048 | |
df7492f9 KH |
5049 | while (charbuf < charbuf_end) |
5050 | { | |
5051 | ASSURE_DESTINATION (safe_room); | |
5052 | c = *charbuf++; | |
b73bfc1c | 5053 | /* Now encode the character C. */ |
df7492f9 KH |
5054 | if (ASCII_CHAR_P (c) && ascii_compatible) |
5055 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
5056 | else if (CHAR_BYTE8_P (c)) |
5057 | { | |
5058 | c = CHAR_TO_BYTE8 (c); | |
5059 | EMIT_ONE_BYTE (c); | |
5060 | } | |
df7492f9 | 5061 | else |
b73bfc1c | 5062 | { |
df7492f9 KH |
5063 | unsigned code; |
5064 | struct charset *charset = char_charset (c, charset_list, &code); | |
5065 | ||
5066 | if (!charset) | |
4ed46869 | 5067 | { |
41cbe562 | 5068 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 5069 | { |
41cbe562 KH |
5070 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
5071 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 5072 | } |
41cbe562 | 5073 | else |
b73bfc1c | 5074 | { |
41cbe562 KH |
5075 | c = coding->default_char; |
5076 | charset = char_charset (c, charset_list, &code); | |
b73bfc1c | 5077 | } |
b73bfc1c | 5078 | } |
df7492f9 KH |
5079 | if (code == CHARSET_INVALID_CODE (charset)) |
5080 | abort (); | |
5081 | if (charset == charset_kanji) | |
5082 | { | |
5083 | int c1, c2; | |
5084 | JIS_TO_SJIS (code); | |
5085 | c1 = code >> 8, c2 = code & 0xFF; | |
5086 | EMIT_TWO_BYTES (c1, c2); | |
5087 | } | |
5088 | else if (charset == charset_kana) | |
5089 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
5090 | else if (charset_kanji2 && charset == charset_kanji2) |
5091 | { | |
5092 | int c1, c2; | |
5093 | ||
5094 | c1 = code >> 8; | |
f07190ca KH |
5095 | if (c1 == 0x21 || (c1 >= 0x23 && c1 <= 0x25) |
5096 | || c1 == 0x28 | |
57a47f8a KH |
5097 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) |
5098 | { | |
5099 | JIS_TO_SJIS2 (code); | |
5100 | c1 = code >> 8, c2 = code & 0xFF; | |
5101 | EMIT_TWO_BYTES (c1, c2); | |
5102 | } | |
5103 | else | |
5104 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
5105 | } | |
df7492f9 KH |
5106 | else |
5107 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
5108 | } | |
5109 | } | |
065e3595 | 5110 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5111 | coding->produced_char += produced_chars; |
5112 | coding->produced = dst - coding->destination; | |
5113 | return 0; | |
5114 | } | |
5115 | ||
5116 | static int | |
5117 | encode_coding_big5 (coding) | |
5118 | struct coding_system *coding; | |
5119 | { | |
5120 | int multibytep = coding->dst_multibyte; | |
5121 | int *charbuf = coding->charbuf; | |
5122 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5123 | unsigned char *dst = coding->destination + coding->produced; | |
5124 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5125 | int safe_room = 4; | |
5126 | int produced_chars = 0; | |
24a73b0a | 5127 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
5128 | int ascii_compatible; |
5129 | struct charset *charset_roman, *charset_big5; | |
5130 | int c; | |
5131 | ||
24a73b0a | 5132 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
5133 | val = charset_list; |
5134 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
5135 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
5136 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
5137 | ||
5138 | while (charbuf < charbuf_end) | |
5139 | { | |
5140 | ASSURE_DESTINATION (safe_room); | |
5141 | c = *charbuf++; | |
5142 | /* Now encode the character C. */ | |
5143 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
5144 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
5145 | else if (CHAR_BYTE8_P (c)) |
5146 | { | |
5147 | c = CHAR_TO_BYTE8 (c); | |
5148 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
5149 | } |
5150 | else | |
5151 | { | |
df7492f9 KH |
5152 | unsigned code; |
5153 | struct charset *charset = char_charset (c, charset_list, &code); | |
5154 | ||
5155 | if (! charset) | |
b73bfc1c | 5156 | { |
41cbe562 | 5157 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 5158 | { |
41cbe562 KH |
5159 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
5160 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 5161 | } |
41cbe562 | 5162 | else |
0eecad43 | 5163 | { |
41cbe562 KH |
5164 | c = coding->default_char; |
5165 | charset = char_charset (c, charset_list, &code); | |
0eecad43 | 5166 | } |
4ed46869 | 5167 | } |
df7492f9 KH |
5168 | if (code == CHARSET_INVALID_CODE (charset)) |
5169 | abort (); | |
5170 | if (charset == charset_big5) | |
b73bfc1c | 5171 | { |
df7492f9 KH |
5172 | int c1, c2; |
5173 | ||
5174 | c1 = code >> 8, c2 = code & 0xFF; | |
5175 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 5176 | } |
df7492f9 KH |
5177 | else |
5178 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 5179 | } |
4ed46869 | 5180 | } |
065e3595 | 5181 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5182 | coding->produced_char += produced_chars; |
5183 | coding->produced = dst - coding->destination; | |
5184 | return 0; | |
4ed46869 KH |
5185 | } |
5186 | ||
5187 | \f | |
df7492f9 | 5188 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
5189 | |
5190 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
5191 | Check if a text is encoded in a coding system of which | |
5192 | encoder/decoder are written in CCL program. If it is, return | |
df7492f9 | 5193 | CATEGORY_MASK_CCL, else return 0. */ |
1397dc18 | 5194 | |
0a28aafb | 5195 | static int |
ff0dacd7 | 5196 | detect_coding_ccl (coding, detect_info) |
df7492f9 | 5197 | struct coding_system *coding; |
ff0dacd7 | 5198 | struct coding_detection_info *detect_info; |
1397dc18 | 5199 | { |
065e3595 | 5200 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5201 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
5202 | int multibytep = coding->src_multibyte; |
5203 | int consumed_chars = 0; | |
5204 | int found = 0; | |
0e219d54 | 5205 | unsigned char *valids; |
df7492f9 KH |
5206 | int head_ascii = coding->head_ascii; |
5207 | Lisp_Object attrs; | |
5208 | ||
ff0dacd7 KH |
5209 | detect_info->checked |= CATEGORY_MASK_CCL; |
5210 | ||
df7492f9 | 5211 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 5212 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
5213 | attrs = CODING_ID_ATTRS (coding->id); |
5214 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
5215 | src += head_ascii; | |
1397dc18 | 5216 | |
b73bfc1c | 5217 | while (1) |
1397dc18 | 5218 | { |
df7492f9 | 5219 | int c; |
065e3595 KH |
5220 | |
5221 | src_base = src; | |
df7492f9 | 5222 | ONE_MORE_BYTE (c); |
065e3595 | 5223 | if (c < 0 || ! valids[c]) |
df7492f9 | 5224 | break; |
ff0dacd7 KH |
5225 | if ((valids[c] > 1)) |
5226 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 5227 | } |
ff0dacd7 | 5228 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
5229 | return 0; |
5230 | ||
5231 | no_more_source: | |
ff0dacd7 KH |
5232 | detect_info->found |= found; |
5233 | return 1; | |
df7492f9 KH |
5234 | } |
5235 | ||
5236 | static void | |
5237 | decode_coding_ccl (coding) | |
5238 | struct coding_system *coding; | |
5239 | { | |
7c78e542 | 5240 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 5241 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
5242 | int *charbuf = coding->charbuf + coding->charbuf_used; |
5243 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
5244 | int consumed_chars = 0; |
5245 | int multibytep = coding->src_multibyte; | |
d0396581 | 5246 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 | 5247 | int source_charbuf[1024]; |
fbdc1721 | 5248 | int source_byteidx[1025]; |
24a73b0a | 5249 | Lisp_Object attrs, charset_list; |
df7492f9 | 5250 | |
24a73b0a | 5251 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5252 | |
d0396581 | 5253 | while (1) |
df7492f9 | 5254 | { |
7c78e542 | 5255 | const unsigned char *p = src; |
df7492f9 KH |
5256 | int i = 0; |
5257 | ||
5258 | if (multibytep) | |
fbdc1721 KH |
5259 | { |
5260 | while (i < 1024 && p < src_end) | |
5261 | { | |
5262 | source_byteidx[i] = p - src; | |
5263 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
5264 | } | |
5265 | source_byteidx[i] = p - src; | |
5266 | } | |
df7492f9 KH |
5267 | else |
5268 | while (i < 1024 && p < src_end) | |
5269 | source_charbuf[i++] = *p++; | |
8f924df7 | 5270 | |
df7492f9 | 5271 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
d0396581 KH |
5272 | ccl->last_block = 1; |
5273 | ccl_driver (ccl, source_charbuf, charbuf, i, charbuf_end - charbuf, | |
5274 | charset_list); | |
5275 | charbuf += ccl->produced; | |
fbdc1721 | 5276 | if (multibytep) |
d0396581 | 5277 | src += source_byteidx[ccl->consumed]; |
df7492f9 | 5278 | else |
d0396581 KH |
5279 | src += ccl->consumed; |
5280 | consumed_chars += ccl->consumed; | |
5281 | if (p == src_end || ccl->status != CCL_STAT_SUSPEND_BY_SRC) | |
df7492f9 KH |
5282 | break; |
5283 | } | |
5284 | ||
d0396581 | 5285 | switch (ccl->status) |
df7492f9 KH |
5286 | { |
5287 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5288 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5289 | break; |
5290 | case CCL_STAT_SUSPEND_BY_DST: | |
d0396581 | 5291 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5292 | break; |
5293 | case CCL_STAT_QUIT: | |
5294 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5295 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5296 | break; |
5297 | default: | |
065e3595 | 5298 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5299 | break; |
5300 | } | |
5301 | coding->consumed_char += consumed_chars; | |
5302 | coding->consumed = src - coding->source; | |
5303 | coding->charbuf_used = charbuf - coding->charbuf; | |
5304 | } | |
5305 | ||
5306 | static int | |
5307 | encode_coding_ccl (coding) | |
5308 | struct coding_system *coding; | |
5309 | { | |
fb608df3 | 5310 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 KH |
5311 | int multibytep = coding->dst_multibyte; |
5312 | int *charbuf = coding->charbuf; | |
5313 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5314 | unsigned char *dst = coding->destination + coding->produced; | |
5315 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
df7492f9 KH |
5316 | int destination_charbuf[1024]; |
5317 | int i, produced_chars = 0; | |
24a73b0a | 5318 | Lisp_Object attrs, charset_list; |
df7492f9 | 5319 | |
24a73b0a | 5320 | CODING_GET_INFO (coding, attrs, charset_list); |
fb608df3 KH |
5321 | if (coding->consumed_char == coding->src_chars |
5322 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
5323 | ccl->last_block = 1; | |
df7492f9 | 5324 | |
8cffd3e7 | 5325 | while (charbuf < charbuf_end) |
df7492f9 | 5326 | { |
fb608df3 | 5327 | ccl_driver (ccl, charbuf, destination_charbuf, |
8cffd3e7 | 5328 | charbuf_end - charbuf, 1024, charset_list); |
df7492f9 | 5329 | if (multibytep) |
8cffd3e7 | 5330 | { |
fb608df3 KH |
5331 | ASSURE_DESTINATION (ccl->produced * 2); |
5332 | for (i = 0; i < ccl->produced; i++) | |
8cffd3e7 KH |
5333 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); |
5334 | } | |
df7492f9 KH |
5335 | else |
5336 | { | |
fb608df3 KH |
5337 | ASSURE_DESTINATION (ccl->produced); |
5338 | for (i = 0; i < ccl->produced; i++) | |
df7492f9 | 5339 | *dst++ = destination_charbuf[i] & 0xFF; |
fb608df3 | 5340 | produced_chars += ccl->produced; |
df7492f9 | 5341 | } |
fb608df3 KH |
5342 | charbuf += ccl->consumed; |
5343 | if (ccl->status == CCL_STAT_QUIT | |
5344 | || ccl->status == CCL_STAT_INVALID_CMD) | |
8cffd3e7 | 5345 | break; |
df7492f9 KH |
5346 | } |
5347 | ||
fb608df3 | 5348 | switch (ccl->status) |
df7492f9 KH |
5349 | { |
5350 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5351 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5352 | break; |
5353 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 5354 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5355 | break; |
5356 | case CCL_STAT_QUIT: | |
5357 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5358 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5359 | break; |
5360 | default: | |
065e3595 | 5361 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 5362 | break; |
1397dc18 | 5363 | } |
df7492f9 KH |
5364 | |
5365 | coding->produced_char += produced_chars; | |
5366 | coding->produced = dst - coding->destination; | |
5367 | return 0; | |
1397dc18 KH |
5368 | } |
5369 | ||
df7492f9 | 5370 | |
1397dc18 | 5371 | \f |
df7492f9 | 5372 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 5373 | |
b73bfc1c | 5374 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 5375 | |
b73bfc1c | 5376 | static void |
df7492f9 | 5377 | decode_coding_raw_text (coding) |
4ed46869 | 5378 | struct coding_system *coding; |
4ed46869 | 5379 | { |
0a9564cb EZ |
5380 | int eol_crlf = |
5381 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5382 | |
df7492f9 | 5383 | coding->chars_at_source = 1; |
119852e7 KH |
5384 | coding->consumed_char = coding->src_chars; |
5385 | coding->consumed = coding->src_bytes; | |
5386 | if (eol_crlf && coding->source[coding->src_bytes - 1] == '\r') | |
5387 | { | |
5388 | coding->consumed_char--; | |
5389 | coding->consumed--; | |
5390 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
5391 | } | |
5392 | else | |
5393 | record_conversion_result (coding, CODING_RESULT_SUCCESS); | |
df7492f9 | 5394 | } |
4ed46869 | 5395 | |
df7492f9 KH |
5396 | static int |
5397 | encode_coding_raw_text (coding) | |
5398 | struct coding_system *coding; | |
5399 | { | |
5400 | int multibytep = coding->dst_multibyte; | |
5401 | int *charbuf = coding->charbuf; | |
5402 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
5403 | unsigned char *dst = coding->destination + coding->produced; | |
5404 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
a0ed9b27 | 5405 | int produced_chars = 0; |
b73bfc1c KH |
5406 | int c; |
5407 | ||
df7492f9 | 5408 | if (multibytep) |
b73bfc1c | 5409 | { |
df7492f9 | 5410 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 5411 | |
df7492f9 KH |
5412 | if (coding->src_multibyte) |
5413 | while (charbuf < charbuf_end) | |
5414 | { | |
5415 | ASSURE_DESTINATION (safe_room); | |
5416 | c = *charbuf++; | |
5417 | if (ASCII_CHAR_P (c)) | |
5418 | EMIT_ONE_ASCII_BYTE (c); | |
5419 | else if (CHAR_BYTE8_P (c)) | |
5420 | { | |
5421 | c = CHAR_TO_BYTE8 (c); | |
5422 | EMIT_ONE_BYTE (c); | |
5423 | } | |
5424 | else | |
5425 | { | |
5426 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 5427 | |
df7492f9 KH |
5428 | CHAR_STRING_ADVANCE (c, p1); |
5429 | while (p0 < p1) | |
9d123124 KH |
5430 | { |
5431 | EMIT_ONE_BYTE (*p0); | |
5432 | p0++; | |
5433 | } | |
df7492f9 KH |
5434 | } |
5435 | } | |
b73bfc1c | 5436 | else |
df7492f9 KH |
5437 | while (charbuf < charbuf_end) |
5438 | { | |
5439 | ASSURE_DESTINATION (safe_room); | |
5440 | c = *charbuf++; | |
5441 | EMIT_ONE_BYTE (c); | |
5442 | } | |
5443 | } | |
5444 | else | |
4ed46869 | 5445 | { |
df7492f9 | 5446 | if (coding->src_multibyte) |
d46c5b12 | 5447 | { |
df7492f9 KH |
5448 | int safe_room = MAX_MULTIBYTE_LENGTH; |
5449 | ||
5450 | while (charbuf < charbuf_end) | |
d46c5b12 | 5451 | { |
df7492f9 KH |
5452 | ASSURE_DESTINATION (safe_room); |
5453 | c = *charbuf++; | |
5454 | if (ASCII_CHAR_P (c)) | |
5455 | *dst++ = c; | |
5456 | else if (CHAR_BYTE8_P (c)) | |
5457 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 5458 | else |
df7492f9 | 5459 | CHAR_STRING_ADVANCE (c, dst); |
d46c5b12 KH |
5460 | } |
5461 | } | |
df7492f9 KH |
5462 | else |
5463 | { | |
5464 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
5465 | while (charbuf < charbuf_end && dst < dst_end) | |
5466 | *dst++ = *charbuf++; | |
8f924df7 | 5467 | } |
319a3947 | 5468 | produced_chars = dst - (coding->destination + coding->produced); |
4ed46869 | 5469 | } |
065e3595 | 5470 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
a0ed9b27 | 5471 | coding->produced_char += produced_chars; |
df7492f9 KH |
5472 | coding->produced = dst - coding->destination; |
5473 | return 0; | |
4ed46869 KH |
5474 | } |
5475 | ||
ff0dacd7 KH |
5476 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
5477 | Check if a text is encoded in a charset-based coding system. If it | |
5478 | is, return 1, else return 0. */ | |
5479 | ||
0a28aafb | 5480 | static int |
ff0dacd7 | 5481 | detect_coding_charset (coding, detect_info) |
df7492f9 | 5482 | struct coding_system *coding; |
ff0dacd7 | 5483 | struct coding_detection_info *detect_info; |
1397dc18 | 5484 | { |
065e3595 | 5485 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5486 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
5487 | int multibytep = coding->src_multibyte; |
5488 | int consumed_chars = 0; | |
07295713 | 5489 | Lisp_Object attrs, valids, name; |
584948ac | 5490 | int found = 0; |
716b3fa0 | 5491 | int head_ascii = coding->head_ascii; |
07295713 | 5492 | int check_latin_extra = 0; |
1397dc18 | 5493 | |
ff0dacd7 KH |
5494 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
5495 | ||
df7492f9 KH |
5496 | coding = &coding_categories[coding_category_charset]; |
5497 | attrs = CODING_ID_ATTRS (coding->id); | |
5498 | valids = AREF (attrs, coding_attr_charset_valids); | |
07295713 | 5499 | name = CODING_ID_NAME (coding->id); |
237aabf4 JR |
5500 | if (strncmp ((char *) SDATA (SYMBOL_NAME (name)), |
5501 | "iso-8859-", sizeof ("iso-8859-") - 1) == 0 | |
5502 | || strncmp ((char *) SDATA (SYMBOL_NAME (name)), | |
5503 | "iso-latin-", sizeof ("iso-latin-") - 1) == 0) | |
07295713 | 5504 | check_latin_extra = 1; |
237aabf4 | 5505 | |
df7492f9 | 5506 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
716b3fa0 | 5507 | src += head_ascii; |
1397dc18 | 5508 | |
b73bfc1c | 5509 | while (1) |
1397dc18 | 5510 | { |
df7492f9 | 5511 | int c; |
716b3fa0 KH |
5512 | Lisp_Object val; |
5513 | struct charset *charset; | |
5514 | int dim, idx; | |
1397dc18 | 5515 | |
065e3595 | 5516 | src_base = src; |
df7492f9 | 5517 | ONE_MORE_BYTE (c); |
065e3595 KH |
5518 | if (c < 0) |
5519 | continue; | |
716b3fa0 KH |
5520 | val = AREF (valids, c); |
5521 | if (NILP (val)) | |
df7492f9 | 5522 | break; |
584948ac | 5523 | if (c >= 0x80) |
07295713 KH |
5524 | { |
5525 | if (c < 0xA0 | |
237aabf4 JR |
5526 | && check_latin_extra |
5527 | && (!VECTORP (Vlatin_extra_code_table) | |
9f0526cb | 5528 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c]))) |
07295713 KH |
5529 | break; |
5530 | found = CATEGORY_MASK_CHARSET; | |
5531 | } | |
716b3fa0 KH |
5532 | if (INTEGERP (val)) |
5533 | { | |
5534 | charset = CHARSET_FROM_ID (XFASTINT (val)); | |
5535 | dim = CHARSET_DIMENSION (charset); | |
5536 | for (idx = 1; idx < dim; idx++) | |
5537 | { | |
5538 | if (src == src_end) | |
5539 | goto too_short; | |
5540 | ONE_MORE_BYTE (c); | |
3ed051d4 | 5541 | if (c < charset->code_space[(dim - 1 - idx) * 2] |
716b3fa0 KH |
5542 | || c > charset->code_space[(dim - 1 - idx) * 2 + 1]) |
5543 | break; | |
5544 | } | |
5545 | if (idx < dim) | |
5546 | break; | |
5547 | } | |
5548 | else | |
5549 | { | |
5550 | idx = 1; | |
5551 | for (; CONSP (val); val = XCDR (val)) | |
5552 | { | |
5553 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); | |
5554 | dim = CHARSET_DIMENSION (charset); | |
5555 | while (idx < dim) | |
5556 | { | |
5557 | if (src == src_end) | |
5558 | goto too_short; | |
5559 | ONE_MORE_BYTE (c); | |
5560 | if (c < charset->code_space[(dim - 1 - idx) * 4] | |
5561 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
5562 | break; | |
5563 | idx++; | |
5564 | } | |
5565 | if (idx == dim) | |
5566 | { | |
5567 | val = Qnil; | |
5568 | break; | |
5569 | } | |
5570 | } | |
5571 | if (CONSP (val)) | |
5572 | break; | |
5573 | } | |
df7492f9 | 5574 | } |
716b3fa0 | 5575 | too_short: |
ff0dacd7 | 5576 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 5577 | return 0; |
4ed46869 | 5578 | |
df7492f9 | 5579 | no_more_source: |
ff0dacd7 KH |
5580 | detect_info->found |= found; |
5581 | return 1; | |
df7492f9 | 5582 | } |
b73bfc1c | 5583 | |
b73bfc1c | 5584 | static void |
df7492f9 | 5585 | decode_coding_charset (coding) |
4ed46869 | 5586 | struct coding_system *coding; |
4ed46869 | 5587 | { |
8f924df7 KH |
5588 | const unsigned char *src = coding->source + coding->consumed; |
5589 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
5590 | const unsigned char *src_base; | |
69a80ea3 | 5591 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
5592 | /* We may produce one charset annocation in one loop and one more at |
5593 | the end. */ | |
69a80ea3 | 5594 | int *charbuf_end |
df80c7f0 | 5595 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
5596 | int consumed_chars = 0, consumed_chars_base; |
5597 | int multibytep = coding->src_multibyte; | |
24a73b0a | 5598 | Lisp_Object attrs, charset_list, valids; |
ff0dacd7 KH |
5599 | int char_offset = coding->produced_char; |
5600 | int last_offset = char_offset; | |
5601 | int last_id = charset_ascii; | |
0a9564cb EZ |
5602 | int eol_crlf = |
5603 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5604 | int byte_after_cr = -1; |
df7492f9 | 5605 | |
24a73b0a | 5606 | CODING_GET_INFO (coding, attrs, charset_list); |
4eb6d3f1 | 5607 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 5608 | |
df7492f9 | 5609 | while (1) |
4ed46869 | 5610 | { |
4eb6d3f1 | 5611 | int c; |
24a73b0a KH |
5612 | Lisp_Object val; |
5613 | struct charset *charset; | |
5614 | int dim; | |
5615 | int len = 1; | |
5616 | unsigned code; | |
df7492f9 KH |
5617 | |
5618 | src_base = src; | |
5619 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 5620 | |
df7492f9 | 5621 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
5622 | { |
5623 | if (byte_after_cr >= 0) | |
5624 | src_base--; | |
5625 | break; | |
5626 | } | |
df7492f9 | 5627 | |
119852e7 KH |
5628 | if (byte_after_cr >= 0) |
5629 | { | |
5630 | c = byte_after_cr; | |
5631 | byte_after_cr = -1; | |
5632 | } | |
5633 | else | |
5634 | { | |
5635 | ONE_MORE_BYTE (c); | |
5636 | if (eol_crlf && c == '\r') | |
5637 | ONE_MORE_BYTE (byte_after_cr); | |
5638 | } | |
065e3595 KH |
5639 | if (c < 0) |
5640 | goto invalid_code; | |
24a73b0a KH |
5641 | code = c; |
5642 | ||
5643 | val = AREF (valids, c); | |
1b17adfd | 5644 | if (! INTEGERP (val) && ! CONSP (val)) |
24a73b0a KH |
5645 | goto invalid_code; |
5646 | if (INTEGERP (val)) | |
d46c5b12 | 5647 | { |
24a73b0a KH |
5648 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
5649 | dim = CHARSET_DIMENSION (charset); | |
5650 | while (len < dim) | |
b73bfc1c | 5651 | { |
24a73b0a KH |
5652 | ONE_MORE_BYTE (c); |
5653 | code = (code << 8) | c; | |
5654 | len++; | |
b73bfc1c | 5655 | } |
24a73b0a KH |
5656 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
5657 | charset, code, c); | |
d46c5b12 | 5658 | } |
df7492f9 | 5659 | else |
d46c5b12 | 5660 | { |
24a73b0a KH |
5661 | /* VAL is a list of charset IDs. It is assured that the |
5662 | list is sorted by charset dimensions (smaller one | |
5663 | comes first). */ | |
5664 | while (CONSP (val)) | |
4eb6d3f1 | 5665 | { |
24a73b0a | 5666 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 5667 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 5668 | while (len < dim) |
4eb6d3f1 | 5669 | { |
acb2a965 KH |
5670 | ONE_MORE_BYTE (c); |
5671 | code = (code << 8) | c; | |
f9d71dcd | 5672 | len++; |
4eb6d3f1 | 5673 | } |
24a73b0a KH |
5674 | CODING_DECODE_CHAR (coding, src, src_base, |
5675 | src_end, charset, code, c); | |
5676 | if (c >= 0) | |
5677 | break; | |
5678 | val = XCDR (val); | |
ff0dacd7 | 5679 | } |
d46c5b12 | 5680 | } |
24a73b0a KH |
5681 | if (c < 0) |
5682 | goto invalid_code; | |
5683 | if (charset->id != charset_ascii | |
5684 | && last_id != charset->id) | |
5685 | { | |
5686 | if (last_id != charset_ascii) | |
69a80ea3 | 5687 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
5688 | last_id = charset->id; |
5689 | last_offset = char_offset; | |
5690 | } | |
5691 | ||
df7492f9 | 5692 | *charbuf++ = c; |
ff0dacd7 | 5693 | char_offset++; |
df7492f9 KH |
5694 | continue; |
5695 | ||
5696 | invalid_code: | |
5697 | src = src_base; | |
5698 | consumed_chars = consumed_chars_base; | |
5699 | ONE_MORE_BYTE (c); | |
065e3595 | 5700 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 5701 | char_offset++; |
df7492f9 | 5702 | coding->errors++; |
4ed46869 KH |
5703 | } |
5704 | ||
df7492f9 | 5705 | no_more_source: |
ff0dacd7 | 5706 | if (last_id != charset_ascii) |
69a80ea3 | 5707 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
5708 | coding->consumed_char += consumed_chars_base; |
5709 | coding->consumed = src_base - coding->source; | |
5710 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
5711 | } |
5712 | ||
df7492f9 KH |
5713 | static int |
5714 | encode_coding_charset (coding) | |
4ed46869 | 5715 | struct coding_system *coding; |
4ed46869 | 5716 | { |
df7492f9 KH |
5717 | int multibytep = coding->dst_multibyte; |
5718 | int *charbuf = coding->charbuf; | |
5719 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5720 | unsigned char *dst = coding->destination + coding->produced; | |
5721 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5722 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
5723 | int produced_chars = 0; | |
24a73b0a | 5724 | Lisp_Object attrs, charset_list; |
df7492f9 | 5725 | int ascii_compatible; |
b73bfc1c | 5726 | int c; |
b73bfc1c | 5727 | |
24a73b0a | 5728 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5729 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 5730 | |
df7492f9 | 5731 | while (charbuf < charbuf_end) |
4ed46869 | 5732 | { |
4eb6d3f1 | 5733 | struct charset *charset; |
df7492f9 | 5734 | unsigned code; |
8f924df7 | 5735 | |
df7492f9 KH |
5736 | ASSURE_DESTINATION (safe_room); |
5737 | c = *charbuf++; | |
5738 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
5739 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 5740 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 5741 | { |
16eafb5d KH |
5742 | c = CHAR_TO_BYTE8 (c); |
5743 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 5744 | } |
d46c5b12 | 5745 | else |
b73bfc1c | 5746 | { |
4eb6d3f1 KH |
5747 | charset = char_charset (c, charset_list, &code); |
5748 | if (charset) | |
5749 | { | |
5750 | if (CHARSET_DIMENSION (charset) == 1) | |
5751 | EMIT_ONE_BYTE (code); | |
5752 | else if (CHARSET_DIMENSION (charset) == 2) | |
5753 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
5754 | else if (CHARSET_DIMENSION (charset) == 3) | |
5755 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
5756 | else | |
5757 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
5758 | (code >> 8) & 0xFF, code & 0xFF); | |
5759 | } | |
5760 | else | |
41cbe562 KH |
5761 | { |
5762 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
5763 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
5764 | else | |
5765 | c = coding->default_char; | |
5766 | EMIT_ONE_BYTE (c); | |
5767 | } | |
4ed46869 | 5768 | } |
4ed46869 KH |
5769 | } |
5770 | ||
065e3595 | 5771 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5772 | coding->produced_char += produced_chars; |
5773 | coding->produced = dst - coding->destination; | |
5774 | return 0; | |
4ed46869 KH |
5775 | } |
5776 | ||
5777 | \f | |
1397dc18 | 5778 | /*** 7. C library functions ***/ |
4ed46869 | 5779 | |
df7492f9 KH |
5780 | /* Setup coding context CODING from information about CODING_SYSTEM. |
5781 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
5782 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 5783 | |
ec6d2bb8 | 5784 | void |
e0e989f6 KH |
5785 | setup_coding_system (coding_system, coding) |
5786 | Lisp_Object coding_system; | |
4ed46869 KH |
5787 | struct coding_system *coding; |
5788 | { | |
df7492f9 KH |
5789 | Lisp_Object attrs; |
5790 | Lisp_Object eol_type; | |
5791 | Lisp_Object coding_type; | |
4608c386 | 5792 | Lisp_Object val; |
4ed46869 | 5793 | |
df7492f9 | 5794 | if (NILP (coding_system)) |
ae6f73fa | 5795 | coding_system = Qundecided; |
c07c8e12 | 5796 | |
df7492f9 | 5797 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 5798 | |
df7492f9 | 5799 | attrs = CODING_ID_ATTRS (coding->id); |
0a9564cb | 5800 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
1f5dbf34 | 5801 | |
df7492f9 KH |
5802 | coding->mode = 0; |
5803 | coding->head_ascii = -1; | |
4a015c45 KH |
5804 | if (VECTORP (eol_type)) |
5805 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5806 | | CODING_REQUIRE_DETECTION_MASK); | |
5807 | else if (! EQ (eol_type, Qunix)) | |
5808 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5809 | | CODING_REQUIRE_ENCODING_MASK); | |
5810 | else | |
5811 | coding->common_flags = 0; | |
5e5c78be KH |
5812 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
5813 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5814 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
5815 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
5816 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
5817 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 5818 | |
df7492f9 | 5819 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 | 5820 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5821 | coding->safe_charsets = SDATA (val); |
df7492f9 | 5822 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
624bda09 | 5823 | coding->carryover_bytes = 0; |
4608c386 | 5824 | |
df7492f9 KH |
5825 | coding_type = CODING_ATTR_TYPE (attrs); |
5826 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 5827 | { |
df7492f9 KH |
5828 | coding->detector = NULL; |
5829 | coding->decoder = decode_coding_raw_text; | |
5830 | coding->encoder = encode_coding_raw_text; | |
5831 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5832 | } |
df7492f9 | 5833 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 5834 | { |
df7492f9 KH |
5835 | int i; |
5836 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5837 | ||
5838 | /* Invoke graphic register 0 to plane 0. */ | |
5839 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
5840 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
5841 | CODING_ISO_INVOCATION (coding, 1) | |
5842 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
5843 | /* Setup the initial status of designation. */ | |
5844 | for (i = 0; i < 4; i++) | |
5845 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
5846 | /* Not single shifting initially. */ | |
5847 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
5848 | /* Beginning of buffer should also be regarded as bol. */ | |
5849 | CODING_ISO_BOL (coding) = 1; | |
5850 | coding->detector = detect_coding_iso_2022; | |
5851 | coding->decoder = decode_coding_iso_2022; | |
5852 | coding->encoder = encode_coding_iso_2022; | |
5853 | if (flags & CODING_ISO_FLAG_SAFE) | |
5854 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 5855 | coding->common_flags |
df7492f9 KH |
5856 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5857 | | CODING_REQUIRE_FLUSHING_MASK); | |
