Commit | Line | Data |
---|---|---|
9542cb1f | 1 | /* Coding system handler (conversion, detection, etc). |
aaef169d | 2 | Copyright (C) 2001, 2002, 2003, 2004, 2005, |
76b6f707 | 3 | 2006, 2007, 2008, 2009 Free Software Foundation, Inc. |
7976eda0 | 4 | Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, |
76b6f707 | 5 | 2005, 2006, 2007, 2008, 2009 |
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 KH |
291 | #include <stdio.h> |
292 | ||
4ed46869 KH |
293 | #include "lisp.h" |
294 | #include "buffer.h" | |
df7492f9 | 295 | #include "character.h" |
4ed46869 KH |
296 | #include "charset.h" |
297 | #include "ccl.h" | |
df7492f9 | 298 | #include "composite.h" |
4ed46869 KH |
299 | #include "coding.h" |
300 | #include "window.h" | |
b8299c66 KL |
301 | #include "frame.h" |
302 | #include "termhooks.h" | |
4ed46869 | 303 | |
df7492f9 | 304 | Lisp_Object Vcoding_system_hash_table; |
4ed46869 | 305 | |
df7492f9 | 306 | Lisp_Object Qcoding_system, Qcoding_aliases, Qeol_type; |
1965cb73 DL |
307 | Lisp_Object Qunix, Qdos; |
308 | extern Lisp_Object Qmac; /* frame.c */ | |
4ed46869 KH |
309 | Lisp_Object Qbuffer_file_coding_system; |
310 | Lisp_Object Qpost_read_conversion, Qpre_write_conversion; | |
df7492f9 | 311 | Lisp_Object Qdefault_char; |
27901516 | 312 | Lisp_Object Qno_conversion, Qundecided; |
df7492f9 | 313 | Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5; |
b49a1807 | 314 | Lisp_Object Qbig, Qlittle; |
bb0115a2 | 315 | Lisp_Object Qcoding_system_history; |
1397dc18 | 316 | Lisp_Object Qvalid_codes; |
2133e2d1 | 317 | Lisp_Object QCcategory, QCmnemonic, QCdefault_char; |
a6f87d34 KH |
318 | Lisp_Object QCdecode_translation_table, QCencode_translation_table; |
319 | Lisp_Object QCpost_read_conversion, QCpre_write_conversion; | |
35befdaa | 320 | Lisp_Object QCascii_compatible_p; |
4ed46869 KH |
321 | |
322 | extern Lisp_Object Qinsert_file_contents, Qwrite_region; | |
387f6ba5 | 323 | Lisp_Object Qcall_process, Qcall_process_region; |
4ed46869 KH |
324 | Lisp_Object Qstart_process, Qopen_network_stream; |
325 | Lisp_Object Qtarget_idx; | |
326 | ||
065e3595 KH |
327 | Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source; |
328 | Lisp_Object Qinterrupted, Qinsufficient_memory; | |
329 | ||
c7183fb8 GM |
330 | extern Lisp_Object Qcompletion_ignore_case; |
331 | ||
44e8490d KH |
332 | /* If a symbol has this property, evaluate the value to define the |
333 | symbol as a coding system. */ | |
334 | static Lisp_Object Qcoding_system_define_form; | |
335 | ||
5d5bf4d8 KH |
336 | int coding_system_require_warning; |
337 | ||
d46c5b12 KH |
338 | Lisp_Object Vselect_safe_coding_system_function; |
339 | ||
7722baf9 EZ |
340 | /* Mnemonic string for each format of end-of-line. */ |
341 | Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; | |
342 | /* Mnemonic string to indicate format of end-of-line is not yet | |
4ed46869 | 343 | decided. */ |
7722baf9 | 344 | Lisp_Object eol_mnemonic_undecided; |
4ed46869 | 345 | |
fcbcfb64 KH |
346 | /* Format of end-of-line decided by system. This is Qunix on |
347 | Unix and Mac, Qdos on DOS/Windows. | |
348 | This has an effect only for external encoding (i.e. for output to | |
349 | file and process), not for in-buffer or Lisp string encoding. */ | |
350 | static Lisp_Object system_eol_type; | |
351 | ||
4ed46869 KH |
352 | #ifdef emacs |
353 | ||
4608c386 KH |
354 | Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
355 | ||
356 | Lisp_Object Qcoding_system_p, Qcoding_system_error; | |
4ed46869 | 357 | |
d46c5b12 KH |
358 | /* Coding system emacs-mule and raw-text are for converting only |
359 | end-of-line format. */ | |
360 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 361 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 362 | |
4ed46869 KH |
363 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
364 | routines by the following three variables. */ | |
365 | /* Coding-system for reading files and receiving data from process. */ | |
366 | Lisp_Object Vcoding_system_for_read; | |
367 | /* Coding-system for writing files and sending data to process. */ | |
368 | Lisp_Object Vcoding_system_for_write; | |
369 | /* Coding-system actually used in the latest I/O. */ | |
370 | Lisp_Object Vlast_coding_system_used; | |
065e3595 KH |
371 | /* Set to non-nil when an error is detected while code conversion. */ |
372 | Lisp_Object Vlast_code_conversion_error; | |
c4825358 | 373 | /* A vector of length 256 which contains information about special |
94487c4e | 374 | Latin codes (especially for dealing with Microsoft codes). */ |
3f003981 | 375 | Lisp_Object Vlatin_extra_code_table; |
c4825358 | 376 | |
9ce27fde KH |
377 | /* Flag to inhibit code conversion of end-of-line format. */ |
378 | int inhibit_eol_conversion; | |
379 | ||
74383408 KH |
380 | /* Flag to inhibit ISO2022 escape sequence detection. */ |
381 | int inhibit_iso_escape_detection; | |
382 | ||
97b1b294 EZ |
383 | /* Flag to inhibit detection of binary files through null bytes. */ |
384 | int inhibit_null_byte_detection; | |
385 | ||
ed29121d EZ |
386 | /* Flag to make buffer-file-coding-system inherit from process-coding. */ |
387 | int inherit_process_coding_system; | |
388 | ||
c4825358 KH |
389 | /* Coding system to be used to encode text for terminal display when |
390 | terminal coding system is nil. */ | |
391 | struct coding_system safe_terminal_coding; | |
392 | ||
02ba4723 KH |
393 | Lisp_Object Vfile_coding_system_alist; |
394 | Lisp_Object Vprocess_coding_system_alist; | |
395 | Lisp_Object Vnetwork_coding_system_alist; | |
4ed46869 | 396 | |
68c45bf0 PE |
397 | Lisp_Object Vlocale_coding_system; |
398 | ||
4ed46869 KH |
399 | #endif /* emacs */ |
400 | ||
f967223b KH |
401 | /* Flag to tell if we look up translation table on character code |
402 | conversion. */ | |
84fbb8a0 | 403 | Lisp_Object Venable_character_translation; |
f967223b KH |
404 | /* Standard translation table to look up on decoding (reading). */ |
405 | Lisp_Object Vstandard_translation_table_for_decode; | |
406 | /* Standard translation table to look up on encoding (writing). */ | |
407 | Lisp_Object Vstandard_translation_table_for_encode; | |
84fbb8a0 | 408 | |
f967223b KH |
409 | Lisp_Object Qtranslation_table; |
410 | Lisp_Object Qtranslation_table_id; | |
411 | Lisp_Object Qtranslation_table_for_decode; | |
412 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 KH |
413 | |
414 | /* Alist of charsets vs revision number. */ | |
df7492f9 | 415 | static Lisp_Object Vcharset_revision_table; |
4ed46869 | 416 | |
02ba4723 KH |
417 | /* Default coding systems used for process I/O. */ |
418 | Lisp_Object Vdefault_process_coding_system; | |
419 | ||
002fdb44 DL |
420 | /* Char table for translating Quail and self-inserting input. */ |
421 | Lisp_Object Vtranslation_table_for_input; | |
422 | ||
df7492f9 KH |
423 | /* Two special coding systems. */ |
424 | Lisp_Object Vsjis_coding_system; | |
425 | Lisp_Object Vbig5_coding_system; | |
426 | ||
df7492f9 KH |
427 | /* ISO2022 section */ |
428 | ||
429 | #define CODING_ISO_INITIAL(coding, reg) \ | |
430 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
431 | coding_attr_iso_initial), \ | |
432 | reg))) | |
433 | ||
434 | ||
435 | #define CODING_ISO_REQUEST(coding, charset_id) \ | |
436 | ((charset_id <= (coding)->max_charset_id \ | |
437 | ? (coding)->safe_charsets[charset_id] \ | |
438 | : -1)) | |
439 | ||
440 | ||
441 | #define CODING_ISO_FLAGS(coding) \ | |
442 | ((coding)->spec.iso_2022.flags) | |
443 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
444 | ((coding)->spec.iso_2022.current_designation[reg]) | |
445 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
446 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
447 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
448 | ((coding)->spec.iso_2022.single_shifting) | |
449 | #define CODING_ISO_BOL(coding) \ | |
450 | ((coding)->spec.iso_2022.bol) | |
451 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
452 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
453 | ||
454 | /* Control characters of ISO2022. */ | |
455 | /* code */ /* function */ | |
456 | #define ISO_CODE_LF 0x0A /* line-feed */ | |
457 | #define ISO_CODE_CR 0x0D /* carriage-return */ | |
458 | #define ISO_CODE_SO 0x0E /* shift-out */ | |
459 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
460 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
461 | #define ISO_CODE_ESC 0x1B /* escape */ | |
462 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
463 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
464 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
465 | ||
466 | /* All code (1-byte) of ISO2022 is classified into one of the | |
467 | followings. */ | |
468 | enum iso_code_class_type | |
469 | { | |
470 | ISO_control_0, /* Control codes in the range | |
471 | 0x00..0x1F and 0x7F, except for the | |
472 | following 5 codes. */ | |
df7492f9 KH |
473 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
474 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
475 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
476 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
477 | ISO_control_1, /* Control codes in the range | |
478 | 0x80..0x9F, except for the | |
479 | following 3 codes. */ | |
480 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
481 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
482 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
483 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
484 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
485 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
486 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
487 | }; | |
05e6f5dc | 488 | |
df7492f9 KH |
489 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
490 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 491 | |
df7492f9 KH |
492 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
493 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
494 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 495 | |
df7492f9 KH |
496 | /* If set, reset graphic planes and registers at end-of-line to the |
497 | initial state. */ | |
498 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 499 | |
df7492f9 KH |
500 | /* If set, reset graphic planes and registers before any control |
501 | characters to the initial state. */ | |
502 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 503 | |
df7492f9 KH |
504 | /* If set, encode by 7-bit environment. */ |
505 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 506 | |
df7492f9 KH |
507 | /* If set, use locking-shift function. */ |
508 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 509 | |
df7492f9 KH |
510 | /* If set, use single-shift function. Overwrite |
511 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
512 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 513 | |
df7492f9 KH |
514 | /* If set, use designation escape sequence. */ |
515 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 516 | |
df7492f9 KH |
517 | /* If set, produce revision number sequence. */ |
518 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 519 | |
df7492f9 KH |
520 | /* If set, produce ISO6429's direction specifying sequence. */ |
521 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 522 | |
df7492f9 KH |
523 | /* If set, assume designation states are reset at beginning of line on |
524 | output. */ | |
525 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 526 | |
df7492f9 KH |
527 | /* If set, designation sequence should be placed at beginning of line |
528 | on output. */ | |
529 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 530 | |
df7492f9 KH |
531 | /* If set, do not encode unsafe charactes on output. */ |
532 | #define CODING_ISO_FLAG_SAFE 0x0800 | |
aa72b389 | 533 | |
df7492f9 KH |
534 | /* If set, extra latin codes (128..159) are accepted as a valid code |
535 | on input. */ | |
536 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 537 | |
df7492f9 | 538 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 539 | |
df7492f9 | 540 | #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 |
aa72b389 | 541 | |
bf16eb23 | 542 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 543 | |
bf16eb23 | 544 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 545 | |
bf16eb23 | 546 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 547 | |
df7492f9 KH |
548 | /* A character to be produced on output if encoding of the original |
549 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
550 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 551 | |
a470d443 KH |
552 | /* UTF-8 section */ |
553 | #define CODING_UTF_8_BOM(coding) \ | |
554 | ((coding)->spec.utf_8_bom) | |
4ed46869 | 555 | |
df7492f9 KH |
556 | /* UTF-16 section */ |
557 | #define CODING_UTF_16_BOM(coding) \ | |
558 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 559 | |
df7492f9 KH |
560 | #define CODING_UTF_16_ENDIAN(coding) \ |
561 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 562 | |
df7492f9 KH |
563 | #define CODING_UTF_16_SURROGATE(coding) \ |
564 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 565 | |
4ed46869 | 566 | |
df7492f9 KH |
567 | /* CCL section */ |
568 | #define CODING_CCL_DECODER(coding) \ | |
569 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
570 | #define CODING_CCL_ENCODER(coding) \ | |
571 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
572 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 573 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 574 | |
5a936b46 | 575 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 576 | |
df7492f9 KH |
577 | enum coding_category |
578 | { | |
579 | coding_category_iso_7, | |
580 | coding_category_iso_7_tight, | |
581 | coding_category_iso_8_1, | |
582 | coding_category_iso_8_2, | |
583 | coding_category_iso_7_else, | |
584 | coding_category_iso_8_else, | |
a470d443 KH |
585 | coding_category_utf_8_auto, |
586 | coding_category_utf_8_nosig, | |
587 | coding_category_utf_8_sig, | |
df7492f9 KH |
588 | coding_category_utf_16_auto, |
589 | coding_category_utf_16_be, | |
590 | coding_category_utf_16_le, | |
591 | coding_category_utf_16_be_nosig, | |
592 | coding_category_utf_16_le_nosig, | |
593 | coding_category_charset, | |
594 | coding_category_sjis, | |
595 | coding_category_big5, | |
596 | coding_category_ccl, | |
597 | coding_category_emacs_mule, | |
598 | /* All above are targets of code detection. */ | |
599 | coding_category_raw_text, | |
600 | coding_category_undecided, | |
601 | coding_category_max | |
602 | }; | |
603 | ||
604 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
605 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
606 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
607 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
608 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
609 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
610 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
a470d443 KH |
611 | #define CATEGORY_MASK_UTF_8_AUTO (1 << coding_category_utf_8_auto) |
612 | #define CATEGORY_MASK_UTF_8_NOSIG (1 << coding_category_utf_8_nosig) | |
613 | #define CATEGORY_MASK_UTF_8_SIG (1 << coding_category_utf_8_sig) | |
b49a1807 | 614 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
615 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
616 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
617 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
618 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
619 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
620 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
621 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
622 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
623 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 624 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
625 | |
626 | /* This value is returned if detect_coding_mask () find nothing other | |
627 | than ASCII characters. */ | |
628 | #define CATEGORY_MASK_ANY \ | |
629 | (CATEGORY_MASK_ISO_7 \ | |
630 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
631 | | CATEGORY_MASK_ISO_8_1 \ | |
632 | | CATEGORY_MASK_ISO_8_2 \ | |
633 | | CATEGORY_MASK_ISO_7_ELSE \ | |
634 | | CATEGORY_MASK_ISO_8_ELSE \ | |
a470d443 KH |