5858 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
5859 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
5860 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
5861 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
5862 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
5863 | { | |
5864 | setup_iso_safe_charsets (attrs); | |
5865 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 5866 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5867 | coding->safe_charsets = SDATA (val); |
df7492f9 KH |
5868 | } |
5869 | CODING_ISO_FLAGS (coding) = flags; | |
e951386e KH |
5870 | CODING_ISO_CMP_STATUS (coding)->state = COMPOSING_NO; |
5871 | CODING_ISO_CMP_STATUS (coding)->method = COMPOSITION_NO; | |
5872 | CODING_ISO_EXTSEGMENT_LEN (coding) = 0; | |
5873 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
d46c5b12 | 5874 | } |
df7492f9 | 5875 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 5876 | { |
df7492f9 KH |
5877 | coding->detector = detect_coding_charset; |
5878 | coding->decoder = decode_coding_charset; | |
5879 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5880 | coding->common_flags |
df7492f9 | 5881 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5882 | } |
df7492f9 | 5883 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5884 | { |
a470d443 KH |
5885 | val = AREF (attrs, coding_attr_utf_bom); |
5886 | CODING_UTF_8_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5887 | : EQ (val, Qt) ? utf_with_bom | |
5888 | : utf_without_bom); | |
df7492f9 KH |
5889 | coding->detector = detect_coding_utf_8; |
5890 | coding->decoder = decode_coding_utf_8; | |
5891 | coding->encoder = encode_coding_utf_8; | |
5892 | coding->common_flags | |
5893 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 KH |
5894 | if (CODING_UTF_8_BOM (coding) == utf_detect_bom) |
5895 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
df7492f9 KH |
5896 | } |
5897 | else if (EQ (coding_type, Qutf_16)) | |
5898 | { | |
a470d443 KH |
5899 | val = AREF (attrs, coding_attr_utf_bom); |
5900 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5901 | : EQ (val, Qt) ? utf_with_bom | |
5902 | : utf_without_bom); | |
df7492f9 | 5903 | val = AREF (attrs, coding_attr_utf_16_endian); |
b49a1807 | 5904 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5905 | : utf_16_little_endian); |
e19c3639 | 5906 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5907 | coding->detector = detect_coding_utf_16; |
5908 | coding->decoder = decode_coding_utf_16; | |
5909 | coding->encoder = encode_coding_utf_16; | |
5910 | coding->common_flags | |
5911 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 | 5912 | if (CODING_UTF_16_BOM (coding) == utf_detect_bom) |
b49a1807 | 5913 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; |
d46c5b12 | 5914 | } |
df7492f9 | 5915 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5916 | { |
df7492f9 KH |
5917 | coding->detector = detect_coding_ccl; |
5918 | coding->decoder = decode_coding_ccl; | |
5919 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5920 | coding->common_flags |
df7492f9 KH |
5921 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5922 | | CODING_REQUIRE_FLUSHING_MASK); | |
5923 | } | |
5924 | else if (EQ (coding_type, Qemacs_mule)) | |
5925 | { | |
5926 | coding->detector = detect_coding_emacs_mule; | |
5927 | coding->decoder = decode_coding_emacs_mule; | |
5928 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5929 | coding->common_flags |
df7492f9 | 5930 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
e951386e | 5931 | coding->spec.emacs_mule.full_support = 1; |
df7492f9 KH |
5932 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) |
5933 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5934 | { | |
5935 | Lisp_Object tail, safe_charsets; | |
5936 | int max_charset_id = 0; | |
5937 | ||
5938 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5939 | tail = XCDR (tail)) | |
5940 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5941 | max_charset_id = XFASTINT (XCAR (tail)); | |
1b3b981b AS |
5942 | safe_charsets = make_uninit_string (max_charset_id + 1); |
5943 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
5944 | for (tail = Vemacs_mule_charset_list; CONSP (tail); |
5945 | tail = XCDR (tail)) | |
8f924df7 | 5946 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5947 | coding->max_charset_id = max_charset_id; |
1b3b981b | 5948 | coding->safe_charsets = SDATA (safe_charsets); |
e951386e | 5949 | coding->spec.emacs_mule.full_support = 1; |
df7492f9 | 5950 | } |
e951386e KH |
5951 | coding->spec.emacs_mule.cmp_status.state = COMPOSING_NO; |
5952 | coding->spec.emacs_mule.cmp_status.method = COMPOSITION_NO; | |
df7492f9 KH |
5953 | } |
5954 | else if (EQ (coding_type, Qshift_jis)) | |
5955 | { | |
5956 | coding->detector = detect_coding_sjis; | |
5957 | coding->decoder = decode_coding_sjis; | |
5958 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5959 | coding->common_flags |
df7492f9 KH |
5960 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5961 | } | |
5962 | else if (EQ (coding_type, Qbig5)) | |
5963 | { | |
5964 | coding->detector = detect_coding_big5; | |
5965 | coding->decoder = decode_coding_big5; | |
5966 | coding->encoder = encode_coding_big5; | |
c952af22 | 5967 | coding->common_flags |
df7492f9 KH |
5968 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5969 | } | |
5970 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5971 | { |
df7492f9 KH |
5972 | coding->detector = NULL; |
5973 | coding->decoder = decode_coding_raw_text; | |
5974 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5975 | if (! EQ (eol_type, Qunix)) |
5976 | { | |
5977 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5978 | if (! VECTORP (eol_type)) | |
5979 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5980 | } | |
5981 | ||
4ed46869 | 5982 | } |
4ed46869 | 5983 | |
df7492f9 | 5984 | return; |
4ed46869 KH |
5985 | } |
5986 | ||
0ff61e78 KH |
5987 | /* Return a list of charsets supported by CODING. */ |
5988 | ||
5989 | Lisp_Object | |
5990 | coding_charset_list (coding) | |
5991 | struct coding_system *coding; | |
5992 | { | |
35befdaa | 5993 | Lisp_Object attrs, charset_list; |
0ff61e78 KH |
5994 | |
5995 | CODING_GET_INFO (coding, attrs, charset_list); | |
5996 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5997 | { | |
5998 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5999 | ||
6000 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
6001 | charset_list = Viso_2022_charset_list; | |
6002 | } | |
6003 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
6004 | { | |
6005 | charset_list = Vemacs_mule_charset_list; | |
6006 | } | |
6007 | return charset_list; | |
6008 | } | |
6009 | ||
6010 | ||
e9f91ece KH |
6011 | /* Return a list of charsets supported by CODING-SYSTEM. */ |
6012 | ||
6013 | Lisp_Object | |
6014 | coding_system_charset_list (coding_system) | |
6015 | Lisp_Object coding_system; | |
6016 | { | |
6017 | int id; | |
6018 | Lisp_Object attrs, charset_list; | |
6019 | ||
6020 | CHECK_CODING_SYSTEM_GET_ID (coding_system, id); | |
6021 | attrs = CODING_ID_ATTRS (id); | |
6022 | ||
6023 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
6024 | { | |
6025 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
6026 | ||
6027 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
6028 | charset_list = Viso_2022_charset_list; | |
6029 | else | |
6030 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
6031 | } | |
6032 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
6033 | { | |
6034 | charset_list = Vemacs_mule_charset_list; | |
6035 | } | |
6036 | else | |
6037 | { | |
6038 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
6039 | } | |
6040 | return charset_list; | |
6041 | } | |
6042 | ||
6043 | ||
df7492f9 KH |
6044 | /* Return raw-text or one of its subsidiaries that has the same |
6045 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 6046 | |
df7492f9 KH |
6047 | Lisp_Object |
6048 | raw_text_coding_system (coding_system) | |
6049 | Lisp_Object coding_system; | |
ec6d2bb8 | 6050 | { |
0be8721c | 6051 | Lisp_Object spec, attrs; |
df7492f9 | 6052 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 6053 | |
d3e4cb56 KH |
6054 | if (NILP (coding_system)) |
6055 | return Qraw_text; | |
df7492f9 KH |
6056 | spec = CODING_SYSTEM_SPEC (coding_system); |
6057 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 6058 | |
df7492f9 KH |
6059 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
6060 | return coding_system; | |
ec6d2bb8 | 6061 | |
df7492f9 KH |
6062 | eol_type = AREF (spec, 2); |
6063 | if (VECTORP (eol_type)) | |
6064 | return Qraw_text; | |
6065 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
6066 | raw_text_eol_type = AREF (spec, 2); | |
6067 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
6068 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
6069 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
6070 | } |
6071 | ||
54f78171 | 6072 | |
df7492f9 KH |
6073 | /* If CODING_SYSTEM doesn't specify end-of-line format but PARENT |
6074 | does, return one of the subsidiary that has the same eol-spec as | |
fcbcfb64 KH |
6075 | PARENT. Otherwise, return CODING_SYSTEM. If PARENT is nil, |
6076 | inherit end-of-line format from the system's setting | |
6077 | (system_eol_type). */ | |
df7492f9 KH |
6078 | |
6079 | Lisp_Object | |
6080 | coding_inherit_eol_type (coding_system, parent) | |
b74e4686 | 6081 | Lisp_Object coding_system, parent; |
54f78171 | 6082 | { |
3e139625 | 6083 | Lisp_Object spec, eol_type; |
54f78171 | 6084 | |
d3e4cb56 KH |
6085 | if (NILP (coding_system)) |
6086 | coding_system = Qraw_text; | |
df7492f9 | 6087 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 6088 | eol_type = AREF (spec, 2); |
fcbcfb64 | 6089 | if (VECTORP (eol_type)) |
df7492f9 | 6090 | { |
df7492f9 KH |
6091 | Lisp_Object parent_eol_type; |
6092 | ||
fcbcfb64 KH |
6093 | if (! NILP (parent)) |
6094 | { | |
6095 | Lisp_Object parent_spec; | |
6096 | ||
4a015c45 | 6097 | parent_spec = CODING_SYSTEM_SPEC (parent); |
fcbcfb64 KH |
6098 | parent_eol_type = AREF (parent_spec, 2); |
6099 | } | |
6100 | else | |
6101 | parent_eol_type = system_eol_type; | |
df7492f9 KH |
6102 | if (EQ (parent_eol_type, Qunix)) |
6103 | coding_system = AREF (eol_type, 0); | |
6104 | else if (EQ (parent_eol_type, Qdos)) | |
6105 | coding_system = AREF (eol_type, 1); | |
6106 | else if (EQ (parent_eol_type, Qmac)) | |
6107 | coding_system = AREF (eol_type, 2); | |
54f78171 | 6108 | } |
df7492f9 | 6109 | return coding_system; |
54f78171 KH |
6110 | } |
6111 | ||
4ed46869 KH |
6112 | /* Emacs has a mechanism to automatically detect a coding system if it |
6113 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
6114 | it's impossible to distinguish some coding systems accurately | |
6115 | because they use the same range of codes. So, at first, coding | |
6116 | systems are categorized into 7, those are: | |
6117 | ||
0ef69138 | 6118 | o coding-category-emacs-mule |
4ed46869 KH |
6119 | |
6120 | The category for a coding system which has the same code range | |
6121 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 6122 | symbol) `emacs-mule' by default. |
4ed46869 KH |
6123 | |
6124 | o coding-category-sjis | |
6125 | ||
6126 | The category for a coding system which has the same code range | |
6127 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 6128 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
6129 | |
6130 | o coding-category-iso-7 | |
6131 | ||
6132 | The category for a coding system which has the same code range | |
7717c392 | 6133 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
6134 | shift and single shift functions. This can encode/decode all |
6135 | charsets. Assigned the coding-system (Lisp symbol) | |
6136 | `iso-2022-7bit' by default. | |
6137 | ||
6138 | o coding-category-iso-7-tight | |
6139 | ||
6140 | Same as coding-category-iso-7 except that this can | |
6141 | encode/decode only the specified charsets. | |
4ed46869 KH |
6142 | |
6143 | o coding-category-iso-8-1 | |
6144 | ||
6145 | The category for a coding system which has the same code range | |
6146 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6147 | for DIMENSION1 charset. This doesn't use any locking shift |
6148 | and single shift functions. Assigned the coding-system (Lisp | |
6149 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
6150 | |
6151 | o coding-category-iso-8-2 | |
6152 | ||
6153 | The category for a coding system which has the same code range | |
6154 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6155 | for DIMENSION2 charset. This doesn't use any locking shift |
6156 | and single shift functions. Assigned the coding-system (Lisp | |
6157 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 6158 | |
7717c392 | 6159 | o coding-category-iso-7-else |
4ed46869 KH |
6160 | |
6161 | The category for a coding system which has the same code range | |
df7492f9 | 6162 | as ISO2022 of 7-bit environemnt but uses locking shift or |
7717c392 KH |
6163 | single shift functions. Assigned the coding-system (Lisp |
6164 | symbol) `iso-2022-7bit-lock' by default. | |
6165 | ||
6166 | o coding-category-iso-8-else | |
6167 | ||
6168 | The category for a coding system which has the same code range | |
df7492f9 | 6169 | as ISO2022 of 8-bit environemnt but uses locking shift or |
7717c392 KH |
6170 | single shift functions. Assigned the coding-system (Lisp |
6171 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
6172 | |
6173 | o coding-category-big5 | |
6174 | ||
6175 | The category for a coding system which has the same code range | |
6176 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6177 | `cn-big5' by default. |
4ed46869 | 6178 | |
fa42c37f KH |
6179 | o coding-category-utf-8 |
6180 | ||
6181 | The category for a coding system which has the same code range | |
6e76ae91 | 6182 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
6183 | symbol) `utf-8' by default. |
6184 | ||
6185 | o coding-category-utf-16-be | |
6186 | ||
6187 | The category for a coding system in which a text has an | |
6188 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
6189 | endian at the head. Assigned the coding-system (Lisp symbol) | |
6190 | `utf-16-be' by default. | |
6191 | ||
6192 | o coding-category-utf-16-le | |
6193 | ||
6194 | The category for a coding system in which a text has an | |
6195 | Unicode signature (cf. Unicode Standard) in the order of | |
6196 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
6197 | symbol) `utf-16-le' by default. | |
6198 | ||
1397dc18 KH |
6199 | o coding-category-ccl |
6200 | ||
6201 | The category for a coding system of which encoder/decoder is | |
6202 | written in CCL programs. The default value is nil, i.e., no | |
6203 | coding system is assigned. | |
6204 | ||
4ed46869 KH |
6205 | o coding-category-binary |
6206 | ||
6207 | The category for a coding system not categorized in any of the | |
6208 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6209 | `no-conversion' by default. |
4ed46869 KH |
6210 | |
6211 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 6212 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
6213 | What Emacs does actually is to detect a category of coding system. |
6214 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 6215 | decide only one possible category, it selects a category of the |
4ed46869 KH |
6216 | highest priority. Priorities of categories are also specified by a |
6217 | user in a Lisp variable `coding-category-list'. | |
6218 | ||
6219 | */ | |
6220 | ||
df7492f9 KH |
6221 | #define EOL_SEEN_NONE 0 |
6222 | #define EOL_SEEN_LF 1 | |
6223 | #define EOL_SEEN_CR 2 | |
6224 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 6225 | |
ff0dacd7 KH |
6226 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
6227 | SOURCE is encoded. If CATEGORY is one of | |
6228 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
6229 | two-byte, else they are encoded by one-byte. | |
6230 | ||
6231 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 6232 | |
bc4bc72a | 6233 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
6234 | |
6235 | static int | |
89528eb3 | 6236 | detect_eol (source, src_bytes, category) |
f6cbaf43 | 6237 | const unsigned char *source; |
df7492f9 | 6238 | EMACS_INT src_bytes; |
89528eb3 | 6239 | enum coding_category category; |
4ed46869 | 6240 | { |
f6cbaf43 | 6241 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 6242 | unsigned char c; |
df7492f9 KH |
6243 | int total = 0; |
6244 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 6245 | |
89528eb3 | 6246 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 6247 | { |
df7492f9 | 6248 | int msb, lsb; |
fa42c37f | 6249 | |
89528eb3 KH |
6250 | msb = category == (coding_category_utf_16_le |
6251 | | coding_category_utf_16_le_nosig); | |
df7492f9 | 6252 | lsb = 1 - msb; |
fa42c37f | 6253 | |
df7492f9 | 6254 | while (src + 1 < src_end) |
fa42c37f | 6255 | { |
df7492f9 KH |
6256 | c = src[lsb]; |
6257 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 6258 | { |
df7492f9 KH |
6259 | int this_eol; |
6260 | ||
6261 | if (c == '\n') | |
6262 | this_eol = EOL_SEEN_LF; | |
6263 | else if (src + 3 >= src_end | |
6264 | || src[msb + 2] != 0 | |
6265 | || src[lsb + 2] != '\n') | |
6266 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 6267 | else |
75f4f1ac EZ |
6268 | { |
6269 | this_eol = EOL_SEEN_CRLF; | |
6270 | src += 2; | |
6271 | } | |
df7492f9 KH |
6272 | |
6273 | if (eol_seen == EOL_SEEN_NONE) | |
6274 | /* This is the first end-of-line. */ | |
6275 | eol_seen = this_eol; | |
6276 | else if (eol_seen != this_eol) | |
fa42c37f | 6277 | { |
75f4f1ac EZ |
6278 | /* The found type is different from what found before. |
6279 | Allow for stray ^M characters in DOS EOL files. */ | |
6280 | if (eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF | |
6281 | || eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR) | |
6282 | eol_seen = EOL_SEEN_CRLF; | |
6283 | else | |
6284 | { | |
6285 | eol_seen = EOL_SEEN_LF; | |
6286 | break; | |
6287 | } | |
fa42c37f | 6288 | } |
df7492f9 KH |
6289 | if (++total == MAX_EOL_CHECK_COUNT) |
6290 | break; | |
fa42c37f | 6291 | } |
df7492f9 | 6292 | src += 2; |
fa42c37f | 6293 | } |
bcf26d6a | 6294 | } |
d46c5b12 | 6295 | else |
c4825358 | 6296 | { |
df7492f9 | 6297 | while (src < src_end) |
27901516 | 6298 | { |
df7492f9 KH |
6299 | c = *src++; |
6300 | if (c == '\n' || c == '\r') | |
6301 | { | |
6302 | int this_eol; | |
d46c5b12 | 6303 | |
df7492f9 KH |
6304 | if (c == '\n') |
6305 | this_eol = EOL_SEEN_LF; | |
6306 | else if (src >= src_end || *src != '\n') | |
6307 | this_eol = EOL_SEEN_CR; | |
6308 | else | |
6309 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 6310 | |
df7492f9 KH |
6311 | if (eol_seen == EOL_SEEN_NONE) |
6312 | /* This is the first end-of-line. */ | |
6313 | eol_seen = this_eol; | |
6314 | else if (eol_seen != this_eol) | |
6315 | { | |
75f4f1ac EZ |
6316 | /* The found type is different from what found before. |
6317 | Allow for stray ^M characters in DOS EOL files. */ | |
6318 | if (eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF | |
6319 | || eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR) | |
6320 | eol_seen = EOL_SEEN_CRLF; | |
6321 | else | |
6322 | { | |
6323 | eol_seen = EOL_SEEN_LF; | |
6324 | break; | |
6325 | } | |
df7492f9 KH |
6326 | } |
6327 | if (++total == MAX_EOL_CHECK_COUNT) | |
6328 | break; | |
6329 | } | |
6330 | } | |
73be902c | 6331 | } |
df7492f9 | 6332 | return eol_seen; |
73be902c KH |
6333 | } |
6334 | ||
df7492f9 | 6335 | |
24a73b0a | 6336 | static Lisp_Object |
df7492f9 KH |
6337 | adjust_coding_eol_type (coding, eol_seen) |
6338 | struct coding_system *coding; | |
6339 | int eol_seen; | |
73be902c | 6340 | { |
0be8721c | 6341 | Lisp_Object eol_type; |
8f924df7 | 6342 | |
df7492f9 KH |
6343 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6344 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
6345 | { |
6346 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
6347 | eol_type = Qunix; | |
6348 | } | |
6f197c07 | 6349 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
6350 | { |
6351 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
6352 | eol_type = Qdos; | |
6353 | } | |
6f197c07 | 6354 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
6355 | { |
6356 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
6357 | eol_type = Qmac; | |
6358 | } | |
6359 | return eol_type; | |
d46c5b12 | 6360 | } |
4ed46869 | 6361 | |
df7492f9 KH |
6362 | /* Detect how a text specified in CODING is encoded. If a coding |
6363 | system is detected, update fields of CODING by the detected coding | |
6364 | system. */ | |
0a28aafb | 6365 | |
df7492f9 KH |
6366 | void |
6367 | detect_coding (coding) | |
d46c5b12 | 6368 | struct coding_system *coding; |
d46c5b12 | 6369 | { |
8f924df7 | 6370 | const unsigned char *src, *src_end; |
73cce38d | 6371 | int saved_mode = coding->mode; |
d46c5b12 | 6372 | |
df7492f9 KH |
6373 | coding->consumed = coding->consumed_char = 0; |
6374 | coding->produced = coding->produced_char = 0; | |
6375 | coding_set_source (coding); | |
1c3478b0 | 6376 | |
df7492f9 | 6377 | src_end = coding->source + coding->src_bytes; |
c0e16b14 | 6378 | coding->head_ascii = 0; |
1c3478b0 | 6379 | |
df7492f9 KH |
6380 | /* If we have not yet decided the text encoding type, detect it |
6381 | now. */ | |
6382 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 6383 | { |
df7492f9 | 6384 | int c, i; |
6cb21a4f | 6385 | struct coding_detection_info detect_info; |
2f3cbb32 | 6386 | int null_byte_found = 0, eight_bit_found = 0; |
df7492f9 | 6387 | |
6cb21a4f | 6388 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
2f3cbb32 | 6389 | for (src = coding->source; src < src_end; src++) |
d46c5b12 | 6390 | { |
df7492f9 | 6391 | c = *src; |
6cb21a4f | 6392 | if (c & 0x80) |
6cb21a4f | 6393 | { |
2f3cbb32 | 6394 | eight_bit_found = 1; |
2f3cbb32 KH |
6395 | if (null_byte_found) |
6396 | break; | |
6397 | } | |
6398 | else if (c < 0x20) | |
6399 | { | |
6400 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
6401 | && ! inhibit_iso_escape_detection | |
6402 | && ! detect_info.checked) | |
6cb21a4f | 6403 | { |
2f3cbb32 KH |
6404 | if (detect_coding_iso_2022 (coding, &detect_info)) |
6405 | { | |
6406 | /* We have scanned the whole data. */ | |
6407 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
6408 | { |
6409 | /* We didn't find an 8-bit code. We may | |
6410 | have found a null-byte, but it's very | |
ce5b453a | 6411 | rare that a binary file conforms to |
c0e16b14 KH |
6412 | ISO-2022. */ |
6413 | src = src_end; | |
6414 | coding->head_ascii = src - coding->source; | |
6415 | } | |
6416 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
6417 | break; |
6418 | } | |
6419 | } | |
97b1b294 | 6420 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
6421 | { |
6422 | null_byte_found = 1; | |
6423 | if (eight_bit_found) | |
6424 | break; | |
6cb21a4f | 6425 | } |
c006c0c8 KH |
6426 | if (! eight_bit_found) |
6427 | coding->head_ascii++; | |
6cb21a4f | 6428 | } |
c006c0c8 | 6429 | else if (! eight_bit_found) |
c0e16b14 | 6430 | coding->head_ascii++; |
d46c5b12 | 6431 | } |
df7492f9 | 6432 | |
2f3cbb32 KH |
6433 | if (null_byte_found || eight_bit_found |
6434 | || coding->head_ascii < coding->src_bytes | |
6cb21a4f | 6435 | || detect_info.found) |
d46c5b12 | 6436 | { |
ff0dacd7 KH |
6437 | enum coding_category category; |
6438 | struct coding_system *this; | |
df7492f9 | 6439 | |
6cb21a4f KH |
6440 | if (coding->head_ascii == coding->src_bytes) |
6441 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
6442 | for (i = 0; i < coding_category_raw_text; i++) | |
6443 | { | |
6444 | category = coding_priorities[i]; | |
6445 | this = coding_categories + category; | |
6446 | if (detect_info.found & (1 << category)) | |
24a73b0a | 6447 | break; |
6cb21a4f KH |
6448 | } |
6449 | else | |
2f3cbb32 KH |
6450 | { |
6451 | if (null_byte_found) | |
ff0dacd7 | 6452 | { |
2f3cbb32 KH |
6453 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; |
6454 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
ff0dacd7 | 6455 | } |
2f3cbb32 KH |
6456 | for (i = 0; i < coding_category_raw_text; i++) |
6457 | { | |
6458 | category = coding_priorities[i]; | |
6459 | this = coding_categories + category; | |
6460 | if (this->id < 0) | |
6461 | { | |
6462 | /* No coding system of this category is defined. */ | |
6463 | detect_info.rejected |= (1 << category); | |
6464 | } | |
6465 | else if (category >= coding_category_raw_text) | |
6466 | continue; | |
6467 | else if (detect_info.checked & (1 << category)) | |
6468 | { | |
6469 | if (detect_info.found & (1 << category)) | |
6470 | break; | |
6471 | } | |
6472 | else if ((*(this->detector)) (coding, &detect_info) | |
6473 | && detect_info.found & (1 << category)) | |
6474 | { | |
6475 | if (category == coding_category_utf_16_auto) | |
6476 | { | |
6477 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6478 | category = coding_category_utf_16_le; | |
6479 | else | |
6480 | category = coding_category_utf_16_be; | |
6481 | } | |
6482 | break; | |
6483 | } | |
6484 | } | |
2f3cbb32 | 6485 | } |
c0e16b14 KH |
6486 | |
6487 | if (i < coding_category_raw_text) | |
6488 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6489 | else if (null_byte_found) | |
6490 | setup_coding_system (Qno_conversion, coding); | |
6491 | else if ((detect_info.rejected & CATEGORY_MASK_ANY) | |
6492 | == CATEGORY_MASK_ANY) | |
6493 | setup_coding_system (Qraw_text, coding); | |
6494 | else if (detect_info.rejected) | |
6495 | for (i = 0; i < coding_category_raw_text; i++) | |
6496 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
6497 | { | |
6498 | this = coding_categories + coding_priorities[i]; | |
6499 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6500 | break; | |
6501 | } | |
d46c5b12 | 6502 | } |
b73bfc1c | 6503 | } |
a470d443 KH |
6504 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6505 | == coding_category_utf_8_auto) | |
6506 | { | |
6507 | Lisp_Object coding_systems; | |
6508 | struct coding_detection_info detect_info; | |
6509 | ||
6510 | coding_systems | |
6511 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); | |
6512 | detect_info.found = detect_info.rejected = 0; | |
6513 | coding->head_ascii = 0; | |
6514 | if (CONSP (coding_systems) | |
6515 | && detect_coding_utf_8 (coding, &detect_info)) | |
6516 | { | |
6517 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
6518 | setup_coding_system (XCAR (coding_systems), coding); | |
6519 | else | |
6520 | setup_coding_system (XCDR (coding_systems), coding); | |
6521 | } | |
6522 | } | |
24a73b0a KH |
6523 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6524 | == coding_category_utf_16_auto) | |
b49a1807 KH |
6525 | { |
6526 | Lisp_Object coding_systems; | |
6527 | struct coding_detection_info detect_info; | |
6528 | ||
6529 | coding_systems | |
a470d443 | 6530 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); |
b49a1807 | 6531 | detect_info.found = detect_info.rejected = 0; |
a470d443 | 6532 | coding->head_ascii = 0; |
b49a1807 | 6533 | if (CONSP (coding_systems) |
24a73b0a | 6534 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
6535 | { |
6536 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6537 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 6538 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
6539 | setup_coding_system (XCDR (coding_systems), coding); |
6540 | } | |
6541 | } | |
73cce38d | 6542 | coding->mode = saved_mode; |
4ed46869 | 6543 | } |
4ed46869 | 6544 | |
d46c5b12 | 6545 | |
aaaf0b1e | 6546 | static void |
df7492f9 | 6547 | decode_eol (coding) |
aaaf0b1e | 6548 | struct coding_system *coding; |
aaaf0b1e | 6549 | { |
24a73b0a KH |
6550 | Lisp_Object eol_type; |
6551 | unsigned char *p, *pbeg, *pend; | |
3ed051d4 | 6552 | |
24a73b0a | 6553 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
0a9564cb | 6554 | if (EQ (eol_type, Qunix) || inhibit_eol_conversion) |
24a73b0a KH |
6555 | return; |
6556 | ||
6557 | if (NILP (coding->dst_object)) | |
6558 | pbeg = coding->destination; | |
6559 | else | |
6560 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
6561 | pend = pbeg + coding->produced; | |
6562 | ||
6563 | if (VECTORP (eol_type)) | |
aaaf0b1e | 6564 | { |
df7492f9 | 6565 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 6566 | |
24a73b0a | 6567 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 6568 | { |
df7492f9 KH |
6569 | if (*p == '\n') |
6570 | eol_seen |= EOL_SEEN_LF; | |
6571 | else if (*p == '\r') | |
aaaf0b1e | 6572 | { |
df7492f9 | 6573 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 6574 | { |
df7492f9 KH |
6575 | eol_seen |= EOL_SEEN_CRLF; |
6576 | p++; | |
aaaf0b1e | 6577 | } |
aaaf0b1e | 6578 | else |
df7492f9 | 6579 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 6580 | } |
aaaf0b1e | 6581 | } |
75f4f1ac EZ |
6582 | /* Handle DOS-style EOLs in a file with stray ^M characters. */ |
6583 | if ((eol_seen & EOL_SEEN_CRLF) != 0 | |
6584 | && (eol_seen & EOL_SEEN_CR) != 0 | |
6585 | && (eol_seen & EOL_SEEN_LF) == 0) | |
6586 | eol_seen = EOL_SEEN_CRLF; | |
6587 | else if (eol_seen != EOL_SEEN_NONE | |
24a73b0a KH |
6588 | && eol_seen != EOL_SEEN_LF |
6589 | && eol_seen != EOL_SEEN_CRLF | |
6590 | && eol_seen != EOL_SEEN_CR) | |
6591 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 6592 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 6593 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 6594 | } |
d46c5b12 | 6595 | |
24a73b0a | 6596 | if (EQ (eol_type, Qmac)) |
27901516 | 6597 | { |
24a73b0a | 6598 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
6599 | if (*p == '\r') |
6600 | *p = '\n'; | |
4ed46869 | 6601 | } |
24a73b0a | 6602 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 6603 | { |
24a73b0a | 6604 | int n = 0; |
b73bfc1c | 6605 | |
24a73b0a KH |
6606 | if (NILP (coding->dst_object)) |
6607 | { | |
4347441b KH |
6608 | /* Start deleting '\r' from the tail to minimize the memory |
6609 | movement. */ | |
24a73b0a KH |
6610 | for (p = pend - 2; p >= pbeg; p--) |
6611 | if (*p == '\r') | |
6612 | { | |
6613 | safe_bcopy ((char *) (p + 1), (char *) p, pend-- - p - 1); | |
6614 | n++; | |
6615 | } | |
6616 | } | |
6617 | else | |
6618 | { | |
4347441b KH |
6619 | int pos_byte = coding->dst_pos_byte; |
6620 | int pos = coding->dst_pos; | |
6621 | int pos_end = pos + coding->produced_char - 1; | |
6622 | ||
6623 | while (pos < pos_end) | |
6624 | { | |
6625 | p = BYTE_POS_ADDR (pos_byte); | |
6626 | if (*p == '\r' && p[1] == '\n') | |
6627 | { | |
6628 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