635 | | CATEGORY_MASK_UTF_8_AUTO \ |
636 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
637 | | CATEGORY_MASK_UTF_8_SIG \ | |
2f3cbb32 | 638 | | CATEGORY_MASK_UTF_16_AUTO \ |
df7492f9 KH |
639 | | CATEGORY_MASK_UTF_16_BE \ |
640 | | CATEGORY_MASK_UTF_16_LE \ | |
641 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
642 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
643 | | CATEGORY_MASK_CHARSET \ | |
644 | | CATEGORY_MASK_SJIS \ | |
645 | | CATEGORY_MASK_BIG5 \ | |
646 | | CATEGORY_MASK_CCL \ | |
647 | | CATEGORY_MASK_EMACS_MULE) | |
648 | ||
649 | ||
650 | #define CATEGORY_MASK_ISO_7BIT \ | |
651 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
652 | ||
653 | #define CATEGORY_MASK_ISO_8BIT \ | |
654 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
655 | ||
656 | #define CATEGORY_MASK_ISO_ELSE \ | |
657 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
658 | ||
659 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
660 | (CATEGORY_MASK_ISO_7 \ | |
661 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
662 | | CATEGORY_MASK_ISO_7_ELSE \ | |
663 | | CATEGORY_MASK_ISO_8_ELSE) | |
664 | ||
665 | #define CATEGORY_MASK_ISO \ | |
666 | ( CATEGORY_MASK_ISO_7BIT \ | |
667 | | CATEGORY_MASK_ISO_8BIT \ | |
668 | | CATEGORY_MASK_ISO_ELSE) | |
669 | ||
670 | #define CATEGORY_MASK_UTF_16 \ | |
2f3cbb32 KH |
671 | (CATEGORY_MASK_UTF_16_AUTO \ |
672 | | CATEGORY_MASK_UTF_16_BE \ | |
df7492f9 KH |
673 | | CATEGORY_MASK_UTF_16_LE \ |
674 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
675 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
676 | ||
a470d443 KH |
677 | #define CATEGORY_MASK_UTF_8 \ |
678 | (CATEGORY_MASK_UTF_8_AUTO \ | |
679 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
680 | | CATEGORY_MASK_UTF_8_SIG) | |
df7492f9 KH |
681 | |
682 | /* List of symbols `coding-category-xxx' ordered by priority. This | |
683 | variable is exposed to Emacs Lisp. */ | |
684 | static Lisp_Object Vcoding_category_list; | |
685 | ||
686 | /* Table of coding categories (Lisp symbols). This variable is for | |
687 | internal use oly. */ | |
688 | static Lisp_Object Vcoding_category_table; | |
689 | ||
690 | /* Table of coding-categories ordered by priority. */ | |
691 | static enum coding_category coding_priorities[coding_category_max]; | |
692 | ||
693 | /* Nth element is a coding context for the coding system bound to the | |
694 | Nth coding category. */ | |
695 | static struct coding_system coding_categories[coding_category_max]; | |
696 | ||
df7492f9 KH |
697 | /*** Commonly used macros and functions ***/ |
698 | ||
699 | #ifndef min | |
700 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
701 | #endif | |
702 | #ifndef max | |
703 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
704 | #endif | |
4ed46869 | 705 | |
24a73b0a KH |
706 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
707 | do { \ | |
708 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
709 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 710 | } while (0) |
4ed46869 | 711 | |
4ed46869 | 712 | |
df7492f9 KH |
713 | /* Safely get one byte from the source text pointed by SRC which ends |
714 | at SRC_END, and set C to that byte. If there are not enough bytes | |
065e3595 KH |
715 | in the source, it jumps to `no_more_source'. If multibytep is |
716 | nonzero, and a multibyte character is found at SRC, set C to the | |
717 | negative value of the character code. The caller should declare | |
718 | and set these variables appropriately in advance: | |
719 | src, src_end, multibytep */ | |
aa72b389 | 720 | |
065e3595 KH |
721 | #define ONE_MORE_BYTE(c) \ |
722 | do { \ | |
723 | if (src == src_end) \ | |
724 | { \ | |
725 | if (src_base < src) \ | |
726 | record_conversion_result \ | |
727 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
728 | goto no_more_source; \ | |
729 | } \ | |
730 | c = *src++; \ | |
731 | if (multibytep && (c & 0x80)) \ | |
732 | { \ | |
733 | if ((c & 0xFE) == 0xC0) \ | |
734 | c = ((c & 1) << 6) | *src++; \ | |
735 | else \ | |
736 | { \ | |
35befdaa KH |
737 | src--; \ |
738 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
739 | record_conversion_result \ |
740 | (coding, CODING_RESULT_INVALID_SRC); \ | |
741 | } \ | |
742 | } \ | |
743 | consumed_chars++; \ | |
aa72b389 KH |
744 | } while (0) |
745 | ||
f56a4450 | 746 | /* Safely get two bytes from the source text pointed by SRC which ends |
220eeac9 KH |
747 | at SRC_END, and set C1 and C2 to those bytes while skipping the |
748 | heading multibyte characters. If there are not enough bytes in the | |
749 | source, it jumps to `no_more_source'. If multibytep is nonzero and | |
750 | a multibyte character is found for C2, set C2 to the negative value | |
751 | of the character code. The caller should declare and set these | |
752 | variables appropriately in advance: | |
f56a4450 KH |
753 | src, src_end, multibytep |
754 | It is intended that this macro is used in detect_coding_utf_16. */ | |
755 | ||
220eeac9 KH |
756 | #define TWO_MORE_BYTES(c1, c2) \ |
757 | do { \ | |
758 | do { \ | |
759 | if (src == src_end) \ | |
760 | goto no_more_source; \ | |
761 | c1 = *src++; \ | |
762 | if (multibytep && (c1 & 0x80)) \ | |
763 | { \ | |
764 | if ((c1 & 0xFE) == 0xC0) \ | |
765 | c1 = ((c1 & 1) << 6) | *src++; \ | |
766 | else \ | |
767 | { \ | |
768 | src += BYTES_BY_CHAR_HEAD (c1) - 1; \ | |
769 | c1 = -1; \ | |
770 | } \ | |
771 | } \ | |
772 | } while (c1 < 0); \ | |
773 | if (src == src_end) \ | |
774 | goto no_more_source; \ | |
775 | c2 = *src++; \ | |
776 | if (multibytep && (c2 & 0x80)) \ | |
777 | { \ | |
778 | if ((c2 & 0xFE) == 0xC0) \ | |
779 | c2 = ((c2 & 1) << 6) | *src++; \ | |
780 | else \ | |
781 | c2 = -1; \ | |
782 | } \ | |
f56a4450 KH |
783 | } while (0) |
784 | ||
aa72b389 | 785 | |
065e3595 KH |
786 | #define ONE_MORE_BYTE_NO_CHECK(c) \ |
787 | do { \ | |
788 | c = *src++; \ | |
789 | if (multibytep && (c & 0x80)) \ | |
790 | { \ | |
791 | if ((c & 0xFE) == 0xC0) \ | |
792 | c = ((c & 1) << 6) | *src++; \ | |
793 | else \ | |
794 | { \ | |
35befdaa KH |
795 | src--; \ |
796 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
797 | record_conversion_result \ |
798 | (coding, CODING_RESULT_INVALID_SRC); \ | |
799 | } \ | |
800 | } \ | |
801 | consumed_chars++; \ | |
aa72b389 KH |
802 | } while (0) |
803 | ||
aa72b389 | 804 | |
df7492f9 KH |
805 | /* Store a byte C in the place pointed by DST and increment DST to the |
806 | next free point, and increment PRODUCED_CHARS. The caller should | |
807 | assure that C is 0..127, and declare and set the variable `dst' | |
808 | appropriately in advance. | |
809 | */ | |
aa72b389 KH |
810 | |
811 | ||
df7492f9 KH |
812 | #define EMIT_ONE_ASCII_BYTE(c) \ |
813 | do { \ | |
814 | produced_chars++; \ | |
815 | *dst++ = (c); \ | |
b6871cc7 | 816 | } while (0) |
aa72b389 KH |
817 | |
818 | ||
df7492f9 | 819 | /* Like EMIT_ONE_ASCII_BYTE byt store two bytes; C1 and C2. */ |
aa72b389 | 820 | |
df7492f9 KH |
821 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
822 | do { \ | |
823 | produced_chars += 2; \ | |
824 | *dst++ = (c1), *dst++ = (c2); \ | |
825 | } while (0) | |
aa72b389 KH |
826 | |
827 | ||
df7492f9 KH |
828 | /* Store a byte C in the place pointed by DST and increment DST to the |
829 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is | |
830 | nonzero, store in an appropriate multibyte from. The caller should | |
831 | declare and set the variables `dst' and `multibytep' appropriately | |
832 | in advance. */ | |
833 | ||
834 | #define EMIT_ONE_BYTE(c) \ | |
835 | do { \ | |
836 | produced_chars++; \ | |
837 | if (multibytep) \ | |
838 | { \ | |
839 | int ch = (c); \ | |
840 | if (ch >= 0x80) \ | |
841 | ch = BYTE8_TO_CHAR (ch); \ | |
842 | CHAR_STRING_ADVANCE (ch, dst); \ | |
843 | } \ | |
844 | else \ | |
845 | *dst++ = (c); \ | |
aa72b389 | 846 | } while (0) |
aa72b389 | 847 | |
aa72b389 | 848 | |
df7492f9 | 849 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 850 | |
e19c3639 KH |
851 | #define EMIT_TWO_BYTES(c1, c2) \ |
852 | do { \ | |
853 | produced_chars += 2; \ | |
854 | if (multibytep) \ | |
855 | { \ | |
856 | int ch; \ | |
857 | \ | |
858 | ch = (c1); \ | |
859 | if (ch >= 0x80) \ | |
860 | ch = BYTE8_TO_CHAR (ch); \ | |
861 | CHAR_STRING_ADVANCE (ch, dst); \ | |
862 | ch = (c2); \ | |
863 | if (ch >= 0x80) \ | |
864 | ch = BYTE8_TO_CHAR (ch); \ | |
865 | CHAR_STRING_ADVANCE (ch, dst); \ | |
866 | } \ | |
867 | else \ | |
868 | { \ | |
869 | *dst++ = (c1); \ | |
870 | *dst++ = (c2); \ | |
871 | } \ | |
aa72b389 KH |
872 | } while (0) |
873 | ||
874 | ||
df7492f9 KH |
875 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
876 | do { \ | |
877 | EMIT_ONE_BYTE (c1); \ | |
878 | EMIT_TWO_BYTES (c2, c3); \ | |
879 | } while (0) | |
aa72b389 | 880 | |
aa72b389 | 881 | |
df7492f9 KH |
882 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
883 | do { \ | |
884 | EMIT_TWO_BYTES (c1, c2); \ | |
885 | EMIT_TWO_BYTES (c3, c4); \ | |
886 | } while (0) | |
aa72b389 | 887 | |
aa72b389 | 888 | |
f6cbaf43 KH |
889 | /* Prototypes for static functions. */ |
890 | static void record_conversion_result P_ ((struct coding_system *coding, | |
891 | enum coding_result_code result)); | |
892 | static int detect_coding_utf_8 P_ ((struct coding_system *, | |
893 | struct coding_detection_info *info)); | |
894 | static void decode_coding_utf_8 P_ ((struct coding_system *)); | |
895 | static int encode_coding_utf_8 P_ ((struct coding_system *)); | |
896 | ||
897 | static int detect_coding_utf_16 P_ ((struct coding_system *, | |
898 | struct coding_detection_info *info)); | |
899 | static void decode_coding_utf_16 P_ ((struct coding_system *)); | |
900 | static int encode_coding_utf_16 P_ ((struct coding_system *)); | |
901 | ||
902 | static int detect_coding_iso_2022 P_ ((struct coding_system *, | |
903 | struct coding_detection_info *info)); | |
904 | static void decode_coding_iso_2022 P_ ((struct coding_system *)); | |
905 | static int encode_coding_iso_2022 P_ ((struct coding_system *)); | |
906 | ||
907 | static int detect_coding_emacs_mule P_ ((struct coding_system *, | |
908 | struct coding_detection_info *info)); | |
909 | static void decode_coding_emacs_mule P_ ((struct coding_system *)); | |
910 | static int encode_coding_emacs_mule P_ ((struct coding_system *)); | |
911 | ||
912 | static int detect_coding_sjis P_ ((struct coding_system *, | |
913 | struct coding_detection_info *info)); | |
914 | static void decode_coding_sjis P_ ((struct coding_system *)); | |
915 | static int encode_coding_sjis P_ ((struct coding_system *)); | |
916 | ||
917 | static int detect_coding_big5 P_ ((struct coding_system *, | |
918 | struct coding_detection_info *info)); | |
919 | static void decode_coding_big5 P_ ((struct coding_system *)); | |
920 | static int encode_coding_big5 P_ ((struct coding_system *)); | |
921 | ||
922 | static int detect_coding_ccl P_ ((struct coding_system *, | |
923 | struct coding_detection_info *info)); | |
924 | static void decode_coding_ccl P_ ((struct coding_system *)); | |
925 | static int encode_coding_ccl P_ ((struct coding_system *)); | |
926 | ||
927 | static void decode_coding_raw_text P_ ((struct coding_system *)); | |
928 | static int encode_coding_raw_text P_ ((struct coding_system *)); | |
929 | ||
930 | static void coding_set_source P_ ((struct coding_system *)); | |
931 | static void coding_set_destination P_ ((struct coding_system *)); | |
932 | static void coding_alloc_by_realloc P_ ((struct coding_system *, EMACS_INT)); | |
933 | static void coding_alloc_by_making_gap P_ ((struct coding_system *, | |
287c57d7 | 934 | EMACS_INT, EMACS_INT)); |
f6cbaf43 KH |
935 | static unsigned char *alloc_destination P_ ((struct coding_system *, |
936 | EMACS_INT, unsigned char *)); | |
937 | static void setup_iso_safe_charsets P_ ((Lisp_Object)); | |
938 | static unsigned char *encode_designation_at_bol P_ ((struct coding_system *, | |
939 | int *, int *, | |
940 | unsigned char *)); | |
941 | static int detect_eol P_ ((const unsigned char *, | |
942 | EMACS_INT, enum coding_category)); | |
943 | static Lisp_Object adjust_coding_eol_type P_ ((struct coding_system *, int)); | |
944 | static void decode_eol P_ ((struct coding_system *)); | |
945 | static Lisp_Object get_translation_table P_ ((Lisp_Object, int, int *)); | |
946 | static Lisp_Object get_translation P_ ((Lisp_Object, int *, int *, | |
947 | int, int *, int *)); | |
948 | static int produce_chars P_ ((struct coding_system *, Lisp_Object, int)); | |
949 | static INLINE void produce_composition P_ ((struct coding_system *, int *, | |
950 | EMACS_INT)); | |
951 | static INLINE void produce_charset P_ ((struct coding_system *, int *, | |
952 | EMACS_INT)); | |
953 | static void produce_annotation P_ ((struct coding_system *, EMACS_INT)); | |
954 | static int decode_coding P_ ((struct coding_system *)); | |
955 | static INLINE int *handle_composition_annotation P_ ((EMACS_INT, EMACS_INT, | |
3ed051d4 | 956 | struct coding_system *, |
f6cbaf43 KH |
957 | int *, EMACS_INT *)); |
958 | static INLINE int *handle_charset_annotation P_ ((EMACS_INT, EMACS_INT, | |
959 | struct coding_system *, | |
960 | int *, EMACS_INT *)); | |
961 | static void consume_chars P_ ((struct coding_system *, Lisp_Object, int)); | |
962 | static int encode_coding P_ ((struct coding_system *)); | |
963 | static Lisp_Object make_conversion_work_buffer P_ ((int)); | |
964 | static Lisp_Object code_conversion_restore P_ ((Lisp_Object)); | |
965 | static INLINE int char_encodable_p P_ ((int, Lisp_Object)); | |
966 | static Lisp_Object make_subsidiaries P_ ((Lisp_Object)); | |
967 | ||
065e3595 KH |
968 | static void |
969 | record_conversion_result (struct coding_system *coding, | |
970 | enum coding_result_code result) | |
971 | { | |
972 | coding->result = result; | |
973 | switch (result) | |
974 | { | |
975 | case CODING_RESULT_INSUFFICIENT_SRC: | |
976 | Vlast_code_conversion_error = Qinsufficient_source; | |
977 | break; | |
978 | case CODING_RESULT_INCONSISTENT_EOL: | |
979 | Vlast_code_conversion_error = Qinconsistent_eol; | |
980 | break; | |
981 | case CODING_RESULT_INVALID_SRC: | |
982 | Vlast_code_conversion_error = Qinvalid_source; | |
983 | break; | |
984 | case CODING_RESULT_INTERRUPT: | |
985 | Vlast_code_conversion_error = Qinterrupted; | |
986 | break; | |
987 | case CODING_RESULT_INSUFFICIENT_MEM: | |
988 | Vlast_code_conversion_error = Qinsufficient_memory; | |
989 | break; | |
35befdaa KH |
990 | default: |
991 | Vlast_code_conversion_error = intern ("Unknown error"); | |
065e3595 KH |
992 | } |
993 | } | |
994 | ||
df7492f9 KH |
995 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
996 | do { \ | |
997 | charset_map_loaded = 0; \ | |
998 | c = DECODE_CHAR (charset, code); \ | |
999 | if (charset_map_loaded) \ | |
1000 | { \ | |
8f924df7 | 1001 | const unsigned char *orig = coding->source; \ |
df7492f9 KH |
1002 | EMACS_INT offset; \ |
1003 | \ | |
1004 | coding_set_source (coding); \ | |
1005 | offset = coding->source - orig; \ | |
1006 | src += offset; \ | |
1007 | src_base += offset; \ | |
1008 | src_end += offset; \ | |
1009 | } \ | |
aa72b389 KH |
1010 | } while (0) |
1011 | ||
1012 | ||
119852e7 KH |
1013 | /* If there are at least BYTES length of room at dst, allocate memory |
1014 | for coding->destination and update dst and dst_end. We don't have | |
1015 | to take care of coding->source which will be relocated. It is | |
1016 | handled by calling coding_set_source in encode_coding. */ | |
1017 | ||
df7492f9 KH |
1018 | #define ASSURE_DESTINATION(bytes) \ |
1019 | do { \ | |
1020 | if (dst + (bytes) >= dst_end) \ | |
1021 | { \ | |
1022 | int more_bytes = charbuf_end - charbuf + (bytes); \ | |
1023 | \ | |
1024 | dst = alloc_destination (coding, more_bytes, dst); \ | |
1025 | dst_end = coding->destination + coding->dst_bytes; \ | |
1026 | } \ | |
1027 | } while (0) | |
aa72b389 | 1028 | |
aa72b389 | 1029 | |
db274c7a KH |
1030 | /* Store multibyte form of the character C in P, and advance P to the |
1031 | end of the multibyte form. This is like CHAR_STRING_ADVANCE but it | |
1032 | never calls MAYBE_UNIFY_CHAR. */ | |
1033 | ||
1034 | #define CHAR_STRING_ADVANCE_NO_UNIFY(c, p) \ | |
1035 | do { \ | |
1036 | if ((c) <= MAX_1_BYTE_CHAR) \ | |
1037 | *(p)++ = (c); \ | |
1038 | else if ((c) <= MAX_2_BYTE_CHAR) \ | |
1039 | *(p)++ = (0xC0 | ((c) >> 6)), \ | |
1040 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
1041 | else if ((c) <= MAX_3_BYTE_CHAR) \ | |
1042 | *(p)++ = (0xE0 | ((c) >> 12)), \ | |
1043 | *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \ | |
1044 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
1045 | else if ((c) <= MAX_4_BYTE_CHAR) \ | |
1046 | *(p)++ = (0xF0 | (c >> 18)), \ | |
1047 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
1048 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
1049 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
1050 | else if ((c) <= MAX_5_BYTE_CHAR) \ | |
1051 | *(p)++ = 0xF8, \ | |
1052 | *(p)++ = (0x80 | ((c >> 18) & 0x0F)), \ | |
1053 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
1054 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
1055 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
1056 | else \ | |
1057 | (p) += BYTE8_STRING ((c) - 0x3FFF80, p); \ | |
1058 | } while (0) | |
1059 | ||
1060 | ||
1061 | /* Return the character code of character whose multibyte form is at | |
1062 | P, and advance P to the end of the multibyte form. This is like | |
1063 | STRING_CHAR_ADVANCE, but it never calls MAYBE_UNIFY_CHAR. */ | |
1064 | ||
1065 | #define STRING_CHAR_ADVANCE_NO_UNIFY(p) \ | |
1066 | (!((p)[0] & 0x80) \ | |
1067 | ? *(p)++ \ | |
1068 | : ! ((p)[0] & 0x20) \ | |
1069 | ? ((p) += 2, \ | |
1070 | ((((p)[-2] & 0x1F) << 6) \ | |
1071 | | ((p)[-1] & 0x3F) \ | |
1072 | | ((unsigned char) ((p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \ | |
1073 | : ! ((p)[0] & 0x10) \ | |
1074 | ? ((p) += 3, \ | |
1075 | ((((p)[-3] & 0x0F) << 12) \ | |
1076 | | (((p)[-2] & 0x3F) << 6) \ | |
1077 | | ((p)[-1] & 0x3F))) \ | |
1078 | : ! ((p)[0] & 0x08) \ | |
1079 | ? ((p) += 4, \ | |
1080 | ((((p)[-4] & 0xF) << 18) \ | |
1081 | | (((p)[-3] & 0x3F) << 12) \ | |
1082 | | (((p)[-2] & 0x3F) << 6) \ | |
1083 | | ((p)[-1] & 0x3F))) \ | |
1084 | : ((p) += 5, \ | |
1085 | ((((p)[-4] & 0x3F) << 18) \ | |
1086 | | (((p)[-3] & 0x3F) << 12) \ | |
1087 | | (((p)[-2] & 0x3F) << 6) \ | |
1088 | | ((p)[-1] & 0x3F)))) | |
1089 | ||
aa72b389 | 1090 | |
df7492f9 KH |
1091 | static void |
1092 | coding_set_source (coding) | |
aa72b389 | 1093 | struct coding_system *coding; |
aa72b389 | 1094 | { |
df7492f9 KH |
1095 | if (BUFFERP (coding->src_object)) |
1096 | { | |
2cb26057 | 1097 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 1098 | |
df7492f9 | 1099 | if (coding->src_pos < 0) |
2cb26057 | 1100 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 1101 | else |
2cb26057 | 1102 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 1103 | } |
df7492f9 | 1104 | else if (STRINGP (coding->src_object)) |
aa72b389 | 1105 | { |
8f924df7 | 1106 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 1107 | } |
df7492f9 KH |
1108 | else |
1109 | /* Otherwise, the source is C string and is never relocated | |
1110 | automatically. Thus we don't have to update anything. */ | |
1111 | ; | |
1112 | } | |
aa72b389 | 1113 | |
df7492f9 KH |
1114 | static void |
1115 | coding_set_destination (coding) | |
1116 | struct coding_system *coding; | |
1117 | { | |
1118 | if (BUFFERP (coding->dst_object)) | |
aa72b389 | 1119 | { |
df7492f9 | 1120 | if (coding->src_pos < 0) |
aa72b389 | 1121 | { |
13818c30 | 1122 | coding->destination = BEG_ADDR + coding->dst_pos_byte - BEG_BYTE; |
28f67a95 KH |
1123 | coding->dst_bytes = (GAP_END_ADDR |
1124 | - (coding->src_bytes - coding->consumed) | |
1125 | - coding->destination); | |
aa72b389 | 1126 | } |
df7492f9 | 1127 | else |
28f67a95 KH |
1128 | { |
1129 | /* We are sure that coding->dst_pos_byte is before the gap | |
1130 | of the buffer. */ | |
1131 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
13818c30 | 1132 | + coding->dst_pos_byte - BEG_BYTE); |
28f67a95 KH |
1133 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) |
1134 | - coding->destination); | |
1135 | } | |
df7492f9 KH |
1136 | } |
1137 | else | |
1138 | /* Otherwise, the destination is C string and is never relocated | |
1139 | automatically. Thus we don't have to update anything. */ | |
1140 | ; | |
1141 | } | |
1142 | ||
1143 | ||
1144 | static void | |
1145 | coding_alloc_by_realloc (coding, bytes) | |
1146 | struct coding_system *coding; | |
1147 | EMACS_INT bytes; | |
1148 | { | |
1149 | coding->destination = (unsigned char *) xrealloc (coding->destination, | |
1150 | coding->dst_bytes + bytes); | |
1151 | coding->dst_bytes += bytes; | |
1152 | } | |
1153 | ||
1154 | static void | |
db274c7a | 1155 | coding_alloc_by_making_gap (coding, gap_head_used, bytes) |
df7492f9 | 1156 | struct coding_system *coding; |
db274c7a | 1157 | EMACS_INT gap_head_used, bytes; |
df7492f9 | 1158 | { |
db274c7a | 1159 | if (EQ (coding->src_object, coding->dst_object)) |
df7492f9 | 1160 | { |
db274c7a KH |
1161 | /* The gap may contain the produced data at the head and not-yet |
1162 | consumed data at the tail. To preserve those data, we at | |
1163 | first make the gap size to zero, then increase the gap | |
1164 | size. */ | |
1165 | EMACS_INT add = GAP_SIZE; | |
1166 | ||
1167 | GPT += gap_head_used, GPT_BYTE += gap_head_used; | |
1168 | GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
df7492f9 KH |
1169 | make_gap (bytes); |
1170 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
db274c7a | 1171 | GPT -= gap_head_used, GPT_BYTE -= gap_head_used; |
df7492f9 | 1172 | } |
730fff51 | 1173 | else |
df7492f9 | 1174 | { |
2c78b7e1 KH |
1175 | Lisp_Object this_buffer; |
1176 | ||
1177 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
1178 | set_buffer_internal (XBUFFER (coding->dst_object)); |
1179 | make_gap (bytes); | |
1180 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 1181 | } |
df7492f9 | 1182 | } |
8f924df7 | 1183 | |
df7492f9 KH |
1184 | |
1185 | static unsigned char * | |
1186 | alloc_destination (coding, nbytes, dst) | |
1187 | struct coding_system *coding; | |
3e139625 | 1188 | EMACS_INT nbytes; |
df7492f9 KH |
1189 | unsigned char *dst; |
1190 | { | |
1191 | EMACS_INT offset = dst - coding->destination; | |
1192 | ||
1193 | if (BUFFERP (coding->dst_object)) | |
db274c7a KH |
1194 | { |
1195 | struct buffer *buf = XBUFFER (coding->dst_object); | |
1196 | ||
1197 | coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes); | |
1198 | } | |
aa72b389 | 1199 | else |
df7492f9 | 1200 | coding_alloc_by_realloc (coding, nbytes); |
065e3595 | 1201 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1202 | coding_set_destination (coding); |
1203 | dst = coding->destination + offset; | |
1204 | return dst; | |
1205 | } | |
aa72b389 | 1206 | |
ff0dacd7 KH |
1207 | /** Macros for annotations. */ |
1208 | ||
1209 | /* Maximum length of annotation data (sum of annotations for | |
1210 | composition and charset). */ | |
69a80ea3 | 1211 | #define MAX_ANNOTATION_LENGTH (4 + (MAX_COMPOSITION_COMPONENTS * 2) - 1 + 4) |
ff0dacd7 KH |
1212 | |
1213 | /* An annotation data is stored in the array coding->charbuf in this | |
1214 | format: | |
69a80ea3 | 1215 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1216 | LENGTH is the number of elements in the annotation. |
1217 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1218 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1219 | |
1220 | The format of the following elements depend on ANNOTATION_MASK. | |
1221 | ||
1222 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1223 | follows: | |
1224 | ... METHOD [ COMPOSITION-COMPONENTS ... ] | |
1225 | METHOD is one of enum composition_method. | |
1226 | Optionnal COMPOSITION-COMPONENTS are characters and composition | |
1227 | rules. | |
1228 | ||
1229 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
1230 | follows. */ | |
1231 | ||
69a80ea3 | 1232 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1233 | do { \ |
1234 | *(buf)++ = -(len); \ | |
1235 | *(buf)++ = (mask); \ | |
69a80ea3 | 1236 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1237 | coding->annotated = 1; \ |
1238 | } while (0); | |
1239 | ||
69a80ea3 KH |
1240 | #define ADD_COMPOSITION_DATA(buf, nchars, method) \ |
1241 | do { \ | |
1242 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ | |
1243 | *buf++ = method; \ | |
ff0dacd7 KH |
1244 | } while (0) |
1245 | ||
1246 | ||
69a80ea3 KH |
1247 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1248 | do { \ | |
1249 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1250 | *buf++ = id; \ | |
ff0dacd7 KH |
1251 | } while (0) |
1252 | ||
df7492f9 KH |
1253 | \f |
1254 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1255 | ||
1256 | ||
1257 | ||
1258 | \f | |
1259 | /*** 3. UTF-8 ***/ | |
1260 | ||
1261 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1262 | Check if a text is encoded in UTF-8. If it is, return 1, else |
1263 | return 0. */ | |
df7492f9 KH |
1264 | |
1265 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1266 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1267 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1268 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1269 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1270 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1271 | ||
a470d443 KH |
1272 | #define UTF_BOM 0xFEFF |
1273 | #define UTF_8_BOM_1 0xEF | |
1274 | #define UTF_8_BOM_2 0xBB | |
1275 | #define UTF_8_BOM_3 0xBF | |
1276 | ||
df7492f9 | 1277 | static int |
ff0dacd7 | 1278 | detect_coding_utf_8 (coding, detect_info) |
df7492f9 | 1279 | struct coding_system *coding; |
ff0dacd7 | 1280 | struct coding_detection_info *detect_info; |
df7492f9 | 1281 | { |
065e3595 | 1282 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1283 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1284 | int multibytep = coding->src_multibyte; |
1285 | int consumed_chars = 0; | |
a470d443 | 1286 | int bom_found = 0; |
df7492f9 KH |
1287 | int found = 0; |
1288 | ||
ff0dacd7 | 1289 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1290 | /* A coding system of this category is always ASCII compatible. */ |
1291 | src += coding->head_ascii; | |
1292 | ||
1293 | while (1) | |
aa72b389 | 1294 | { |
df7492f9 | 1295 | int c, c1, c2, c3, c4; |
aa72b389 | 1296 | |
065e3595 | 1297 | src_base = src; |
df7492f9 | 1298 | ONE_MORE_BYTE (c); |
065e3595 | 1299 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1300 | continue; |
1301 | ONE_MORE_BYTE (c1); | |
065e3595 | 1302 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1303 | break; |
1304 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1305 | { |
a470d443 | 1306 | found = 1; |
df7492f9 | 1307 | continue; |
aa72b389 | 1308 | } |
df7492f9 | 1309 | ONE_MORE_BYTE (c2); |
065e3595 | 1310 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1311 | break; |
1312 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1313 | { |
a470d443 KH |
1314 | found = 1; |
1315 | if (src_base == coding->source | |
1316 | && c == UTF_8_BOM_1 && c1 == UTF_8_BOM_2 && c2 == UTF_8_BOM_3) | |
1317 | bom_found = 1; | |
df7492f9 | 1318 | continue; |
aa72b389 | 1319 | } |
df7492f9 | 1320 | ONE_MORE_BYTE (c3); |
065e3595 | 1321 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1322 | break; |
1323 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1324 | { |
a470d443 | 1325 | found = 1; |
df7492f9 KH |
1326 | continue; |
1327 | } | |
1328 | ONE_MORE_BYTE (c4); | |
065e3595 | 1329 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1330 | break; |
1331 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1332 | { | |
a470d443 | 1333 | found = 1; |
df7492f9 KH |
1334 | continue; |
1335 | } | |
1336 | break; | |
aa72b389 | 1337 | } |
ff0dacd7 | 1338 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1339 | return 0; |
aa72b389 | 1340 | |
df7492f9 | 1341 | no_more_source: |
065e3595 | 1342 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1343 | { |
ff0dacd7 | 1344 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1345 | return 0; |
aa72b389 | 1346 | } |
a470d443 KH |
1347 | if (bom_found) |
1348 | { | |
1349 | /* The first character 0xFFFE doesn't necessarily mean a BOM. */ | |
1350 | detect_info->found |= CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG; | |
1351 | } | |
1352 | else | |
1353 | { | |
1354 | detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG; | |
0e17387a KH |
1355 | if (found) |
1356 | detect_info->found |= CATEGORY_MASK_UTF_8_NOSIG; | |
a470d443 | 1357 | } |
ff0dacd7 | 1358 | return 1; |
aa72b389 KH |
1359 | } |
1360 | ||
4ed46869 | 1361 | |
b73bfc1c | 1362 | static void |
df7492f9 | 1363 | decode_coding_utf_8 (coding) |
b73bfc1c | 1364 | struct coding_system *coding; |
b73bfc1c | 1365 | { |
8f924df7 KH |
1366 | const unsigned char *src = coding->source + coding->consumed; |
1367 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1368 | const unsigned char *src_base; | |
69a80ea3 KH |
1369 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1370 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
453b38f0 | 1371 | int consumed_chars = 0, consumed_chars_base = 0; |
df7492f9 | 1372 | int multibytep = coding->src_multibyte; |
a470d443 | 1373 | enum utf_bom_type bom = CODING_UTF_8_BOM (coding); |
24a73b0a | 1374 | Lisp_Object attr, charset_list; |
119852e7 KH |
1375 | int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); |
1376 | int byte_after_cr = -1; | |
4ed46869 | 1377 | |
24a73b0a | 1378 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1379 | |
a470d443 KH |
1380 | if (bom != utf_without_bom) |
1381 | { | |
1382 | int c1, c2, c3; | |
1383 | ||
1384 | src_base = src; | |
1385 | ONE_MORE_BYTE (c1); | |
1386 | if (! UTF_8_3_OCTET_LEADING_P (c1)) | |
1387 | src = src_base; | |
1388 | else | |
1389 | { | |
159bd5a2 | 1390 | ONE_MORE_BYTE (c2); |
a470d443 KH |
1391 | if (! UTF_8_EXTRA_OCTET_P (c2)) |
1392 | src = src_base; | |
1393 | else | |
1394 | { | |
159bd5a2 | 1395 | ONE_MORE_BYTE (c3); |
a470d443 KH |
1396 | if (! UTF_8_EXTRA_OCTET_P (c3)) |
1397 | src = src_base; | |
1398 | else | |
1399 | { | |
1400 | if ((c1 != UTF_8_BOM_1) | |
1401 | || (c2 != UTF_8_BOM_2) || (c3 != UTF_8_BOM_3)) | |
1402 | src = src_base; | |
1403 | else | |
1404 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1405 | } | |
1406 | } | |
1407 | } | |
1408 | } | |
1409 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1410 | ||
1411 | ||
1412 | ||
df7492f9 | 1413 | while (1) |
b73bfc1c | 1414 | { |
df7492f9 | 1415 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1416 | |
df7492f9 KH |
1417 | src_base = src; |
1418 | consumed_chars_base = consumed_chars; | |
4af310db | 1419 | |
df7492f9 | 1420 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1421 | { |
1422 | if (byte_after_cr >= 0) | |
1423 | src_base--; | |
1424 | break; | |
1425 | } | |
df7492f9 | 1426 | |
119852e7 KH |
1427 | if (byte_after_cr >= 0) |
1428 | c1 = byte_after_cr, byte_after_cr = -1; | |
1429 | else | |
1430 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1431 | if (c1 < 0) |
1432 | { | |
1433 | c = - c1; | |
1434 | } | |
1435 | else if (UTF_8_1_OCTET_P(c1)) | |
df7492f9 | 1436 | { |
119852e7 KH |
1437 | if (eol_crlf && c1 == '\r') |
1438 | ONE_MORE_BYTE (byte_after_cr); | |
df7492f9 | 1439 | c = c1; |
4af310db | 1440 | } |
df7492f9 | 1441 | else |
4af310db | 1442 | { |
df7492f9 | 1443 | ONE_MORE_BYTE (c2); |
065e3595 | 1444 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1445 | goto invalid_code; |
1446 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1447 | { |
b0edb2c5 DL |
1448 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1449 | /* Reject overlong sequences here and below. Encoders | |
1450 | producing them are incorrect, they can be misleading, | |
1451 | and they mess up read/write invariance. */ | |
1452 | if (c < 128) | |
1453 | goto invalid_code; | |
4af310db | 1454 | } |
df7492f9 | 1455 | else |
aa72b389 | 1456 | { |
df7492f9 | 1457 | ONE_MORE_BYTE (c3); |
065e3595 | 1458 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1459 | goto invalid_code; |
1460 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1461 | { |
1462 | c = (((c1 & 0xF) << 12) | |
1463 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1464 | if (c < 0x800 |
1465 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1466 | goto invalid_code; |
1467 | } | |
df7492f9 KH |
1468 | else |
1469 | { | |