6629 | n++; | |
6630 | pos_end--; | |
6631 | } | |
6632 | pos++; | |
69b8522d KH |
6633 | if (coding->dst_multibyte) |
6634 | pos_byte += BYTES_BY_CHAR_HEAD (*p); | |
6635 | else | |
6636 | pos_byte++; | |
4347441b | 6637 | } |
24a73b0a KH |
6638 | } |
6639 | coding->produced -= n; | |
6640 | coding->produced_char -= n; | |
aaaf0b1e | 6641 | } |
4ed46869 KH |
6642 | } |
6643 | ||
7d64c6ad | 6644 | |
a6f87d34 KH |
6645 | /* Return a translation table (or list of them) from coding system |
6646 | attribute vector ATTRS for encoding (ENCODEP is nonzero) or | |
6647 | decoding (ENCODEP is zero). */ | |
7d64c6ad | 6648 | |
e6a54062 | 6649 | static Lisp_Object |
09ee6fdd KH |
6650 | get_translation_table (attrs, encodep, max_lookup) |
6651 | Lisp_Object attrs; | |
6652 | int encodep, *max_lookup; | |
7d64c6ad KH |
6653 | { |
6654 | Lisp_Object standard, translation_table; | |
09ee6fdd | 6655 | Lisp_Object val; |
7d64c6ad | 6656 | |
4bed5909 CY |
6657 | if (NILP (Venable_character_translation)) |
6658 | { | |
6659 | if (max_lookup) | |
6660 | *max_lookup = 0; | |
6661 | return Qnil; | |
6662 | } | |
7d64c6ad KH |
6663 | if (encodep) |
6664 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
6665 | standard = Vstandard_translation_table_for_encode; | |
6666 | else | |
6667 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
6668 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 6669 | if (NILP (translation_table)) |
09ee6fdd KH |
6670 | translation_table = standard; |
6671 | else | |
a6f87d34 | 6672 | { |
09ee6fdd KH |
6673 | if (SYMBOLP (translation_table)) |
6674 | translation_table = Fget (translation_table, Qtranslation_table); | |
6675 | else if (CONSP (translation_table)) | |
6676 | { | |
6677 | translation_table = Fcopy_sequence (translation_table); | |
6678 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
6679 | if (SYMBOLP (XCAR (val))) | |
6680 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
6681 | } | |
6682 | if (CHAR_TABLE_P (standard)) | |
6683 | { | |
6684 | if (CONSP (translation_table)) | |
6685 | translation_table = nconc2 (translation_table, | |
6686 | Fcons (standard, Qnil)); | |
6687 | else | |
6688 | translation_table = Fcons (translation_table, | |
6689 | Fcons (standard, Qnil)); | |
6690 | } | |
a6f87d34 | 6691 | } |
2170c8f0 KH |
6692 | |
6693 | if (max_lookup) | |
09ee6fdd | 6694 | { |
2170c8f0 KH |
6695 | *max_lookup = 1; |
6696 | if (CHAR_TABLE_P (translation_table) | |
6697 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
6698 | { | |
6699 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
6700 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6701 | *max_lookup = XFASTINT (val); | |
6702 | } | |
6703 | else if (CONSP (translation_table)) | |
6704 | { | |
6705 | Lisp_Object tail, val; | |
09ee6fdd | 6706 | |
2170c8f0 KH |
6707 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
6708 | if (CHAR_TABLE_P (XCAR (tail)) | |
6709 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
6710 | { | |
6711 | val = XCHAR_TABLE (XCAR (tail))->extras[1]; | |
6712 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6713 | *max_lookup = XFASTINT (val); | |
6714 | } | |
6715 | } | |
a6f87d34 | 6716 | } |
7d64c6ad KH |
6717 | return translation_table; |
6718 | } | |
6719 | ||
09ee6fdd KH |
6720 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
6721 | do { \ | |
6722 | trans = Qnil; \ | |
6723 | if (CHAR_TABLE_P (table)) \ | |
6724 | { \ | |
6725 | trans = CHAR_TABLE_REF (table, c); \ | |
6726 | if (CHARACTERP (trans)) \ | |
6727 | c = XFASTINT (trans), trans = Qnil; \ | |
6728 | } \ | |
6729 | else if (CONSP (table)) \ | |
6730 | { \ | |
6731 | Lisp_Object tail; \ | |
6732 | \ | |
6733 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
6734 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
6735 | { \ | |
6736 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
6737 | if (CHARACTERP (trans)) \ | |
6738 | c = XFASTINT (trans), trans = Qnil; \ | |
6739 | else if (! NILP (trans)) \ | |
6740 | break; \ | |
6741 | } \ | |
6742 | } \ | |
e6a54062 KH |
6743 | } while (0) |
6744 | ||
7d64c6ad | 6745 | |
e951386e KH |
6746 | /* Return a translation of character(s) at BUF according to TRANS. |
6747 | TRANS is TO-CHAR or ((FROM . TO) ...) where | |
6748 | FROM = [FROM-CHAR ...], TO is TO-CHAR or [TO-CHAR ...]. | |
6749 | The return value is TO-CHAR or ([FROM-CHAR ...] . TO) if a | |
6750 | translation is found, and Qnil if not found.. | |
6751 | If BUF is too short to lookup characters in FROM, return Qt. */ | |
6752 | ||
69a80ea3 | 6753 | static Lisp_Object |
e951386e KH |
6754 | get_translation (trans, buf, buf_end) |
6755 | Lisp_Object trans; | |
69a80ea3 | 6756 | int *buf, *buf_end; |
69a80ea3 | 6757 | { |
e951386e KH |
6758 | |
6759 | if (INTEGERP (trans)) | |
6760 | return trans; | |
6761 | for (; CONSP (trans); trans = XCDR (trans)) | |
69a80ea3 | 6762 | { |
e951386e KH |
6763 | Lisp_Object val = XCAR (trans); |
6764 | Lisp_Object from = XCAR (val); | |
6765 | int len = ASIZE (from); | |
6766 | int i; | |
69a80ea3 | 6767 | |
e951386e | 6768 | for (i = 0; i < len; i++) |
69a80ea3 | 6769 | { |
e951386e KH |
6770 | if (buf + i == buf_end) |
6771 | return Qt; | |
6772 | if (XINT (AREF (from, i)) != buf[i]) | |
6773 | break; | |
69a80ea3 | 6774 | } |
e951386e KH |
6775 | if (i == len) |
6776 | return val; | |
69a80ea3 | 6777 | } |
e951386e | 6778 | return Qnil; |
69a80ea3 KH |
6779 | } |
6780 | ||
6781 | ||
d46c5b12 | 6782 | static int |
69a80ea3 | 6783 | produce_chars (coding, translation_table, last_block) |
df7492f9 | 6784 | struct coding_system *coding; |
69a80ea3 KH |
6785 | Lisp_Object translation_table; |
6786 | int last_block; | |
4ed46869 | 6787 | { |
df7492f9 KH |
6788 | unsigned char *dst = coding->destination + coding->produced; |
6789 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
119852e7 KH |
6790 | EMACS_INT produced; |
6791 | EMACS_INT produced_chars = 0; | |
69a80ea3 | 6792 | int carryover = 0; |
4ed46869 | 6793 | |
df7492f9 | 6794 | if (! coding->chars_at_source) |
4ed46869 | 6795 | { |
119852e7 | 6796 | /* Source characters are in coding->charbuf. */ |
fba4576f AS |
6797 | int *buf = coding->charbuf; |
6798 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 6799 | |
db274c7a KH |
6800 | if (EQ (coding->src_object, coding->dst_object)) |
6801 | { | |
6802 | coding_set_source (coding); | |
6803 | dst_end = ((unsigned char *) coding->source) + coding->consumed; | |
6804 | } | |
4ed46869 | 6805 | |
df7492f9 | 6806 | while (buf < buf_end) |
4ed46869 | 6807 | { |
69a80ea3 | 6808 | int c = *buf, i; |
bc4bc72a | 6809 | |
df7492f9 KH |
6810 | if (c >= 0) |
6811 | { | |
69a80ea3 KH |
6812 | int from_nchars = 1, to_nchars = 1; |
6813 | Lisp_Object trans = Qnil; | |
6814 | ||
09ee6fdd | 6815 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6816 | if (! NILP (trans)) |
69a80ea3 | 6817 | { |
e951386e KH |
6818 | trans = get_translation (trans, buf, buf_end); |
6819 | if (INTEGERP (trans)) | |
6820 | c = XINT (trans); | |
6821 | else if (CONSP (trans)) | |
6822 | { | |
6823 | from_nchars = ASIZE (XCAR (trans)); | |
6824 | trans = XCDR (trans); | |
6825 | if (INTEGERP (trans)) | |
6826 | c = XINT (trans); | |
6827 | else | |
6828 | { | |
6829 | to_nchars = ASIZE (trans); | |
6830 | c = XINT (AREF (trans, 0)); | |
6831 | } | |
6832 | } | |
6833 | else if (EQ (trans, Qt) && ! last_block) | |
69a80ea3 | 6834 | break; |
69a80ea3 KH |
6835 | } |
6836 | ||
6837 | if (dst + MAX_MULTIBYTE_LENGTH * to_nchars > dst_end) | |
6838 | { | |
6839 | dst = alloc_destination (coding, | |
6840 | buf_end - buf | |
6841 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
6842 | dst); | |
db274c7a KH |
6843 | if (EQ (coding->src_object, coding->dst_object)) |
6844 | { | |
6845 | coding_set_source (coding); | |
e951386e KH |
6846 | dst_end = (((unsigned char *) coding->source) |
6847 | + coding->consumed); | |
db274c7a KH |
6848 | } |
6849 | else | |
6850 | dst_end = coding->destination + coding->dst_bytes; | |
69a80ea3 KH |
6851 | } |
6852 | ||
433f7f87 | 6853 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 6854 | { |
433f7f87 KH |
6855 | if (i > 0) |
6856 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
6857 | if (coding->dst_multibyte |
6858 | || ! CHAR_BYTE8_P (c)) | |
db274c7a | 6859 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
69a80ea3 KH |
6860 | else |
6861 | *dst++ = CHAR_TO_BYTE8 (c); | |
6862 | } | |
6863 | produced_chars += to_nchars; | |
e951386e | 6864 | buf += from_nchars; |
d46c5b12 | 6865 | } |
df7492f9 | 6866 | else |
69a80ea3 KH |
6867 | /* This is an annotation datum. (-C) is the length. */ |
6868 | buf += -c; | |
4ed46869 | 6869 | } |
69a80ea3 | 6870 | carryover = buf_end - buf; |
4ed46869 | 6871 | } |
fa42c37f | 6872 | else |
fa42c37f | 6873 | { |
119852e7 | 6874 | /* Source characters are at coding->source. */ |
8f924df7 | 6875 | const unsigned char *src = coding->source; |
119852e7 | 6876 | const unsigned char *src_end = src + coding->consumed; |
4ed46869 | 6877 | |
db274c7a KH |
6878 | if (EQ (coding->dst_object, coding->src_object)) |
6879 | dst_end = (unsigned char *) src; | |
df7492f9 | 6880 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 6881 | { |
df7492f9 | 6882 | if (coding->src_multibyte) |
fa42c37f | 6883 | { |
71c81426 | 6884 | int multibytep = 1; |
4533845d | 6885 | EMACS_INT consumed_chars = 0; |
d46c5b12 | 6886 | |
df7492f9 KH |
6887 | while (1) |
6888 | { | |
8f924df7 | 6889 | const unsigned char *src_base = src; |
df7492f9 | 6890 | int c; |
b73bfc1c | 6891 | |
df7492f9 | 6892 | ONE_MORE_BYTE (c); |
119852e7 | 6893 | if (dst == dst_end) |
df7492f9 | 6894 | { |
119852e7 KH |
6895 | if (EQ (coding->src_object, coding->dst_object)) |
6896 | dst_end = (unsigned char *) src; | |
6897 | if (dst == dst_end) | |
df7492f9 | 6898 | { |
119852e7 KH |
6899 | EMACS_INT offset = src - coding->source; |
6900 | ||
6901 | dst = alloc_destination (coding, src_end - src + 1, | |
6902 | dst); | |
6903 | dst_end = coding->destination + coding->dst_bytes; | |
6904 | coding_set_source (coding); | |
6905 | src = coding->source + offset; | |
6906 | src_end = coding->source + coding->src_bytes; | |
db274c7a KH |
6907 | if (EQ (coding->src_object, coding->dst_object)) |
6908 | dst_end = (unsigned char *) src; | |
df7492f9 | 6909 | } |
df7492f9 KH |
6910 | } |
6911 | *dst++ = c; | |
6912 | produced_chars++; | |
6913 | } | |
6914 | no_more_source: | |
6915 | ; | |
fa42c37f KH |
6916 | } |
6917 | else | |
df7492f9 KH |
6918 | while (src < src_end) |
6919 | { | |
71c81426 | 6920 | int multibytep = 1; |
df7492f9 | 6921 | int c = *src++; |
b73bfc1c | 6922 | |
df7492f9 KH |
6923 | if (dst >= dst_end - 1) |
6924 | { | |
2c78b7e1 | 6925 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 6926 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
6927 | if (dst >= dst_end - 1) |
6928 | { | |
119852e7 | 6929 | EMACS_INT offset = src - coding->source; |
db274c7a | 6930 | EMACS_INT more_bytes; |
119852e7 | 6931 | |
db274c7a KH |
6932 | if (EQ (coding->src_object, coding->dst_object)) |
6933 | more_bytes = ((src_end - src) / 2) + 2; | |
6934 | else | |
6935 | more_bytes = src_end - src + 2; | |
6936 | dst = alloc_destination (coding, more_bytes, dst); | |
2c78b7e1 KH |
6937 | dst_end = coding->destination + coding->dst_bytes; |
6938 | coding_set_source (coding); | |
119852e7 | 6939 | src = coding->source + offset; |
2c78b7e1 | 6940 | src_end = coding->source + coding->src_bytes; |
db274c7a KH |
6941 | if (EQ (coding->src_object, coding->dst_object)) |
6942 | dst_end = (unsigned char *) src; | |
2c78b7e1 | 6943 | } |
df7492f9 KH |
6944 | } |
6945 | EMIT_ONE_BYTE (c); | |
6946 | } | |
d46c5b12 | 6947 | } |
df7492f9 KH |
6948 | else |
6949 | { | |
6950 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 6951 | { |
119852e7 | 6952 | EMACS_INT require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 6953 | |
df7492f9 | 6954 | if (require > 0) |
fa42c37f | 6955 | { |
df7492f9 KH |
6956 | EMACS_INT offset = src - coding->source; |
6957 | ||
6958 | dst = alloc_destination (coding, require, dst); | |
6959 | coding_set_source (coding); | |
6960 | src = coding->source + offset; | |
6961 | src_end = coding->source + coding->src_bytes; | |
fa42c37f KH |
6962 | } |
6963 | } | |
119852e7 | 6964 | produced_chars = coding->consumed_char; |
df7492f9 | 6965 | while (src < src_end) |
14daee73 | 6966 | *dst++ = *src++; |
fa42c37f KH |
6967 | } |
6968 | } | |
6969 | ||
df7492f9 | 6970 | produced = dst - (coding->destination + coding->produced); |
284201e4 | 6971 | if (BUFFERP (coding->dst_object) && produced_chars > 0) |
df7492f9 KH |
6972 | insert_from_gap (produced_chars, produced); |
6973 | coding->produced += produced; | |
6974 | coding->produced_char += produced_chars; | |
69a80ea3 | 6975 | return carryover; |
fa42c37f KH |
6976 | } |
6977 | ||
ff0dacd7 KH |
6978 | /* Compose text in CODING->object according to the annotation data at |
6979 | CHARBUF. CHARBUF is an array: | |
e951386e | 6980 | [ -LENGTH ANNOTATION_MASK NCHARS NBYTES METHOD [ COMPONENTS... ] ] |
df7492f9 | 6981 | */ |
4ed46869 | 6982 | |
df7492f9 | 6983 | static INLINE void |
69a80ea3 | 6984 | produce_composition (coding, charbuf, pos) |
4ed46869 | 6985 | struct coding_system *coding; |
df7492f9 | 6986 | int *charbuf; |
69a80ea3 | 6987 | EMACS_INT pos; |
4ed46869 | 6988 | { |
df7492f9 | 6989 | int len; |
69a80ea3 | 6990 | EMACS_INT to; |
df7492f9 | 6991 | enum composition_method method; |
df7492f9 | 6992 | Lisp_Object components; |
fa42c37f | 6993 | |
e951386e | 6994 | len = -charbuf[0] - MAX_ANNOTATION_LENGTH; |
69a80ea3 | 6995 | to = pos + charbuf[2]; |
e951386e | 6996 | method = (enum composition_method) (charbuf[4]); |
d46c5b12 | 6997 | |
df7492f9 KH |
6998 | if (method == COMPOSITION_RELATIVE) |
6999 | components = Qnil; | |
e951386e | 7000 | else |
d46c5b12 | 7001 | { |
df7492f9 | 7002 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
e951386e | 7003 | int i, j; |
b73bfc1c | 7004 | |
e951386e KH |
7005 | if (method == COMPOSITION_WITH_RULE) |
7006 | len = charbuf[2] * 3 - 2; | |
7007 | charbuf += MAX_ANNOTATION_LENGTH; | |
7008 | /* charbuf = [ CHRA ... CHAR] or [ CHAR -2 RULE ... CHAR ] */ | |
7009 | for (i = j = 0; i < len && charbuf[i] != -1; i++, j++) | |
9ffd559c | 7010 | { |
e951386e KH |
7011 | if (charbuf[i] >= 0) |
7012 | args[j] = make_number (charbuf[i]); | |
7013 | else | |
7014 | { | |
7015 | i++; | |
7016 | args[j] = make_number (charbuf[i] % 0x100); | |
7017 | } | |
9ffd559c | 7018 | } |
e951386e | 7019 | components = (i == j ? Fstring (j, args) : Fvector (j, args)); |
d46c5b12 | 7020 | } |
69a80ea3 | 7021 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
7022 | } |
7023 | ||
d46c5b12 | 7024 | |
ff0dacd7 KH |
7025 | /* Put `charset' property on text in CODING->object according to |
7026 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 7027 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 7028 | */ |
d46c5b12 | 7029 | |
ff0dacd7 | 7030 | static INLINE void |
69a80ea3 | 7031 | produce_charset (coding, charbuf, pos) |
d46c5b12 | 7032 | struct coding_system *coding; |
ff0dacd7 | 7033 | int *charbuf; |
69a80ea3 | 7034 | EMACS_INT pos; |
d46c5b12 | 7035 | { |
69a80ea3 KH |
7036 | EMACS_INT from = pos - charbuf[2]; |
7037 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); | |
b73bfc1c | 7038 | |
69a80ea3 | 7039 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
7040 | Qcharset, CHARSET_NAME (charset), |
7041 | coding->dst_object); | |
d46c5b12 KH |
7042 | } |
7043 | ||
d46c5b12 | 7044 | |
df7492f9 KH |
7045 | #define CHARBUF_SIZE 0x4000 |
7046 | ||
7047 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
7048 | do { \ | |
8510724d | 7049 | int size = CHARBUF_SIZE; \ |
df7492f9 KH |
7050 | \ |
7051 | coding->charbuf = NULL; \ | |
7052 | while (size > 1024) \ | |
7053 | { \ | |
7054 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
7055 | if (coding->charbuf) \ | |
7056 | break; \ | |
7057 | size >>= 1; \ | |
7058 | } \ | |
7059 | if (! coding->charbuf) \ | |
7060 | { \ | |
065e3595 | 7061 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
df7492f9 KH |
7062 | return coding->result; \ |
7063 | } \ | |
7064 | coding->charbuf_size = size; \ | |
7065 | } while (0) | |
4ed46869 | 7066 | |
d46c5b12 KH |
7067 | |
7068 | static void | |
69a80ea3 | 7069 | produce_annotation (coding, pos) |
d46c5b12 | 7070 | struct coding_system *coding; |
69a80ea3 | 7071 | EMACS_INT pos; |
d46c5b12 | 7072 | { |
df7492f9 KH |
7073 | int *charbuf = coding->charbuf; |
7074 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 7075 | |
ff0dacd7 KH |
7076 | if (NILP (coding->dst_object)) |
7077 | return; | |
d46c5b12 | 7078 | |
df7492f9 | 7079 | while (charbuf < charbuf_end) |
a84f1519 | 7080 | { |
df7492f9 | 7081 | if (*charbuf >= 0) |
e951386e | 7082 | pos++, charbuf++; |
d46c5b12 | 7083 | else |
d46c5b12 | 7084 | { |
df7492f9 | 7085 | int len = -*charbuf; |
e951386e KH |
7086 | |
7087 | if (len > 2) | |
7088 | switch (charbuf[1]) | |
7089 | { | |
7090 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
7091 | produce_composition (coding, charbuf, pos); | |
7092 | break; | |
7093 | case CODING_ANNOTATE_CHARSET_MASK: | |
7094 | produce_charset (coding, charbuf, pos); | |
7095 | break; | |
7096 | } | |
df7492f9 | 7097 | charbuf += len; |
d46c5b12 | 7098 | } |
a84f1519 | 7099 | } |
d46c5b12 KH |
7100 | } |
7101 | ||
df7492f9 KH |
7102 | /* Decode the data at CODING->src_object into CODING->dst_object. |
7103 | CODING->src_object is a buffer, a string, or nil. | |
7104 | CODING->dst_object is a buffer. | |
d46c5b12 | 7105 | |
df7492f9 KH |
7106 | If CODING->src_object is a buffer, it must be the current buffer. |
7107 | In this case, if CODING->src_pos is positive, it is a position of | |
7108 | the source text in the buffer, otherwise, the source text is in the | |
7109 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
7110 | the text from GPT (which must be the same as PT). If this is the | |
7111 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7112 | negative. | |
d46c5b12 | 7113 | |
b6828792 | 7114 | If CODING->src_object is a string, CODING->src_pos is an index to |
df7492f9 | 7115 | that string. |
d46c5b12 | 7116 | |
df7492f9 KH |
7117 | If CODING->src_object is nil, CODING->source must already point to |
7118 | the non-relocatable memory area. In this case, CODING->src_pos is | |
7119 | an offset from CODING->source. | |
73be902c | 7120 | |
df7492f9 KH |
7121 | The decoded data is inserted at the current point of the buffer |
7122 | CODING->dst_object. | |
7123 | */ | |
d46c5b12 | 7124 | |
df7492f9 KH |
7125 | static int |
7126 | decode_coding (coding) | |
d46c5b12 | 7127 | struct coding_system *coding; |
d46c5b12 | 7128 | { |
df7492f9 | 7129 | Lisp_Object attrs; |
24a73b0a | 7130 | Lisp_Object undo_list; |
7d64c6ad | 7131 | Lisp_Object translation_table; |
d0396581 | 7132 | struct ccl_spec cclspec; |
69a80ea3 KH |
7133 | int carryover; |
7134 | int i; | |
d46c5b12 | 7135 | |
df7492f9 KH |
7136 | if (BUFFERP (coding->src_object) |
7137 | && coding->src_pos > 0 | |
7138 | && coding->src_pos < GPT | |
7139 | && coding->src_pos + coding->src_chars > GPT) | |
7140 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 7141 | |
24a73b0a | 7142 | undo_list = Qt; |
df7492f9 | 7143 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 7144 | { |
df7492f9 KH |
7145 | if (current_buffer != XBUFFER (coding->dst_object)) |
7146 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7147 | if (GPT != PT) | |
7148 | move_gap_both (PT, PT_BYTE); | |
24a73b0a KH |
7149 | undo_list = current_buffer->undo_list; |
7150 | current_buffer->undo_list = Qt; | |
1c3478b0 KH |
7151 | } |
7152 | ||
df7492f9 KH |
7153 | coding->consumed = coding->consumed_char = 0; |
7154 | coding->produced = coding->produced_char = 0; | |
7155 | coding->chars_at_source = 0; | |
065e3595 | 7156 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 7157 | coding->errors = 0; |
1c3478b0 | 7158 | |
df7492f9 KH |
7159 | ALLOC_CONVERSION_WORK_AREA (coding); |
7160 | ||
7161 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 7162 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 7163 | |
69a80ea3 | 7164 | carryover = 0; |
d0396581 KH |
7165 | if (coding->decoder == decode_coding_ccl) |
7166 | { | |
7167 | coding->spec.ccl = &cclspec; | |
7168 | setup_ccl_program (&cclspec.ccl, CODING_CCL_DECODER (coding)); | |
7169 | } | |
df7492f9 | 7170 | do |
b73bfc1c | 7171 | { |
69a80ea3 KH |
7172 | EMACS_INT pos = coding->dst_pos + coding->produced_char; |
7173 | ||
df7492f9 KH |
7174 | coding_set_source (coding); |
7175 | coding->annotated = 0; | |
69a80ea3 | 7176 | coding->charbuf_used = carryover; |
df7492f9 | 7177 | (*(coding->decoder)) (coding); |
df7492f9 | 7178 | coding_set_destination (coding); |
69a80ea3 | 7179 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 7180 | if (coding->annotated) |
69a80ea3 KH |
7181 | produce_annotation (coding, pos); |
7182 | for (i = 0; i < carryover; i++) | |
7183 | coding->charbuf[i] | |
7184 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 7185 | } |
d0396581 KH |
7186 | while (coding->result == CODING_RESULT_INSUFFICIENT_DST |
7187 | || (coding->consumed < coding->src_bytes | |
7188 | && (coding->result == CODING_RESULT_SUCCESS | |
7189 | || coding->result == CODING_RESULT_INVALID_SRC))); | |
d46c5b12 | 7190 | |
69a80ea3 KH |
7191 | if (carryover > 0) |
7192 | { | |
7193 | coding_set_destination (coding); | |
7194 | coding->charbuf_used = carryover; | |
7195 | produce_chars (coding, translation_table, 1); | |
7196 | } | |
7197 | ||
df7492f9 KH |
7198 | coding->carryover_bytes = 0; |
7199 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 7200 | { |
df7492f9 | 7201 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 7202 | const unsigned char *src; |
df7492f9 KH |
7203 | |
7204 | coding_set_source (coding); | |
7205 | coding_set_destination (coding); | |
7206 | src = coding->source + coding->consumed; | |
7207 | ||
7208 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 7209 | { |
df7492f9 KH |
7210 | /* Flush out unprocessed data as binary chars. We are sure |
7211 | that the number of data is less than the size of | |
7212 | coding->charbuf. */ | |
065e3595 | 7213 | coding->charbuf_used = 0; |
b2dab6c8 JR |
7214 | coding->chars_at_source = 0; |
7215 | ||
df7492f9 | 7216 | while (nbytes-- > 0) |
1c3478b0 | 7217 | { |
df7492f9 | 7218 | int c = *src++; |
98725083 | 7219 | |
1c91457d KH |
7220 | if (c & 0x80) |
7221 | c = BYTE8_TO_CHAR (c); | |
7222 | coding->charbuf[coding->charbuf_used++] = c; | |
1c3478b0 | 7223 | } |
f6cbaf43 | 7224 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 7225 | } |
d46c5b12 | 7226 | else |
df7492f9 KH |
7227 | { |
7228 | /* Record unprocessed bytes in coding->carryover. We are | |
7229 | sure that the number of data is less than the size of | |
7230 | coding->carryover. */ | |
7231 | unsigned char *p = coding->carryover; | |
7232 | ||
f289d375 KH |
7233 | if (nbytes > sizeof coding->carryover) |
7234 | nbytes = sizeof coding->carryover; | |
df7492f9 KH |
7235 | coding->carryover_bytes = nbytes; |
7236 | while (nbytes-- > 0) | |
7237 | *p++ = *src++; | |
1c3478b0 | 7238 | } |
df7492f9 | 7239 | coding->consumed = coding->src_bytes; |
b73bfc1c | 7240 | } |
69f76525 | 7241 | |
0a9564cb EZ |
7242 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix) |
7243 | && !inhibit_eol_conversion) | |
4347441b | 7244 | decode_eol (coding); |
24a73b0a KH |
7245 | if (BUFFERP (coding->dst_object)) |
7246 | { | |
7247 | current_buffer->undo_list = undo_list; | |
7248 | record_insert (coding->dst_pos, coding->produced_char); | |
7249 | } | |
73be902c | 7250 | return coding->result; |
4ed46869 KH |
7251 | } |
7252 | ||
aaaf0b1e | 7253 | |
e1c23804 | 7254 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
7255 | ending before LIMIT of CODING->src_object (buffer or string), store |
7256 | the data in BUF, set *STOP to a starting position of the next | |
7257 | composition (if any) or to LIMIT, and return the address of the | |
7258 | next element of BUF. | |
7259 | ||
7260 | If such an annotation is not found, set *STOP to a starting | |
7261 | position of a composition after POS (if any) or to LIMIT, and | |
7262 | return BUF. */ | |
7263 | ||
7264 | static INLINE int * | |
7265 | handle_composition_annotation (pos, limit, coding, buf, stop) | |
7266 | EMACS_INT pos, limit; | |
aaaf0b1e | 7267 | struct coding_system *coding; |
ff0dacd7 KH |
7268 | int *buf; |
7269 | EMACS_INT *stop; | |
aaaf0b1e | 7270 | { |
ff0dacd7 KH |
7271 | EMACS_INT start, end; |
7272 | Lisp_Object prop; | |
aaaf0b1e | 7273 | |
ff0dacd7 KH |
7274 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
7275 | || end > limit) | |
7276 | *stop = limit; | |
7277 | else if (start > pos) | |
7278 | *stop = start; | |
7279 | else | |
aaaf0b1e | 7280 | { |
ff0dacd7 | 7281 | if (start == pos) |
aaaf0b1e | 7282 | { |
ff0dacd7 KH |
7283 | /* We found a composition. Store the corresponding |
7284 | annotation data in BUF. */ | |
7285 | int *head = buf; | |
7286 | enum composition_method method = COMPOSITION_METHOD (prop); | |
7287 | int nchars = COMPOSITION_LENGTH (prop); | |
7288 | ||
e951386e | 7289 | ADD_COMPOSITION_DATA (buf, nchars, 0, method); |
ff0dacd7 | 7290 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 7291 | { |
ff0dacd7 KH |
7292 | Lisp_Object components; |
7293 | int len, i, i_byte; | |
7294 | ||
7295 | components = COMPOSITION_COMPONENTS (prop); | |
7296 | if (VECTORP (components)) | |
aaaf0b1e | 7297 | { |
ff0dacd7 KH |
7298 | len = XVECTOR (components)->size; |
7299 | for (i = 0; i < len; i++) | |
7300 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 7301 | } |
ff0dacd7 | 7302 | else if (STRINGP (components)) |
aaaf0b1e | 7303 | { |
8f924df7 | 7304 | len = SCHARS (components); |
ff0dacd7 KH |
7305 | i = i_byte = 0; |
7306 | while (i < len) | |
7307 | { | |
7308 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
7309 | buf++; | |
7310 | } | |
7311 | } | |
7312 | else if (INTEGERP (components)) | |
7313 | { | |
7314 | len = 1; | |
7315 | *buf++ = XINT (components); | |
7316 | } | |
7317 | else if (CONSP (components)) | |
7318 | { | |
7319 | for (len = 0; CONSP (components); | |
7320 | len++, components = XCDR (components)) | |
7321 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 7322 | } |
aaaf0b1e | 7323 | else |
ff0dacd7 KH |
7324 | abort (); |
7325 | *head -= len; | |
aaaf0b1e | 7326 | } |
aaaf0b1e | 7327 | } |
ff0dacd7 KH |
7328 | |
7329 | if (find_composition (end, limit, &start, &end, &prop, | |
7330 | coding->src_object) | |
7331 | && end <= limit) | |
7332 | *stop = start; | |
7333 | else | |
7334 | *stop = limit; | |
aaaf0b1e | 7335 | } |
ff0dacd7 KH |
7336 | return buf; |
7337 | } | |
7338 | ||
7339 | ||
e1c23804 | 7340 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
7341 | CODING->src_object (buffer of string), store the data in BUF, set |
7342 | *STOP to the position where the value of `charset' property changes | |
7343 | (limiting by LIMIT), and return the address of the next element of | |
7344 | BUF. | |
7345 | ||
7346 | If the property value is nil, set *STOP to the position where the | |
7347 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
7348 | ||
7349 | static INLINE int * | |
7350 | handle_charset_annotation (pos, limit, coding, buf, stop) | |
7351 | EMACS_INT pos, limit; | |
7352 | struct coding_system *coding; | |
7353 | int *buf; | |
7354 | EMACS_INT *stop; | |
7355 | { | |
7356 | Lisp_Object val, next; | |
7357 | int id; | |
7358 | ||
7359 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
7360 | if (! NILP (val) && CHARSETP (val)) | |
7361 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
7362 | else | |
7363 | id = -1; | |
69a80ea3 | 7364 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
7365 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
7366 | coding->src_object, | |
7367 | make_number (limit)); | |
7368 | *stop = XINT (next); | |
7369 | return buf; | |
7370 | } | |
7371 | ||
7372 | ||
df7492f9 | 7373 | static void |
09ee6fdd | 7374 | consume_chars (coding, translation_table, max_lookup) |
df7492f9 | 7375 | struct coding_system *coding; |
433f7f87 | 7376 | Lisp_Object translation_table; |
09ee6fdd | 7377 | int max_lookup; |
df7492f9 KH |
7378 | { |
7379 | int *buf = coding->charbuf; | |
ff0dacd7 | 7380 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 7381 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 7382 | const unsigned char *src_end = coding->source + coding->src_bytes; |
ff0dacd7 KH |
7383 | EMACS_INT pos = coding->src_pos + coding->consumed_char; |
7384 | EMACS_INT end_pos = coding->src_pos + coding->src_chars; | |
df7492f9 KH |
7385 | int multibytep = coding->src_multibyte; |
7386 | Lisp_Object eol_type; | |
7387 | int c; | |
ff0dacd7 | 7388 | EMACS_INT stop, stop_composition, stop_charset; |
09ee6fdd | 7389 | int *lookup_buf = NULL; |
433f7f87 KH |
7390 | |
7391 | if (! NILP (translation_table)) | |
09ee6fdd | 7392 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 7393 | |
0a9564cb | 7394 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
df7492f9 KH |
7395 | if (VECTORP (eol_type)) |
7396 | eol_type = Qunix; | |
88993dfd | 7397 | |
df7492f9 KH |
7398 | /* Note: composition handling is not yet implemented. */ |
7399 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 7400 | |
0b5670c9 KH |
7401 | if (NILP (coding->src_object)) |
7402 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 7403 | else |
0b5670c9 KH |
7404 | { |
7405 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
7406 | stop = stop_composition = pos; | |
7407 | else | |
7408 | stop = stop_composition = end_pos; | |
7409 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
7410 | stop = stop_charset = pos; | |
7411 | else | |
7412 | stop_charset = end_pos; | |
7413 | } | |
ec6d2bb8 | 7414 | |
24a73b0a | 7415 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 7416 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 7417 | while (buf < buf_end) |
aaaf0b1e | 7418 | { |
433f7f87 KH |
7419 | Lisp_Object trans; |
7420 | ||
df7492f9 | 7421 | if (pos == stop) |
ec6d2bb8 | 7422 | { |
df7492f9 KH |
7423 | if (pos == end_pos) |
7424 | break; | |
ff0dacd7 KH |
7425 | if (pos == stop_composition) |
7426 | buf = handle_composition_annotation (pos, end_pos, coding, | |
7427 | buf, &stop_composition); | |
7428 | if (pos == stop_charset) | |
7429 | buf = handle_charset_annotation (pos, end_pos, coding, | |
7430 | buf, &stop_charset); | |
7431 | stop = (stop_composition < stop_charset | |
7432 | ? stop_composition : stop_charset); | |
df7492f9 KH |
7433 | } |
7434 | ||
7435 | if (! multibytep) | |
4776e638 | 7436 | { |
d3e4cb56 | 7437 | EMACS_INT bytes; |
aaaf0b1e | 7438 | |
4d1e6632 KH |
7439 | if (coding->encoder == encode_coding_raw_text |
7440 | || coding->encoder == encode_coding_ccl) | |
ea29edf2 KH |
7441 | c = *src++, pos++; |
7442 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
db274c7a | 7443 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes; |
4776e638 | 7444 | else |
f03caae0 | 7445 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 7446 | } |
df7492f9 | 7447 | else |
db274c7a | 7448 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos++; |
df7492f9 KH |
7449 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
7450 | c = '\n'; | |
7451 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 7452 | { |
df7492f9 | 7453 | if (c == '\n') |
aaaf0b1e | 7454 | { |
df7492f9 KH |
7455 | if (EQ (eol_type, Qdos)) |
7456 | *buf++ = '\r'; | |
7457 | else | |
7458 | c = '\r'; | |
aaaf0b1e KH |
7459 | } |
7460 | } | |
433f7f87 | 7461 | |
e6a54062 | 7462 | trans = Qnil; |
09ee6fdd | 7463 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 7464 | if (NILP (trans)) |
433f7f87 KH |
7465 | *buf++ = c; |
7466 | else | |
7467 | { | |
7468 | int from_nchars = 1, to_nchars = 1; | |
7469 | int *lookup_buf_end; | |
7470 | const unsigned char *p = src; | |
7471 | int i; | |
7472 | ||
7473 | lookup_buf[0] = c; | |
7474 | for (i = 1; i < max_lookup && p < src_end; i++) | |
7475 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
7476 | lookup_buf_end = lookup_buf + i; | |
e951386e KH |
7477 | trans = get_translation (trans, lookup_buf, lookup_buf_end); |
7478 | if (INTEGERP (trans)) | |
7479 | c = XINT (trans); | |
7480 | else if (CONSP (trans)) | |
7481 | { | |
7482 | from_nchars = ASIZE (XCAR (trans)); | |
7483 | trans = XCDR (trans); | |
7484 | if (INTEGERP (trans)) | |
7485 | c = XINT (trans); | |
7486 | else | |
7487 | { | |
7488 | to_nchars = ASIZE (trans); | |
7489 | if (buf + to_nchars > buf_end) | |
7490 | break; | |
7491 | c = XINT (AREF (trans, 0)); | |
7492 | } | |
7493 | } | |
7494 | else | |
433f7f87 | 7495 | break; |
e951386e | 7496 | *buf++ = c; |
433f7f87 KH |
7497 | for (i = 1; i < to_nchars; i++) |
7498 | *buf++ = XINT (AREF (trans, i)); | |
7499 | for (i = 1; i < from_nchars; i++, pos++) | |
7500 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
7501 | } | |
aaaf0b1e | 7502 | } |
ec6d2bb8 | 7503 | |
df7492f9 KH |
7504 | coding->consumed = src - coding->source; |
7505 | coding->consumed_char = pos - coding->src_pos; | |
7506 | coding->charbuf_used = buf - coding->charbuf; | |
7507 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
7508 | } |
7509 | ||
4ed46869 | 7510 | |
df7492f9 KH |
7511 | /* Encode the text at CODING->src_object into CODING->dst_object. |
7512 | CODING->src_object is a buffer or a string. | |
7513 | CODING->dst_object is a buffer or nil. | |
7514 | ||
7515 | If CODING->src_object is a buffer, it must be the current buffer. | |
7516 | In this case, if CODING->src_pos is positive, it is a position of | |
7517 | the source text in the buffer, otherwise. the source text is in the | |
7518 | gap area of the buffer, and coding->src_pos specifies the offset of | |
7519 | the text from GPT (which must be the same as PT). If this is the | |
7520 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7521 | negative and CODING should not have `pre-write-conversion'. | |
7522 | ||
7523 | If CODING->src_object is a string, CODING should not have | |
7524 | `pre-write-conversion'. | |
7525 | ||
7526 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
7527 | the current point of that buffer. | |
7528 | ||
7529 | If CODING->dst_object is nil, the encoded data is placed at the | |
7530 | memory area specified by CODING->destination. */ | |
7531 | ||
7532 | static int | |
7533 | encode_coding (coding) | |
4ed46869 | 7534 | struct coding_system *coding; |
4ed46869 | 7535 | { |
df7492f9 | 7536 | Lisp_Object attrs; |
7d64c6ad | 7537 | Lisp_Object translation_table; |
09ee6fdd | 7538 | int max_lookup; |
fb608df3 | 7539 | struct ccl_spec cclspec; |
9861e777 | 7540 | |
df7492f9 | 7541 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
7542 | if (coding->encoder == encode_coding_raw_text) |
7543 | translation_table = Qnil, max_lookup = 0; | |
7544 | else | |
7545 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 7546 | |
df7492f9 | 7547 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 7548 | { |
df7492f9 KH |
7549 | set_buffer_internal (XBUFFER (coding->dst_object)); |
7550 | coding->dst_multibyte | |
7551 | = ! NILP (current_buffer->enable_multibyte_characters); | |
8844fa83 | 7552 | } |
4ed46869 | 7553 | |
b73bfc1c | 7554 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 7555 | coding->produced = coding->produced_char = 0; |
065e3595 | 7556 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 7557 | coding->errors = 0; |
b73bfc1c | 7558 | |
df7492f9 | 7559 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 7560 | |
fb608df3 KH |
7561 | if (coding->encoder == encode_coding_ccl) |
7562 | { | |
7563 | coding->spec.ccl = &cclspec; | |
7564 | setup_ccl_program (&cclspec.ccl, CODING_CCL_ENCODER (coding)); | |
7565 | } | |
df7492f9 KH |
7566 | do { |
7567 | coding_set_source (coding); | |
09ee6fdd | 7568 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
7569 | coding_set_destination (coding); |
7570 | (*(coding->encoder)) (coding); | |
7571 | } while (coding->consumed_char < coding->src_chars); | |
7572 | ||
284201e4 | 7573 | if (BUFFERP (coding->dst_object) && coding->produced_char > 0) |
df7492f9 KH |
7574 | insert_from_gap (coding->produced_char, coding->produced); |
7575 | ||
7576 | return (coding->result); | |
ec6d2bb8 KH |
7577 | } |
7578 | ||
fb88bf2d | 7579 | |
24a73b0a KH |
7580 | /* Name (or base name) of work buffer for code conversion. */ |
7581 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 7582 | |
24a73b0a KH |
7583 | /* A working buffer used by the top level conversion. Once it is |
7584 | created, it is never destroyed. It has the name | |
7585 | Vcode_conversion_workbuf_name. The other working buffers are | |
7586 | destroyed after the use is finished, and their names are modified | |
7587 | versions of Vcode_conversion_workbuf_name. */ | |
7588 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 7589 | |
24a73b0a KH |
7590 | /* 1 iff Vcode_conversion_reused_workbuf is already in use. */ |
7591 | static int reused_workbuf_in_use; | |
4ed46869 | 7592 | |
24a73b0a KH |
7593 | |
7594 | /* Return a working buffer of code convesion. MULTIBYTE specifies the | |
7595 | multibyteness of returning buffer. */ | |
b73bfc1c | 7596 | |
f6cbaf43 | 7597 | static Lisp_Object |
24a73b0a | 7598 | make_conversion_work_buffer (multibyte) |
f6cbaf43 | 7599 | int multibyte; |
df7492f9 | 7600 | { |
24a73b0a KH |
7601 | Lisp_Object name, workbuf; |
7602 | struct buffer *current; | |
4ed46869 | 7603 | |
24a73b0a | 7604 | if (reused_workbuf_in_use++) |
065e3595 KH |
7605 | { |
7606 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
7607 | workbuf = Fget_buffer_create (name); | |
7608 | } | |
df7492f9 | 7609 | else |
065e3595 | 7610 | { |
159bd5a2 | 7611 | if (NILP (Fbuffer_live_p (Vcode_conversion_reused_workbuf))) |
a993c7a1 KH |
7612 | Vcode_conversion_reused_workbuf |
7613 | = Fget_buffer_create (Vcode_conversion_workbuf_name); | |
7614 | workbuf = Vcode_conversion_reused_workbuf; | |
065e3595 | 7615 | } |
24a73b0a KH |
7616 | current = current_buffer; |
7617 | set_buffer_internal (XBUFFER (workbuf)); | |
df36ff1f CY |
7618 | /* We can't allow modification hooks to run in the work buffer. For |
7619 | instance, directory_files_internal assumes that file decoding | |
7620 | doesn't compile new regexps. */ | |
7621 | Fset (Fmake_local_variable (Qinhibit_modification_hooks), Qt); | |
3ed051d4 | 7622 | Ferase_buffer (); |
df7492f9 | 7623 | current_buffer->undo_list = Qt; |
24a73b0a | 7624 | current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil; |
df7492f9 | 7625 | set_buffer_internal (current); |
24a73b0a | 7626 | return workbuf; |
df7492f9 | 7627 | } |
d46c5b12 | 7628 | |
24a73b0a | 7629 | |
4776e638 | 7630 | static Lisp_Object |
24a73b0a KH |
7631 | code_conversion_restore (arg) |
7632 | Lisp_Object arg; | |
4776e638 | 7633 | { |
24a73b0a | 7634 | Lisp_Object current, workbuf; |
948bdcf3 | 7635 | struct gcpro gcpro1; |
24a73b0a | 7636 | |
948bdcf3 | 7637 | GCPRO1 (arg); |
24a73b0a KH |
7638 | current = XCAR (arg); |
7639 | workbuf = XCDR (arg); | |
7640 | if (! NILP (workbuf)) | |
7641 | { | |
7642 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
7643 | reused_workbuf_in_use = 0; | |
7644 | else if (! NILP (Fbuffer_live_p (workbuf))) | |
7645 | Fkill_buffer (workbuf); | |
7646 | } | |
7647 | set_buffer_internal (XBUFFER (current)); | |
948bdcf3 | 7648 | UNGCPRO; |
4776e638 KH |
7649 | return Qnil; |
7650 | } | |
b73bfc1c | 7651 | |
24a73b0a KH |
7652 | Lisp_Object |
7653 | code_conversion_save (with_work_buf, multibyte) | |
4776e638 | 7654 | int with_work_buf, multibyte; |
df7492f9 | 7655 | { |
24a73b0a | 7656 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 7657 | |
4776e638 | 7658 | if (with_work_buf) |
24a73b0a KH |
7659 | workbuf = make_conversion_work_buffer (multibyte); |
7660 | record_unwind_protect (code_conversion_restore, | |
7661 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 7662 | return workbuf; |
df7492f9 | 7663 | } |
d46c5b12 | 7664 | |
df7492f9 KH |
7665 | int |
7666 | decode_coding_gap (coding, chars, bytes) | |
7667 | struct coding_system *coding; | |
7668 | EMACS_INT chars, bytes; | |
7669 | { | |
7670 | int count = specpdl_ptr - specpdl; | |
5e5c78be | 7671 | Lisp_Object attrs; |
fb88bf2d | 7672 | |
24a73b0a | 7673 | code_conversion_save (0, 0); |
ec6d2bb8 | 7674 | |
24a73b0a | 7675 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7676 | coding->src_chars = chars; |
7677 | coding->src_bytes = bytes; | |
7678 | coding->src_pos = -chars; | |
7679 | coding->src_pos_byte = -bytes; | |
7680 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 7681 | coding->dst_object = coding->src_object; |
df7492f9 KH |
7682 | coding->dst_pos = PT; |
7683 | coding->dst_pos_byte = PT_BYTE; | |
71c81426 | 7684 | coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters); |
4ed46869 | 7685 | |
df7492f9 KH |
7686 | if (CODING_REQUIRE_DETECTION (coding)) |
7687 | detect_coding (coding); | |
8f924df7 | 7688 | |
9286b333 | 7689 | coding->mode |= CODING_MODE_LAST_BLOCK; |
287c57d7 | 7690 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 | 7691 | decode_coding (coding); |
287c57d7 | 7692 | current_buffer->text->inhibit_shrinking = 0; |
d46c5b12 | 7693 | |
5e5c78be KH |
7694 | attrs = CODING_ID_ATTRS (coding->id); |
7695 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 7696 | { |
5e5c78be KH |
7697 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
7698 | Lisp_Object val; | |
7699 | ||
7700 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
7701 | val = call1 (CODING_ATTR_POST_READ (attrs), |
7702 | make_number (coding->produced_char)); | |
5e5c78be KH |
7703 | CHECK_NATNUM (val); |
7704 | coding->produced_char += Z - prev_Z; | |
7705 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 7706 | } |
4ed46869 | 7707 | |
df7492f9 | 7708 | unbind_to (count, Qnil); |
b73bfc1c KH |
7709 | return coding->result; |
7710 | } | |
52d41803 | 7711 | |
4ed46869 | 7712 | int |
df7492f9 | 7713 | encode_coding_gap (coding, chars, bytes) |
4ed46869 | 7714 | struct coding_system *coding; |
df7492f9 | 7715 | EMACS_INT chars, bytes; |
4ed46869 | 7716 | { |
df7492f9 | 7717 | int count = specpdl_ptr - specpdl; |
4ed46869 | 7718 | |
24a73b0a | 7719 | code_conversion_save (0, 0); |
4ed46869 | 7720 | |
24a73b0a | 7721 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7722 | coding->src_chars = chars; |
7723 | coding->src_bytes = bytes; | |
7724 | coding->src_pos = -chars; | |
7725 | coding->src_pos_byte = -bytes; | |
7726 | coding->src_multibyte = chars < bytes; | |
7727 | coding->dst_object = coding->src_object; | |
7728 | coding->dst_pos = PT; | |
7729 | coding->dst_pos_byte = PT_BYTE; | |
4ed46869 | 7730 | |
df7492f9 | 7731 | encode_coding (coding); |
b73bfc1c | 7732 | |
df7492f9 KH |
7733 | unbind_to (count, Qnil); |
7734 | return coding->result; | |
7735 | } | |
4ed46869 | 7736 | |
d46c5b12 | 7737 | |
df7492f9 KH |
7738 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
7739 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 7740 | |
df7492f9 | 7741 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 7742 | |
df7492f9 KH |
7743 | If it is a buffer, the text is at point of the buffer. FROM and TO |
7744 | are positions in the buffer. | |
b73bfc1c | 7745 | |
df7492f9 KH |
7746 | If it is a string, the text is at the beginning of the string. |
7747 | FROM and TO are indices to the string. | |
4ed46869 | 7748 | |
df7492f9 KH |
7749 | If it is nil, the text is at coding->source. FROM and TO are |
7750 | indices to coding->source. | |
bb10be8b | 7751 | |
df7492f9 | 7752 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 7753 | |
df7492f9 KH |
7754 | If it is a buffer, the decoded text is inserted at point of the |
7755 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
7756 | is deleted. | |
4ed46869 | 7757 | |
df7492f9 KH |
7758 | If it is Qt, a string is made from the decoded text, and |
7759 | set in CODING->dst_object. | |
d46c5b12 | 7760 | |
df7492f9 | 7761 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 7762 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
7763 | CODING->destination by xmalloc. If the decoded text is longer than |
7764 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
7765 | */ | |
d46c5b12 | 7766 | |
df7492f9 KH |
7767 | void |
7768 | decode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
7769 | dst_object) | |
d46c5b12 | 7770 | struct coding_system *coding; |
df7492f9 KH |
7771 | Lisp_Object src_object; |
7772 | EMACS_INT from, from_byte, to, to_byte; | |
7773 | Lisp_Object dst_object; | |
d46c5b12 | 7774 | { |
df7492f9 KH |
7775 | int count = specpdl_ptr - specpdl; |
7776 | unsigned char *destination; | |
7777 | EMACS_INT dst_bytes; | |
7778 | EMACS_INT chars = to - from; | |
7779 | EMACS_INT bytes = to_byte - from_byte; | |
7780 | Lisp_Object attrs; | |
4776e638 | 7781 | int saved_pt = -1, saved_pt_byte; |
64cedb0c | 7782 | int need_marker_adjustment = 0; |
b3bfad50 | 7783 | Lisp_Object old_deactivate_mark; |
d46c5b12 | 7784 | |
b3bfad50 | 7785 | old_deactivate_mark = Vdeactivate_mark; |
93dec019 | 7786 | |
df7492f9 | 7787 | if (NILP (dst_object)) |
d46c5b12 | 7788 | { |
df7492f9 KH |
7789 | destination = coding->destination; |
7790 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 7791 | } |
93dec019 | 7792 | |
df7492f9 KH |
7793 | coding->src_object = src_object; |
7794 | coding->src_chars = chars; | |
7795 | coding->src_bytes = bytes; | |
7796 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 7797 | |
df7492f9 | 7798 | if (STRINGP (src_object)) |
d46c5b12 | 7799 | { |
df7492f9 KH |
7800 | coding->src_pos = from; |
7801 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7802 | } |
df7492f9 | 7803 | else if (BUFFERP (src_object)) |
88993dfd | 7804 | { |
df7492f9 KH |
7805 | set_buffer_internal (XBUFFER (src_object)); |
7806 | if (from != GPT) | |
7807 | move_gap_both (from, from_byte); | |
7808 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 7809 | { |
64cedb0c KH |
7810 | struct Lisp_Marker *tail; |
7811 | ||
7812 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7813 | { | |
7814 | tail->need_adjustment | |
7815 | = tail->charpos == (tail->insertion_type ? from : to); | |
7816 | need_marker_adjustment |= tail->need_adjustment; | |
7817 | } | |
4776e638 | 7818 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 | 7819 | TEMP_SET_PT_BOTH (from, from_byte); |
f4a3cc44 | 7820 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 KH |
7821 | del_range_both (from, from_byte, to, to_byte, 1); |
7822 | coding->src_pos = -chars; | |
7823 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 7824 | } |
df7492f9 | 7825 | else |
fb88bf2d | 7826 | { |
df7492f9 KH |
7827 | coding->src_pos = from; |
7828 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 7829 | } |
88993dfd KH |
7830 | } |
7831 | ||
df7492f9 KH |
7832 | if (CODING_REQUIRE_DETECTION (coding)) |
7833 | detect_coding (coding); | |
7834 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 7835 | |
2cb26057 KH |
7836 | if (EQ (dst_object, Qt) |
7837 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
7838 | && NILP (dst_object))) | |
b73bfc1c | 7839 | { |
a1567c45 SM |
7840 | coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding); |
7841 | coding->dst_object = code_conversion_save (1, coding->dst_multibyte); | |
df7492f9 KH |
7842 | coding->dst_pos = BEG; |
7843 | coding->dst_pos_byte = BEG_BYTE; | |
b73bfc1c | 7844 | } |
df7492f9 | 7845 | else if (BUFFERP (dst_object)) |
d46c5b12 | 7846 | { |
24a73b0a | 7847 | code_conversion_save (0, 0); |
df7492f9 KH |
7848 | coding->dst_object = dst_object; |
7849 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
7850 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
7851 | coding->dst_multibyte | |
7852 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
d46c5b12 KH |
7853 | } |
7854 | else | |
7855 | { | |
24a73b0a | 7856 | code_conversion_save (0, 0); |
df7492f9 | 7857 | coding->dst_object = Qnil; |
0154725e SM |
7858 | /* Most callers presume this will return a multibyte result, and they |
7859 | won't use `binary' or `raw-text' anyway, so let's not worry about | |
7860 | CODING_FOR_UNIBYTE. */ | |
bb555731 | 7861 | coding->dst_multibyte = 1; |
d46c5b12 KH |
7862 | } |
7863 | ||
df7492f9 | 7864 | decode_coding (coding); |
fa46990e | 7865 | |
df7492f9 KH |
7866 | if (BUFFERP (coding->dst_object)) |
7867 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 7868 | |
df7492f9 | 7869 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 7870 | { |
b3bfad50 | 7871 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
df7492f9 | 7872 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
2b4f9037 | 7873 | Lisp_Object val; |
d46c5b12 | 7874 | |
c0cc7f7f | 7875 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
b3bfad50 KH |
7876 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7877 | old_deactivate_mark); | |
d4850d67 KH |
7878 | val = safe_call1 (CODING_ATTR_POST_READ (attrs), |
7879 | make_number (coding->produced_char)); | |
df7492f9 KH |
7880 | UNGCPRO; |
7881 | CHECK_NATNUM (val); | |
7882 | coding->produced_char += Z - prev_Z; | |
7883 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 7884 | } |
de79a6a5 | 7885 | |
df7492f9 | 7886 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 7887 | { |
df7492f9 KH |
7888 | coding->dst_object = Fbuffer_string (); |
7889 | } | |
7890 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
7891 | { | |
7892 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7893 | if (dst_bytes < coding->produced) | |
7894 | { | |
b3bfad50 | 7895 | destination = xrealloc (destination, coding->produced); |
df7492f9 KH |
7896 | if (! destination) |
7897 | { | |
065e3595 | 7898 | record_conversion_result (coding, |
ebaf11b6 | 7899 | CODING_RESULT_INSUFFICIENT_MEM); |
df7492f9 KH |
7900 | unbind_to (count, Qnil); |
7901 | return; | |
7902 | } | |
7903 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
7904 | move_gap_both (BEGV, BEGV_BYTE); | |
7905 | bcopy (BEGV_ADDR, destination, coding->produced); | |
7906 | coding->destination = destination; | |
d46c5b12 | 7907 | } |
ec6d2bb8 | 7908 | } |
b73bfc1c | 7909 | |
4776e638 KH |
7910 | if (saved_pt >= 0) |
7911 | { | |
7912 | /* This is the case of: | |
7913 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7914 | As we have moved PT while replacing the original buffer | |
7915 | contents, we must recover it now. */ | |
7916 | set_buffer_internal (XBUFFER (src_object)); | |
f4a3cc44 | 7917 | current_buffer->text->inhibit_shrinking = 0; |
4776e638 KH |
7918 | if (saved_pt < from) |
7919 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7920 | else if (saved_pt < from + chars) | |
7921 | TEMP_SET_PT_BOTH (from, from_byte); | |
7922 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
7923 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
7924 | saved_pt_byte + (coding->produced - bytes)); | |
7925 | else | |
7926 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
7927 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7928 | |
7929 | if (need_marker_adjustment) | |
7930 | { | |
7931 | struct Lisp_Marker *tail; | |
7932 | ||
7933 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7934 | if (tail->need_adjustment) | |
7935 | { | |
7936 | tail->need_adjustment = 0; | |
7937 | if (tail->insertion_type) | |
7938 | { | |
7939 | tail->bytepos = from_byte; | |
7940 | tail->charpos = from; | |
7941 | } | |
7942 | else | |
7943 | { | |
7944 | tail->bytepos = from_byte + coding->produced; | |
7945 | tail->charpos | |
7946 | = (NILP (current_buffer->enable_multibyte_characters) | |
7947 | ? tail->bytepos : from + coding->produced_char); | |
7948 | } | |
7949 | } | |
7950 | } | |
d46c5b12 | 7951 | } |
4776e638 | 7952 | |
b3bfad50 | 7953 | Vdeactivate_mark = old_deactivate_mark; |
065e3595 | 7954 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
7955 | } |
7956 | ||
d46c5b12 | 7957 | |
df7492f9 KH |
7958 | void |
7959 | encode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
7960 | dst_object) | |
d46c5b12 | 7961 | struct coding_system *coding; |
df7492f9 KH |
7962 | Lisp_Object src_object; |
7963 | EMACS_INT from, from_byte, to, to_byte; | |
7964 | Lisp_Object dst_object; | |
d46c5b12 | 7965 | { |
b73bfc1c | 7966 | int count = specpdl_ptr - specpdl; |
df7492f9 KH |
7967 | EMACS_INT chars = to - from; |
7968 | EMACS_INT bytes = to_byte - from_byte; | |
7969 | Lisp_Object attrs; | |
4776e638 | 7970 | int saved_pt = -1, saved_pt_byte; |
64cedb0c | 7971 | int need_marker_adjustment = 0; |
c02d943b | 7972 | int kill_src_buffer = 0; |
b3bfad50 | 7973 | Lisp_Object old_deactivate_mark; |
df7492f9 | 7974 | |
b3bfad50 | 7975 | old_deactivate_mark = Vdeactivate_mark; |
df7492f9 KH |
7976 | |
7977 | coding->src_object = src_object; | |
7978 | coding->src_chars = chars; | |
7979 | coding->src_bytes = bytes; | |
7980 | coding->src_multibyte = chars < bytes; | |
7981 | ||
7982 | attrs = CODING_ID_ATTRS (coding->id); | |
7983 | ||
64cedb0c KH |
7984 | if (EQ (src_object, dst_object)) |
7985 | { | |
7986 | struct Lisp_Marker *tail; | |
7987 | ||
7988 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7989 | { | |
7990 | tail->need_adjustment | |
7991 | = tail->charpos == (tail->insertion_type ? from : to); | |
7992 | need_marker_adjustment |= tail->need_adjustment; | |
7993 | } | |
7994 | } | |
7995 | ||
df7492f9 | 7996 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) |
6bac5b12 | 7997 | { |
24a73b0a | 7998 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
7999 | set_buffer_internal (XBUFFER (coding->src_object)); |
8000 | if (STRINGP (src_object)) | |
8001 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
8002 | else if (BUFFERP (src_object)) | |
8003 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
8004 | else | |
8005 | insert_1_both (coding->source + from, chars, bytes, 0, 0, 0); | |
d46c5b12 | 8006 | |
df7492f9 KH |
8007 | if (EQ (src_object, dst_object)) |
8008 | { | |
8009 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 8010 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
8011 | del_range_both (from, from_byte, to, to_byte, 1); |
8012 | set_buffer_internal (XBUFFER (coding->src_object)); | |
8013 | } | |
8014 | ||
d4850d67 KH |
8015 | { |
8016 | Lisp_Object args[3]; | |
b3bfad50 | 8017 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d4850d67 | 8018 | |
b3bfad50 KH |
8019 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
8020 | old_deactivate_mark); | |
d4850d67 KH |
8021 | args[0] = CODING_ATTR_PRE_WRITE (attrs); |
8022 | args[1] = make_number (BEG); | |
8023 | args[2] = make_number (Z); | |
8024 | safe_call (3, args); | |
b3bfad50 | 8025 | UNGCPRO; |
d4850d67 | 8026 | } |
c02d943b KH |
8027 | if (XBUFFER (coding->src_object) != current_buffer) |
8028 | kill_src_buffer = 1; | |
ac87bbef | 8029 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
8030 | if (BEG != GPT) |
8031 | move_gap_both (BEG, BEG_BYTE); | |
8032 | coding->src_chars = Z - BEG; | |
8033 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
8034 | coding->src_pos = BEG; | |
8035 | coding->src_pos_byte = BEG_BYTE; | |
8036 | coding->src_multibyte = Z < Z_BYTE; | |
8037 | } | |
8038 | else if (STRINGP (src_object)) | |
d46c5b12 | 8039 | { |
24a73b0a | 8040 | code_conversion_save (0, 0); |
df7492f9 KH |
8041 | coding->src_pos = from; |
8042 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 8043 | } |
df7492f9 | 8044 | else if (BUFFERP (src_object)) |
b73bfc1c | 8045 | { |
24a73b0a | 8046 | code_conversion_save (0, 0); |
df7492f9 | 8047 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 8048 | if (EQ (src_object, dst_object)) |
d46c5b12 | 8049 | { |
4776e638 | 8050 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
8051 | coding->src_object = del_range_1 (from, to, 1, 1); |
8052 | coding->src_pos = 0; | |
8053 | coding->src_pos_byte = 0; | |
d46c5b12 | 8054 | } |
df7492f9 | 8055 | else |
d46c5b12 | 8056 | { |
ff0dacd7 KH |
8057 | if (from < GPT && to >= GPT) |
8058 | move_gap_both (from, from_byte); | |
df7492f9 KH |
8059 | coding->src_pos = from; |
8060 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 8061 | } |
d46c5b12 | 8062 | } |
4776e638 | 8063 | else |
24a73b0a | 8064 | code_conversion_save (0, 0); |
d46c5b12 | 8065 | |
df7492f9 | 8066 | if (BUFFERP (dst_object)) |
88993dfd | 8067 | { |
df7492f9 | 8068 | coding->dst_object = dst_object; |
28f67a95 KH |
8069 | if (EQ (src_object, dst_object)) |
8070 | { | |
8071 | coding->dst_pos = from; | |
8072 | coding->dst_pos_byte = from_byte; | |
8073 | } | |
8074 | else | |
8075 | { | |
319a3947 KH |
8076 | struct buffer *current = current_buffer; |
8077 | ||
8078 | set_buffer_temp (XBUFFER (dst_object)); | |
8079 | coding->dst_pos = PT; | |
8080 | coding->dst_pos_byte = PT_BYTE; | |
8081 | move_gap_both (coding->dst_pos, coding->dst_pos_byte); | |
8082 | set_buffer_temp (current); | |
28f67a95 | 8083 | } |
df7492f9 KH |
8084 | coding->dst_multibyte |
8085 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
88993dfd | 8086 | } |
df7492f9 | 8087 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 8088 | { |
df7492f9 | 8089 | coding->dst_object = Qnil; |
df7492f9 | 8090 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
8091 | if (coding->dst_bytes == 0) |
8092 | coding->dst_bytes = 1; | |
8093 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 8094 | coding->dst_multibyte = 0; |
d46c5b12 KH |
8095 | } |
8096 | else | |
8097 | { | |
df7492f9 KH |
8098 | coding->dst_object = Qnil; |
8099 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
8100 | } |
8101 | ||
df7492f9 | 8102 | encode_coding (coding); |
d46c5b12 | 8103 | |
df7492f9 | 8104 | if (EQ (dst_object, Qt)) |
d46c5b12 | 8105 | { |
df7492f9 KH |
8106 | if (BUFFERP (coding->dst_object)) |
8107 | coding->dst_object = Fbuffer_string (); | |
8108 | else | |
d46c5b12 | 8109 | { |
df7492f9 KH |
8110 | coding->dst_object |
8111 | = make_unibyte_string ((char *) coding->destination, | |
8112 | coding->produced); | |
8113 | xfree (coding->destination); | |
d46c5b12 | 8114 | } |
4ed46869 | 8115 | } |
d46c5b12 | 8116 | |
4776e638 KH |
8117 | if (saved_pt >= 0) |
8118 | { | |
8119 | /* This is the case of: | |
8120 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
8121 | As we have moved PT while replacing the original buffer | |
8122 | contents, we must recover it now. */ | |
8123 | set_buffer_internal (XBUFFER (src_object)); | |
8124 | if (saved_pt < from) | |
8125 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
8126 | else if (saved_pt < from + chars) | |
8127 | TEMP_SET_PT_BOTH (from, from_byte); | |
8128 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
8129 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
8130 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 8131 | else |
4776e638 KH |
8132 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
8133 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
8134 | |
8135 | if (need_marker_adjustment) | |
8136 | { | |
8137 | struct Lisp_Marker *tail; | |
8138 | ||
8139 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
8140 | if (tail->need_adjustment) | |
8141 | { | |
8142 | tail->need_adjustment = 0; | |
8143 | if (tail->insertion_type) | |
8144 | { | |
8145 | tail->bytepos = from_byte; | |
8146 | tail->charpos = from; | |
8147 | } | |
8148 | else | |
8149 | { | |
8150 | tail->bytepos = from_byte + coding->produced; | |
8151 | tail->charpos | |
8152 | = (NILP (current_buffer->enable_multibyte_characters) | |
8153 | ? tail->bytepos : from + coding->produced_char); | |
8154 | } | |
8155 | } | |
8156 | } | |
4776e638 KH |
8157 | } |
8158 | ||
c02d943b KH |
8159 | if (kill_src_buffer) |
8160 | Fkill_buffer (coding->src_object); | |
b3bfad50 KH |
8161 | |
8162 | Vdeactivate_mark = old_deactivate_mark; | |
df7492f9 | 8163 | unbind_to (count, Qnil); |
b73bfc1c KH |
8164 | } |
8165 | ||
df7492f9 | 8166 | |
b73bfc1c | 8167 | Lisp_Object |
df7492f9 | 8168 | preferred_coding_system () |
b73bfc1c | 8169 | { |
df7492f9 | 8170 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 8171 | |
df7492f9 | 8172 | return CODING_ID_NAME (id); |
4ed46869 KH |
8173 | } |
8174 | ||
8175 | \f | |
8176 | #ifdef emacs | |
1397dc18 | 8177 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 8178 | |
4ed46869 | 8179 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 8180 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 8181 | See the documentation of `define-coding-system' for information |
48b0f3ae | 8182 | about coding-system objects. */) |
d4a1d553 JB |
8183 | (object) |
8184 | Lisp_Object object; | |
4ed46869 | 8185 | { |
d4a1d553 JB |
8186 | if (NILP (object) |
8187 | || CODING_SYSTEM_ID (object) >= 0) | |
44e8490d | 8188 | return Qt; |
d4a1d553 JB |
8189 | if (! SYMBOLP (object) |
8190 | || NILP (Fget (object, Qcoding_system_define_form))) | |
44e8490d KH |
8191 | return Qnil; |
8192 | return Qt; | |
4ed46869 KH |
8193 | } |
8194 | ||
9d991de8 RS |
8195 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
8196 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae PJ |
8197 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
8198 | (prompt) | |
4ed46869 KH |
8199 | Lisp_Object prompt; |
8200 | { | |
e0e989f6 | 8201 | Lisp_Object val; |
9d991de8 RS |
8202 | do |
8203 | { | |
4608c386 KH |