1470 | ONE_MORE_BYTE (c4); | |
065e3595 | 1471 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1472 | goto invalid_code; |
1473 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1474 | { |
df7492f9 KH |
1475 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1476 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1477 | if (c < 0x10000) |
1478 | goto invalid_code; | |
1479 | } | |
df7492f9 KH |
1480 | else |
1481 | { | |
1482 | ONE_MORE_BYTE (c5); | |
065e3595 | 1483 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1484 | goto invalid_code; |
1485 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1486 | { | |
1487 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1488 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1489 | | (c5 & 0x3F)); | |
b0edb2c5 | 1490 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1491 | goto invalid_code; |
1492 | } | |
1493 | else | |
1494 | goto invalid_code; | |
1495 | } | |
1496 | } | |
aa72b389 | 1497 | } |
b73bfc1c | 1498 | } |
df7492f9 KH |
1499 | |
1500 | *charbuf++ = c; | |
1501 | continue; | |
1502 | ||
1503 | invalid_code: | |
1504 | src = src_base; | |
1505 | consumed_chars = consumed_chars_base; | |
1506 | ONE_MORE_BYTE (c); | |
1507 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1508 | coding->errors++; | |
aa72b389 KH |
1509 | } |
1510 | ||
df7492f9 KH |
1511 | no_more_source: |
1512 | coding->consumed_char += consumed_chars_base; | |
1513 | coding->consumed = src_base - coding->source; | |
1514 | coding->charbuf_used = charbuf - coding->charbuf; | |
1515 | } | |
1516 | ||
1517 | ||
1518 | static int | |
1519 | encode_coding_utf_8 (coding) | |
1520 | struct coding_system *coding; | |
1521 | { | |
1522 | int multibytep = coding->dst_multibyte; | |
1523 | int *charbuf = coding->charbuf; | |
1524 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1525 | unsigned char *dst = coding->destination + coding->produced; | |
1526 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
e19c3639 | 1527 | int produced_chars = 0; |
df7492f9 KH |
1528 | int c; |
1529 | ||
a470d443 KH |
1530 | if (CODING_UTF_8_BOM (coding) == utf_with_bom) |
1531 | { | |
1532 | ASSURE_DESTINATION (3); | |
1533 | EMIT_THREE_BYTES (UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3); | |
1534 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1535 | } | |
1536 | ||
df7492f9 | 1537 | if (multibytep) |
aa72b389 | 1538 | { |
df7492f9 KH |
1539 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1540 | ||
1541 | while (charbuf < charbuf_end) | |
b73bfc1c | 1542 | { |
df7492f9 | 1543 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1544 | |
df7492f9 KH |
1545 | ASSURE_DESTINATION (safe_room); |
1546 | c = *charbuf++; | |
28f67a95 KH |
1547 | if (CHAR_BYTE8_P (c)) |
1548 | { | |
1549 | c = CHAR_TO_BYTE8 (c); | |
1550 | EMIT_ONE_BYTE (c); | |
1551 | } | |
1552 | else | |
1553 | { | |
db274c7a | 1554 | CHAR_STRING_ADVANCE_NO_UNIFY (c, pend); |
28f67a95 KH |
1555 | for (p = str; p < pend; p++) |
1556 | EMIT_ONE_BYTE (*p); | |
1557 | } | |
b73bfc1c | 1558 | } |
aa72b389 | 1559 | } |
df7492f9 KH |
1560 | else |
1561 | { | |
1562 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1563 | ||
1564 | while (charbuf < charbuf_end) | |
b73bfc1c | 1565 | { |
df7492f9 KH |
1566 | ASSURE_DESTINATION (safe_room); |
1567 | c = *charbuf++; | |
f03caae0 KH |
1568 | if (CHAR_BYTE8_P (c)) |
1569 | *dst++ = CHAR_TO_BYTE8 (c); | |
1570 | else | |
db274c7a | 1571 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
df7492f9 | 1572 | produced_chars++; |
4ed46869 KH |
1573 | } |
1574 | } | |
065e3595 | 1575 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1576 | coding->produced_char += produced_chars; |
1577 | coding->produced = dst - coding->destination; | |
1578 | return 0; | |
4ed46869 KH |
1579 | } |
1580 | ||
b73bfc1c | 1581 | |
df7492f9 | 1582 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
1583 | Check if a text is encoded in one of UTF-16 based coding systems. |
1584 | If it is, return 1, else return 0. */ | |
aa72b389 | 1585 | |
df7492f9 KH |
1586 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1587 | (((val) & 0xFC00) == 0xD800) | |
1588 | ||
1589 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1590 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1591 | |
df7492f9 KH |
1592 | #define UTF_16_INVALID_P(val) \ |
1593 | (((val) == 0xFFFE) \ | |
1594 | || ((val) == 0xFFFF) \ | |
1595 | || UTF_16_LOW_SURROGATE_P (val)) | |
aa72b389 | 1596 | |
aa72b389 | 1597 | |
df7492f9 | 1598 | static int |
ff0dacd7 | 1599 | detect_coding_utf_16 (coding, detect_info) |
aa72b389 | 1600 | struct coding_system *coding; |
ff0dacd7 | 1601 | struct coding_detection_info *detect_info; |
aa72b389 | 1602 | { |
8f924df7 KH |
1603 | const unsigned char *src = coding->source, *src_base = src; |
1604 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
1605 | int multibytep = coding->src_multibyte; |
1606 | int consumed_chars = 0; | |
1607 | int c1, c2; | |
aa72b389 | 1608 | |
ff0dacd7 | 1609 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1610 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1611 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1612 | { |
1613 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1614 | return 0; | |
1615 | } | |
24a73b0a | 1616 | |
f56a4450 | 1617 | TWO_MORE_BYTES (c1, c2); |
df7492f9 | 1618 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1619 | { |
b49a1807 KH |
1620 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1621 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1622 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1623 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1624 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1625 | } |
df7492f9 | 1626 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1627 | { |
b49a1807 KH |
1628 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1629 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1630 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1631 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1632 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1633 | } | |
220eeac9 | 1634 | else if (c2 < 0) |
f56a4450 KH |
1635 | { |
1636 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1637 | return 0; | |
1638 | } | |
2f3cbb32 | 1639 | else |
24a73b0a | 1640 | { |
2f3cbb32 KH |
1641 | /* We check the dispersion of Eth and Oth bytes where E is even and |
1642 | O is odd. If both are high, we assume binary data.*/ | |
1643 | unsigned char e[256], o[256]; | |
1644 | unsigned e_num = 1, o_num = 1; | |
1645 | ||
1646 | memset (e, 0, 256); | |
1647 | memset (o, 0, 256); | |
1648 | e[c1] = 1; | |
1649 | o[c2] = 1; | |
1650 | ||
24a73b0a KH |
1651 | detect_info->rejected |
1652 | |= (CATEGORY_MASK_UTF_16_BE | CATEGORY_MASK_UTF_16_LE); | |
2f3cbb32 KH |
1653 | |
1654 | while (1) | |
1655 | { | |
f56a4450 | 1656 | TWO_MORE_BYTES (c1, c2); |
220eeac9 | 1657 | if (c2 < 0) |
f56a4450 | 1658 | break; |
2f3cbb32 KH |
1659 | if (! e[c1]) |
1660 | { | |
1661 | e[c1] = 1; | |
1662 | e_num++; | |
1663 | if (e_num >= 128) | |
1664 | break; | |
1665 | } | |
1666 | if (! o[c2]) | |
1667 | { | |
1668 | o[c1] = 1; | |
1669 | o_num++; | |
1670 | if (o_num >= 128) | |
1671 | break; | |
1672 | } | |
1673 | } | |
1674 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1675 | return 0; | |
ff0dacd7 | 1676 | } |
2f3cbb32 | 1677 | |
df7492f9 | 1678 | no_more_source: |
ff0dacd7 | 1679 | return 1; |
df7492f9 | 1680 | } |
aa72b389 | 1681 | |
df7492f9 KH |
1682 | static void |
1683 | decode_coding_utf_16 (coding) | |
1684 | struct coding_system *coding; | |
1685 | { | |
8f924df7 KH |
1686 | const unsigned char *src = coding->source + coding->consumed; |
1687 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1688 | const unsigned char *src_base; | |
69a80ea3 KH |
1689 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1690 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
3a8406e1 | 1691 | int consumed_chars = 0, consumed_chars_base = 0; |
df7492f9 | 1692 | int multibytep = coding->src_multibyte; |
a470d443 | 1693 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1694 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); |
1695 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
24a73b0a | 1696 | Lisp_Object attr, charset_list; |
119852e7 KH |
1697 | int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); |
1698 | int byte_after_cr1 = -1, byte_after_cr2 = -1; | |
df7492f9 | 1699 | |
24a73b0a | 1700 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1701 | |
a470d443 | 1702 | if (bom == utf_with_bom) |
aa72b389 | 1703 | { |
df7492f9 | 1704 | int c, c1, c2; |
4af310db | 1705 | |
aa72b389 | 1706 | src_base = src; |
df7492f9 KH |
1707 | ONE_MORE_BYTE (c1); |
1708 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1709 | c = (c1 << 8) | c2; |
aa72b389 | 1710 | |
b49a1807 KH |
1711 | if (endian == utf_16_big_endian |
1712 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1713 | { |
b49a1807 KH |
1714 | /* The first two bytes are not BOM. Treat them as bytes |
1715 | for a normal character. */ | |
1716 | src = src_base; | |
1717 | coding->errors++; | |
aa72b389 | 1718 | } |
a470d443 | 1719 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
b49a1807 | 1720 | } |
a470d443 | 1721 | else if (bom == utf_detect_bom) |
b49a1807 KH |
1722 | { |
1723 | /* We have already tried to detect BOM and failed in | |
1724 | detect_coding. */ | |
a470d443 | 1725 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 | 1726 | } |
aa72b389 | 1727 | |
df7492f9 KH |
1728 | while (1) |
1729 | { | |
1730 | int c, c1, c2; | |
1731 | ||
1732 | src_base = src; | |
1733 | consumed_chars_base = consumed_chars; | |
1734 | ||
1735 | if (charbuf + 2 >= charbuf_end) | |
b71f6f73 KH |
1736 | { |
1737 | if (byte_after_cr1 >= 0) | |
1738 | src_base -= 2; | |
1739 | break; | |
1740 | } | |
df7492f9 | 1741 | |
119852e7 KH |
1742 | if (byte_after_cr1 >= 0) |
1743 | c1 = byte_after_cr1, byte_after_cr1 = -1; | |
1744 | else | |
1745 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1746 | if (c1 < 0) |
1747 | { | |
1748 | *charbuf++ = -c1; | |
1749 | continue; | |
1750 | } | |
119852e7 KH |
1751 | if (byte_after_cr2 >= 0) |
1752 | c2 = byte_after_cr2, byte_after_cr2 = -1; | |
1753 | else | |
1754 | ONE_MORE_BYTE (c2); | |
065e3595 KH |
1755 | if (c2 < 0) |
1756 | { | |
1757 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1758 | *charbuf++ = -c2; | |
1759 | continue; | |
1760 | } | |
df7492f9 | 1761 | c = (endian == utf_16_big_endian |
e19c3639 | 1762 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
119852e7 | 1763 | |
df7492f9 | 1764 | if (surrogate) |
fd3ae0b9 | 1765 | { |
df7492f9 | 1766 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1767 | { |
df7492f9 KH |
1768 | if (endian == utf_16_big_endian) |
1769 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1770 | else | |
1771 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1772 | *charbuf++ = c1; | |
1773 | *charbuf++ = c2; | |
1774 | coding->errors++; | |
1775 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1776 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1777 | else |
df7492f9 | 1778 | *charbuf++ = c; |
fd3ae0b9 KH |
1779 | } |
1780 | else | |
df7492f9 KH |
1781 | { |
1782 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1783 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1784 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1785 | } |
fd3ae0b9 | 1786 | } |
aa72b389 | 1787 | else |
df7492f9 KH |
1788 | { |
1789 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1790 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1791 | else | |
119852e7 KH |
1792 | { |
1793 | if (eol_crlf && c == '\r') | |
1794 | { | |
1795 | ONE_MORE_BYTE (byte_after_cr1); | |
1796 | ONE_MORE_BYTE (byte_after_cr2); | |
1797 | } | |
1798 | *charbuf++ = c; | |
1799 | } | |
8f924df7 | 1800 | } |
aa72b389 | 1801 | } |
df7492f9 KH |
1802 | |
1803 | no_more_source: | |
1804 | coding->consumed_char += consumed_chars_base; | |
1805 | coding->consumed = src_base - coding->source; | |
1806 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1807 | } |
b73bfc1c | 1808 | |
df7492f9 KH |
1809 | static int |
1810 | encode_coding_utf_16 (coding) | |
1811 | struct coding_system *coding; | |
1812 | { | |
1813 | int multibytep = coding->dst_multibyte; | |
1814 | int *charbuf = coding->charbuf; | |
1815 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1816 | unsigned char *dst = coding->destination + coding->produced; | |
1817 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1818 | int safe_room = 8; | |
a470d443 | 1819 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1820 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; |
1821 | int produced_chars = 0; | |
24a73b0a | 1822 | Lisp_Object attrs, charset_list; |
df7492f9 | 1823 | int c; |
4ed46869 | 1824 | |
24a73b0a | 1825 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 1826 | |
a470d443 | 1827 | if (bom != utf_without_bom) |
df7492f9 KH |
1828 | { |
1829 | ASSURE_DESTINATION (safe_room); | |
1830 | if (big_endian) | |
df7492f9 | 1831 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1832 | else |
1833 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
a470d443 | 1834 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 KH |
1835 | } |
1836 | ||
1837 | while (charbuf < charbuf_end) | |
1838 | { | |
1839 | ASSURE_DESTINATION (safe_room); | |
1840 | c = *charbuf++; | |
e19c3639 KH |
1841 | if (c >= MAX_UNICODE_CHAR) |
1842 | c = coding->default_char; | |
df7492f9 KH |
1843 | |
1844 | if (c < 0x10000) | |
1845 | { | |
1846 | if (big_endian) | |
1847 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1848 | else | |
1849 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1850 | } | |
1851 | else | |
1852 | { | |
1853 | int c1, c2; | |
1854 | ||
1855 | c -= 0x10000; | |
1856 | c1 = (c >> 10) + 0xD800; | |
1857 | c2 = (c & 0x3FF) + 0xDC00; | |
1858 | if (big_endian) | |
1859 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1860 | else | |
1861 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1862 | } | |
1863 | } | |
065e3595 | 1864 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1865 | coding->produced = dst - coding->destination; |
1866 | coding->produced_char += produced_chars; | |
1867 | return 0; | |
1868 | } | |
1869 | ||
1870 | \f | |
1871 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1872 | ||
1873 | /* Emacs' internal format for representation of multiple character | |
1874 | sets is a kind of multi-byte encoding, i.e. characters are | |
1875 | represented by variable-length sequences of one-byte codes. | |
1876 | ||
1877 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1878 | represented by one-byte sequences which are their ASCII codes, in | |
1879 | the range 0x00 through 0x7F. | |
1880 | ||
1881 | 8-bit characters of the range 0x80..0x9F are represented by | |
1882 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1883 | code + 0x20). | |
1884 | ||
1885 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1886 | one-byte sequences which are their 8-bit code. | |
1887 | ||
1888 | The other characters are represented by a sequence of `base | |
1889 | leading-code', optional `extended leading-code', and one or two | |
1890 | `position-code's. The length of the sequence is determined by the | |
1891 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1892 | whereas extended leading-code and position-code take the range 0xA0 | |
1893 | through 0xFF. See `charset.h' for more details about leading-code | |
1894 | and position-code. | |
1895 | ||
1896 | --- CODE RANGE of Emacs' internal format --- | |
1897 | character set range | |
1898 | ------------- ----- | |
1899 | ascii 0x00..0x7F | |
1900 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1901 | eight-bit-graphic 0xA0..0xBF | |
1902 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1903 | --------------------------------------------- | |
1904 | ||
1905 | As this is the internal character representation, the format is | |
1906 | usually not used externally (i.e. in a file or in a data sent to a | |
1907 | process). But, it is possible to have a text externally in this | |
1908 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1909 | ||