8204 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
8205 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 8206 | } |
8f924df7 | 8207 | while (SCHARS (val) == 0); |
e0e989f6 | 8208 | return (Fintern (val, Qnil)); |
4ed46869 KH |
8209 | } |
8210 | ||
9b787f3e | 8211 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae | 8212 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
c7183fb8 GM |
8213 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. |
8214 | Ignores case when completing coding systems (all Emacs coding systems | |
8215 | are lower-case). */) | |
48b0f3ae | 8216 | (prompt, default_coding_system) |
9b787f3e | 8217 | Lisp_Object prompt, default_coding_system; |
4ed46869 | 8218 | { |
f44d27ce | 8219 | Lisp_Object val; |
c7183fb8 GM |
8220 | int count = SPECPDL_INDEX (); |
8221 | ||
9b787f3e | 8222 | if (SYMBOLP (default_coding_system)) |
57d25e6f | 8223 | default_coding_system = SYMBOL_NAME (default_coding_system); |
c7183fb8 | 8224 | specbind (Qcompletion_ignore_case, Qt); |
4608c386 | 8225 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
8226 | Qt, Qnil, Qcoding_system_history, |
8227 | default_coding_system, Qnil); | |
c7183fb8 | 8228 | unbind_to (count, Qnil); |
8f924df7 | 8229 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
8230 | } |
8231 | ||
8232 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
8233 | 1, 1, 0, | |
48b0f3ae | 8234 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
8235 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
8236 | It is valid if it is nil or a symbol defined as a coding system by the | |
8237 | function `define-coding-system'. */) | |
df7492f9 | 8238 | (coding_system) |
4ed46869 KH |
8239 | Lisp_Object coding_system; |
8240 | { | |
44e8490d KH |
8241 | Lisp_Object define_form; |
8242 | ||
8243 | define_form = Fget (coding_system, Qcoding_system_define_form); | |
8244 | if (! NILP (define_form)) | |
8245 | { | |
8246 | Fput (coding_system, Qcoding_system_define_form, Qnil); | |
8247 | safe_eval (define_form); | |
8248 | } | |
4ed46869 KH |
8249 | if (!NILP (Fcoding_system_p (coding_system))) |
8250 | return coding_system; | |
fcad4ec4 | 8251 | xsignal1 (Qcoding_system_error, coding_system); |
4ed46869 | 8252 | } |
df7492f9 | 8253 | |
3a73fa5d | 8254 | \f |
89528eb3 KH |
8255 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
8256 | HIGHEST is nonzero, return the coding system of the highest | |
8257 | priority among the detected coding systems. Otherwize return a | |
8258 | list of detected coding systems sorted by their priorities. If | |
8259 | MULTIBYTEP is nonzero, it is assumed that the bytes are in correct | |
8260 | multibyte form but contains only ASCII and eight-bit chars. | |
8261 | Otherwise, the bytes are raw bytes. | |
8262 | ||
8263 | CODING-SYSTEM controls the detection as below: | |
8264 | ||
8265 | If it is nil, detect both text-format and eol-format. If the | |
8266 | text-format part of CODING-SYSTEM is already specified | |
8267 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
8268 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
8269 | detect only text-format. */ | |
8270 | ||
d46c5b12 | 8271 | Lisp_Object |
24a73b0a KH |
8272 | detect_coding_system (src, src_chars, src_bytes, highest, multibytep, |
8273 | coding_system) | |
8f924df7 | 8274 | const unsigned char *src; |
13818c30 SM |
8275 | EMACS_INT src_chars, src_bytes; |
8276 | int highest; | |
0a28aafb | 8277 | int multibytep; |
df7492f9 | 8278 | Lisp_Object coding_system; |
4ed46869 | 8279 | { |
8f924df7 | 8280 | const unsigned char *src_end = src + src_bytes; |
df7492f9 | 8281 | Lisp_Object attrs, eol_type; |
4533845d | 8282 | Lisp_Object val = Qnil; |
df7492f9 | 8283 | struct coding_system coding; |
89528eb3 | 8284 | int id; |
ff0dacd7 | 8285 | struct coding_detection_info detect_info; |
24a73b0a | 8286 | enum coding_category base_category; |
2f3cbb32 | 8287 | int null_byte_found = 0, eight_bit_found = 0; |
b73bfc1c | 8288 | |
df7492f9 KH |
8289 | if (NILP (coding_system)) |
8290 | coding_system = Qundecided; | |
8291 | setup_coding_system (coding_system, &coding); | |
8292 | attrs = CODING_ID_ATTRS (coding.id); | |
8293 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 8294 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 8295 | |
df7492f9 | 8296 | coding.source = src; |
24a73b0a | 8297 | coding.src_chars = src_chars; |
df7492f9 KH |
8298 | coding.src_bytes = src_bytes; |
8299 | coding.src_multibyte = multibytep; | |
8300 | coding.consumed = 0; | |
89528eb3 | 8301 | coding.mode |= CODING_MODE_LAST_BLOCK; |
c0e16b14 | 8302 | coding.head_ascii = 0; |
d46c5b12 | 8303 | |
ff0dacd7 | 8304 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 8305 | |
89528eb3 | 8306 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
8307 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
8308 | if (base_category == coding_category_undecided) | |
4ed46869 | 8309 | { |
ff0dacd7 KH |
8310 | enum coding_category category; |
8311 | struct coding_system *this; | |
8312 | int c, i; | |
88993dfd | 8313 | |
24a73b0a | 8314 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
2f3cbb32 | 8315 | for (; src < src_end; src++) |
4ed46869 | 8316 | { |
df7492f9 | 8317 | c = *src; |
6cb21a4f | 8318 | if (c & 0x80) |
6cb21a4f | 8319 | { |
2f3cbb32 | 8320 | eight_bit_found = 1; |
2f3cbb32 KH |
8321 | if (null_byte_found) |
8322 | break; | |
8323 | } | |
c0e16b14 | 8324 | else if (c < 0x20) |
2f3cbb32 KH |
8325 | { |
8326 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
8327 | && ! inhibit_iso_escape_detection | |
8328 | && ! detect_info.checked) | |
6cb21a4f | 8329 | { |
2f3cbb32 KH |
8330 | if (detect_coding_iso_2022 (&coding, &detect_info)) |
8331 | { | |
8332 | /* We have scanned the whole data. */ | |
8333 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
8334 | { |
8335 | /* We didn't find an 8-bit code. We may | |
8336 | have found a null-byte, but it's very | |
8337 | rare that a binary file confirm to | |
8338 | ISO-2022. */ | |
8339 | src = src_end; | |
8340 | coding.head_ascii = src - coding.source; | |
8341 | } | |
8342 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
8343 | break; |
8344 | } | |
8345 | } | |
97b1b294 | 8346 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
8347 | { |
8348 | null_byte_found = 1; | |
8349 | if (eight_bit_found) | |
8350 | break; | |
6cb21a4f | 8351 | } |
c006c0c8 KH |
8352 | if (! eight_bit_found) |
8353 | coding.head_ascii++; | |
6cb21a4f | 8354 | } |
c006c0c8 | 8355 | else if (! eight_bit_found) |
c0e16b14 | 8356 | coding.head_ascii++; |
4ed46869 | 8357 | } |
88993dfd | 8358 | |
2f3cbb32 KH |
8359 | if (null_byte_found || eight_bit_found |
8360 | || coding.head_ascii < coding.src_bytes | |
6cb21a4f KH |
8361 | || detect_info.found) |
8362 | { | |
2f3cbb32 | 8363 | if (coding.head_ascii == coding.src_bytes) |
6cb21a4f KH |
8364 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ |
8365 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 8366 | { |
6cb21a4f | 8367 | category = coding_priorities[i]; |
c7266f4a | 8368 | this = coding_categories + category; |
6cb21a4f | 8369 | if (detect_info.found & (1 << category)) |
ff0dacd7 KH |
8370 | break; |
8371 | } | |
6cb21a4f | 8372 | else |
2f3cbb32 KH |
8373 | { |
8374 | if (null_byte_found) | |
8375 | { | |
8376 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; | |
8377 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
8378 | } | |
8379 | for (i = 0; i < coding_category_raw_text; i++) | |
8380 | { | |
8381 | category = coding_priorities[i]; | |
8382 | this = coding_categories + category; | |
6cb21a4f | 8383 | |
2f3cbb32 KH |
8384 | if (this->id < 0) |
8385 | { | |
8386 | /* No coding system of this category is defined. */ | |
8387 | detect_info.rejected |= (1 << category); | |
8388 | } | |
8389 | else if (category >= coding_category_raw_text) | |
8390 | continue; | |
8391 | else if (detect_info.checked & (1 << category)) | |
8392 | { | |
8393 | if (highest | |
8394 | && (detect_info.found & (1 << category))) | |
6cb21a4f | 8395 | break; |
2f3cbb32 KH |
8396 | } |
8397 | else if ((*(this->detector)) (&coding, &detect_info) | |
8398 | && highest | |
8399 | && (detect_info.found & (1 << category))) | |
8400 | { | |
8401 | if (category == coding_category_utf_16_auto) | |
8402 | { | |
8403 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8404 | category = coding_category_utf_16_le; | |
8405 | else | |
8406 | category = coding_category_utf_16_be; | |
8407 | } | |
8408 | break; | |
8409 | } | |
8410 | } | |
8411 | } | |
6cb21a4f | 8412 | } |
ec6d2bb8 | 8413 | |
4cddb209 KH |
8414 | if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY |
8415 | || null_byte_found) | |
ec6d2bb8 | 8416 | { |
ff0dacd7 | 8417 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
4cddb209 | 8418 | id = CODING_SYSTEM_ID (Qno_conversion); |
89528eb3 KH |
8419 | val = Fcons (make_number (id), Qnil); |
8420 | } | |
ff0dacd7 | 8421 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 8422 | { |
ff0dacd7 | 8423 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
8424 | id = coding_categories[coding_category_undecided].id; |
8425 | val = Fcons (make_number (id), Qnil); | |
8426 | } | |
8427 | else if (highest) | |
8428 | { | |
ff0dacd7 | 8429 | if (detect_info.found) |
ec6d2bb8 | 8430 | { |
ff0dacd7 KH |
8431 | detect_info.found = 1 << category; |
8432 | val = Fcons (make_number (this->id), Qnil); | |
8433 | } | |
8434 | else | |
8435 | for (i = 0; i < coding_category_raw_text; i++) | |
8436 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
8437 | { | |
8438 | detect_info.found = 1 << coding_priorities[i]; | |
8439 | id = coding_categories[coding_priorities[i]].id; | |
8440 | val = Fcons (make_number (id), Qnil); | |
8441 | break; | |
8442 | } | |
8443 | } | |
89528eb3 KH |
8444 | else |
8445 | { | |
ff0dacd7 KH |
8446 | int mask = detect_info.rejected | detect_info.found; |
8447 | int found = 0; | |
ec6d2bb8 | 8448 | |
89528eb3 | 8449 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
8450 | { |
8451 | category = coding_priorities[i]; | |
8452 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 8453 | { |
ff0dacd7 KH |
8454 | found |= 1 << category; |
8455 | id = coding_categories[category].id; | |
c7266f4a KH |
8456 | if (id >= 0) |
8457 | val = Fcons (make_number (id), val); | |
ff0dacd7 KH |
8458 | } |
8459 | } | |
8460 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
8461 | { | |
8462 | category = coding_priorities[i]; | |
8463 | if (detect_info.found & (1 << category)) | |
8464 | { | |
8465 | id = coding_categories[category].id; | |
8466 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 8467 | } |
ec6d2bb8 | 8468 | } |
ff0dacd7 | 8469 | detect_info.found |= found; |
ec6d2bb8 | 8470 | } |
ec6d2bb8 | 8471 | } |
a470d443 KH |
8472 | else if (base_category == coding_category_utf_8_auto) |
8473 | { | |
8474 | if (detect_coding_utf_8 (&coding, &detect_info)) | |
8475 | { | |
8476 | struct coding_system *this; | |
8477 | ||
8478 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
8479 | this = coding_categories + coding_category_utf_8_sig; | |
8480 | else | |
8481 | this = coding_categories + coding_category_utf_8_nosig; | |
8482 | val = Fcons (make_number (this->id), Qnil); | |
8483 | } | |
8484 | } | |
24a73b0a KH |
8485 | else if (base_category == coding_category_utf_16_auto) |
8486 | { | |
8487 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
8488 | { | |
24a73b0a KH |
8489 | struct coding_system *this; |
8490 | ||
8491 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8492 | this = coding_categories + coding_category_utf_16_le; | |
8493 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
8494 | this = coding_categories + coding_category_utf_16_be; | |
8495 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
8496 | this = coding_categories + coding_category_utf_16_be_nosig; | |
8497 | else | |
8498 | this = coding_categories + coding_category_utf_16_le_nosig; | |
8499 | val = Fcons (make_number (this->id), Qnil); | |
8500 | } | |
8501 | } | |
df7492f9 KH |
8502 | else |
8503 | { | |
ff0dacd7 | 8504 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 8505 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 8506 | } |
df7492f9 | 8507 | |
89528eb3 | 8508 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 8509 | { |
4533845d | 8510 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol = -1; |
df7492f9 KH |
8511 | Lisp_Object tail; |
8512 | ||
89528eb3 KH |
8513 | if (VECTORP (eol_type)) |
8514 | { | |
ff0dacd7 | 8515 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
2f3cbb32 KH |
8516 | { |
8517 | if (null_byte_found) | |
8518 | normal_eol = EOL_SEEN_LF; | |
8519 | else | |
8520 | normal_eol = detect_eol (coding.source, src_bytes, | |
8521 | coding_category_raw_text); | |
8522 | } | |
ff0dacd7 KH |
8523 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
8524 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
8525 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
8526 | coding_category_utf_16_be); | |
ff0dacd7 KH |
8527 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
8528 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
8529 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
8530 | coding_category_utf_16_le); | |
8531 | } | |
8532 | else | |
8533 | { | |
8534 | if (EQ (eol_type, Qunix)) | |
8535 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
8536 | else if (EQ (eol_type, Qdos)) | |
8537 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
8538 | else | |
8539 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
8540 | } | |
8541 | ||
df7492f9 KH |
8542 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
8543 | { | |
89528eb3 | 8544 | enum coding_category category; |
df7492f9 | 8545 | int this_eol; |
89528eb3 KH |
8546 | |
8547 | id = XINT (XCAR (tail)); | |
8548 | attrs = CODING_ID_ATTRS (id); | |
8549 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8550 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
8551 | if (VECTORP (eol_type)) |
8552 | { | |
89528eb3 KH |
8553 | if (category == coding_category_utf_16_be |
8554 | || category == coding_category_utf_16_be_nosig) | |
8555 | this_eol = utf_16_be_eol; | |
8556 | else if (category == coding_category_utf_16_le | |
8557 | || category == coding_category_utf_16_le_nosig) | |
8558 | this_eol = utf_16_le_eol; | |
df7492f9 | 8559 | else |
89528eb3 KH |
8560 | this_eol = normal_eol; |
8561 | ||
df7492f9 KH |
8562 | if (this_eol == EOL_SEEN_LF) |
8563 | XSETCAR (tail, AREF (eol_type, 0)); | |
8564 | else if (this_eol == EOL_SEEN_CRLF) | |
8565 | XSETCAR (tail, AREF (eol_type, 1)); | |
8566 | else if (this_eol == EOL_SEEN_CR) | |
8567 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
8568 | else |
8569 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 8570 | } |
89528eb3 KH |
8571 | else |
8572 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
8573 | } |
8574 | } | |
ec6d2bb8 | 8575 | |
4533845d | 8576 | return (highest ? (CONSP (val) ? XCAR (val) : Qnil) : val); |
ec6d2bb8 KH |
8577 | } |
8578 | ||
ec6d2bb8 | 8579 | |
d46c5b12 KH |
8580 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
8581 | 2, 3, 0, | |
48b0f3ae PJ |
8582 | doc: /* Detect coding system of the text in the region between START and END. |
8583 | Return a list of possible coding systems ordered by priority. | |
b811c52b KH |
8584 | The coding systems to try and their priorities follows what |
8585 | the function `coding-system-priority-list' (which see) returns. | |
ec6d2bb8 | 8586 | |
12e0131a | 8587 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8588 | characters as ESC), it returns a list of single element `undecided' |
8589 | or its subsidiary coding system according to a detected end-of-line | |
8590 | format. | |
ec6d2bb8 | 8591 | |
48b0f3ae PJ |
8592 | If optional argument HIGHEST is non-nil, return the coding system of |
8593 | highest priority. */) | |
8594 | (start, end, highest) | |
d46c5b12 KH |
8595 | Lisp_Object start, end, highest; |
8596 | { | |
8597 | int from, to; | |
8598 | int from_byte, to_byte; | |
ec6d2bb8 | 8599 | |
b7826503 PJ |
8600 | CHECK_NUMBER_COERCE_MARKER (start); |
8601 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 8602 | |
d46c5b12 KH |
8603 | validate_region (&start, &end); |
8604 | from = XINT (start), to = XINT (end); | |
8605 | from_byte = CHAR_TO_BYTE (from); | |
8606 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 8607 | |
d46c5b12 KH |
8608 | if (from < GPT && to >= GPT) |
8609 | move_gap_both (to, to_byte); | |
c210f766 | 8610 | |
d46c5b12 | 8611 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 8612 | to - from, to_byte - from_byte, |
0a28aafb KH |
8613 | !NILP (highest), |
8614 | !NILP (current_buffer | |
df7492f9 KH |
8615 | ->enable_multibyte_characters), |
8616 | Qnil); | |
ec6d2bb8 KH |
8617 | } |
8618 | ||
d46c5b12 KH |
8619 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
8620 | 1, 2, 0, | |
48b0f3ae PJ |
8621 | doc: /* Detect coding system of the text in STRING. |
8622 | Return a list of possible coding systems ordered by priority. | |
67ceab9d KH |
8623 | The coding systems to try and their priorities follows what |
8624 | the function `coding-system-priority-list' (which see) returns. | |
fb88bf2d | 8625 | |
12e0131a | 8626 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8627 | characters as ESC), it returns a list of single element `undecided' |
8628 | or its subsidiary coding system according to a detected end-of-line | |
8629 | format. | |
d46c5b12 | 8630 | |
48b0f3ae PJ |
8631 | If optional argument HIGHEST is non-nil, return the coding system of |
8632 | highest priority. */) | |
8633 | (string, highest) | |
d46c5b12 KH |
8634 | Lisp_Object string, highest; |
8635 | { | |
b7826503 | 8636 | CHECK_STRING (string); |
b73bfc1c | 8637 | |
24a73b0a KH |
8638 | return detect_coding_system (SDATA (string), |
8639 | SCHARS (string), SBYTES (string), | |
8f924df7 | 8640 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 8641 | Qnil); |
4ed46869 | 8642 | } |
4ed46869 | 8643 | |
b73bfc1c | 8644 | |
df7492f9 KH |
8645 | static INLINE int |
8646 | char_encodable_p (c, attrs) | |
8647 | int c; | |
8648 | Lisp_Object attrs; | |
05e6f5dc | 8649 | { |
df7492f9 | 8650 | Lisp_Object tail; |
df7492f9 | 8651 | struct charset *charset; |
7d64c6ad | 8652 | Lisp_Object translation_table; |
d46c5b12 | 8653 | |
7d64c6ad | 8654 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 8655 | if (! NILP (translation_table)) |
7d64c6ad | 8656 | c = translate_char (translation_table, c); |
df7492f9 KH |
8657 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
8658 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 8659 | { |
df7492f9 KH |
8660 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
8661 | if (CHAR_CHARSET_P (c, charset)) | |
8662 | break; | |
e133c8fa | 8663 | } |
df7492f9 | 8664 | return (! NILP (tail)); |
05e6f5dc | 8665 | } |
83fa074f | 8666 | |
fb88bf2d | 8667 | |
df7492f9 KH |
8668 | /* Return a list of coding systems that safely encode the text between |
8669 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
8670 | systems not to check. The returned list doesn't contain any such | |
48468dac | 8671 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 8672 | unibyte, return t. */ |
e077cc80 | 8673 | |
df7492f9 KH |
8674 | DEFUN ("find-coding-systems-region-internal", |
8675 | Ffind_coding_systems_region_internal, | |
8676 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
8677 | doc: /* Internal use only. */) | |
8678 | (start, end, exclude) | |
8679 | Lisp_Object start, end, exclude; | |
8680 | { | |
8681 | Lisp_Object coding_attrs_list, safe_codings; | |
8682 | EMACS_INT start_byte, end_byte; | |
7c78e542 | 8683 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8684 | int c; |
0e727afa | 8685 | Lisp_Object tail, elt, work_table; |
d46c5b12 | 8686 | |
df7492f9 KH |
8687 | if (STRINGP (start)) |
8688 | { | |
8689 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 8690 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8691 | return Qt; |
8692 | start_byte = 0; | |
8f924df7 | 8693 | end_byte = SBYTES (start); |
df7492f9 KH |
8694 | } |
8695 | else | |
d46c5b12 | 8696 | { |
df7492f9 KH |
8697 | CHECK_NUMBER_COERCE_MARKER (start); |
8698 | CHECK_NUMBER_COERCE_MARKER (end); | |
8699 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
8700 | args_out_of_range (start, end); | |
8701 | if (NILP (current_buffer->enable_multibyte_characters)) | |
8702 | return Qt; | |
8703 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8704 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8705 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
8706 | return Qt; | |
d46c5b12 | 8707 | |
e1c23804 | 8708 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 8709 | { |
e1c23804 DL |
8710 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8711 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8712 | else |
e1c23804 | 8713 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
8714 | } |
8715 | } | |
8716 | ||
df7492f9 KH |
8717 | coding_attrs_list = Qnil; |
8718 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
8719 | if (NILP (exclude) | |
8720 | || NILP (Fmemq (XCAR (tail), exclude))) | |
8721 | { | |
8722 | Lisp_Object attrs; | |
d46c5b12 | 8723 | |
df7492f9 KH |
8724 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
8725 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
8726 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
8727 | { |
8728 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 8729 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
8730 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
8731 | } | |
df7492f9 | 8732 | } |
d46c5b12 | 8733 | |
df7492f9 | 8734 | if (STRINGP (start)) |
8f924df7 | 8735 | p = pbeg = SDATA (start); |
df7492f9 KH |
8736 | else |
8737 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
8738 | pend = p + (end_byte - start_byte); | |
b843d1ae | 8739 | |
df7492f9 KH |
8740 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
8741 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 8742 | |
0e727afa | 8743 | work_table = Fmake_char_table (Qnil, Qnil); |
05e6f5dc | 8744 | while (p < pend) |
72d1a715 | 8745 | { |
df7492f9 KH |
8746 | if (ASCII_BYTE_P (*p)) |
8747 | p++; | |
72d1a715 RS |
8748 | else |
8749 | { | |
df7492f9 | 8750 | c = STRING_CHAR_ADVANCE (p); |
0e727afa YM |
8751 | if (!NILP (char_table_ref (work_table, c))) |
8752 | /* This character was already checked. Ignore it. */ | |
8753 | continue; | |
12410ef1 | 8754 | |
df7492f9 KH |
8755 | charset_map_loaded = 0; |
8756 | for (tail = coding_attrs_list; CONSP (tail);) | |
8757 | { | |
8758 | elt = XCAR (tail); | |
8759 | if (NILP (elt)) | |
8760 | tail = XCDR (tail); | |
8761 | else if (char_encodable_p (c, elt)) | |
8762 | tail = XCDR (tail); | |
8763 | else if (CONSP (XCDR (tail))) | |
8764 | { | |
8765 | XSETCAR (tail, XCAR (XCDR (tail))); | |
8766 | XSETCDR (tail, XCDR (XCDR (tail))); | |
8767 | } | |
8768 | else | |
8769 | { | |
8770 | XSETCAR (tail, Qnil); | |
8771 | tail = XCDR (tail); | |
8772 | } | |
8773 | } | |
8774 | if (charset_map_loaded) | |
8775 | { | |
8776 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 8777 | |
df7492f9 | 8778 | if (STRINGP (start)) |
8f924df7 | 8779 | pbeg = SDATA (start); |
df7492f9 KH |
8780 | else |
8781 | pbeg = BYTE_POS_ADDR (start_byte); | |
8782 | p = pbeg + p_offset; | |
8783 | pend = pbeg + pend_offset; | |
8784 | } | |
0e727afa | 8785 | char_table_set (work_table, c, Qt); |
df7492f9 | 8786 | } |
ec6d2bb8 | 8787 | } |
fb88bf2d | 8788 | |
988b3759 | 8789 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
8790 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
8791 | if (! NILP (XCAR (tail))) | |
8792 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 8793 | |
05e6f5dc KH |
8794 | return safe_codings; |
8795 | } | |
4956c225 | 8796 | |
d46c5b12 | 8797 | |
8f924df7 KH |
8798 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
8799 | Sunencodable_char_position, 3, 5, 0, | |
8800 | doc: /* | |
8801 | Return position of first un-encodable character in a region. | |
d4a1d553 | 8802 | START and END specify the region and CODING-SYSTEM specifies the |
8f924df7 | 8803 | encoding to check. Return nil if CODING-SYSTEM does encode the region. |
d46c5b12 | 8804 | |
8f924df7 KH |
8805 | If optional 4th argument COUNT is non-nil, it specifies at most how |
8806 | many un-encodable characters to search. In this case, the value is a | |
8807 | list of positions. | |
d46c5b12 | 8808 | |
8f924df7 KH |
8809 | If optional 5th argument STRING is non-nil, it is a string to search |
8810 | for un-encodable characters. In that case, START and END are indexes | |
8811 | to the string. */) | |
8812 | (start, end, coding_system, count, string) | |
8813 | Lisp_Object start, end, coding_system, count, string; | |
8814 | { | |
8815 | int n; | |
8816 | struct coding_system coding; | |
7d64c6ad | 8817 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 KH |
8818 | Lisp_Object positions; |
8819 | int from, to; | |
8820 | const unsigned char *p, *stop, *pend; | |
8821 | int ascii_compatible; | |
fb88bf2d | 8822 | |
8f924df7 KH |
8823 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
8824 | attrs = CODING_ID_ATTRS (coding.id); | |
8825 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
8826 | return Qnil; | |
8827 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
8828 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 8829 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 8830 | |
8f924df7 KH |
8831 | if (NILP (string)) |
8832 | { | |
8833 | validate_region (&start, &end); | |
8834 | from = XINT (start); | |
8835 | to = XINT (end); | |
8836 | if (NILP (current_buffer->enable_multibyte_characters) | |
8837 | || (ascii_compatible | |
8838 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
8839 | return Qnil; | |
8840 | p = CHAR_POS_ADDR (from); | |
8841 | pend = CHAR_POS_ADDR (to); | |
8842 | if (from < GPT && to >= GPT) | |
8843 | stop = GPT_ADDR; | |
8844 | else | |
8845 | stop = pend; | |
8846 | } | |
8847 | else | |
8848 | { | |
8849 | CHECK_STRING (string); | |
8850 | CHECK_NATNUM (start); | |
8851 | CHECK_NATNUM (end); | |
8852 | from = XINT (start); | |
8853 | to = XINT (end); | |
8854 | if (from > to | |
8855 | || to > SCHARS (string)) | |
8856 | args_out_of_range_3 (string, start, end); | |
8857 | if (! STRING_MULTIBYTE (string)) | |
8858 | return Qnil; | |
8859 | p = SDATA (string) + string_char_to_byte (string, from); | |
8860 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
8861 | if (ascii_compatible && (to - from) == (pend - p)) | |
8862 | return Qnil; | |
8863 | } | |
f2558efd | 8864 | |
8f924df7 KH |
8865 | if (NILP (count)) |
8866 | n = 1; | |
8867 | else | |
b73bfc1c | 8868 | { |
8f924df7 KH |
8869 | CHECK_NATNUM (count); |
8870 | n = XINT (count); | |
b73bfc1c KH |
8871 | } |
8872 | ||
8f924df7 KH |
8873 | positions = Qnil; |
8874 | while (1) | |
d46c5b12 | 8875 | { |
8f924df7 | 8876 | int c; |
ec6d2bb8 | 8877 | |
8f924df7 KH |
8878 | if (ascii_compatible) |
8879 | while (p < stop && ASCII_BYTE_P (*p)) | |
8880 | p++, from++; | |
8881 | if (p >= stop) | |
0e79d667 | 8882 | { |
8f924df7 KH |
8883 | if (p >= pend) |
8884 | break; | |
8885 | stop = pend; | |
8886 | p = GAP_END_ADDR; | |
0e79d667 | 8887 | } |
ec6d2bb8 | 8888 | |
8f924df7 KH |
8889 | c = STRING_CHAR_ADVANCE (p); |
8890 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
8891 | && ! char_charset (translate_char (translation_table, c), |
8892 | charset_list, NULL)) | |
ec6d2bb8 | 8893 | { |
8f924df7 KH |
8894 | positions = Fcons (make_number (from), positions); |
8895 | n--; | |
8896 | if (n == 0) | |
8897 | break; | |
ec6d2bb8 KH |
8898 | } |
8899 | ||
8f924df7 KH |
8900 | from++; |
8901 | } | |
d46c5b12 | 8902 | |
8f924df7 KH |
8903 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
8904 | } | |
d46c5b12 | 8905 | |
d46c5b12 | 8906 | |
df7492f9 KH |
8907 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
8908 | Scheck_coding_systems_region, 3, 3, 0, | |
8909 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 8910 | |
df7492f9 KH |
8911 | START and END are buffer positions specifying the region. |
8912 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 8913 | |
df7492f9 | 8914 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
d4a1d553 | 8915 | CODING-SYSTEM is a member of CODING-SYSTEM-LIST and can't encode the |
df7492f9 KH |
8916 | whole region, POS0, POS1, ... are buffer positions where non-encodable |
8917 | characters are found. | |
93dec019 | 8918 | |
df7492f9 KH |
8919 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
8920 | value is nil. | |
93dec019 | 8921 | |
df7492f9 KH |
8922 | START may be a string. In that case, check if the string is |
8923 | encodable, and the value contains indices to the string instead of | |
5704f39a KH |
8924 | buffer positions. END is ignored. |
8925 | ||
4c1958f4 | 8926 | If the current buffer (or START if it is a string) is unibyte, the value |
5704f39a | 8927 | is nil. */) |
df7492f9 KH |
8928 | (start, end, coding_system_list) |
8929 | Lisp_Object start, end, coding_system_list; | |
05e6f5dc | 8930 | { |
df7492f9 KH |
8931 | Lisp_Object list; |
8932 | EMACS_INT start_byte, end_byte; | |
8933 | int pos; | |
7c78e542 | 8934 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8935 | int c; |
7d64c6ad | 8936 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 8937 | |
05e6f5dc KH |
8938 | if (STRINGP (start)) |
8939 | { | |
df7492f9 | 8940 | if (!STRING_MULTIBYTE (start) |
4c1958f4 | 8941 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8942 | return Qnil; |
8943 | start_byte = 0; | |
8f924df7 | 8944 | end_byte = SBYTES (start); |
df7492f9 | 8945 | pos = 0; |
d46c5b12 | 8946 | } |
05e6f5dc | 8947 | else |
b73bfc1c | 8948 | { |
b7826503 PJ |
8949 | CHECK_NUMBER_COERCE_MARKER (start); |
8950 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
8951 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
8952 | args_out_of_range (start, end); | |
8953 | if (NILP (current_buffer->enable_multibyte_characters)) | |
df7492f9 KH |
8954 | return Qnil; |
8955 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8956 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8957 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
5704f39a | 8958 | return Qnil; |
df7492f9 | 8959 | |
e1c23804 | 8960 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 8961 | { |
e1c23804 DL |
8962 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8963 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8964 | else |
e1c23804 | 8965 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 8966 | } |
e1c23804 | 8967 | pos = XINT (start); |