1910 | In that case, a sequence of one-byte codes has a slightly different | |
1911 | form. | |
1912 | ||
1913 | At first, all characters in eight-bit-control are represented by | |
1914 | one-byte sequences which are their 8-bit code. | |
1915 | ||
1916 | Next, character composition data are represented by the byte | |
1917 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1918 | where, | |
1919 | METHOD is 0xF0 plus one of composition method (enum | |
1920 | composition_method), | |
1921 | ||
1922 | BYTES is 0xA0 plus a byte length of this composition data, | |
1923 | ||
1924 | CHARS is 0x20 plus a number of characters composed by this | |
1925 | data, | |
1926 | ||
1927 | COMPONENTs are characters of multibye form or composition | |
1928 | rules encoded by two-byte of ASCII codes. | |
1929 | ||
1930 | In addition, for backward compatibility, the following formats are | |
1931 | also recognized as composition data on decoding. | |
1932 | ||
1933 | 0x80 MSEQ ... | |
1934 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1935 | ||
1936 | Here, | |
1937 | MSEQ is a multibyte form but in these special format: | |
1938 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1939 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1940 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1941 | represents a composition rule. | |
1942 | */ | |
1943 | ||
1944 | char emacs_mule_bytes[256]; | |
1945 | ||
df7492f9 | 1946 | int |
ff0dacd7 | 1947 | emacs_mule_char (coding, src, nbytes, nchars, id) |
df7492f9 | 1948 | struct coding_system *coding; |
065e3595 | 1949 | const unsigned char *src; |
ff0dacd7 | 1950 | int *nbytes, *nchars, *id; |
df7492f9 | 1951 | { |
8f924df7 KH |
1952 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1953 | const unsigned char *src_base = src; | |
df7492f9 | 1954 | int multibytep = coding->src_multibyte; |
df7492f9 KH |
1955 | struct charset *charset; |
1956 | unsigned code; | |
1957 | int c; | |
1958 | int consumed_chars = 0; | |
1959 | ||
1960 | ONE_MORE_BYTE (c); | |
065e3595 | 1961 | if (c < 0) |
df7492f9 | 1962 | { |
065e3595 KH |
1963 | c = -c; |
1964 | charset = emacs_mule_charset[0]; | |
1965 | } | |
1966 | else | |
1967 | { | |
4d41e8b7 KH |
1968 | if (c >= 0xA0) |
1969 | { | |
b3af4b28 | 1970 | /* Old style component character of a composition. */ |
4d41e8b7 KH |
1971 | if (c == 0xA0) |
1972 | { | |
1973 | ONE_MORE_BYTE (c); | |
1974 | c -= 0x80; | |
1975 | } | |
1976 | else | |
1977 | c -= 0x20; | |
1978 | } | |
1979 | ||
065e3595 | 1980 | switch (emacs_mule_bytes[c]) |
b73bfc1c | 1981 | { |
065e3595 | 1982 | case 2: |
df7492f9 KH |
1983 | if (! (charset = emacs_mule_charset[c])) |
1984 | goto invalid_code; | |
1985 | ONE_MORE_BYTE (c); | |
9ffd559c | 1986 | if (c < 0xA0) |
065e3595 | 1987 | goto invalid_code; |
df7492f9 | 1988 | code = c & 0x7F; |
065e3595 KH |
1989 | break; |
1990 | ||
1991 | case 3: | |
1992 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
1993 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
1994 | { | |
1995 | ONE_MORE_BYTE (c); | |
9ffd559c | 1996 | if (c < 0xA0 || ! (charset = emacs_mule_charset[c])) |
065e3595 KH |
1997 | goto invalid_code; |
1998 | ONE_MORE_BYTE (c); | |
9ffd559c | 1999 | if (c < 0xA0) |
065e3595 KH |
2000 | goto invalid_code; |
2001 | code = c & 0x7F; | |
2002 | } | |
2003 | else | |
2004 | { | |
2005 | if (! (charset = emacs_mule_charset[c])) | |
2006 | goto invalid_code; | |
2007 | ONE_MORE_BYTE (c); | |
9ffd559c | 2008 | if (c < 0xA0) |
065e3595 KH |
2009 | goto invalid_code; |
2010 | code = (c & 0x7F) << 8; | |
2011 | ONE_MORE_BYTE (c); | |
9ffd559c | 2012 | if (c < 0xA0) |
065e3595 KH |
2013 | goto invalid_code; |
2014 | code |= c & 0x7F; | |
2015 | } | |
2016 | break; | |
2017 | ||
2018 | case 4: | |
2019 | ONE_MORE_BYTE (c); | |
2020 | if (c < 0 || ! (charset = emacs_mule_charset[c])) | |
df7492f9 KH |
2021 | goto invalid_code; |
2022 | ONE_MORE_BYTE (c); | |
9ffd559c | 2023 | if (c < 0xA0) |
065e3595 | 2024 | goto invalid_code; |
781d7a48 | 2025 | code = (c & 0x7F) << 8; |
df7492f9 | 2026 | ONE_MORE_BYTE (c); |
9ffd559c | 2027 | if (c < 0xA0) |
065e3595 | 2028 | goto invalid_code; |
df7492f9 | 2029 | code |= c & 0x7F; |
065e3595 | 2030 | break; |
df7492f9 | 2031 | |
065e3595 KH |
2032 | case 1: |
2033 | code = c; | |
2034 | charset = CHARSET_FROM_ID (ASCII_BYTE_P (code) | |
2035 | ? charset_ascii : charset_eight_bit); | |
2036 | break; | |
df7492f9 | 2037 | |
065e3595 KH |
2038 | default: |
2039 | abort (); | |
2040 | } | |
2041 | c = DECODE_CHAR (charset, code); | |
2042 | if (c < 0) | |
2043 | goto invalid_code; | |
df7492f9 | 2044 | } |
df7492f9 KH |
2045 | *nbytes = src - src_base; |
2046 | *nchars = consumed_chars; | |
ff0dacd7 KH |
2047 | if (id) |
2048 | *id = charset->id; | |
df7492f9 KH |
2049 | return c; |
2050 | ||
2051 | no_more_source: | |
2052 | return -2; | |
2053 | ||
2054 | invalid_code: | |
2055 | return -1; | |
2056 | } | |
2057 | ||
2058 | ||
2059 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
2060 | Check if a text is encoded in `emacs-mule'. If it is, return 1, |
2061 | else return 0. */ | |
df7492f9 KH |
2062 | |
2063 | static int | |
ff0dacd7 | 2064 | detect_coding_emacs_mule (coding, detect_info) |
df7492f9 | 2065 | struct coding_system *coding; |
ff0dacd7 | 2066 | struct coding_detection_info *detect_info; |
df7492f9 | 2067 | { |
065e3595 | 2068 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 2069 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
2070 | int multibytep = coding->src_multibyte; |
2071 | int consumed_chars = 0; | |
2072 | int c; | |
2073 | int found = 0; | |
2074 | ||
ff0dacd7 | 2075 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
2076 | /* A coding system of this category is always ASCII compatible. */ |
2077 | src += coding->head_ascii; | |
2078 | ||
2079 | while (1) | |
2080 | { | |
065e3595 | 2081 | src_base = src; |
df7492f9 | 2082 | ONE_MORE_BYTE (c); |
065e3595 KH |
2083 | if (c < 0) |
2084 | continue; | |
df7492f9 KH |
2085 | if (c == 0x80) |
2086 | { | |
2087 | /* Perhaps the start of composite character. We simple skip | |
2088 | it because analyzing it is too heavy for detecting. But, | |
2089 | at least, we check that the composite character | |
3ed051d4 | 2090 | constitutes of more than 4 bytes. */ |
8f924df7 | 2091 | const unsigned char *src_base; |
df7492f9 KH |
2092 | |
2093 | repeat: | |
2094 | src_base = src; | |
2095 | do | |
2096 | { | |
2097 | ONE_MORE_BYTE (c); | |
2098 | } | |
2099 | while (c >= 0xA0); | |
2100 | ||
2101 | if (src - src_base <= 4) | |
2102 | break; | |
ff0dacd7 | 2103 | found = CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
2104 | if (c == 0x80) |
2105 | goto repeat; | |
b73bfc1c | 2106 | } |
df7492f9 KH |
2107 | |
2108 | if (c < 0x80) | |
b73bfc1c | 2109 | { |
df7492f9 KH |
2110 | if (c < 0x20 |
2111 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
2112 | break; | |
2113 | } | |
2114 | else | |
2115 | { | |
0e219d54 | 2116 | int more_bytes = emacs_mule_bytes[*src_base] - 1; |
df7492f9 | 2117 | |
0e219d54 | 2118 | while (more_bytes > 0) |
df7492f9 KH |
2119 | { |
2120 | ONE_MORE_BYTE (c); | |
0e219d54 KH |
2121 | if (c < 0xA0) |
2122 | { | |
2123 | src--; /* Unread the last byte. */ | |
2124 | break; | |
2125 | } | |
2126 | more_bytes--; | |
df7492f9 | 2127 | } |
0e219d54 | 2128 | if (more_bytes != 0) |
df7492f9 | 2129 | break; |
ff0dacd7 | 2130 | found = CATEGORY_MASK_EMACS_MULE; |
4ed46869 KH |
2131 | } |
2132 | } | |
ff0dacd7 | 2133 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
2134 | return 0; |
2135 | ||
2136 | no_more_source: | |
065e3595 | 2137 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 2138 | { |
ff0dacd7 | 2139 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
89528eb3 KH |
2140 | return 0; |
2141 | } | |
ff0dacd7 KH |
2142 | detect_info->found |= found; |
2143 | return 1; | |
4ed46869 KH |
2144 | } |
2145 | ||
b73bfc1c | 2146 | |
df7492f9 KH |
2147 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
2148 | ||
2149 | /* Decode a character represented as a component of composition | |
2150 | sequence of Emacs 20/21 style at SRC. Set C to that character and | |
2151 | update SRC to the head of next character (or an encoded composition | |
2152 | rule). If SRC doesn't points a composition component, set C to -1. | |
2153 | If SRC points an invalid byte sequence, global exit by a return | |
2154 | value 0. */ | |
2155 | ||
2156 | #define DECODE_EMACS_MULE_COMPOSITION_CHAR(buf) \ | |
f937a7db | 2157 | do \ |
df7492f9 KH |
2158 | { \ |
2159 | int c; \ | |
2160 | int nbytes, nchars; \ | |
2161 | \ | |
2162 | if (src == src_end) \ | |
2163 | break; \ | |
ff0dacd7 | 2164 | c = emacs_mule_char (coding, src, &nbytes, &nchars, NULL);\ |
df7492f9 KH |
2165 | if (c < 0) \ |
2166 | { \ | |
2167 | if (c == -2) \ | |
2168 | break; \ | |
2169 | goto invalid_code; \ | |
2170 | } \ | |
2171 | *buf++ = c; \ | |
2172 | src += nbytes; \ | |
2173 | consumed_chars += nchars; \ | |
2174 | } \ | |
f937a7db | 2175 | while (0) |
df7492f9 KH |
2176 | |
2177 | ||
2178 | /* Decode a composition rule represented as a component of composition | |
781d7a48 KH |
2179 | sequence of Emacs 20 style at SRC. Store the decoded rule in *BUF, |
2180 | and increment BUF. If SRC points an invalid byte sequence, set C | |
2181 | to -1. */ | |
df7492f9 | 2182 | |
781d7a48 | 2183 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(buf) \ |
df7492f9 KH |
2184 | do { \ |
2185 | int c, gref, nref; \ | |
2186 | \ | |
781d7a48 | 2187 | if (src >= src_end) \ |
df7492f9 KH |
2188 | goto invalid_code; \ |
2189 | ONE_MORE_BYTE_NO_CHECK (c); \ | |
4d41e8b7 | 2190 | c -= 0xA0; \ |
df7492f9 KH |
2191 | if (c < 0 || c >= 81) \ |
2192 | goto invalid_code; \ | |
2193 | \ | |
2194 | gref = c / 9, nref = c % 9; \ | |
2195 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
2196 | } while (0) | |
2197 | ||
2198 | ||
781d7a48 KH |
2199 | /* Decode a composition rule represented as a component of composition |
2200 | sequence of Emacs 21 style at SRC. Store the decoded rule in *BUF, | |
2201 | and increment BUF. If SRC points an invalid byte sequence, set C | |
2202 | to -1. */ | |
2203 | ||
2204 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(buf) \ | |
2205 | do { \ | |
2206 | int gref, nref; \ | |
2207 | \ | |
2208 | if (src + 1>= src_end) \ | |
2209 | goto invalid_code; \ | |
2210 | ONE_MORE_BYTE_NO_CHECK (gref); \ | |
2211 | gref -= 0x20; \ | |
2212 | ONE_MORE_BYTE_NO_CHECK (nref); \ | |
2213 | nref -= 0x20; \ | |
2214 | if (gref < 0 || gref >= 81 \ | |
2215 | || nref < 0 || nref >= 81) \ | |
2216 | goto invalid_code; \ | |
2217 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
2218 | } while (0) | |
2219 | ||
2220 | ||
df7492f9 | 2221 | #define DECODE_EMACS_MULE_21_COMPOSITION(c) \ |
aa72b389 | 2222 | do { \ |
df7492f9 | 2223 | /* Emacs 21 style format. The first three bytes at SRC are \ |
781d7a48 | 2224 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is \ |
df7492f9 KH |
2225 | the byte length of this composition information, CHARS is the \ |
2226 | number of characters composed by this composition. */ \ | |
781d7a48 KH |
2227 | enum composition_method method = c - 0xF2; \ |
2228 | int *charbuf_base = charbuf; \ | |
df7492f9 KH |
2229 | int consumed_chars_limit; \ |
2230 | int nbytes, nchars; \ | |
2231 | \ | |
2232 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
2233 | if (c < 0) \ |
2234 | goto invalid_code; \ | |
df7492f9 KH |
2235 | nbytes = c - 0xA0; \ |
2236 | if (nbytes < 3) \ | |
2237 | goto invalid_code; \ | |
2238 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
2239 | if (c < 0) \ |
2240 | goto invalid_code; \ | |
df7492f9 | 2241 | nchars = c - 0xA0; \ |
69a80ea3 | 2242 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ |
df7492f9 KH |
2243 | consumed_chars_limit = consumed_chars_base + nbytes; \ |
2244 | if (method != COMPOSITION_RELATIVE) \ | |
aa72b389 | 2245 | { \ |
df7492f9 KH |
2246 | int i = 0; \ |
2247 | while (consumed_chars < consumed_chars_limit) \ | |
aa72b389 | 2248 | { \ |
df7492f9 | 2249 | if (i % 2 && method != COMPOSITION_WITH_ALTCHARS) \ |
781d7a48 | 2250 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (charbuf); \ |
df7492f9 KH |
2251 | else \ |
2252 | DECODE_EMACS_MULE_COMPOSITION_CHAR (charbuf); \ | |
781d7a48 | 2253 | i++; \ |
aa72b389 | 2254 | } \ |
df7492f9 KH |
2255 | if (consumed_chars < consumed_chars_limit) \ |
2256 | goto invalid_code; \ | |
781d7a48 | 2257 | charbuf_base[0] -= i; \ |
aa72b389 KH |
2258 | } \ |
2259 | } while (0) | |
93dec019 | 2260 | |
aa72b389 | 2261 | |
d959f512 KH |
2262 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION(c) \ |
2263 | do { \ | |
2264 | /* Emacs 20 style format for relative composition. */ \ | |
2265 | /* Store multibyte form of characters to be composed. */ \ | |
2266 | enum composition_method method = COMPOSITION_RELATIVE; \ | |
2267 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ | |
2268 | int *buf = components; \ | |
2269 | int i, j; \ | |
2270 | \ | |
2271 | src = src_base; \ | |
2272 | ONE_MORE_BYTE (c); /* skip 0x80 */ \ | |
2273 | for (i = 0; *src >= 0xA0 && i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
2274 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
2275 | if (i < 2) \ | |
2276 | goto invalid_code; \ | |
2277 | ADD_COMPOSITION_DATA (charbuf, i, method); \ | |
2278 | for (j = 0; j < i; j++) \ | |
2279 | *charbuf++ = components[j]; \ | |
df7492f9 KH |
2280 | } while (0) |
2281 | ||
2282 | ||
2283 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION(c) \ | |
2284 | do { \ | |
2285 | /* Emacs 20 style format for rule-base composition. */ \ | |
2286 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 2287 | enum composition_method method = COMPOSITION_WITH_RULE; \ |
4d41e8b7 | 2288 | int *charbuf_base = charbuf; \ |
df7492f9 KH |
2289 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
2290 | int *buf = components; \ | |
2291 | int i, j; \ | |
4d41e8b7 | 2292 | \ |
df7492f9 | 2293 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ |
4d41e8b7 | 2294 | for (i = 1; i < MAX_COMPOSITION_COMPONENTS; i++) \ |
df7492f9 | 2295 | { \ |
4d41e8b7 KH |
2296 | if (*src < 0xA0) \ |
2297 | break; \ | |
781d7a48 | 2298 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (buf); \ |
df7492f9 KH |
2299 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ |
2300 | } \ | |
4d41e8b7 | 2301 | if (i <= 1 || (buf - components) % 2 == 0) \ |
df7492f9 | 2302 | goto invalid_code; \ |
4d41e8b7 | 2303 | if (charbuf + i + (i / 2) + 1 >= charbuf_end) \ |
df7492f9 | 2304 | goto no_more_source; \ |
4d41e8b7 KH |
2305 | ADD_COMPOSITION_DATA (charbuf, i, method); \ |
2306 | i = i * 2 - 1; \ | |
df7492f9 KH |
2307 | for (j = 0; j < i; j++) \ |
2308 | *charbuf++ = components[j]; \ | |
4d41e8b7 | 2309 | charbuf_base[0] -= i; \ |
df7492f9 KH |
2310 | for (j = 0; j < i; j += 2) \ |
2311 | *charbuf++ = components[j]; \ | |
2312 | } while (0) | |
2313 | ||
aa72b389 KH |
2314 | |
2315 | static void | |
df7492f9 | 2316 | decode_coding_emacs_mule (coding) |
aa72b389 | 2317 | struct coding_system *coding; |
aa72b389 | 2318 | { |
8f924df7 KH |
2319 | const unsigned char *src = coding->source + coding->consumed; |
2320 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2321 | const unsigned char *src_base; | |
69a80ea3 KH |
2322 | int *charbuf = coding->charbuf + coding->charbuf_used; |
2323 | int *charbuf_end | |
2324 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 | 2325 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2326 | int multibytep = coding->src_multibyte; |
24a73b0a | 2327 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2328 | int char_offset = coding->produced_char; |
2329 | int last_offset = char_offset; | |
2330 | int last_id = charset_ascii; | |
119852e7 KH |
2331 | int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); |
2332 | int byte_after_cr = -1; | |
aa72b389 | 2333 | |
24a73b0a | 2334 | CODING_GET_INFO (coding, attrs, charset_list); |
aa72b389 | 2335 | |
aa72b389 KH |
2336 | while (1) |
2337 | { | |
df7492f9 KH |
2338 | int c; |
2339 | ||
aa72b389 | 2340 | src_base = src; |
df7492f9 KH |
2341 | consumed_chars_base = consumed_chars; |
2342 | ||
2343 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
2344 | { |
2345 | if (byte_after_cr >= 0) | |
2346 | src_base--; | |
2347 | break; | |
2348 | } | |