b73bfc1c | 8968 | } |
7553d0e1 | 8969 | |
df7492f9 KH |
8970 | list = Qnil; |
8971 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 8972 | { |
df7492f9 | 8973 | elt = XCAR (tail); |
7d64c6ad | 8974 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
8975 | ASET (attrs, coding_attr_trans_tbl, |
8976 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 8977 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
8978 | } |
8979 | ||
df7492f9 | 8980 | if (STRINGP (start)) |
8f924df7 | 8981 | p = pbeg = SDATA (start); |
72d1a715 | 8982 | else |
df7492f9 KH |
8983 | p = pbeg = BYTE_POS_ADDR (start_byte); |
8984 | pend = p + (end_byte - start_byte); | |
4ed46869 | 8985 | |
df7492f9 KH |
8986 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
8987 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 8988 | |
df7492f9 | 8989 | while (p < pend) |
d46c5b12 | 8990 | { |
df7492f9 KH |
8991 | if (ASCII_BYTE_P (*p)) |
8992 | p++; | |
e133c8fa | 8993 | else |
05e6f5dc | 8994 | { |
df7492f9 KH |
8995 | c = STRING_CHAR_ADVANCE (p); |
8996 | ||
8997 | charset_map_loaded = 0; | |
8998 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
8999 | { | |
9000 | elt = XCDR (XCAR (tail)); | |
9001 | if (! char_encodable_p (c, XCAR (elt))) | |
9002 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
9003 | } | |
9004 | if (charset_map_loaded) | |
9005 | { | |
9006 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
9007 | ||
9008 | if (STRINGP (start)) | |
8f924df7 | 9009 | pbeg = SDATA (start); |
df7492f9 KH |
9010 | else |
9011 | pbeg = BYTE_POS_ADDR (start_byte); | |
9012 | p = pbeg + p_offset; | |
9013 | pend = pbeg + pend_offset; | |
9014 | } | |
05e6f5dc | 9015 | } |
df7492f9 | 9016 | pos++; |
d46c5b12 | 9017 | } |
4ed46869 | 9018 | |
df7492f9 KH |
9019 | tail = list; |
9020 | list = Qnil; | |
9021 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 9022 | { |
df7492f9 KH |
9023 | elt = XCAR (tail); |
9024 | if (CONSP (XCDR (XCDR (elt)))) | |
9025 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
9026 | list); | |
ec6d2bb8 | 9027 | } |
2b4f9037 | 9028 | |
df7492f9 | 9029 | return list; |
d46c5b12 KH |
9030 | } |
9031 | ||
3fd9494b | 9032 | |
b73bfc1c | 9033 | Lisp_Object |
df7492f9 KH |
9034 | code_convert_region (start, end, coding_system, dst_object, encodep, norecord) |
9035 | Lisp_Object start, end, coding_system, dst_object; | |
9036 | int encodep, norecord; | |
4ed46869 | 9037 | { |
3a73fa5d | 9038 | struct coding_system coding; |
df7492f9 KH |
9039 | EMACS_INT from, from_byte, to, to_byte; |
9040 | Lisp_Object src_object; | |
4ed46869 | 9041 | |
b7826503 PJ |
9042 | CHECK_NUMBER_COERCE_MARKER (start); |
9043 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
9044 | if (NILP (coding_system)) |
9045 | coding_system = Qno_conversion; | |
9046 | else | |
9047 | CHECK_CODING_SYSTEM (coding_system); | |
9048 | src_object = Fcurrent_buffer (); | |
9049 | if (NILP (dst_object)) | |
9050 | dst_object = src_object; | |
9051 | else if (! EQ (dst_object, Qt)) | |
9052 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 9053 | |
d46c5b12 KH |
9054 | validate_region (&start, &end); |
9055 | from = XFASTINT (start); | |
df7492f9 | 9056 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 9057 | to = XFASTINT (end); |
df7492f9 | 9058 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 9059 | |
df7492f9 KH |
9060 | setup_coding_system (coding_system, &coding); |
9061 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 9062 | |
df7492f9 KH |
9063 | if (encodep) |
9064 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
9065 | dst_object); | |
9066 | else | |
9067 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
9068 | dst_object); | |
9069 | if (! norecord) | |
9070 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 9071 | |
df7492f9 KH |
9072 | return (BUFFERP (dst_object) |
9073 | ? make_number (coding.produced_char) | |
9074 | : coding.dst_object); | |
4031e2bf | 9075 | } |
78108bcd | 9076 | |
4ed46869 | 9077 | |
4031e2bf | 9078 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 9079 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 9080 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
9081 | When called from a program, takes four arguments: |
9082 | START, END, CODING-SYSTEM, and DESTINATION. | |
9083 | START and END are buffer positions. | |
8844fa83 | 9084 | |
df7492f9 | 9085 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
2354b80b | 9086 | If nil, the region between START and END is replaced by the decoded text. |
1560f91a EZ |
9087 | If buffer, the decoded text is inserted in that buffer after point (point |
9088 | does not move). | |
446dcd75 | 9089 | In those cases, the length of the decoded text is returned. |
319a3947 | 9090 | If DESTINATION is t, the decoded text is returned. |
8844fa83 | 9091 | |
48b0f3ae PJ |
9092 | This function sets `last-coding-system-used' to the precise coding system |
9093 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 9094 | not fully specified.) */) |
df7492f9 KH |
9095 | (start, end, coding_system, destination) |
9096 | Lisp_Object start, end, coding_system, destination; | |
4031e2bf | 9097 | { |
df7492f9 | 9098 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 9099 | } |
8844fa83 | 9100 | |
3a73fa5d | 9101 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
9102 | 3, 4, "r\nzCoding system: ", |
9103 | doc: /* Encode the current region by specified coding system. | |
d4a1d553 JB |
9104 | When called from a program, takes four arguments: |
9105 | START, END, CODING-SYSTEM and DESTINATION. | |
9106 | START and END are buffer positions. | |
d46c5b12 | 9107 | |
df7492f9 KH |
9108 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
9109 | If nil, the region between START and END is replace by the encoded text. | |
1560f91a EZ |
9110 | If buffer, the encoded text is inserted in that buffer after point (point |
9111 | does not move). | |
446dcd75 | 9112 | In those cases, the length of the encoded text is returned. |
319a3947 | 9113 | If DESTINATION is t, the encoded text is returned. |
2391eaa4 | 9114 | |
48b0f3ae PJ |
9115 | This function sets `last-coding-system-used' to the precise coding system |
9116 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 9117 | not fully specified.) */) |
df7492f9 KH |
9118 | (start, end, coding_system, destination) |
9119 | Lisp_Object start, end, coding_system, destination; | |
3a73fa5d | 9120 | { |
df7492f9 | 9121 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
9122 | } |
9123 | ||
9124 | Lisp_Object | |
df7492f9 KH |
9125 | code_convert_string (string, coding_system, dst_object, |
9126 | encodep, nocopy, norecord) | |
9127 | Lisp_Object string, coding_system, dst_object; | |
9128 | int encodep, nocopy, norecord; | |
b73bfc1c | 9129 | { |
4031e2bf | 9130 | struct coding_system coding; |
df7492f9 | 9131 | EMACS_INT chars, bytes; |
ec6d2bb8 | 9132 | |
b7826503 | 9133 | CHECK_STRING (string); |
d46c5b12 | 9134 | if (NILP (coding_system)) |
4956c225 | 9135 | { |
df7492f9 KH |
9136 | if (! norecord) |
9137 | Vlast_coding_system_used = Qno_conversion; | |
9138 | if (NILP (dst_object)) | |
9139 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 9140 | } |
b73bfc1c | 9141 | |
df7492f9 KH |
9142 | if (NILP (coding_system)) |
9143 | coding_system = Qno_conversion; | |
9144 | else | |
9145 | CHECK_CODING_SYSTEM (coding_system); | |
9146 | if (NILP (dst_object)) | |
9147 | dst_object = Qt; | |
9148 | else if (! EQ (dst_object, Qt)) | |
9149 | CHECK_BUFFER (dst_object); | |
73be902c | 9150 | |
df7492f9 | 9151 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 9152 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
9153 | chars = SCHARS (string); |
9154 | bytes = SBYTES (string); | |
df7492f9 KH |
9155 | if (encodep) |
9156 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
9157 | else | |
9158 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
9159 | if (! norecord) | |
9160 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 9161 | |
df7492f9 KH |
9162 | return (BUFFERP (dst_object) |
9163 | ? make_number (coding.produced_char) | |
9164 | : coding.dst_object); | |
4ed46869 | 9165 | } |
73be902c | 9166 | |
b73bfc1c | 9167 | |
ecec61c1 | 9168 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 9169 | Do not set Vlast_coding_system_used. |
4ed46869 | 9170 | |
ec6d2bb8 KH |
9171 | This function is called only from macros DECODE_FILE and |
9172 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 9173 | |
ecec61c1 KH |
9174 | Lisp_Object |
9175 | code_convert_string_norecord (string, coding_system, encodep) | |
9176 | Lisp_Object string, coding_system; | |
9177 | int encodep; | |
4ed46869 | 9178 | { |
0be8721c | 9179 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
9180 | } |
9181 | ||
4ed46869 | 9182 | |
df7492f9 KH |
9183 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
9184 | 2, 4, 0, | |
9185 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
9186 | ||
9187 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
9188 | if the decoding operation is trivial. | |
ecec61c1 | 9189 | |
d4a1d553 | 9190 | Optional fourth arg BUFFER non-nil means that the decoded text is |
1560f91a EZ |
9191 | inserted in that buffer after point (point does not move). In this |
9192 | case, the return value is the length of the decoded text. | |
ecec61c1 | 9193 | |
df7492f9 KH |
9194 | This function sets `last-coding-system-used' to the precise coding system |
9195 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
d4a1d553 | 9196 | not fully specified.) */) |
df7492f9 KH |
9197 | (string, coding_system, nocopy, buffer) |
9198 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 9199 | { |
df7492f9 KH |
9200 | return code_convert_string (string, coding_system, buffer, |
9201 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
9202 | } |
9203 | ||
df7492f9 KH |
9204 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
9205 | 2, 4, 0, | |
9206 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
9207 | ||
9208 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
9209 | itself if the encoding operation is trivial. | |
9210 | ||
d4a1d553 | 9211 | Optional fourth arg BUFFER non-nil means that the encoded text is |
1560f91a EZ |
9212 | inserted in that buffer after point (point does not move). In this |
9213 | case, the return value is the length of the encoded text. | |
df7492f9 KH |
9214 | |
9215 | This function sets `last-coding-system-used' to the precise coding system | |
9216 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
9217 | not fully specified.) */) | |
9218 | (string, coding_system, nocopy, buffer) | |
9219 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 9220 | { |
df7492f9 | 9221 | return code_convert_string (string, coding_system, buffer, |
c197f191 | 9222 | 1, ! NILP (nocopy), 1); |
4ed46869 | 9223 | } |
df7492f9 | 9224 | |
3a73fa5d | 9225 | \f |
4ed46869 | 9226 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
9227 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
9228 | Return the corresponding character. */) | |
9229 | (code) | |
4ed46869 | 9230 | Lisp_Object code; |
4ed46869 | 9231 | { |
df7492f9 KH |
9232 | Lisp_Object spec, attrs, val; |
9233 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
9234 | int c; | |
4ed46869 | 9235 | |
df7492f9 KH |
9236 | CHECK_NATNUM (code); |
9237 | c = XFASTINT (code); | |
9238 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9239 | attrs = AREF (spec, 0); | |
4ed46869 | 9240 | |
df7492f9 KH |
9241 | if (ASCII_BYTE_P (c) |
9242 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9243 | return code; | |
4ed46869 | 9244 | |
df7492f9 KH |
9245 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9246 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
9247 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
9248 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 9249 | |
df7492f9 KH |
9250 | if (c <= 0x7F) |
9251 | charset = charset_roman; | |
9252 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 9253 | { |
df7492f9 KH |
9254 | charset = charset_kana; |
9255 | c -= 0x80; | |
4ed46869 | 9256 | } |
55ab7be3 | 9257 | else |
4ed46869 | 9258 | { |
004068e4 | 9259 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
9260 | |
9261 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
9262 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
9263 | error ("Invalid code: %d", code); | |
9264 | SJIS_TO_JIS (c); | |
9265 | charset = charset_kanji; | |
4ed46869 | 9266 | } |
df7492f9 KH |
9267 | c = DECODE_CHAR (charset, c); |
9268 | if (c < 0) | |
9269 | error ("Invalid code: %d", code); | |
9270 | return make_number (c); | |
93dec019 | 9271 | } |
4ed46869 | 9272 | |
48b0f3ae | 9273 | |
4ed46869 | 9274 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
8acf0c0e | 9275 | doc: /* Encode a Japanese character CH to shift_jis encoding. |
48b0f3ae PJ |
9276 | Return the corresponding code in SJIS. */) |
9277 | (ch) | |
df7492f9 | 9278 | Lisp_Object ch; |
4ed46869 | 9279 | { |
df7492f9 KH |
9280 | Lisp_Object spec, attrs, charset_list; |
9281 | int c; | |
9282 | struct charset *charset; | |
9283 | unsigned code; | |
48b0f3ae | 9284 | |
df7492f9 KH |
9285 | CHECK_CHARACTER (ch); |
9286 | c = XFASTINT (ch); | |
9287 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9288 | attrs = AREF (spec, 0); | |
9289 | ||
9290 | if (ASCII_CHAR_P (c) | |
9291 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9292 | return ch; | |
9293 | ||
9294 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9295 | charset = char_charset (c, charset_list, &code); | |
9296 | if (code == CHARSET_INVALID_CODE (charset)) | |
9297 | error ("Can't encode by shift_jis encoding: %d", c); | |
9298 | JIS_TO_SJIS (code); | |
9299 | ||
9300 | return make_number (code); | |
4ed46869 KH |
9301 | } |
9302 | ||
9303 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
9304 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
9305 | Return the corresponding character. */) | |
9306 | (code) | |
4ed46869 | 9307 | Lisp_Object code; |
d46c5b12 | 9308 | { |
df7492f9 KH |
9309 | Lisp_Object spec, attrs, val; |
9310 | struct charset *charset_roman, *charset_big5, *charset; | |
9311 | int c; | |
6289dd10 | 9312 | |
df7492f9 KH |
9313 | CHECK_NATNUM (code); |
9314 | c = XFASTINT (code); | |
9315 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9316 | attrs = AREF (spec, 0); | |
4ed46869 | 9317 | |
df7492f9 KH |
9318 | if (ASCII_BYTE_P (c) |
9319 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9320 | return code; | |
6289dd10 | 9321 | |
df7492f9 KH |
9322 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9323 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
9324 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 9325 | |
df7492f9 KH |
9326 | if (c <= 0x7F) |
9327 | charset = charset_roman; | |
c28a9453 KH |
9328 | else |
9329 | { | |
df7492f9 KH |
9330 | int b1 = c >> 8, b2 = c & 0x7F; |
9331 | if (b1 < 0xA1 || b1 > 0xFE | |
9332 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
9333 | error ("Invalid code: %d", code); | |
9334 | charset = charset_big5; | |
c28a9453 | 9335 | } |
df7492f9 KH |
9336 | c = DECODE_CHAR (charset, (unsigned )c); |
9337 | if (c < 0) | |
9338 | error ("Invalid code: %d", code); | |
9339 | return make_number (c); | |
d46c5b12 | 9340 | } |
6289dd10 | 9341 | |
4ed46869 | 9342 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
8acf0c0e | 9343 | doc: /* Encode the Big5 character CH to BIG5 coding system. |
48b0f3ae PJ |
9344 | Return the corresponding character code in Big5. */) |
9345 | (ch) | |
4ed46869 KH |
9346 | Lisp_Object ch; |
9347 | { | |
df7492f9 KH |
9348 | Lisp_Object spec, attrs, charset_list; |
9349 | struct charset *charset; | |
9350 | int c; | |
9351 | unsigned code; | |
9352 | ||
9353 | CHECK_CHARACTER (ch); | |
9354 | c = XFASTINT (ch); | |
9355 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9356 | attrs = AREF (spec, 0); | |
9357 | if (ASCII_CHAR_P (c) | |
9358 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9359 | return ch; | |
9360 | ||
9361 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9362 | charset = char_charset (c, charset_list, &code); | |
9363 | if (code == CHARSET_INVALID_CODE (charset)) | |
9364 | error ("Can't encode by Big5 encoding: %d", c); | |
9365 | ||
9366 | return make_number (code); | |
4ed46869 | 9367 | } |
48b0f3ae | 9368 | |
3a73fa5d | 9369 | \f |
002fdb44 | 9370 | DEFUN ("set-terminal-coding-system-internal", Fset_terminal_coding_system_internal, |
68bba4e4 | 9371 | Sset_terminal_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9372 | doc: /* Internal use only. */) |
6ed8eeff | 9373 | (coding_system, terminal) |
b74e4686 | 9374 | Lisp_Object coding_system; |
6ed8eeff | 9375 | Lisp_Object terminal; |
4ed46869 | 9376 | { |
6ed8eeff | 9377 | struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); |
b7826503 | 9378 | CHECK_SYMBOL (coding_system); |
b8299c66 | 9379 | setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding); |
70c22245 | 9380 | /* We had better not send unsafe characters to terminal. */ |
c73bd236 | 9381 | terminal_coding->mode |= CODING_MODE_SAFE_ENCODING; |
df7492f9 | 9382 | /* Characer composition should be disabled. */ |
c73bd236 | 9383 | terminal_coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b8299c66 KL |
9384 | terminal_coding->src_multibyte = 1; |
9385 | terminal_coding->dst_multibyte = 0; | |
4ed46869 KH |
9386 | return Qnil; |
9387 | } | |
9388 | ||
c4825358 KH |
9389 | DEFUN ("set-safe-terminal-coding-system-internal", |
9390 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 9391 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 9392 | doc: /* Internal use only. */) |
48b0f3ae | 9393 | (coding_system) |
b74e4686 | 9394 | Lisp_Object coding_system; |
d46c5b12 | 9395 | { |
b7826503 | 9396 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
9397 | setup_coding_system (Fcheck_coding_system (coding_system), |
9398 | &safe_terminal_coding); | |
df7492f9 KH |
9399 | /* Characer composition should be disabled. */ |
9400 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
9401 | safe_terminal_coding.src_multibyte = 1; |
9402 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
9403 | return Qnil; |
9404 | } | |
4ed46869 | 9405 | |
002fdb44 | 9406 | DEFUN ("terminal-coding-system", Fterminal_coding_system, |
68bba4e4 | 9407 | Sterminal_coding_system, 0, 1, 0, |
6ed8eeff | 9408 | doc: /* Return coding system specified for terminal output on the given terminal. |
708e05dc | 9409 | TERMINAL may be a terminal object, a frame, or nil for the selected |
6ed8eeff KL |
9410 | frame's terminal device. */) |
9411 | (terminal) | |
9412 | Lisp_Object terminal; | |
4ed46869 | 9413 | { |
985773c9 MB |
9414 | struct coding_system *terminal_coding |
9415 | = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); | |
9416 | Lisp_Object coding_system = CODING_ID_NAME (terminal_coding->id); | |
ae6f73fa | 9417 | |
ae6f73fa | 9418 | /* For backward compatibility, return nil if it is `undecided'. */ |
f75c90a9 | 9419 | return (! EQ (coding_system, Qundecided) ? coding_system : Qnil); |
4ed46869 KH |
9420 | } |
9421 | ||
002fdb44 | 9422 | DEFUN ("set-keyboard-coding-system-internal", Fset_keyboard_coding_system_internal, |
68bba4e4 | 9423 | Sset_keyboard_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9424 | doc: /* Internal use only. */) |
6ed8eeff | 9425 | (coding_system, terminal) |
4ed46869 | 9426 | Lisp_Object coding_system; |
6ed8eeff | 9427 | Lisp_Object terminal; |
4ed46869 | 9428 | { |
6ed8eeff | 9429 | struct terminal *t = get_terminal (terminal, 1); |
b7826503 | 9430 | CHECK_SYMBOL (coding_system); |
624bda09 KH |
9431 | if (NILP (coding_system)) |
9432 | coding_system = Qno_conversion; | |
9433 | else | |
9434 | Fcheck_coding_system (coding_system); | |
9435 | setup_coding_system (coding_system, TERMINAL_KEYBOARD_CODING (t)); | |
df7492f9 | 9436 | /* Characer composition should be disabled. */ |
c73bd236 MB |
9437 | TERMINAL_KEYBOARD_CODING (t)->common_flags |
9438 | &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
9439 | return Qnil; |
9440 | } | |
9441 | ||
9442 | DEFUN ("keyboard-coding-system", | |
985773c9 | 9443 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 1, 0, |
48b0f3ae | 9444 | doc: /* Return coding system specified for decoding keyboard input. */) |
985773c9 MB |
9445 | (terminal) |
9446 | Lisp_Object terminal; | |
4ed46869 | 9447 | { |
985773c9 MB |
9448 | return CODING_ID_NAME (TERMINAL_KEYBOARD_CODING |
9449 | (get_terminal (terminal, 1))->id); | |
4ed46869 KH |
9450 | } |
9451 | ||
4ed46869 | 9452 | \f |
a5d301df KH |
9453 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
9454 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
9455 | doc: /* Choose a coding system for an operation based on the target name. |
9456 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
9457 | DECODING-SYSTEM is the coding system to use for decoding | |
9458 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
9459 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 9460 | |
48b0f3ae PJ |
9461 | The first argument OPERATION specifies an I/O primitive: |
9462 | For file I/O, `insert-file-contents' or `write-region'. | |
9463 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
9464 | For network I/O, `open-network-stream'. | |
05e6f5dc | 9465 | |
48b0f3ae PJ |
9466 | The remaining arguments should be the same arguments that were passed |
9467 | to the primitive. Depending on which primitive, one of those arguments | |
9468 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
9469 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 9470 | |
48b0f3ae | 9471 | TARGET has a meaning which depends on OPERATION: |
b883cdb2 | 9472 | For file I/O, TARGET is a file name (except for the special case below). |
48b0f3ae | 9473 | For process I/O, TARGET is a process name. |
d4a1d553 | 9474 | For network I/O, TARGET is a service name or a port number. |
05e6f5dc | 9475 | |
d4a1d553 | 9476 | This function looks up what is specified for TARGET in |
48b0f3ae PJ |
9477 | `file-coding-system-alist', `process-coding-system-alist', |
9478 | or `network-coding-system-alist' depending on OPERATION. | |
9479 | They may specify a coding system, a cons of coding systems, | |
9480 | or a function symbol to call. | |
9481 | In the last case, we call the function with one argument, | |
9482 | which is a list of all the arguments given to this function. | |
1011c487 MB |
9483 | If the function can't decide a coding system, it can return |
9484 | `undecided' so that the normal code-detection is performed. | |
48b0f3ae | 9485 | |
b883cdb2 MB |
9486 | If OPERATION is `insert-file-contents', the argument corresponding to |
9487 | TARGET may be a cons (FILENAME . BUFFER). In that case, FILENAME is a | |
9488 | file name to look up, and BUFFER is a buffer that contains the file's | |
9489 | contents (not yet decoded). If `file-coding-system-alist' specifies a | |
9490 | function to call for FILENAME, that function should examine the | |
9491 | contents of BUFFER instead of reading the file. | |
9492 | ||
d918f936 | 9493 | usage: (find-operation-coding-system OPERATION ARGUMENTS...) */) |
48b0f3ae | 9494 | (nargs, args) |
4ed46869 KH |
9495 | int nargs; |
9496 | Lisp_Object *args; | |
6b89e3aa | 9497 | { |
4ed46869 KH |
9498 | Lisp_Object operation, target_idx, target, val; |
9499 | register Lisp_Object chain; | |
177c0ea7 | 9500 | |
4ed46869 KH |
9501 | if (nargs < 2) |
9502 | error ("Too few arguments"); | |
9503 | operation = args[0]; | |
9504 | if (!SYMBOLP (operation) | |
9505 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
3ed051d4 | 9506 | error ("Invalid first argument"); |
4ed46869 KH |
9507 | if (nargs < 1 + XINT (target_idx)) |
9508 | error ("Too few arguments for operation: %s", | |
8f924df7 | 9509 | SDATA (SYMBOL_NAME (operation))); |
4ed46869 KH |
9510 | target = args[XINT (target_idx) + 1]; |
9511 | if (!(STRINGP (target) | |
091a0ff0 KH |
9512 | || (EQ (operation, Qinsert_file_contents) && CONSP (target) |
9513 | && STRINGP (XCAR (target)) && BUFFERP (XCDR (target))) | |
4ed46869 | 9514 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) |
df7492f9 | 9515 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
091a0ff0 KH |
9516 | if (CONSP (target)) |
9517 | target = XCAR (target); | |
4ed46869 | 9518 | |
2e34157c RS |
9519 | chain = ((EQ (operation, Qinsert_file_contents) |
9520 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 9521 | ? Vfile_coding_system_alist |
2e34157c | 9522 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
9523 | ? Vnetwork_coding_system_alist |
9524 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
9525 | if (NILP (chain)) |
9526 | return Qnil; | |
9527 | ||
03699b14 | 9528 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 9529 | { |
f44d27ce | 9530 | Lisp_Object elt; |
6b89e3aa | 9531 | |
df7492f9 | 9532 | elt = XCAR (chain); |
4ed46869 KH |
9533 | if (CONSP (elt) |
9534 | && ((STRINGP (target) | |
03699b14 KR |
9535 | && STRINGP (XCAR (elt)) |
9536 | && fast_string_match (XCAR (elt), target) >= 0) | |
9537 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 9538 | { |
03699b14 | 9539 | val = XCDR (elt); |
b19fd4c5 KH |
9540 | /* Here, if VAL is both a valid coding system and a valid |
9541 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
9542 | if (CONSP (val)) |
9543 | return val; | |
9544 | if (! SYMBOLP (val)) | |
9545 | return Qnil; | |
9546 | if (! NILP (Fcoding_system_p (val))) | |
9547 | return Fcons (val, val); | |
b19fd4c5 | 9548 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 9549 | { |
e2b97060 MB |
9550 | /* We use call1 rather than safe_call1 |
9551 | so as to get bug reports about functions called here | |
9552 | which don't handle the current interface. */ | |
9553 | val = call1 (val, Flist (nargs, args)); | |
b19fd4c5 KH |
9554 | if (CONSP (val)) |
9555 | return val; | |
9556 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
9557 | return Fcons (val, val); | |
6b89e3aa | 9558 | } |
02ba4723 | 9559 | return Qnil; |
6b89e3aa KH |
9560 | } |
9561 | } | |
4ed46869 | 9562 | return Qnil; |
6b89e3aa KH |
9563 | } |
9564 | ||
df7492f9 | 9565 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 9566 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 9567 | doc: /* Assign higher priority to the coding systems given as arguments. |
d4a1d553 | 9568 | If multiple coding systems belong to the same category, |
a3181084 DL |
9569 | all but the first one are ignored. |
9570 | ||
d4a1d553 | 9571 | usage: (set-coding-system-priority &rest coding-systems) */) |
df7492f9 KH |
9572 | (nargs, args) |
9573 | int nargs; | |
9574 | Lisp_Object *args; | |
9575 | { | |
9576 | int i, j; | |
9577 | int changed[coding_category_max]; | |
9578 | enum coding_category priorities[coding_category_max]; | |
9579 | ||
9580 | bzero (changed, sizeof changed); | |
6b89e3aa | 9581 | |
df7492f9 | 9582 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 9583 | { |
df7492f9 KH |
9584 | enum coding_category category; |
9585 | Lisp_Object spec, attrs; | |
6b89e3aa | 9586 | |
df7492f9 KH |
9587 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
9588 | attrs = AREF (spec, 0); | |
9589 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
9590 | if (changed[category]) | |
9591 | /* Ignore this coding system because a coding system of the | |
9592 | same category already had a higher priority. */ | |
9593 | continue; | |
9594 | changed[category] = 1; | |
9595 | priorities[j++] = category; | |
9596 | if (coding_categories[category].id >= 0 | |
9597 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
9598 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 9599 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 9600 | } |
6b89e3aa | 9601 | |
df7492f9 KH |
9602 | /* Now we have decided top J priorities. Reflect the order of the |
9603 | original priorities to the remaining priorities. */ | |
6b89e3aa | 9604 | |
df7492f9 | 9605 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 9606 | { |
df7492f9 KH |
9607 | while (j < coding_category_max |
9608 | && changed[coding_priorities[j]]) | |
9609 | j++; | |
9610 | if (j == coding_category_max) | |
9611 | abort (); | |
9612 | priorities[i] = coding_priorities[j]; | |
9613 | } | |
6b89e3aa | 9614 | |
df7492f9 | 9615 | bcopy (priorities, coding_priorities, sizeof priorities); |
177c0ea7 | 9616 | |
ff563fce KH |
9617 | /* Update `coding-category-list'. */ |
9618 | Vcoding_category_list = Qnil; | |
9619 | for (i = coding_category_max - 1; i >= 0; i--) | |
9620 | Vcoding_category_list | |
9621 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
9622 | Vcoding_category_list); | |
6b89e3aa | 9623 | |
df7492f9 | 9624 | return Qnil; |
6b89e3aa KH |
9625 | } |
9626 | ||
df7492f9 KH |
9627 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
9628 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 | 9629 | doc: /* Return a list of coding systems ordered by their priorities. |
b811c52b KH |
9630 | The list contains a subset of coding systems; i.e. coding systems |
9631 | assigned to each coding category (see `coding-category-list'). | |
9632 | ||
da7db224 | 9633 | HIGHESTP non-nil means just return the highest priority one. */) |
df7492f9 KH |
9634 | (highestp) |
9635 | Lisp_Object highestp; | |
d46c5b12 KH |
9636 | { |
9637 | int i; | |
df7492f9 | 9638 | Lisp_Object val; |
6b89e3aa | 9639 | |
df7492f9 | 9640 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 9641 | { |
df7492f9 KH |
9642 | enum coding_category category = coding_priorities[i]; |
9643 | int id = coding_categories[category].id; | |
9644 | Lisp_Object attrs; | |
068a9dbd | 9645 | |
df7492f9 KH |
9646 | if (id < 0) |
9647 | continue; | |
9648 | attrs = CODING_ID_ATTRS (id); | |
9649 | if (! NILP (highestp)) | |
9650 | return CODING_ATTR_BASE_NAME (attrs); | |
9651 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
9652 | } | |
9653 | return Fnreverse (val); | |
9654 | } | |
068a9dbd | 9655 | |
91433552 | 9656 | static const char *const suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
9657 | |
9658 | static Lisp_Object | |
df7492f9 KH |
9659 | make_subsidiaries (base) |
9660 | Lisp_Object base; | |
068a9dbd | 9661 | { |
df7492f9 | 9662 | Lisp_Object subsidiaries; |
8f924df7 | 9663 | int base_name_len = SBYTES (SYMBOL_NAME (base)); |
df7492f9 KH |
9664 | char *buf = (char *) alloca (base_name_len + 6); |
9665 | int i; | |
068a9dbd | 9666 | |
8f924df7 | 9667 | bcopy (SDATA (SYMBOL_NAME (base)), buf, base_name_len); |
df7492f9 KH |
9668 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
9669 | for (i = 0; i < 3; i++) | |
068a9dbd | 9670 | { |
df7492f9 KH |
9671 | bcopy (suffixes[i], buf + base_name_len, strlen (suffixes[i]) + 1); |
9672 | ASET (subsidiaries, i, intern (buf)); | |
068a9dbd | 9673 | } |
df7492f9 | 9674 | return subsidiaries; |
068a9dbd KH |
9675 | } |
9676 | ||
9677 | ||
df7492f9 KH |
9678 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
9679 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
9680 | doc: /* For internal use only. |
9681 | usage: (define-coding-system-internal ...) */) | |
df7492f9 KH |
9682 | (nargs, args) |
9683 | int nargs; | |
9684 | Lisp_Object *args; | |
068a9dbd | 9685 | { |
df7492f9 KH |
9686 | Lisp_Object name; |
9687 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
9688 | Lisp_Object attrs; /* Vector of attributes. */ | |
9689 | Lisp_Object eol_type; | |
9690 | Lisp_Object aliases; | |
9691 | Lisp_Object coding_type, charset_list, safe_charsets; | |
9692 | enum coding_category category; | |
9693 | Lisp_Object tail, val; | |
9694 | int max_charset_id = 0; | |
9695 | int i; | |
068a9dbd | 9696 | |
df7492f9 KH |
9697 | if (nargs < coding_arg_max) |
9698 | goto short_args; | |
068a9dbd | 9699 | |
df7492f9 | 9700 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 9701 | |
df7492f9 KH |
9702 | name = args[coding_arg_name]; |
9703 | CHECK_SYMBOL (name); | |
9704 | CODING_ATTR_BASE_NAME (attrs) = name; | |
068a9dbd | 9705 | |
df7492f9 KH |
9706 | val = args[coding_arg_mnemonic]; |
9707 | if (! STRINGP (val)) | |
9708 | CHECK_CHARACTER (val); | |
9709 | CODING_ATTR_MNEMONIC (attrs) = val; | |
068a9dbd | 9710 | |
df7492f9 KH |
9711 | coding_type = args[coding_arg_coding_type]; |
9712 | CHECK_SYMBOL (coding_type); | |
9713 | CODING_ATTR_TYPE (attrs) = coding_type; | |
068a9dbd | 9714 | |
df7492f9 KH |
9715 | charset_list = args[coding_arg_charset_list]; |
9716 | if (SYMBOLP (charset_list)) | |
9717 | { | |
9718 | if (EQ (charset_list, Qiso_2022)) | |
9719 | { | |
9720 | if (! EQ (coding_type, Qiso_2022)) | |
9721 | error ("Invalid charset-list"); | |
9722 | charset_list = Viso_2022_charset_list; | |
9723 | } | |
9724 | else if (EQ (charset_list, Qemacs_mule)) | |
9725 | { | |
9726 | if (! EQ (coding_type, Qemacs_mule)) | |
9727 | error ("Invalid charset-list"); | |
9728 | charset_list = Vemacs_mule_charset_list; | |
9729 | } | |
9730 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
9731 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
9732 | max_charset_id = XFASTINT (XCAR (tail)); | |
9733 | } | |
068a9dbd KH |
9734 | else |
9735 | { | |
df7492f9 | 9736 | charset_list = Fcopy_sequence (charset_list); |
985773c9 | 9737 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
068a9dbd | 9738 | { |
df7492f9 KH |
9739 | struct charset *charset; |
9740 | ||
985773c9 | 9741 | val = XCAR (tail); |
df7492f9 KH |
9742 | CHECK_CHARSET_GET_CHARSET (val, charset); |
9743 | if (EQ (coding_type, Qiso_2022) | |
9744 | ? CHARSET_ISO_FINAL (charset) < 0 | |
9745 | : EQ (coding_type, Qemacs_mule) | |
9746 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
9747 | : 0) | |
9748 | error ("Can't handle charset `%s'", | |
8f924df7 | 9749 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 9750 | |
8f924df7 | 9751 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
9752 | if (max_charset_id < charset->id) |
9753 | max_charset_id = charset->id; | |
068a9dbd KH |
9754 | } |
9755 | } | |
df7492f9 | 9756 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; |
068a9dbd | 9757 | |
1b3b981b AS |
9758 | safe_charsets = make_uninit_string (max_charset_id + 1); |
9759 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 | 9760 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
8f924df7 | 9761 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 9762 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; |
068a9dbd | 9763 | |
584948ac | 9764 | CODING_ATTR_ASCII_COMPAT (attrs) = args[coding_arg_ascii_compatible_p]; |
3a73fa5d | 9765 | |
df7492f9 | 9766 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 9767 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9768 | CHECK_SYMBOL (val); |
df7492f9 | 9769 | CODING_ATTR_DECODE_TBL (attrs) = val; |
3a73fa5d | 9770 | |
df7492f9 | 9771 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 9772 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9773 | CHECK_SYMBOL (val); |
df7492f9 | 9774 | CODING_ATTR_ENCODE_TBL (attrs) = val; |
d46c5b12 | 9775 | |
df7492f9 KH |
9776 | val = args[coding_arg_post_read_conversion]; |
9777 | CHECK_SYMBOL (val); | |
9778 | CODING_ATTR_POST_READ (attrs) = val; | |
d46c5b12 | 9779 | |
df7492f9 KH |
9780 | val = args[coding_arg_pre_write_conversion]; |
9781 | CHECK_SYMBOL (val); | |
9782 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
3a73fa5d | 9783 | |
df7492f9 KH |
9784 | val = args[coding_arg_default_char]; |
9785 | if (NILP (val)) | |
9786 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
9787 | else | |
9788 | { | |
8f924df7 | 9789 | CHECK_CHARACTER (val); |
df7492f9 KH |
9790 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; |
9791 | } | |
4031e2bf | 9792 | |
8f924df7 KH |
9793 | val = args[coding_arg_for_unibyte]; |
9794 | CODING_ATTR_FOR_UNIBYTE (attrs) = NILP (val) ? Qnil : Qt; | |
3a73fa5d | 9795 | |
df7492f9 KH |
9796 | val = args[coding_arg_plist]; |
9797 | CHECK_LIST (val); | |
9798 | CODING_ATTR_PLIST (attrs) = val; | |
3a73fa5d | 9799 | |
df7492f9 KH |
9800 | if (EQ (coding_type, Qcharset)) |
9801 | { | |
c7c66a95 KH |
9802 | /* Generate a lisp vector of 256 elements. Each element is nil, |
9803 | integer, or a list of charset IDs. | |
3a73fa5d | 9804 | |
c7c66a95 KH |
9805 | If Nth element is nil, the byte code N is invalid in this |
9806 | coding system. | |
4ed46869 | 9807 | |
c7c66a95 KH |
9808 | If Nth element is a number NUM, N is the first byte of a |
9809 | charset whose ID is NUM. | |
4ed46869 | 9810 | |
c7c66a95 KH |
9811 | If Nth element is a list of charset IDs, N is the first byte |
9812 | of one of them. The list is sorted by dimensions of the | |
2bc515e4 | 9813 | charsets. A charset of smaller dimension comes firtst. */ |
df7492f9 | 9814 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 9815 | |
5c99c2e6 | 9816 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 9817 | { |
c7c66a95 KH |
9818 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
9819 | int dim = CHARSET_DIMENSION (charset); | |
9820 | int idx = (dim - 1) * 4; | |
4ed46869 | 9821 | |
5c99c2e6 | 9822 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
584948ac | 9823 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
4031e2bf | 9824 | |
15d143f7 KH |
9825 | for (i = charset->code_space[idx]; |
9826 | i <= charset->code_space[idx + 1]; i++) | |
9827 | { | |
c7c66a95 KH |
9828 | Lisp_Object tmp, tmp2; |
9829 | int dim2; | |
ec6d2bb8 | 9830 | |
c7c66a95 KH |
9831 | tmp = AREF (val, i); |
9832 | if (NILP (tmp)) | |
9833 | tmp = XCAR (tail); | |
9834 | else if (NUMBERP (tmp)) | |
9835 | { | |
9836 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
9837 | if (dim < dim2) | |
c7c66a95 | 9838 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
9839 | else |
9840 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 9841 | } |
15d143f7 | 9842 | else |
c7c66a95 KH |
9843 | { |
9844 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
9845 | { | |
9846 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
9847 | if (dim < dim2) | |
9848 | break; | |
9849 | } | |
9850 | if (NILP (tmp2)) | |
9851 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
9852 | else | |
9853 | { | |
9854 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
9855 | XSETCAR (tmp2, XCAR (tail)); | |
9856 | } | |
9857 | } | |
9858 | ASET (val, i, tmp); | |
15d143f7 | 9859 | } |
df7492f9 KH |
9860 | } |
9861 | ASET (attrs, coding_attr_charset_valids, val); | |
9862 | category = coding_category_charset; | |
9863 | } | |
9864 | else if (EQ (coding_type, Qccl)) | |
9865 | { | |
9866 | Lisp_Object valids; | |
ecec61c1 | 9867 | |
df7492f9 KH |
9868 | if (nargs < coding_arg_ccl_max) |
9869 | goto short_args; | |
ecec61c1 | 9870 | |
df7492f9 KH |
9871 | val = args[coding_arg_ccl_decoder]; |
9872 | CHECK_CCL_PROGRAM (val); | |
9873 | if (VECTORP (val)) | |
9874 | val = Fcopy_sequence (val); | |
9875 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 9876 | |
df7492f9 KH |
9877 | val = args[coding_arg_ccl_encoder]; |
9878 | CHECK_CCL_PROGRAM (val); | |
9879 | if (VECTORP (val)) | |
9880 | val = Fcopy_sequence (val); | |
9881 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 9882 | |
df7492f9 KH |
9883 | val = args[coding_arg_ccl_valids]; |
9884 | valids = Fmake_string (make_number (256), make_number (0)); | |
9885 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
9886 | { | |
8dcbea82 | 9887 | int from, to; |
ecec61c1 | 9888 | |
df7492f9 KH |
9889 | val = Fcar (tail); |
9890 | if (INTEGERP (val)) | |
8dcbea82 KH |
9891 | { |
9892 | from = to = XINT (val); | |
9893 | if (from < 0 || from > 255) | |
9894 | args_out_of_range_3 (val, make_number (0), make_number (255)); | |
9895 | } | |
df7492f9 KH |
9896 | else |
9897 | { | |
df7492f9 | 9898 | CHECK_CONS (val); |
8f924df7 KH |
9899 | CHECK_NATNUM_CAR (val); |
9900 | CHECK_NATNUM_CDR (val); | |
df7492f9 | 9901 | from = XINT (XCAR (val)); |
8f924df7 | 9902 | if (from > 255) |
8dcbea82 KH |
9903 | args_out_of_range_3 (XCAR (val), |
9904 | make_number (0), make_number (255)); | |
df7492f9 | 9905 | to = XINT (XCDR (val)); |
8dcbea82 KH |
9906 | if (to < from || to > 255) |
9907 | args_out_of_range_3 (XCDR (val), | |
9908 | XCAR (val), make_number (255)); | |
df7492f9 | 9909 | } |
8dcbea82 | 9910 | for (i = from; i <= to; i++) |
8f924df7 | 9911 | SSET (valids, i, 1); |
df7492f9 KH |
9912 | } |
9913 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 9914 | |
df7492f9 | 9915 | category = coding_category_ccl; |
55ab7be3 | 9916 | } |
df7492f9 | 9917 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 9918 | { |
df7492f9 | 9919 | Lisp_Object bom, endian; |
4ed46869 | 9920 | |
584948ac | 9921 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; |
4ed46869 | 9922 | |
df7492f9 KH |
9923 | if (nargs < coding_arg_utf16_max) |
9924 | goto short_args; | |
4ed46869 | 9925 | |
df7492f9 KH |
9926 | bom = args[coding_arg_utf16_bom]; |
9927 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9928 | { | |
9929 | CHECK_CONS (bom); | |
8f924df7 KH |
9930 | val = XCAR (bom); |
9931 | CHECK_CODING_SYSTEM (val); | |
9932 | val = XCDR (bom); | |
9933 | CHECK_CODING_SYSTEM (val); | |
df7492f9 | 9934 | } |
a470d443 | 9935 | ASET (attrs, coding_attr_utf_bom, bom); |
df7492f9 KH |
9936 | |
9937 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
9938 | CHECK_SYMBOL (endian); |
9939 | if (NILP (endian)) | |
9940 | endian = Qbig; | |
9941 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 9942 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
9943 | ASET (attrs, coding_attr_utf_16_endian, endian); |
9944 | ||
9945 | category = (CONSP (bom) | |
9946 | ? coding_category_utf_16_auto | |
9947 | : NILP (bom) | |
b49a1807 | 9948 | ? (EQ (endian, Qbig) |
df7492f9 KH |
9949 | ? coding_category_utf_16_be_nosig |
9950 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 9951 | : (EQ (endian, Qbig) |
df7492f9 KH |
9952 | ? coding_category_utf_16_be |
9953 | : coding_category_utf_16_le)); | |
9954 | } | |
9955 | else if (EQ (coding_type, Qiso_2022)) | |
9956 | { | |
9957 | Lisp_Object initial, reg_usage, request, flags; | |
4776e638 | 9958 | int i; |
1397dc18 | 9959 | |
df7492f9 KH |
9960 | if (nargs < coding_arg_iso2022_max) |
9961 | goto short_args; | |
9962 | ||
9963 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
9964 | CHECK_VECTOR (initial); | |
9965 | for (i = 0; i < 4; i++) | |
9966 | { | |
9967 | val = Faref (initial, make_number (i)); | |
9968 | if (! NILP (val)) | |
9969 | { | |
584948ac KH |
9970 | struct charset *charset; |
9971 | ||
9972 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
9973 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
9974 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
9975 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9976 | } |
9977 | else | |
9978 | ASET (initial, i, make_number (-1)); | |
9979 | } | |
9980 | ||
9981 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
9982 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
9983 | CHECK_NUMBER_CAR (reg_usage); |
9984 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
9985 | |
9986 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
9987 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 9988 | { |
df7492f9 | 9989 | int id; |
8f924df7 | 9990 | Lisp_Object tmp; |
df7492f9 KH |
9991 | |
9992 | val = Fcar (tail); | |
9993 | CHECK_CONS (val); | |
8f924df7 KH |
9994 | tmp = XCAR (val); |
9995 | CHECK_CHARSET_GET_ID (tmp, id); | |
9996 | CHECK_NATNUM_CDR (val); | |
df7492f9 KH |
9997 | if (XINT (XCDR (val)) >= 4) |
9998 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
8f924df7 | 9999 | XSETCAR (val, make_number (id)); |
1397dc18 | 10000 | } |
4ed46869 | 10001 | |
df7492f9 KH |
10002 | flags = args[coding_arg_iso2022_flags]; |
10003 | CHECK_NATNUM (flags); | |
10004 | i = XINT (flags); | |
10005 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
10006 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
10007 | ||
10008 | ASET (attrs, coding_attr_iso_initial, initial); | |
10009 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
10010 | ASET (attrs, coding_attr_iso_request, request); | |
10011 | ASET (attrs, coding_attr_iso_flags, flags); | |
10012 | setup_iso_safe_charsets (attrs); | |
10013 | ||
10014 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
10015 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
10016 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
10017 | ? coding_category_iso_7_else | |
10018 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
10019 | ? coding_category_iso_7 | |
10020 | : coding_category_iso_7_tight); | |
10021 | else | |
10022 | { | |
10023 | int id = XINT (AREF (initial, 1)); | |
10024 | ||
c6fb6e98 | 10025 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
10026 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
10027 | || id < 0) | |
10028 | ? coding_category_iso_8_else | |
10029 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
10030 | ? coding_category_iso_8_1 | |
10031 | : coding_category_iso_8_2); | |
10032 | } | |
0ce7886f KH |
10033 | if (category != coding_category_iso_8_1 |
10034 | && category != coding_category_iso_8_2) | |
10035 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; | |
df7492f9 KH |
10036 | } |
10037 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 10038 | { |
df7492f9 KH |
10039 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
10040 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
584948ac | 10041 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
df7492f9 | 10042 | category = coding_category_emacs_mule; |
c28a9453 | 10043 | } |
df7492f9 | 10044 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 10045 | { |
df7492f9 KH |
10046 | |
10047 | struct charset *charset; | |
10048 | ||
7d64c6ad | 10049 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 10050 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 10051 | error ("There should be three or four charsets"); |
df7492f9 KH |
10052 | |
10053 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10054 | if (CHARSET_DIMENSION (charset) != 1) | |
10055 | error ("Dimension of charset %s is not one", | |
8f924df7 | 10056 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
10057 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
10058 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
10059 | |
10060 | charset_list = XCDR (charset_list); | |
10061 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10062 | if (CHARSET_DIMENSION (charset) != 1) | |
10063 | error ("Dimension of charset %s is not one", | |
8f924df7 | 10064 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
10065 | |
10066 | charset_list = XCDR (charset_list); | |
10067 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10068 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
10069 | error ("Dimension of charset %s is not two", |
10070 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
10071 | ||
10072 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
10073 | if (! NILP (charset_list)) |
10074 | { | |
10075 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10076 | if (CHARSET_DIMENSION (charset) != 2) | |
10077 | error ("Dimension of charset %s is not two", | |
10078 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
10079 | } | |
df7492f9 KH |
10080 | |
10081 | category = coding_category_sjis; | |
10082 | Vsjis_coding_system = name; | |
c28a9453 | 10083 | } |
df7492f9 KH |
10084 | else if (EQ (coding_type, Qbig5)) |
10085 | { | |
10086 | struct charset *charset; | |
4ed46869 | 10087 | |
df7492f9 KH |
10088 | if (XINT (Flength (charset_list)) != 2) |
10089 | error ("There should be just two charsets"); | |
10090 | ||
10091 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10092 | if (CHARSET_DIMENSION (charset) != 1) | |
10093 | error ("Dimension of charset %s is not one", | |
8f924df7 | 10094 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
10095 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
10096 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
10097 | |
10098 | charset_list = XCDR (charset_list); | |
10099 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10100 | if (CHARSET_DIMENSION (charset) != 2) | |
10101 | error ("Dimension of charset %s is not two", | |
8f924df7 | 10102 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 10103 | |
df7492f9 KH |
10104 | category = coding_category_big5; |
10105 | Vbig5_coding_system = name; | |
10106 | } | |
10107 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 10108 | { |
584948ac KH |
10109 | category = coding_category_raw_text; |
10110 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
c28a9453 | 10111 | } |
df7492f9 | 10112 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 10113 | { |
a470d443 KH |
10114 | Lisp_Object bom; |
10115 | ||
584948ac | 10116 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
a470d443 KH |
10117 | |
10118 | if (nargs < coding_arg_utf8_max) | |
10119 | goto short_args; | |
10120 | ||
10121 | bom = args[coding_arg_utf8_bom]; | |
10122 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
10123 | { | |
10124 | CHECK_CONS (bom); | |
10125 | val = XCAR (bom); | |
10126 | CHECK_CODING_SYSTEM (val); | |
10127 | val = XCDR (bom); | |
10128 | CHECK_CODING_SYSTEM (val); | |
10129 | } | |
10130 | ASET (attrs, coding_attr_utf_bom, bom); | |
10131 | ||
10132 | category = (CONSP (bom) ? coding_category_utf_8_auto | |
10133 | : NILP (bom) ? coding_category_utf_8_nosig | |
10134 | : coding_category_utf_8_sig); | |
4ed46869 | 10135 | } |
df7492f9 KH |
10136 | else if (EQ (coding_type, Qundecided)) |
10137 | category = coding_category_undecided; | |
4ed46869 | 10138 | else |
df7492f9 | 10139 | error ("Invalid coding system type: %s", |
8f924df7 | 10140 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 10141 | |
df7492f9 | 10142 | CODING_ATTR_CATEGORY (attrs) = make_number (category); |
01378f49 KH |
10143 | CODING_ATTR_PLIST (attrs) |
10144 | = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category), | |
10145 | CODING_ATTR_PLIST (attrs))); | |
35befdaa | 10146 | CODING_ATTR_PLIST (attrs) |
3ed051d4 | 10147 | = Fcons (QCascii_compatible_p, |
35befdaa KH |
10148 | Fcons (CODING_ATTR_ASCII_COMPAT (attrs), |
10149 | CODING_ATTR_PLIST (attrs))); | |
c4825358 | 10150 | |
df7492f9 KH |
10151 | eol_type = args[coding_arg_eol_type]; |
10152 | if (! NILP (eol_type) | |
10153 | && ! EQ (eol_type, Qunix) | |
10154 | && ! EQ (eol_type, Qdos) | |
10155 | && ! EQ (eol_type, Qmac)) | |
10156 | error ("Invalid eol-type"); | |
4ed46869 | 10157 | |
df7492f9 | 10158 | aliases = Fcons (name, Qnil); |
4ed46869 | 10159 | |
df7492f9 KH |
10160 | if (NILP (eol_type)) |
10161 | { | |
10162 | eol_type = make_subsidiaries (name); | |
10163 | for (i = 0; i < 3; i++) | |
1397dc18 | 10164 | { |
df7492f9 KH |
10165 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
10166 | ||
10167 | this_name = AREF (eol_type, i); | |
10168 | this_aliases = Fcons (this_name, Qnil); | |
10169 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
10170 | this_spec = Fmake_vector (make_number (3), attrs); | |
10171 | ASET (this_spec, 1, this_aliases); | |
10172 | ASET (this_spec, 2, this_eol_type); | |
10173 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
10174 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
583f71ca KH |
10175 | val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist); |
10176 | if (NILP (val)) | |
10177 | Vcoding_system_alist | |
10178 | = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
10179 | Vcoding_system_alist); | |
1397dc18 | 10180 | } |
d46c5b12 | 10181 | } |
4ed46869 | 10182 | |
df7492f9 KH |
10183 | spec_vec = Fmake_vector (make_number (3), attrs); |
10184 | ASET (spec_vec, 1, aliases); | |
10185 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 10186 | |
df7492f9 KH |
10187 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
10188 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
583f71ca KH |
10189 | val = Fassoc (Fsymbol_name (name), Vcoding_system_alist); |
10190 | if (NILP (val)) | |
10191 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
10192 | Vcoding_system_alist); | |
48b0f3ae | 10193 | |
df7492f9 KH |
10194 | { |
10195 | int id = coding_categories[category].id; | |
48b0f3ae | 10196 | |
df7492f9 KH |
10197 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
10198 | setup_coding_system (name, &coding_categories[category]); | |
10199 | } | |
48b0f3ae | 10200 | |
d46c5b12 | 10201 | return Qnil; |
48b0f3ae | 10202 | |
df7492f9 KH |
10203 | short_args: |
10204 | return Fsignal (Qwrong_number_of_arguments, | |
10205 | Fcons (intern ("define-coding-system-internal"), | |
10206 | make_number (nargs))); | |
d46c5b12 | 10207 | } |
4ed46869 | 10208 | |
d6925f38 | 10209 | |
a6f87d34 KH |
10210 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
10211 | 3, 3, 0, | |
10212 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
10213 | (coding_system, prop, val) | |
10214 | Lisp_Object coding_system, prop, val; | |
10215 | { | |
3dbe7859 | 10216 | Lisp_Object spec, attrs; |
a6f87d34 KH |
10217 | |
10218 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10219 | attrs = AREF (spec, 0); | |
10220 | if (EQ (prop, QCmnemonic)) | |
10221 | { | |
10222 | if (! STRINGP (val)) | |
10223 | CHECK_CHARACTER (val); | |
10224 | CODING_ATTR_MNEMONIC (attrs) = val; | |
10225 | } | |
2133e2d1 | 10226 | else if (EQ (prop, QCdefault_char)) |
a6f87d34 KH |
10227 | { |
10228 | if (NILP (val)) | |
10229 | val = make_number (' '); | |
10230 | else | |
10231 | CHECK_CHARACTER (val); | |
10232 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; | |
10233 | } | |
10234 | else if (EQ (prop, QCdecode_translation_table)) | |
10235 | { | |
10236 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10237 | CHECK_SYMBOL (val); | |
10238 | CODING_ATTR_DECODE_TBL (attrs) = val; | |
10239 | } | |
10240 | else if (EQ (prop, QCencode_translation_table)) | |
10241 | { | |
10242 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10243 | CHECK_SYMBOL (val); | |
10244 | CODING_ATTR_ENCODE_TBL (attrs) = val; | |
10245 | } | |
10246 | else if (EQ (prop, QCpost_read_conversion)) | |
10247 | { | |
10248 | CHECK_SYMBOL (val); | |
10249 | CODING_ATTR_POST_READ (attrs) = val; | |
10250 | } | |
10251 | else if (EQ (prop, QCpre_write_conversion)) | |
10252 | { | |
10253 | CHECK_SYMBOL (val); | |
10254 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
10255 | } | |
35befdaa KH |
10256 | else if (EQ (prop, QCascii_compatible_p)) |
10257 | { | |
10258 | CODING_ATTR_ASCII_COMPAT (attrs) = val; | |
10259 | } | |
a6f87d34 KH |
10260 | |
10261 | CODING_ATTR_PLIST (attrs) | |
10262 | = Fplist_put (CODING_ATTR_PLIST (attrs), prop, val); | |
10263 | return val; | |
10264 | } | |
10265 | ||
10266 | ||
df7492f9 KH |
10267 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
10268 | Sdefine_coding_system_alias, 2, 2, 0, | |
10269 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
10270 | (alias, coding_system) | |
10271 | Lisp_Object alias, coding_system; | |
66cfb530 | 10272 | { |
583f71ca | 10273 | Lisp_Object spec, aliases, eol_type, val; |
4ed46869 | 10274 | |
df7492f9 KH |
10275 | CHECK_SYMBOL (alias); |
10276 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10277 | aliases = AREF (spec, 1); | |
d4a1d553 | 10278 | /* ALIASES should be a list of length more than zero, and the first |
d6925f38 KH |
10279 | element is a base coding system. Append ALIAS at the tail of the |
10280 | list. */ | |
df7492f9 KH |
10281 | while (!NILP (XCDR (aliases))) |
10282 | aliases = XCDR (aliases); | |
8f924df7 | 10283 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 10284 | |
df7492f9 KH |
10285 | eol_type = AREF (spec, 2); |
10286 | if (VECTORP (eol_type)) | |
4ed46869 | 10287 | { |
df7492f9 KH |
10288 | Lisp_Object subsidiaries; |
10289 | int i; | |
4ed46869 | 10290 | |
df7492f9 KH |
10291 | subsidiaries = make_subsidiaries (alias); |
10292 | for (i = 0; i < 3; i++) | |
10293 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
10294 | AREF (eol_type, i)); | |
4ed46869 | 10295 | } |
df7492f9 KH |
10296 | |
10297 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 10298 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
583f71ca KH |
10299 | val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist); |
10300 | if (NILP (val)) | |
10301 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), | |
10302 | Vcoding_system_alist); | |
66cfb530 | 10303 | |
4ed46869 KH |
10304 | return Qnil; |
10305 | } | |
10306 | ||
df7492f9 KH |
10307 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
10308 | 1, 1, 0, | |
10309 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 10310 | Any alias or subsidiary coding system is not a base coding system. */) |
df7492f9 KH |
10311 | (coding_system) |
10312 | Lisp_Object coding_system; | |
d46c5b12 | 10313 | { |
df7492f9 | 10314 | Lisp_Object spec, attrs; |
d46c5b12 | 10315 | |
df7492f9 KH |
10316 | if (NILP (coding_system)) |
10317 | return (Qno_conversion); | |
10318 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10319 | attrs = AREF (spec, 0); | |
10320 | return CODING_ATTR_BASE_NAME (attrs); | |
10321 | } | |
1397dc18 | 10322 | |
df7492f9 KH |
10323 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
10324 | 1, 1, 0, | |
10325 | doc: "Return the property list of CODING-SYSTEM.") | |
10326 | (coding_system) | |
10327 | Lisp_Object coding_system; | |
10328 | { | |
10329 | Lisp_Object spec, attrs; | |
1397dc18 | 10330 | |
df7492f9 KH |
10331 | if (NILP (coding_system)) |
10332 | coding_system = Qno_conversion; | |
10333 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10334 | attrs = AREF (spec, 0); | |
10335 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
10336 | } |
10337 | ||
df7492f9 KH |
10338 | |
10339 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
10340 | 1, 1, 0, | |
da7db224 | 10341 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
df7492f9 KH |
10342 | (coding_system) |
10343 | Lisp_Object coding_system; | |
66cfb530 | 10344 | { |
df7492f9 | 10345 | Lisp_Object spec; |
84d60297 | 10346 | |
df7492f9 KH |
10347 | if (NILP (coding_system)) |
10348 | coding_system = Qno_conversion; | |
10349 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 10350 | return AREF (spec, 1); |
df7492f9 | 10351 | } |
66cfb530 | 10352 | |
df7492f9 KH |
10353 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
10354 | Scoding_system_eol_type, 1, 1, 0, | |
10355 | doc: /* Return eol-type of CODING-SYSTEM. | |
d4a1d553 | 10356 | An eol-type is an integer 0, 1, 2, or a vector of coding systems. |
66cfb530 | 10357 | |
df7492f9 KH |
10358 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
10359 | and CR respectively. | |
66cfb530 | 10360 | |
df7492f9 KH |
10361 | A vector value indicates that a format of end-of-line should be |
10362 | detected automatically. Nth element of the vector is the subsidiary | |
10363 | coding system whose eol-type is N. */) | |
6b89e3aa KH |
10364 | (coding_system) |
10365 | Lisp_Object coding_system; | |
10366 | { | |
df7492f9 KH |
10367 | Lisp_Object spec, eol_type; |
10368 | int n; | |
6b89e3aa | 10369 | |
df7492f9 KH |
10370 | if (NILP (coding_system)) |
10371 | coding_system = Qno_conversion; | |
10372 | if (! CODING_SYSTEM_P (coding_system)) | |
10373 | return Qnil; | |
10374 | spec = CODING_SYSTEM_SPEC (coding_system); | |
10375 | eol_type = AREF (spec, 2); | |
10376 | if (VECTORP (eol_type)) | |
10377 | return Fcopy_sequence (eol_type); | |
10378 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
10379 | return make_number (n); | |
6b89e3aa KH |
10380 | } |
10381 | ||
4ed46869 KH |
10382 | #endif /* emacs */ |
10383 | ||
10384 | \f | |
1397dc18 | 10385 | /*** 9. Post-amble ***/ |
4ed46869 | 10386 | |
dfcf069d | 10387 | void |
4ed46869 KH |
10388 | init_coding_once () |
10389 | { | |
10390 | int i; | |
10391 | ||
df7492f9 KH |
10392 | for (i = 0; i < coding_category_max; i++) |
10393 | { | |
10394 | coding_categories[i].id = -1; | |
10395 | coding_priorities[i] = i; | |
10396 | } | |
4ed46869 KH |
10397 | |
10398 | /* ISO2022 specific initialize routine. */ | |
10399 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 10400 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
10401 | for (i = 0x21; i < 0x7F; i++) |
10402 | iso_code_class[i] = ISO_graphic_plane_0; | |
10403 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 10404 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
10405 | for (i = 0xA1; i < 0xFF; i++) |
10406 | iso_code_class[i] = ISO_graphic_plane_1; | |
10407 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
10408 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
10409 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
10410 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
10411 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
10412 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
10413 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
10414 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
10415 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
10416 | ||
df7492f9 KH |
10417 | for (i = 0; i < 256; i++) |
10418 | { | |
10419 | emacs_mule_bytes[i] = 1; | |
10420 | } | |
7c78e542 KH |
10421 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
10422 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
10423 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
10424 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