aa72b389 | 2349 | |
119852e7 KH |
2350 | if (byte_after_cr >= 0) |
2351 | c = byte_after_cr, byte_after_cr = -1; | |
2352 | else | |
2353 | ONE_MORE_BYTE (c); | |
065e3595 KH |
2354 | if (c < 0) |
2355 | { | |
2356 | *charbuf++ = -c; | |
2357 | char_offset++; | |
2358 | } | |
2359 | else if (c < 0x80) | |
aa72b389 | 2360 | { |
119852e7 KH |
2361 | if (eol_crlf && c == '\r') |
2362 | ONE_MORE_BYTE (byte_after_cr); | |
df7492f9 KH |
2363 | *charbuf++ = c; |
2364 | char_offset++; | |
aa72b389 | 2365 | } |
df7492f9 KH |
2366 | else if (c == 0x80) |
2367 | { | |
df7492f9 | 2368 | ONE_MORE_BYTE (c); |
065e3595 KH |
2369 | if (c < 0) |
2370 | goto invalid_code; | |
781d7a48 KH |
2371 | if (c - 0xF2 >= COMPOSITION_RELATIVE |
2372 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) | |
df7492f9 KH |
2373 | DECODE_EMACS_MULE_21_COMPOSITION (c); |
2374 | else if (c < 0xC0) | |
2375 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (c); | |
2376 | else if (c == 0xFF) | |
2377 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (c); | |
2378 | else | |
2379 | goto invalid_code; | |
2380 | } | |
2381 | else if (c < 0xA0 && emacs_mule_bytes[c] > 1) | |
2382 | { | |
2383 | int nbytes, nchars; | |
ff0dacd7 KH |
2384 | int id; |
2385 | ||
781d7a48 KH |
2386 | src = src_base; |
2387 | consumed_chars = consumed_chars_base; | |
ff0dacd7 | 2388 | c = emacs_mule_char (coding, src, &nbytes, &nchars, &id); |
df7492f9 KH |
2389 | if (c < 0) |
2390 | { | |
2391 | if (c == -2) | |
2392 | break; | |
2393 | goto invalid_code; | |
2394 | } | |
ff0dacd7 KH |
2395 | if (last_id != id) |
2396 | { | |
2397 | if (last_id != charset_ascii) | |
69a80ea3 | 2398 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
2399 | last_id = id; |
2400 | last_offset = char_offset; | |
2401 | } | |
df7492f9 | 2402 | *charbuf++ = c; |
781d7a48 KH |
2403 | src += nbytes; |
2404 | consumed_chars += nchars; | |
df7492f9 KH |
2405 | char_offset++; |
2406 | } | |
4d41e8b7 KH |
2407 | else |
2408 | goto invalid_code; | |
df7492f9 KH |
2409 | continue; |
2410 | ||
2411 | invalid_code: | |
2412 | src = src_base; | |
2413 | consumed_chars = consumed_chars_base; | |
2414 | ONE_MORE_BYTE (c); | |
2415 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2416 | char_offset++; |
df7492f9 KH |
2417 | coding->errors++; |
2418 | } | |
2419 | ||
2420 | no_more_source: | |
ff0dacd7 | 2421 | if (last_id != charset_ascii) |
69a80ea3 | 2422 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2423 | coding->consumed_char += consumed_chars_base; |
2424 | coding->consumed = src_base - coding->source; | |
2425 | coding->charbuf_used = charbuf - coding->charbuf; | |
2426 | } | |
2427 | ||
2428 | ||
2429 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2430 | do { \ | |
2431 | if (id < 0xA0) \ | |
2432 | codes[0] = id, codes[1] = 0; \ | |
2433 | else if (id < 0xE0) \ | |
2434 | codes[0] = 0x9A, codes[1] = id; \ | |
2435 | else if (id < 0xF0) \ | |
2436 | codes[0] = 0x9B, codes[1] = id; \ | |
2437 | else if (id < 0xF5) \ | |
2438 | codes[0] = 0x9C, codes[1] = id; \ | |
2439 | else \ | |
2440 | codes[0] = 0x9D, codes[1] = id; \ | |
2441 | } while (0); | |
2442 | ||
aa72b389 | 2443 | |
df7492f9 KH |
2444 | static int |
2445 | encode_coding_emacs_mule (coding) | |
2446 | struct coding_system *coding; | |
2447 | { | |
2448 | int multibytep = coding->dst_multibyte; | |
2449 | int *charbuf = coding->charbuf; | |
2450 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2451 | unsigned char *dst = coding->destination + coding->produced; | |
2452 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2453 | int safe_room = 8; | |
df7492f9 | 2454 | int produced_chars = 0; |
24a73b0a | 2455 | Lisp_Object attrs, charset_list; |
df7492f9 | 2456 | int c; |
ff0dacd7 | 2457 | int preferred_charset_id = -1; |
df7492f9 | 2458 | |
24a73b0a | 2459 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2460 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2461 | { | |
2462 | CODING_ATTR_CHARSET_LIST (attrs) | |
2463 | = charset_list = Vemacs_mule_charset_list; | |
2464 | } | |
df7492f9 KH |
2465 | |
2466 | while (charbuf < charbuf_end) | |
2467 | { | |
2468 | ASSURE_DESTINATION (safe_room); | |
2469 | c = *charbuf++; | |
ff0dacd7 KH |
2470 | |
2471 | if (c < 0) | |
2472 | { | |
2473 | /* Handle an annotation. */ | |
2474 | switch (*charbuf) | |
2475 | { | |
2476 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2477 | /* Not yet implemented. */ | |
2478 | break; | |
2479 | case CODING_ANNOTATE_CHARSET_MASK: | |
2480 | preferred_charset_id = charbuf[3]; | |
2481 | if (preferred_charset_id >= 0 | |
2482 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2483 | charset_list))) | |
2484 | preferred_charset_id = -1; | |
2485 | break; | |
2486 | default: | |
2487 | abort (); | |
2488 | } | |
2489 | charbuf += -c - 1; | |
2490 | continue; | |
2491 | } | |
2492 | ||
df7492f9 KH |
2493 | if (ASCII_CHAR_P (c)) |
2494 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2495 | else if (CHAR_BYTE8_P (c)) |
2496 | { | |
2497 | c = CHAR_TO_BYTE8 (c); | |
2498 | EMIT_ONE_BYTE (c); | |
2499 | } | |
df7492f9 | 2500 | else |
aa72b389 | 2501 | { |
df7492f9 KH |
2502 | struct charset *charset; |
2503 | unsigned code; | |
2504 | int dimension; | |
2505 | int emacs_mule_id; | |
2506 | unsigned char leading_codes[2]; | |
2507 | ||
ff0dacd7 KH |
2508 | if (preferred_charset_id >= 0) |
2509 | { | |
2510 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
905ca9d2 KH |
2511 | if (CHAR_CHARSET_P (c, charset)) |
2512 | code = ENCODE_CHAR (charset, c); | |
2513 | else | |
2514 | charset = char_charset (c, charset_list, &code); | |
ff0dacd7 KH |
2515 | } |
2516 | else | |
2517 | charset = char_charset (c, charset_list, &code); | |
df7492f9 KH |
2518 | if (! charset) |
2519 | { | |
2520 | c = coding->default_char; | |
2521 | if (ASCII_CHAR_P (c)) | |
2522 | { | |
2523 | EMIT_ONE_ASCII_BYTE (c); | |
2524 | continue; | |
2525 | } | |
2526 | charset = char_charset (c, charset_list, &code); | |
2527 | } | |
2528 | dimension = CHARSET_DIMENSION (charset); | |
2529 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2530 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2531 | EMIT_ONE_BYTE (leading_codes[0]); | |
2532 | if (leading_codes[1]) | |
2533 | EMIT_ONE_BYTE (leading_codes[1]); | |
2534 | if (dimension == 1) | |
1fa663f9 | 2535 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2536 | else |
df7492f9 | 2537 | { |
1fa663f9 | 2538 | code |= 0x8080; |
df7492f9 KH |
2539 | EMIT_ONE_BYTE (code >> 8); |
2540 | EMIT_ONE_BYTE (code & 0xFF); | |
2541 | } | |
aa72b389 | 2542 | } |
aa72b389 | 2543 | } |
065e3595 | 2544 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2545 | coding->produced_char += produced_chars; |
2546 | coding->produced = dst - coding->destination; | |
2547 | return 0; | |
aa72b389 | 2548 | } |
b73bfc1c | 2549 | |
4ed46869 | 2550 | \f |
df7492f9 | 2551 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2552 | |
2553 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2554 | Since the intention of this note is to help understand the |
5a936b46 | 2555 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2556 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2557 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2558 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2559 | |
2560 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2561 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2562 | is encoded using bytes less than 128. This may make the encoded |
2563 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2564 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2565 | Significant Bit). |
b73bfc1c | 2566 | |
cfb43547 DL |
2567 | There are two kinds of character sets: control character sets and |
2568 | graphic character sets. The former contain control characters such | |
4ed46869 | 2569 | as `newline' and `escape' to provide control functions (control |
39787efd | 2570 | functions are also provided by escape sequences). The latter |
cfb43547 | 2571 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2572 | two control character sets and many graphic character sets. |
2573 | ||
2574 | Graphic character sets are classified into one of the following | |
39787efd KH |
2575 | four classes, according to the number of bytes (DIMENSION) and |
2576 | number of characters in one dimension (CHARS) of the set: | |
2577 | - DIMENSION1_CHARS94 | |
2578 | - DIMENSION1_CHARS96 | |
2579 | - DIMENSION2_CHARS94 | |
2580 | - DIMENSION2_CHARS96 | |
2581 | ||
2582 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2583 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2584 | hereafter). The <F> of each character set is decided by ECMA(*) |
2585 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2586 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2587 | |
2588 | Note (*): ECMA = European Computer Manufacturers Association | |
2589 | ||
cfb43547 | 2590 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2591 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2592 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2593 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2594 | o DIMENSION2_CHARS96 -- none for the moment | |
2595 | ||
39787efd | 2596 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2597 | C0 [0x00..0x1F] -- control character plane 0 |
2598 | GL [0x20..0x7F] -- graphic character plane 0 | |
2599 | C1 [0x80..0x9F] -- control character plane 1 | |
2600 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2601 | ||
2602 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2603 | C1 by an escape sequence. The most common case is that: |
2604 | - ISO646's control character set is designated/invoked to C0, and | |
2605 | - ISO6429's control character set is designated/invoked to C1, | |
2606 | and usually these designations/invocations are omitted in encoded | |
2607 | text. In a 7-bit environment, only C0 can be used, and a control | |
2608 | character for C1 is encoded by an appropriate escape sequence to | |
2609 | fit into the environment. All control characters for C1 are | |
2610 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2611 | |
2612 | A graphic character set is at first designated to one of four | |
2613 | graphic registers (G0 through G3), then these graphic registers are | |
2614 | invoked to GL or GR. These designations and invocations can be | |
2615 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2616 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2617 | these invocations and designations are omitted in encoded text. | |
2618 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2619 | |
39787efd KH |
2620 | When a graphic character set of CHARS94 is invoked to GL, codes |
2621 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2622 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2623 | be used. | |
4ed46869 KH |
2624 | |
2625 | There are two ways of invocation: locking-shift and single-shift. | |
2626 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2627 | invocation, whereas with single-shift, the invocation affects the |
2628 | following character only and doesn't affect the locking-shift | |
2629 | state. Invocations are done by the following control characters or | |
2630 | escape sequences: | |
4ed46869 KH |
2631 | |
2632 | ---------------------------------------------------------------------- | |
39787efd | 2633 | abbrev function cntrl escape seq description |
4ed46869 | 2634 | ---------------------------------------------------------------------- |
39787efd KH |
2635 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2636 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2637 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2638 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2639 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2640 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2641 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2642 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2643 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2644 | ---------------------------------------------------------------------- |
39787efd KH |
2645 | (*) These are not used by any known coding system. |
2646 | ||
2647 | Control characters for these functions are defined by macros | |
2648 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2649 | |
39787efd | 2650 | Designations are done by the following escape sequences: |
4ed46869 KH |
2651 | ---------------------------------------------------------------------- |
2652 | escape sequence description | |
2653 | ---------------------------------------------------------------------- | |
2654 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2655 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2656 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2657 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2658 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2659 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2660 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2661 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2662 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2663 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2664 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2665 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2666 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2667 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2668 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2669 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2670 | ---------------------------------------------------------------------- | |
2671 | ||
2672 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2673 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2674 | |
2675 | Note (*): Although these designations are not allowed in ISO2022, | |
2676 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2677 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2678 | 7-bit environment, non-locking-shift, and non-single-shift. |
2679 | ||
2680 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2681 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2682 | |
cfb43547 | 2683 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2684 | same multilingual text in ISO2022. Actually, there exist many |
2685 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2686 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2687 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2688 | localized platforms), and all of these are variants of ISO2022. |
2689 | ||
2690 | In addition to the above, Emacs handles two more kinds of escape | |
2691 | sequences: ISO6429's direction specification and Emacs' private | |
2692 | sequence for specifying character composition. | |
2693 | ||
39787efd | 2694 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2695 | o CSI ']' -- end of the current direction |
2696 | o CSI '0' ']' -- end of the current direction | |
2697 | o CSI '1' ']' -- start of left-to-right text | |
2698 | o CSI '2' ']' -- start of right-to-left text | |
2699 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2700 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2701 | ||
2702 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2703 | o ESC '0' -- start relative composition |
2704 | o ESC '1' -- end composition | |
2705 | o ESC '2' -- start rule-base composition (*) | |
2706 | o ESC '3' -- start relative composition with alternate chars (**) | |
2707 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2708 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2709 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2710 | |
5a936b46 DL |
2711 | (*) This form is used only in Emacs 20.7 and older versions, |
2712 | but newer versions can safely decode it. | |
cfb43547 | 2713 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2714 | and older versions can't decode it. |
ec6d2bb8 | 2715 | |
cfb43547 | 2716 | Here's a list of example usages of these composition escape |
b73bfc1c | 2717 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2718 | |
b73bfc1c | 2719 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2720 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2721 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2722 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2723 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2724 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2725 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2726 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2727 | |
2728 | enum iso_code_class_type iso_code_class[256]; | |
2729 | ||
df7492f9 KH |
2730 | #define SAFE_CHARSET_P(coding, id) \ |
2731 | ((id) <= (coding)->max_charset_id \ | |
2732 | && (coding)->safe_charsets[id] >= 0) | |
2733 | ||
2734 | ||
2735 | #define SHIFT_OUT_OK(category) \ | |
2736 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
2737 | ||
2738 | static void | |
f0064e1f DL |
2739 | setup_iso_safe_charsets (attrs) |
2740 | Lisp_Object attrs; | |
df7492f9 KH |
2741 | { |
2742 | Lisp_Object charset_list, safe_charsets; | |
2743 | Lisp_Object request; | |
2744 | Lisp_Object reg_usage; | |
2745 | Lisp_Object tail; | |
2746 | int reg94, reg96; | |
2747 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
2748 | int max_charset_id; | |
2749 | ||
2750 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2751 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2752 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2753 | { | |
2754 | CODING_ATTR_CHARSET_LIST (attrs) | |
2755 | = charset_list = Viso_2022_charset_list; | |
2756 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
2757 | } | |
2758 | ||
2759 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2760 | return; | |
2761 | ||
2762 | max_charset_id = 0; | |
2763 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2764 | { | |
2765 | int id = XINT (XCAR (tail)); | |
2766 | if (max_charset_id < id) | |
2767 | max_charset_id = id; | |
2768 | } | |
d46c5b12 | 2769 | |
df7492f9 KH |
2770 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
2771 | make_number (255)); | |
2772 | request = AREF (attrs, coding_attr_iso_request); | |
2773 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2774 | reg94 = XINT (XCAR (reg_usage)); | |
2775 | reg96 = XINT (XCDR (reg_usage)); | |
2776 | ||
2777 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2778 | { | |
2779 | Lisp_Object id; | |
2780 | Lisp_Object reg; | |
2781 | struct charset *charset; | |
2782 | ||
2783 | id = XCAR (tail); | |
2784 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2785 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2786 | if (! NILP (reg)) |
8f924df7 | 2787 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2788 | else if (charset->iso_chars_96) |
2789 | { | |
2790 | if (reg96 < 4) | |
8f924df7 | 2791 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2792 | } |
2793 | else | |
2794 | { | |
2795 | if (reg94 < 4) | |
8f924df7 | 2796 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2797 | } |
2798 | } | |
2799 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2800 | } | |
d46c5b12 | 2801 | |
b6871cc7 | 2802 | |
4ed46869 | 2803 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
2804 | Check if a text is encoded in one of ISO-2022 based codig systems. |
2805 | If it is, return 1, else return 0. */ | |
4ed46869 | 2806 | |
0a28aafb | 2807 | static int |
ff0dacd7 | 2808 | detect_coding_iso_2022 (coding, detect_info) |
df7492f9 | 2809 | struct coding_system *coding; |
ff0dacd7 | 2810 | struct coding_detection_info *detect_info; |
4ed46869 | 2811 | { |
8f924df7 KH |
2812 | const unsigned char *src = coding->source, *src_base = src; |
2813 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 2814 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 2815 | int single_shifting = 0; |
df7492f9 KH |
2816 | int id; |
2817 | int c, c1; | |
2818 | int consumed_chars = 0; | |
2819 | int i; | |
ff0dacd7 KH |
2820 | int rejected = 0; |
2821 | int found = 0; | |
cee53ed4 | 2822 | int composition_count = -1; |
ff0dacd7 KH |
2823 | |
2824 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2825 | |
2826 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2827 | { | |
2828 | struct coding_system *this = &(coding_categories[i]); | |
2829 | Lisp_Object attrs, val; | |
2830 | ||
c6b278e7 KH |
2831 | if (this->id < 0) |
2832 | continue; | |
df7492f9 KH |
2833 | attrs = CODING_ID_ATTRS (this->id); |
2834 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
2835 | && ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs), Viso_2022_charset_list)) | |
2836 | setup_iso_safe_charsets (attrs); | |
2837 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
2838 | this->max_charset_id = SCHARS (val) - 1; |
2839 | this->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
2840 | } |
2841 | ||
2842 | /* A coding system of this category is always ASCII compatible. */ | |
2843 | src += coding->head_ascii; | |
3f003981 | 2844 | |
ff0dacd7 | 2845 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 2846 | { |
065e3595 | 2847 | src_base = src; |
df7492f9 | 2848 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2849 | switch (c) |
2850 | { | |
2851 | case ISO_CODE_ESC: | |
74383408 KH |
2852 | if (inhibit_iso_escape_detection) |
2853 | break; | |
f46869e4 | 2854 | single_shifting = 0; |
df7492f9 | 2855 | ONE_MORE_BYTE (c); |
d46c5b12 | 2856 | if (c >= '(' && c <= '/') |
4ed46869 | 2857 | { |
bf9cdd4e | 2858 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 2859 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2860 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2861 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
2862 | /* Invalid designation sequence. Just ignore. */ |
2863 | break; | |
bf9cdd4e KH |
2864 | } |
2865 | else if (c == '$') | |
2866 | { | |
2867 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 2868 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
2869 | if (c >= '@' && c <= 'B') |
2870 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
ff0dacd7 | 2871 | id = iso_charset_table[1][0][c]; |
bf9cdd4e | 2872 | else if (c >= '(' && c <= '/') |
bcf26d6a | 2873 | { |
df7492f9 | 2874 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2875 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2876 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
2877 | /* Invalid designation sequence. Just ignore. */ |
2878 | break; | |
bcf26d6a | 2879 | } |
bf9cdd4e | 2880 | else |
ff0dacd7 | 2881 | /* Invalid designation sequence. Just ignore it. */ |
d46c5b12 KH |
2882 | break; |
2883 | } | |
ae9ff118 | 2884 | else if (c == 'N' || c == 'O') |
d46c5b12 | 2885 | { |
ae9ff118 | 2886 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
2887 | single_shifting = 1; |
2888 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
d46c5b12 | 2889 | break; |
4ed46869 | 2890 | } |
cee53ed4 KH |
2891 | else if (c == '1') |
2892 | { | |
2893 | /* End of composition. */ | |
2894 | if (composition_count < 0 | |
2895 | || composition_count > MAX_COMPOSITION_COMPONENTS) | |
2896 | /* Invalid */ | |
2897 | break; | |
2898 | composition_count = -1; | |
2899 | found |= CATEGORY_MASK_ISO; | |
2900 | } | |
ec6d2bb8 KH |
2901 | else if (c >= '0' && c <= '4') |
2902 | { | |
2903 | /* ESC <Fp> for start/end composition. */ | |
cee53ed4 | 2904 | composition_count = 0; |
ec6d2bb8 KH |
2905 | break; |
2906 | } | |
bf9cdd4e | 2907 | else |
df7492f9 | 2908 | { |
ff0dacd7 | 2909 | /* Invalid escape sequence. Just ignore it. */ |
df7492f9 KH |
2910 | break; |
2911 | } | |
d46c5b12 KH |
2912 | |
2913 | /* We found a valid designation sequence for CHARSET. */ | |
ff0dacd7 | 2914 | rejected |= CATEGORY_MASK_ISO_8BIT; |
df7492f9 KH |
2915 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], |
2916 | id)) | |
ff0dacd7 | 2917 | found |= CATEGORY_MASK_ISO_7; |
d46c5b12 | 2918 | else |
ff0dacd7 | 2919 | rejected |= CATEGORY_MASK_ISO_7; |
df7492f9 KH |
2920 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], |
2921 | id)) | |
ff0dacd7 | 2922 | found |= CATEGORY_MASK_ISO_7_TIGHT; |
d46c5b12 | 2923 | else |
ff0dacd7 | 2924 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; |
df7492f9 KH |
2925 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], |
2926 | id)) | |
ff0dacd7 | 2927 | found |= CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 | 2928 | else |
ff0dacd7 | 2929 | rejected |= CATEGORY_MASK_ISO_7_ELSE; |
df7492f9 KH |
2930 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], |
2931 | id)) | |
ff0dacd7 | 2932 | found |= CATEGORY_MASK_ISO_8_ELSE; |
ae9ff118 | 2933 | else |
ff0dacd7 | 2934 | rejected |= CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
2935 | break; |
2936 | ||
4ed46869 | 2937 | case ISO_CODE_SO: |
d46c5b12 | 2938 | case ISO_CODE_SI: |
ff0dacd7 | 2939 | /* Locking shift out/in. */ |
74383408 KH |
2940 | if (inhibit_iso_escape_detection) |
2941 | break; | |
f46869e4 | 2942 | single_shifting = 0; |
ff0dacd7 | 2943 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
d46c5b12 KH |
2944 | break; |
2945 | ||
4ed46869 | 2946 | case ISO_CODE_CSI: |
ff0dacd7 | 2947 | /* Control sequence introducer. */ |
f46869e4 | 2948 | single_shifting = 0; |
ff0dacd7 KH |
2949 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2950 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
2951 | goto check_extra_latin; | |
2952 | ||
4ed46869 KH |
2953 | case ISO_CODE_SS2: |
2954 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
2955 | /* Single shift. */ |
2956 | if (inhibit_iso_escape_detection) | |
2957 | break; | |
75e2a253 | 2958 | single_shifting = 0; |
ff0dacd7 KH |
2959 | rejected |= CATEGORY_MASK_ISO_7BIT; |
2960 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2961 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 | 2962 | found |= CATEGORY_MASK_ISO_8_1, single_shifting = 1; |
ff0dacd7 KH |
2963 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
2964 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 KH |
2965 | found |= CATEGORY_MASK_ISO_8_2, single_shifting = 1; |
2966 | if (single_shifting) | |
2967 | break; | |
ff0dacd7 | 2968 | goto check_extra_latin; |
4ed46869 KH |
2969 | |
2970 | default: | |
065e3595 KH |
2971 | if (c < 0) |
2972 | continue; | |
4ed46869 | 2973 | if (c < 0x80) |
f46869e4 | 2974 | { |
cee53ed4 KH |
2975 | if (composition_count >= 0) |
2976 | composition_count++; | |
f46869e4 KH |
2977 | single_shifting = 0; |
2978 | break; | |
2979 | } | |
ff0dacd7 | 2980 | if (c >= 0xA0) |
c4825358 | 2981 | { |
ff0dacd7 KH |
2982 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2983 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 2984 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
2985 | 0xA0..0FF. If the byte length is even, we include |
2986 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
2987 | only when we are not single shifting. */ | |
2988 | if (! single_shifting | |
2989 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 2990 | { |
e17de821 | 2991 | int i = 1; |
b73bfc1c KH |
2992 | while (src < src_end) |
2993 | { | |
df7492f9 | 2994 | ONE_MORE_BYTE (c); |
b73bfc1c KH |
2995 | if (c < 0xA0) |
2996 | break; | |
2997 | i++; | |
2998 | } | |
2999 | ||
3000 | if (i & 1 && src < src_end) | |
cee53ed4 KH |
3001 | { |
3002 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3003 | if (composition_count >= 0) | |
3004 | composition_count += i; | |
3005 | } | |
f46869e4 | 3006 | else |
cee53ed4 KH |
3007 | { |
3008 | found |= CATEGORY_MASK_ISO_8_2; | |
3009 | if (composition_count >= 0) | |
3010 | composition_count += i / 2; | |
3011 | } | |
f46869e4 | 3012 | } |
ff0dacd7 | 3013 | break; |
4ed46869 | 3014 | } |
ff0dacd7 KH |
3015 | check_extra_latin: |
3016 | single_shifting = 0; | |
3017 | if (! VECTORP (Vlatin_extra_code_table) | |
3018 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
3019 | { | |
3020 | rejected = CATEGORY_MASK_ISO; | |
3021 | break; | |
3022 | } | |
3023 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3024 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
3025 | found |= CATEGORY_MASK_ISO_8_1; | |
3026 | else | |
3027 | rejected |= CATEGORY_MASK_ISO_8_1; | |
75e2a253 | 3028 | rejected |= CATEGORY_MASK_ISO_8_2; |
4ed46869 KH |
3029 | } |
3030 | } | |
ff0dacd7 KH |
3031 | detect_info->rejected |= CATEGORY_MASK_ISO; |
3032 | return 0; | |
4ed46869 | 3033 | |
df7492f9 | 3034 | no_more_source: |
ff0dacd7 KH |
3035 | detect_info->rejected |= rejected; |
3036 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 3037 | return 1; |
4ed46869 | 3038 | } |
ec6d2bb8 | 3039 | |
4ed46869 | 3040 | |
134b9549 KH |
3041 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
3042 | escape sequence should be kept. */ | |
df7492f9 KH |
3043 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
3044 | do { \ | |
3045 | int id, prev; \ | |
3046 | \ | |
3047 | if (final < '0' || final >= 128 \ | |
3048 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
3049 | || !SAFE_CHARSET_P (coding, id)) \ | |
3050 | { \ | |
3051 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
3052 | chars_96 = -1; \ |
3053 | break; \ | |
df7492f9 KH |
3054 | } \ |
3055 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
3056 | if (id == charset_jisx0201_roman) \ |
3057 | { \ | |
3058 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3059 | id = charset_ascii; \ | |
3060 | } \ | |
3061 | else if (id == charset_jisx0208_1978) \ | |
3062 | { \ | |
3063 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3064 | id = charset_jisx0208; \ | |
3065 | } \ | |
df7492f9 KH |
3066 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
3067 | /* If there was an invalid designation to REG previously, and this \ | |
3068 | designation is ASCII to REG, we should keep this designation \ | |
3069 | sequence. */ \ | |
3070 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 3071 | chars_96 = -1; \ |
4ed46869 KH |
3072 | } while (0) |
3073 | ||
d46c5b12 | 3074 | |
df7492f9 KH |
3075 | #define MAYBE_FINISH_COMPOSITION() \ |
3076 | do { \ | |
3077 | int i; \ | |
3078 | if (composition_state == COMPOSING_NO) \ | |
3079 | break; \ | |
3080 | /* It is assured that we have enough room for producing \ | |
3081 | characters stored in the table `components'. */ \ | |
3082 | if (charbuf + component_idx > charbuf_end) \ | |
3083 | goto no_more_source; \ | |
3084 | composition_state = COMPOSING_NO; \ | |
3085 | if (method == COMPOSITION_RELATIVE \ | |
3086 | || method == COMPOSITION_WITH_ALTCHARS) \ | |
3087 | { \ | |
3088 | for (i = 0; i < component_idx; i++) \ | |
3089 | *charbuf++ = components[i]; \ | |
3090 | char_offset += component_idx; \ | |
3091 | } \ | |
3092 | else \ | |
3093 | { \ | |
3094 | for (i = 0; i < component_idx; i += 2) \ | |
3095 | *charbuf++ = components[i]; \ | |
3096 | char_offset += (component_idx / 2) + 1; \ | |
3097 | } \ | |
3098 | } while (0) | |
3099 | ||
d46c5b12 | 3100 | |
aa72b389 KH |
3101 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
3102 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 | |
3103 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
3104 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
3105 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
aa72b389 | 3106 | */ |
ec6d2bb8 | 3107 | |
df7492f9 KH |
3108 | #define DECODE_COMPOSITION_START(c1) \ |
3109 | do { \ | |
3110 | if (c1 == '0' \ | |
781d7a48 | 3111 | && composition_state == COMPOSING_COMPONENT_RULE) \ |
df7492f9 KH |
3112 | { \ |
3113 | component_len = component_idx; \ | |
3114 | composition_state = COMPOSING_CHAR; \ | |
3115 | } \ | |
3116 | else \ | |
3117 | { \ | |
8f924df7 | 3118 | const unsigned char *p; \ |
df7492f9 KH |
3119 | \ |
3120 | MAYBE_FINISH_COMPOSITION (); \ | |
3121 | if (charbuf + MAX_COMPOSITION_COMPONENTS > charbuf_end) \ | |
3122 | goto no_more_source; \ | |
3123 | for (p = src; p < src_end - 1; p++) \ | |
3124 | if (*p == ISO_CODE_ESC && p[1] == '1') \ | |
3125 | break; \ | |
3126 | if (p == src_end - 1) \ | |
3127 | { \ | |
cee53ed4 KH |
3128 | if (coding->mode & CODING_MODE_LAST_BLOCK) \ |
3129 | goto invalid_code; \ | |
9286b333 KH |
3130 | /* The current composition doesn't end in the current \ |
3131 | source. */ \ | |
3132 | record_conversion_result \ | |
3133 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
df7492f9 KH |
3134 | goto no_more_source; \ |
3135 | } \ | |
3136 | \ | |
3137 | /* This is surely the start of a composition. */ \ | |
3138 | method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
3139 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