10425 | } |
10426 | ||
10427 | #ifdef emacs | |
10428 | ||
dfcf069d | 10429 | void |
e0e989f6 KH |
10430 | syms_of_coding () |
10431 | { | |
df7492f9 | 10432 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
10433 | { |
10434 | Lisp_Object args[2]; | |
10435 | args[0] = QCtest; | |
10436 | args[1] = Qeq; | |
10437 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
10438 | } | |
df7492f9 KH |
10439 | |
10440 | staticpro (&Vsjis_coding_system); | |
10441 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 10442 | |
df7492f9 KH |
10443 | staticpro (&Vbig5_coding_system); |
10444 | Vbig5_coding_system = Qnil; | |
10445 | ||
24a73b0a KH |
10446 | staticpro (&Vcode_conversion_reused_workbuf); |
10447 | Vcode_conversion_reused_workbuf = Qnil; | |
10448 | ||
10449 | staticpro (&Vcode_conversion_workbuf_name); | |
d67b4f80 | 10450 | Vcode_conversion_workbuf_name = make_pure_c_string (" *code-conversion-work*"); |
e0e989f6 | 10451 | |
24a73b0a | 10452 | reused_workbuf_in_use = 0; |
df7492f9 KH |
10453 | |
10454 | DEFSYM (Qcharset, "charset"); | |
10455 | DEFSYM (Qtarget_idx, "target-idx"); | |
10456 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
10457 | Fset (Qcoding_system_history, Qnil); |
10458 | ||
9ce27fde | 10459 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 10460 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 10461 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
10462 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
10463 | ||
df7492f9 | 10464 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 10465 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
10466 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
10467 | ||
df7492f9 | 10468 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 10469 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10470 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
10471 | ||
df7492f9 | 10472 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 10473 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10474 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
10475 | ||
df7492f9 | 10476 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 10477 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
10478 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
10479 | ||
df7492f9 KH |
10480 | DEFSYM (Qcoding_system, "coding-system"); |
10481 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 10482 | |
df7492f9 KH |
10483 | DEFSYM (Qeol_type, "eol-type"); |
10484 | DEFSYM (Qunix, "unix"); | |
10485 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 10486 | |
df7492f9 KH |
10487 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
10488 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
10489 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
10490 | DEFSYM (Qdefault_char, "default-char"); | |
10491 | DEFSYM (Qundecided, "undecided"); | |
10492 | DEFSYM (Qno_conversion, "no-conversion"); | |
10493 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 10494 | |
df7492f9 | 10495 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 10496 | |
df7492f9 | 10497 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 10498 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 10499 | |
df7492f9 | 10500 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
10501 | DEFSYM (Qbig, "big"); |
10502 | DEFSYM (Qlittle, "little"); | |
27901516 | 10503 | |
df7492f9 KH |
10504 | DEFSYM (Qshift_jis, "shift-jis"); |
10505 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 10506 | |
df7492f9 | 10507 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 10508 | |
df7492f9 | 10509 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 | 10510 | Fput (Qcoding_system_error, Qerror_conditions, |
d67b4f80 | 10511 | pure_cons (Qcoding_system_error, pure_cons (Qerror, Qnil))); |
4ed46869 | 10512 | Fput (Qcoding_system_error, Qerror_message, |
d67b4f80 | 10513 | make_pure_c_string ("Invalid coding system")); |
4ed46869 | 10514 | |
05e6f5dc KH |
10515 | /* Intern this now in case it isn't already done. |
10516 | Setting this variable twice is harmless. | |
10517 | But don't staticpro it here--that is done in alloc.c. */ | |
d67b4f80 | 10518 | Qchar_table_extra_slots = intern_c_string ("char-table-extra-slots"); |
70c22245 | 10519 | |
df7492f9 | 10520 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 10521 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
10522 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
10523 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
10524 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 10525 | |
df7492f9 | 10526 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 10527 | |
df7492f9 | 10528 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 10529 | |
01378f49 | 10530 | DEFSYM (QCcategory, ":category"); |
a6f87d34 | 10531 | DEFSYM (QCmnemonic, ":mnemonic"); |
2133e2d1 | 10532 | DEFSYM (QCdefault_char, ":default-char"); |
a6f87d34 KH |
10533 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); |
10534 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
10535 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
10536 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
35befdaa | 10537 | DEFSYM (QCascii_compatible_p, ":ascii-compatible-p"); |
01378f49 | 10538 | |
df7492f9 KH |
10539 | Vcoding_category_table |
10540 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
10541 | staticpro (&Vcoding_category_table); | |
10542 | /* Followings are target of code detection. */ | |
10543 | ASET (Vcoding_category_table, coding_category_iso_7, | |
d67b4f80 | 10544 | intern_c_string ("coding-category-iso-7")); |
df7492f9 | 10545 | ASET (Vcoding_category_table, coding_category_iso_7_tight, |
d67b4f80 | 10546 | intern_c_string ("coding-category-iso-7-tight")); |
df7492f9 | 10547 | ASET (Vcoding_category_table, coding_category_iso_8_1, |
d67b4f80 | 10548 | intern_c_string ("coding-category-iso-8-1")); |
df7492f9 | 10549 | ASET (Vcoding_category_table, coding_category_iso_8_2, |
d67b4f80 | 10550 | intern_c_string ("coding-category-iso-8-2")); |
df7492f9 | 10551 | ASET (Vcoding_category_table, coding_category_iso_7_else, |
d67b4f80 | 10552 | intern_c_string ("coding-category-iso-7-else")); |
df7492f9 | 10553 | ASET (Vcoding_category_table, coding_category_iso_8_else, |
d67b4f80 | 10554 | intern_c_string ("coding-category-iso-8-else")); |
a470d443 | 10555 | ASET (Vcoding_category_table, coding_category_utf_8_auto, |
d67b4f80 | 10556 | intern_c_string ("coding-category-utf-8-auto")); |
a470d443 | 10557 | ASET (Vcoding_category_table, coding_category_utf_8_nosig, |
d67b4f80 | 10558 | intern_c_string ("coding-category-utf-8")); |
a470d443 | 10559 | ASET (Vcoding_category_table, coding_category_utf_8_sig, |
d67b4f80 | 10560 | intern_c_string ("coding-category-utf-8-sig")); |
df7492f9 | 10561 | ASET (Vcoding_category_table, coding_category_utf_16_be, |
d67b4f80 | 10562 | intern_c_string ("coding-category-utf-16-be")); |
ff563fce | 10563 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
d67b4f80 | 10564 | intern_c_string ("coding-category-utf-16-auto")); |
df7492f9 | 10565 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
d67b4f80 | 10566 | intern_c_string ("coding-category-utf-16-le")); |
df7492f9 | 10567 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, |
d67b4f80 | 10568 | intern_c_string ("coding-category-utf-16-be-nosig")); |
df7492f9 | 10569 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, |
d67b4f80 | 10570 | intern_c_string ("coding-category-utf-16-le-nosig")); |
df7492f9 | 10571 | ASET (Vcoding_category_table, coding_category_charset, |
d67b4f80 | 10572 | intern_c_string ("coding-category-charset")); |
df7492f9 | 10573 | ASET (Vcoding_category_table, coding_category_sjis, |
d67b4f80 | 10574 | intern_c_string ("coding-category-sjis")); |
df7492f9 | 10575 | ASET (Vcoding_category_table, coding_category_big5, |
d67b4f80 | 10576 | intern_c_string ("coding-category-big5")); |
df7492f9 | 10577 | ASET (Vcoding_category_table, coding_category_ccl, |
d67b4f80 | 10578 | intern_c_string ("coding-category-ccl")); |
df7492f9 | 10579 | ASET (Vcoding_category_table, coding_category_emacs_mule, |
d67b4f80 | 10580 | intern_c_string ("coding-category-emacs-mule")); |
df7492f9 KH |
10581 | /* Followings are NOT target of code detection. */ |
10582 | ASET (Vcoding_category_table, coding_category_raw_text, | |
d67b4f80 | 10583 | intern_c_string ("coding-category-raw-text")); |
df7492f9 | 10584 | ASET (Vcoding_category_table, coding_category_undecided, |
d67b4f80 | 10585 | intern_c_string ("coding-category-undecided")); |
ecf488bc | 10586 | |
065e3595 KH |
10587 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
10588 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
10589 | DEFSYM (Qinvalid_source, "invalid-source"); | |
10590 | DEFSYM (Qinterrupted, "interrupted"); | |
10591 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
44e8490d | 10592 | DEFSYM (Qcoding_system_define_form, "coding-system-define-form"); |
065e3595 | 10593 | |
4ed46869 KH |
10594 | defsubr (&Scoding_system_p); |
10595 | defsubr (&Sread_coding_system); | |
10596 | defsubr (&Sread_non_nil_coding_system); | |
10597 | defsubr (&Scheck_coding_system); | |
10598 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 10599 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 10600 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 10601 | defsubr (&Sunencodable_char_position); |
df7492f9 | 10602 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
10603 | defsubr (&Sdecode_coding_region); |
10604 | defsubr (&Sencode_coding_region); | |
10605 | defsubr (&Sdecode_coding_string); | |
10606 | defsubr (&Sencode_coding_string); | |
10607 | defsubr (&Sdecode_sjis_char); | |
10608 | defsubr (&Sencode_sjis_char); | |
10609 | defsubr (&Sdecode_big5_char); | |
10610 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 10611 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 10612 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 10613 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 10614 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 10615 | defsubr (&Skeyboard_coding_system); |
a5d301df | 10616 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 10617 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 10618 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 10619 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 10620 | defsubr (&Scoding_system_put); |
df7492f9 KH |
10621 | defsubr (&Scoding_system_base); |
10622 | defsubr (&Scoding_system_plist); | |
10623 | defsubr (&Scoding_system_aliases); | |
10624 | defsubr (&Scoding_system_eol_type); | |
10625 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 10626 | |
4608c386 | 10627 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
48b0f3ae PJ |
10628 | doc: /* List of coding systems. |
10629 | ||
10630 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 10631 | updated by the functions `define-coding-system' and |
48b0f3ae | 10632 | `define-coding-system-alias'. */); |
4608c386 KH |
10633 | Vcoding_system_list = Qnil; |
10634 | ||
10635 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, | |
48b0f3ae PJ |
10636 | doc: /* Alist of coding system names. |
10637 | Each element is one element list of coding system name. | |
446dcd75 | 10638 | This variable is given to `completing-read' as COLLECTION argument. |
48b0f3ae PJ |
10639 | |
10640 | Do not alter the value of this variable manually. This variable should be | |
10641 | updated by the functions `make-coding-system' and | |
10642 | `define-coding-system-alias'. */); | |
4608c386 KH |
10643 | Vcoding_system_alist = Qnil; |
10644 | ||
4ed46869 | 10645 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
48b0f3ae PJ |
10646 | doc: /* List of coding-categories (symbols) ordered by priority. |
10647 | ||
10648 | On detecting a coding system, Emacs tries code detection algorithms | |
10649 | associated with each coding-category one by one in this order. When | |
10650 | one algorithm agrees with a byte sequence of source text, the coding | |
0ec31faf KH |
10651 | system bound to the corresponding coding-category is selected. |
10652 | ||
42205607 | 10653 | Don't modify this variable directly, but use `set-coding-priority'. */); |
4ed46869 KH |
10654 | { |
10655 | int i; | |
10656 | ||
10657 | Vcoding_category_list = Qnil; | |
df7492f9 | 10658 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 10659 | Vcoding_category_list |
d46c5b12 KH |
10660 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
10661 | Vcoding_category_list); | |
4ed46869 KH |
10662 | } |
10663 | ||
10664 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, | |
48b0f3ae PJ |
10665 | doc: /* Specify the coding system for read operations. |
10666 | It is useful to bind this variable with `let', but do not set it globally. | |
10667 | If the value is a coding system, it is used for decoding on read operation. | |
446dcd75 JB |
10668 | If not, an appropriate element is used from one of the coding system alists. |
10669 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae | 10670 | `process-coding-system-alist', and `network-coding-system-alist'. */); |
4ed46869 KH |
10671 | Vcoding_system_for_read = Qnil; |
10672 | ||
10673 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, | |
48b0f3ae PJ |
10674 | doc: /* Specify the coding system for write operations. |
10675 | Programs bind this variable with `let', but you should not set it globally. | |
10676 | If the value is a coding system, it is used for encoding of output, | |
10677 | when writing it to a file and when sending it to a file or subprocess. | |
10678 | ||
10679 | If this does not specify a coding system, an appropriate element | |
446dcd75 JB |
10680 | is used from one of the coding system alists. |
10681 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae PJ |
10682 | `process-coding-system-alist', and `network-coding-system-alist'. |
10683 | For output to files, if the above procedure does not specify a coding system, | |
10684 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
10685 | Vcoding_system_for_write = Qnil; |
10686 | ||
10687 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, | |
df7492f9 KH |
10688 | doc: /* |
10689 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
10690 | Vlast_coding_system_used = Qnil; |
10691 | ||
065e3595 KH |
10692 | DEFVAR_LISP ("last-code-conversion-error", &Vlast_code_conversion_error, |
10693 | doc: /* | |
10694 | Error status of the last code conversion. | |
10695 | ||
10696 | When an error was detected in the last code conversion, this variable | |
10697 | is set to one of the following symbols. | |
10698 | `insufficient-source' | |
10699 | `inconsistent-eol' | |
10700 | `invalid-source' | |
10701 | `interrupted' | |
10702 | `insufficient-memory' | |
10703 | When no error was detected, the value doesn't change. So, to check | |
10704 | the error status of a code conversion by this variable, you must | |
10705 | explicitly set this variable to nil before performing code | |
10706 | conversion. */); | |
10707 | Vlast_code_conversion_error = Qnil; | |
10708 | ||
9ce27fde | 10709 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
df7492f9 KH |
10710 | doc: /* |
10711 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
10712 | See info node `Coding Systems' and info node `Text and Binary' concerning |
10713 | such conversion. */); | |
9ce27fde KH |
10714 | inhibit_eol_conversion = 0; |
10715 | ||
ed29121d | 10716 | DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
df7492f9 KH |
10717 | doc: /* |
10718 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
10719 | Bind it to t if the process output is to be treated as if it were a file |
10720 | read from some filesystem. */); | |
ed29121d EZ |
10721 | inherit_process_coding_system = 0; |
10722 | ||
02ba4723 | 10723 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
df7492f9 KH |
10724 | doc: /* |
10725 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
10726 | The format is ((PATTERN . VAL) ...), |
10727 | where PATTERN is a regular expression matching a file name, | |
10728 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10729 | If VAL is a coding system, it is used for both decoding and encoding | |
10730 | the file contents. | |
10731 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10732 | and the cdr part is used for encoding. | |
10733 | If VAL is a function symbol, the function must return a coding system | |
2c53e699 KH |
10734 | or a cons of coding systems which are used as above. The function is |
10735 | called with an argument that is a list of the arguments with which | |
5a0bbd9a KH |
10736 | `find-operation-coding-system' was called. If the function can't decide |
10737 | a coding system, it can return `undecided' so that the normal | |
10738 | code-detection is performed. | |
48b0f3ae PJ |
10739 | |
10740 | See also the function `find-operation-coding-system' | |
10741 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
10742 | Vfile_coding_system_alist = Qnil; |
10743 | ||
10744 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, | |
df7492f9 KH |
10745 | doc: /* |
10746 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
10747 | The format is ((PATTERN . VAL) ...), |
10748 | where PATTERN is a regular expression matching a program name, | |
10749 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10750 | If VAL is a coding system, it is used for both decoding what received | |
10751 | from the program and encoding what sent to the program. | |
10752 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10753 | and the cdr part is used for encoding. | |
10754 | If VAL is a function symbol, the function must return a coding system | |
10755 | or a cons of coding systems which are used as above. | |
10756 | ||
10757 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
10758 | Vprocess_coding_system_alist = Qnil; |
10759 | ||
10760 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, | |
df7492f9 KH |
10761 | doc: /* |
10762 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
10763 | The format is ((PATTERN . VAL) ...), |
10764 | where PATTERN is a regular expression matching a network service name | |
10765 | or is a port number to connect to, | |
10766 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10767 | If VAL is a coding system, it is used for both decoding what received | |
10768 | from the network stream and encoding what sent to the network stream. | |
10769 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10770 | and the cdr part is used for encoding. | |
10771 | If VAL is a function symbol, the function must return a coding system | |
10772 | or a cons of coding systems which are used as above. | |
10773 | ||
10774 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 10775 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 10776 | |
68c45bf0 | 10777 | DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
75205970 RS |
10778 | doc: /* Coding system to use with system messages. |
10779 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
10780 | Vlocale_coding_system = Qnil; |
10781 | ||
005f0d35 | 10782 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
7722baf9 | 10783 | DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
df7492f9 KH |
10784 | doc: /* |
10785 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
d67b4f80 | 10786 | eol_mnemonic_unix = make_pure_c_string (":"); |
4ed46869 | 10787 | |
7722baf9 | 10788 | DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
df7492f9 KH |
10789 | doc: /* |
10790 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
d67b4f80 | 10791 | eol_mnemonic_dos = make_pure_c_string ("\\"); |
4ed46869 | 10792 | |
7722baf9 | 10793 | DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
df7492f9 KH |
10794 | doc: /* |
10795 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
d67b4f80 | 10796 | eol_mnemonic_mac = make_pure_c_string ("/"); |
4ed46869 | 10797 | |
7722baf9 | 10798 | DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
df7492f9 KH |
10799 | doc: /* |
10800 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
d67b4f80 | 10801 | eol_mnemonic_undecided = make_pure_c_string (":"); |
4ed46869 | 10802 | |
84fbb8a0 | 10803 | DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
df7492f9 KH |
10804 | doc: /* |
10805 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 10806 | Venable_character_translation = Qt; |
bdd9fb48 | 10807 | |
f967223b | 10808 | DEFVAR_LISP ("standard-translation-table-for-decode", |
48b0f3ae PJ |
10809 | &Vstandard_translation_table_for_decode, |
10810 | doc: /* Table for translating characters while decoding. */); | |
f967223b | 10811 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 10812 | |
f967223b | 10813 | DEFVAR_LISP ("standard-translation-table-for-encode", |
48b0f3ae PJ |
10814 | &Vstandard_translation_table_for_encode, |
10815 | doc: /* Table for translating characters while encoding. */); | |
f967223b | 10816 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 10817 | |
df7492f9 | 10818 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table, |
48b0f3ae PJ |
10819 | doc: /* Alist of charsets vs revision numbers. |
10820 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
10821 | designate it with the escape sequence identifying revision (cdr part |
10822 | of the element). */); | |
10823 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
10824 | |
10825 | DEFVAR_LISP ("default-process-coding-system", | |
10826 | &Vdefault_process_coding_system, | |
48b0f3ae PJ |
10827 | doc: /* Cons of coding systems used for process I/O by default. |
10828 | The car part is used for decoding a process output, | |
10829 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 10830 | Vdefault_process_coding_system = Qnil; |
c4825358 | 10831 | |
3f003981 | 10832 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
df7492f9 KH |
10833 | doc: /* |
10834 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
10835 | This is a vector of length 256. |
10836 | If Nth element is non-nil, the existence of code N in a file | |
10837 | \(or output of subprocess) doesn't prevent it to be detected as | |
10838 | a coding system of ISO 2022 variant which has a flag | |
10839 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
10840 | or reading output of a subprocess. | |
446dcd75 | 10841 | Only 128th through 159th elements have a meaning. */); |
3f003981 | 10842 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
10843 | |
10844 | DEFVAR_LISP ("select-safe-coding-system-function", | |
10845 | &Vselect_safe_coding_system_function, | |
df7492f9 KH |
10846 | doc: /* |
10847 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
10848 | |
10849 | If set, this function is called to force a user to select a proper | |
10850 | coding system which can encode the text in the case that a default | |
fdecf907 GM |
10851 | coding system used in each operation can't encode the text. The |
10852 | function should take care that the buffer is not modified while | |
10853 | the coding system is being selected. | |
48b0f3ae PJ |
10854 | |
10855 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
10856 | Vselect_safe_coding_system_function = Qnil; |
10857 | ||
5d5bf4d8 KH |
10858 | DEFVAR_BOOL ("coding-system-require-warning", |
10859 | &coding_system_require_warning, | |
10860 | doc: /* Internal use only. | |
6b89e3aa KH |
10861 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
10862 | called even if `coding-system-for-write' is non-nil. The command | |
10863 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
10864 | coding_system_require_warning = 0; |
10865 | ||
10866 | ||
22ab2303 | 10867 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
74383408 | 10868 | &inhibit_iso_escape_detection, |
df7492f9 | 10869 | doc: /* |
97b1b294 | 10870 | If non-nil, Emacs ignores ISO-2022 escape sequences during code detection. |
48b0f3ae | 10871 | |
97b1b294 EZ |
10872 | When Emacs reads text, it tries to detect how the text is encoded. |
10873 | This code detection is sensitive to escape sequences. If Emacs sees | |
10874 | a valid ISO-2022 escape sequence, it assumes the text is encoded in one | |
10875 | of the ISO2022 encodings, and decodes text by the corresponding coding | |
10876 | system (e.g. `iso-2022-7bit'). | |
48b0f3ae PJ |
10877 | |
10878 | However, there may be a case that you want to read escape sequences in | |
10879 | a file as is. In such a case, you can set this variable to non-nil. | |
97b1b294 EZ |
10880 | Then the code detection will ignore any escape sequences, and no text is |
10881 | detected as encoded in some ISO-2022 encoding. The result is that all | |
48b0f3ae PJ |
10882 | escape sequences become visible in a buffer. |
10883 | ||
10884 | The default value is nil, and it is strongly recommended not to change | |
10885 | it. That is because many Emacs Lisp source files that contain | |
10886 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
10887 | in Emacs's distribution, and they won't be decoded correctly on | |
10888 | reading if you suppress escape sequence detection. | |
10889 | ||
10890 | The other way to read escape sequences in a file without decoding is | |
97b1b294 | 10891 | to explicitly specify some coding system that doesn't use ISO-2022 |
48b0f3ae | 10892 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); |
74383408 | 10893 | inhibit_iso_escape_detection = 0; |
002fdb44 | 10894 | |
97b1b294 EZ |
10895 | DEFVAR_BOOL ("inhibit-null-byte-detection", |
10896 | &inhibit_null_byte_detection, | |
10897 | doc: /* If non-nil, Emacs ignores null bytes on code detection. | |
10898 | By default, Emacs treats it as binary data, and does not attempt to | |
10899 | decode it. The effect is as if you specified `no-conversion' for | |
10900 | reading that text. | |
10901 | ||
10902 | Set this to non-nil when a regular text happens to include null bytes. | |
10903 | Examples are Index nodes of Info files and null-byte delimited output | |
10904 | from GNU Find and GNU Grep. Emacs will then ignore the null bytes and | |
10905 | decode text as usual. */); | |
10906 | inhibit_null_byte_detection = 0; | |
10907 | ||
002fdb44 | 10908 | DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input, |
15c8f9d1 | 10909 | doc: /* Char table for translating self-inserting characters. |
446dcd75 | 10910 | This is applied to the result of input methods, not their input. |
8434d0b8 EZ |
10911 | See also `keyboard-translate-table'. |
10912 | ||
10913 | Use of this variable for character code unification was rendered | |
10914 | obsolete in Emacs 23.1 and later, since Unicode is now the basis of | |
10915 | internal character representation. */); | |
002fdb44 | 10916 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 10917 | |
2c78b7e1 KH |
10918 | { |
10919 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 10920 | Lisp_Object plist[16]; |
2c78b7e1 KH |
10921 | int i; |
10922 | ||
10923 | for (i = 0; i < coding_arg_max; i++) | |
10924 | args[i] = Qnil; | |
10925 | ||
d67b4f80 | 10926 | plist[0] = intern_c_string (":name"); |
2c78b7e1 | 10927 | plist[1] = args[coding_arg_name] = Qno_conversion; |
d67b4f80 | 10928 | plist[2] = intern_c_string (":mnemonic"); |
2c78b7e1 | 10929 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); |
d67b4f80 | 10930 | plist[4] = intern_c_string (":coding-type"); |
2c78b7e1 | 10931 | plist[5] = args[coding_arg_coding_type] = Qraw_text; |
d67b4f80 | 10932 | plist[6] = intern_c_string (":ascii-compatible-p"); |
2c78b7e1 | 10933 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; |
d67b4f80 | 10934 | plist[8] = intern_c_string (":default-char"); |
2c78b7e1 | 10935 | plist[9] = args[coding_arg_default_char] = make_number (0); |
d67b4f80 | 10936 | plist[10] = intern_c_string (":for-unibyte"); |
8f924df7 | 10937 | plist[11] = args[coding_arg_for_unibyte] = Qt; |
d67b4f80 DN |
10938 | plist[12] = intern_c_string (":docstring"); |
10939 | plist[13] = make_pure_c_string ("Do no conversion.\n\ | |
2c78b7e1 KH |
10940 | \n\ |
10941 | When you visit a file with this coding, the file is read into a\n\ | |
10942 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
10943 | character."); | |
d67b4f80 | 10944 | plist[14] = intern_c_string (":eol-type"); |
8f924df7 KH |
10945 | plist[15] = args[coding_arg_eol_type] = Qunix; |
10946 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 | 10947 | Fdefine_coding_system_internal (coding_arg_max, args); |
ae6f73fa KH |
10948 | |
10949 | plist[1] = args[coding_arg_name] = Qundecided; | |
10950 | plist[3] = args[coding_arg_mnemonic] = make_number ('-'); | |
10951 | plist[5] = args[coding_arg_coding_type] = Qundecided; | |
10952 | /* This is already set. | |
35befdaa | 10953 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */ |
d67b4f80 | 10954 | plist[8] = intern_c_string (":charset-list"); |
ae6f73fa KH |
10955 | plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil); |
10956 | plist[11] = args[coding_arg_for_unibyte] = Qnil; | |
d67b4f80 | 10957 | plist[13] = make_pure_c_string ("No conversion on encoding, automatic conversion on decoding."); |
ae6f73fa KH |
10958 | plist[15] = args[coding_arg_eol_type] = Qnil; |
10959 | args[coding_arg_plist] = Flist (16, plist); | |
10960 | Fdefine_coding_system_internal (coding_arg_max, args); | |
2c78b7e1 KH |
10961 | } |
10962 | ||
2c78b7e1 | 10963 | setup_coding_system (Qno_conversion, &safe_terminal_coding); |
ff563fce KH |
10964 | |
10965 | { | |
10966 | int i; | |
10967 | ||
10968 | for (i = 0; i < coding_category_max; i++) | |
10969 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
10970 | } | |
fcbcfb64 KH |
10971 | #if defined (MSDOS) || defined (WINDOWSNT) |
10972 | system_eol_type = Qdos; | |
10973 | #else | |
10974 | system_eol_type = Qunix; | |
10975 | #endif | |
10976 | staticpro (&system_eol_type); | |
4ed46869 KH |
10977 | } |
10978 | ||
68c45bf0 PE |
10979 | char * |
10980 | emacs_strerror (error_number) | |
10981 | int error_number; | |
10982 | { | |
10983 | char *str; | |
10984 | ||
ca9c0567 | 10985 | synchronize_system_messages_locale (); |
68c45bf0 PE |
10986 | str = strerror (error_number); |
10987 | ||
10988 | if (! NILP (Vlocale_coding_system)) | |
10989 | { | |
10990 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
10991 | Vlocale_coding_system, | |
10992 | 0); | |
d5db4077 | 10993 | str = (char *) SDATA (dec); |
68c45bf0 PE |
10994 | } |
10995 | ||
10996 | return str; | |
10997 | } | |
10998 | ||
4ed46869 | 10999 | #endif /* emacs */ |
9ffd559c KH |
11000 | |
11001 | /* arch-tag: 3a3a2b01-5ff6-4071-9afe-f5b808d9229d | |
11002 | (do not change this comment) */ |