3140 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
3141 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
3142 | composition_state = (c1 <= '2' ? COMPOSING_CHAR \ | |
3143 | : COMPOSING_COMPONENT_CHAR); \ | |
3144 | component_idx = component_len = 0; \ | |
3145 | } \ | |
ec6d2bb8 KH |
3146 | } while (0) |
3147 | ||
ec6d2bb8 | 3148 | |
df7492f9 KH |
3149 | /* Handle compositoin end sequence ESC 1. */ |
3150 | ||
3151 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 3152 | do { \ |
df7492f9 KH |
3153 | int nchars = (component_len > 0 ? component_idx - component_len \ |
3154 | : method == COMPOSITION_RELATIVE ? component_idx \ | |
3155 | : (component_idx + 1) / 2); \ | |
3156 | int i; \ | |
3157 | int *saved_charbuf = charbuf; \ | |
3158 | \ | |
69a80ea3 | 3159 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ |
df7492f9 | 3160 | if (method != COMPOSITION_RELATIVE) \ |
ec6d2bb8 | 3161 | { \ |
df7492f9 KH |
3162 | if (component_len == 0) \ |
3163 | for (i = 0; i < component_idx; i++) \ | |
3164 | *charbuf++ = components[i]; \ | |
3165 | else \ | |
3166 | for (i = 0; i < component_len; i++) \ | |
3167 | *charbuf++ = components[i]; \ | |
3168 | *saved_charbuf = saved_charbuf - charbuf; \ | |
ec6d2bb8 | 3169 | } \ |
df7492f9 KH |
3170 | if (method == COMPOSITION_WITH_RULE) \ |
3171 | for (i = 0; i < component_idx; i += 2, char_offset++) \ | |
3172 | *charbuf++ = components[i]; \ | |
ec6d2bb8 | 3173 | else \ |
df7492f9 KH |
3174 | for (i = component_len; i < component_idx; i++, char_offset++) \ |
3175 | *charbuf++ = components[i]; \ | |
3176 | coding->annotated = 1; \ | |
3177 | composition_state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
3178 | } while (0) |
3179 | ||
df7492f9 | 3180 | |
ec6d2bb8 KH |
3181 | /* Decode a composition rule from the byte C1 (and maybe one more byte |
3182 | from SRC) and store one encoded composition rule in | |
3183 | coding->cmp_data. */ | |
3184 | ||
3185 | #define DECODE_COMPOSITION_RULE(c1) \ | |
3186 | do { \ | |
ec6d2bb8 KH |
3187 | (c1) -= 32; \ |
3188 | if (c1 < 81) /* old format (before ver.21) */ \ | |
3189 | { \ | |
3190 | int gref = (c1) / 9; \ | |
3191 | int nref = (c1) % 9; \ | |
3192 | if (gref == 4) gref = 10; \ | |
3193 | if (nref == 4) nref = 10; \ | |
df7492f9 | 3194 | c1 = COMPOSITION_ENCODE_RULE (gref, nref); \ |
ec6d2bb8 | 3195 | } \ |
b73bfc1c | 3196 | else if (c1 < 93) /* new format (after ver.21) */ \ |
ec6d2bb8 KH |
3197 | { \ |
3198 | ONE_MORE_BYTE (c2); \ | |
df7492f9 | 3199 | c1 = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \ |
ec6d2bb8 | 3200 | } \ |
df7492f9 KH |
3201 | else \ |
3202 | c1 = 0; \ | |
ec6d2bb8 | 3203 | } while (0) |
88993dfd | 3204 | |
d46c5b12 | 3205 | |
4ed46869 KH |
3206 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
3207 | ||
b73bfc1c | 3208 | static void |
df7492f9 | 3209 | decode_coding_iso_2022 (coding) |
4ed46869 | 3210 | struct coding_system *coding; |
4ed46869 | 3211 | { |
8f924df7 KH |
3212 | const unsigned char *src = coding->source + coding->consumed; |
3213 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
3214 | const unsigned char *src_base; | |
69a80ea3 | 3215 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ff0dacd7 | 3216 | int *charbuf_end |
69a80ea3 | 3217 | = coding->charbuf + coding->charbuf_size - 4 - MAX_ANNOTATION_LENGTH; |
df7492f9 | 3218 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 3219 | int multibytep = coding->src_multibyte; |
4ed46869 | 3220 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
3221 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3222 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 3223 | int charset_id_2, charset_id_3; |
df7492f9 KH |
3224 | struct charset *charset; |
3225 | int c; | |
3226 | /* For handling composition sequence. */ | |
3227 | #define COMPOSING_NO 0 | |
3228 | #define COMPOSING_CHAR 1 | |
3229 | #define COMPOSING_RULE 2 | |
3230 | #define COMPOSING_COMPONENT_CHAR 3 | |
3231 | #define COMPOSING_COMPONENT_RULE 4 | |
3232 | ||
3233 | int composition_state = COMPOSING_NO; | |
3234 | enum composition_method method; | |
3235 | int components[MAX_COMPOSITION_COMPONENTS * 2 + 1]; | |
3236 | int component_idx; | |
3237 | int component_len; | |
24a73b0a | 3238 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
3239 | int char_offset = coding->produced_char; |
3240 | int last_offset = char_offset; | |
3241 | int last_id = charset_ascii; | |
119852e7 KH |
3242 | int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); |
3243 | int byte_after_cr = -1; | |
df7492f9 | 3244 | |
24a73b0a | 3245 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 3246 | setup_iso_safe_charsets (attrs); |
287c57d7 KH |
3247 | /* Charset list may have been changed. */ |
3248 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
3249 | coding->safe_charsets = (char *) SDATA (CODING_ATTR_SAFE_CHARSETS(attrs)); | |
b73bfc1c KH |
3250 | |
3251 | while (1) | |
4ed46869 | 3252 | { |
463f5630 | 3253 | int c1, c2; |
b73bfc1c KH |
3254 | |
3255 | src_base = src; | |
df7492f9 KH |
3256 | consumed_chars_base = consumed_chars; |
3257 | ||
3258 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
3259 | { |
3260 | if (byte_after_cr >= 0) | |
3261 | src_base--; | |
3262 | break; | |
3263 | } | |
df7492f9 | 3264 | |
119852e7 KH |
3265 | if (byte_after_cr >= 0) |
3266 | c1 = byte_after_cr, byte_after_cr = -1; | |
3267 | else | |
3268 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
3269 | if (c1 < 0) |
3270 | goto invalid_code; | |
4ed46869 | 3271 | |
98725083 | 3272 | /* We produce at most one character. */ |
4ed46869 KH |
3273 | switch (iso_code_class [c1]) |
3274 | { | |
3275 | case ISO_0x20_or_0x7F: | |
df7492f9 | 3276 | if (composition_state != COMPOSING_NO) |
ec6d2bb8 | 3277 | { |
df7492f9 KH |
3278 | if (composition_state == COMPOSING_RULE |
3279 | || composition_state == COMPOSING_COMPONENT_RULE) | |
3280 | { | |
cee53ed4 KH |
3281 | if (component_idx < MAX_COMPOSITION_COMPONENTS * 2 + 1) |
3282 | { | |
3283 | DECODE_COMPOSITION_RULE (c1); | |
3284 | components[component_idx++] = c1; | |
3285 | composition_state--; | |
3286 | continue; | |
3287 | } | |
3288 | /* Too long composition. */ | |
3289 | MAYBE_FINISH_COMPOSITION (); | |
df7492f9 | 3290 | } |
4ed46869 | 3291 | } |
df7492f9 KH |
3292 | if (charset_id_0 < 0 |
3293 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
3294 | /* This is SPACE or DEL. */ |
3295 | charset = CHARSET_FROM_ID (charset_ascii); | |
3296 | else | |
3297 | charset = CHARSET_FROM_ID (charset_id_0); | |
3298 | break; | |
4ed46869 KH |
3299 | |
3300 | case ISO_graphic_plane_0: | |
781d7a48 | 3301 | if (composition_state != COMPOSING_NO) |
b73bfc1c | 3302 | { |
781d7a48 KH |
3303 | if (composition_state == COMPOSING_RULE |
3304 | || composition_state == COMPOSING_COMPONENT_RULE) | |
3305 | { | |
cee53ed4 KH |
3306 | if (component_idx < MAX_COMPOSITION_COMPONENTS * 2 + 1) |
3307 | { | |
3308 | DECODE_COMPOSITION_RULE (c1); | |
3309 | components[component_idx++] = c1; | |
3310 | composition_state--; | |
3311 | continue; | |
3312 | } | |
3313 | MAYBE_FINISH_COMPOSITION (); | |
781d7a48 | 3314 | } |
b73bfc1c | 3315 | } |
134b9549 KH |
3316 | if (charset_id_0 < 0) |
3317 | charset = CHARSET_FROM_ID (charset_ascii); | |
3318 | else | |
3319 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
3320 | break; |
3321 | ||
3322 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
3323 | if (charset_id_1 < 0 |
3324 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
3325 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
3326 | goto invalid_code; | |
4ed46869 KH |
3327 | /* This is a graphic character, we fall down ... */ |
3328 | ||
3329 | case ISO_graphic_plane_1: | |
df7492f9 KH |
3330 | if (charset_id_1 < 0) |
3331 | goto invalid_code; | |
3332 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
3333 | break; |
3334 | ||
df7492f9 | 3335 | case ISO_control_0: |
119852e7 KH |
3336 | if (eol_crlf && c1 == '\r') |
3337 | ONE_MORE_BYTE (byte_after_cr); | |
df7492f9 KH |
3338 | MAYBE_FINISH_COMPOSITION (); |
3339 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
3340 | break; |
3341 | ||
df7492f9 KH |
3342 | case ISO_control_1: |
3343 | MAYBE_FINISH_COMPOSITION (); | |
3344 | goto invalid_code; | |
3345 | ||
4ed46869 | 3346 | case ISO_shift_out: |
df7492f9 KH |
3347 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3348 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3349 | goto invalid_code; | |
3350 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3351 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3352 | continue; |
4ed46869 KH |
3353 | |
3354 | case ISO_shift_in: | |
df7492f9 KH |
3355 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3356 | goto invalid_code; | |
3357 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3358 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3359 | continue; |
4ed46869 KH |
3360 | |
3361 | case ISO_single_shift_2_7: | |
3362 | case ISO_single_shift_2: | |
df7492f9 KH |
3363 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3364 | goto invalid_code; | |
4ed46869 KH |
3365 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3366 | c1 = 'N'; | |
3367 | goto label_escape_sequence; | |
3368 | ||
3369 | case ISO_single_shift_3: | |
df7492f9 KH |
3370 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3371 | goto invalid_code; | |
4ed46869 KH |
3372 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3373 | c1 = 'O'; | |
3374 | goto label_escape_sequence; | |
3375 | ||
3376 | case ISO_control_sequence_introducer: | |
3377 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3378 | c1 = '['; | |
3379 | goto label_escape_sequence; | |
3380 | ||
3381 | case ISO_escape: | |
3382 | ONE_MORE_BYTE (c1); | |
3383 | label_escape_sequence: | |
df7492f9 | 3384 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3385 | designation, direction specification, and character |
3386 | composition specification. */ | |
3387 | switch (c1) | |
3388 | { | |
3389 | case '&': /* revision of following character set */ | |
3390 | ONE_MORE_BYTE (c1); | |
3391 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3392 | goto invalid_code; |
4ed46869 KH |
3393 | ONE_MORE_BYTE (c1); |
3394 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3395 | goto invalid_code; |
4ed46869 KH |
3396 | ONE_MORE_BYTE (c1); |
3397 | goto label_escape_sequence; | |
3398 | ||
3399 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3400 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3401 | goto invalid_code; | |
134b9549 KH |
3402 | { |
3403 | int reg, chars96; | |
3404 | ||
3405 | ONE_MORE_BYTE (c1); | |
3406 | if (c1 >= '@' && c1 <= 'B') | |
3407 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3408 | or JISX0208.1980 */ |
134b9549 KH |
3409 | reg = 0, chars96 = 0; |
3410 | } | |
3411 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3412 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3413 | reg = c1 - 0x28, chars96 = 0; | |
3414 | ONE_MORE_BYTE (c1); | |
3415 | } | |
3416 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3417 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3418 | reg = c1 - 0x2C, chars96 = 1; | |
3419 | ONE_MORE_BYTE (c1); | |
3420 | } | |
3421 | else | |
3422 | goto invalid_code; | |
3423 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3424 | /* We must update these variables now. */ | |
3425 | if (reg == 0) | |
3426 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3427 | else if (reg == 1) | |
3428 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3429 | if (chars96 < 0) | |
3430 | goto invalid_code; | |
3431 | } | |
b73bfc1c | 3432 | continue; |
4ed46869 KH |
3433 | |
3434 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3435 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3436 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3437 | goto invalid_code; | |
3438 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3439 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3440 | continue; |
4ed46869 KH |
3441 | |
3442 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3443 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3444 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3445 | goto invalid_code; | |
3446 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3447 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3448 | continue; |
4ed46869 KH |
3449 | |
3450 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3451 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3452 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3453 | goto invalid_code; | |
134b9549 KH |
3454 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3455 | if (charset_id_2 < 0) | |
3456 | charset = CHARSET_FROM_ID (charset_ascii); | |
3457 | else | |
3458 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3459 | ONE_MORE_BYTE (c1); |
e7046a18 | 3460 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3461 | goto invalid_code; |
4ed46869 KH |
3462 | break; |
3463 | ||
3464 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3465 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3466 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3467 | goto invalid_code; | |
134b9549 KH |
3468 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3469 | if (charset_id_3 < 0) | |
3470 | charset = CHARSET_FROM_ID (charset_ascii); | |
3471 | else | |
3472 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3473 | ONE_MORE_BYTE (c1); |
e7046a18 | 3474 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3475 | goto invalid_code; |
4ed46869 KH |
3476 | break; |
3477 | ||
ec6d2bb8 | 3478 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3479 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3480 | goto invalid_code; | |
ec6d2bb8 | 3481 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3482 | continue; |
4ed46869 | 3483 | |
ec6d2bb8 | 3484 | case '1': /* end composition */ |
df7492f9 KH |
3485 | if (composition_state == COMPOSING_NO) |
3486 | goto invalid_code; | |
3487 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3488 | continue; |
4ed46869 KH |
3489 | |
3490 | case '[': /* specification of direction */ | |
df7492f9 KH |
3491 | if (! CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION) |
3492 | goto invalid_code; | |
4ed46869 | 3493 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3494 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
df7492f9 | 3495 | left-to-right, and nozero means right-to-left. */ |
4ed46869 KH |
3496 | ONE_MORE_BYTE (c1); |
3497 | switch (c1) | |
3498 | { | |
3499 | case ']': /* end of the current direction */ | |
d46c5b12 | 3500 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3501 | |
3502 | case '0': /* end of the current direction */ | |
3503 | case '1': /* start of left-to-right direction */ | |
3504 | ONE_MORE_BYTE (c1); | |
3505 | if (c1 == ']') | |
d46c5b12 | 3506 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3507 | else |
df7492f9 | 3508 | goto invalid_code; |
4ed46869 KH |
3509 | break; |
3510 | ||
3511 | case '2': /* start of right-to-left direction */ | |
3512 | ONE_MORE_BYTE (c1); | |
3513 | if (c1 == ']') | |
d46c5b12 | 3514 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3515 | else |
df7492f9 | 3516 | goto invalid_code; |
4ed46869 KH |
3517 | break; |
3518 | ||
3519 | default: | |
df7492f9 | 3520 | goto invalid_code; |
4ed46869 | 3521 | } |
b73bfc1c | 3522 | continue; |
4ed46869 | 3523 | |
103e0180 | 3524 | case '%': |
103e0180 KH |
3525 | ONE_MORE_BYTE (c1); |
3526 | if (c1 == '/') | |
3527 | { | |
3528 | /* CTEXT extended segment: | |
3529 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3530 | We keep these bytes as is for the moment. | |
3531 | They may be decoded by post-read-conversion. */ | |
3532 | int dim, M, L; | |
4776e638 | 3533 | int size; |
8f924df7 | 3534 | |
103e0180 KH |
3535 | ONE_MORE_BYTE (dim); |
3536 | ONE_MORE_BYTE (M); | |
3537 | ONE_MORE_BYTE (L); | |
3538 | size = ((M - 128) * 128) + (L - 128); | |
4776e638 KH |
3539 | if (charbuf + 8 + size > charbuf_end) |
3540 | goto break_loop; | |
3541 | *charbuf++ = ISO_CODE_ESC; | |
3542 | *charbuf++ = '%'; | |
3543 | *charbuf++ = '/'; | |
3544 | *charbuf++ = dim; | |
3545 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3546 | *charbuf++ = BYTE8_TO_CHAR (L); | |
103e0180 KH |
3547 | while (size-- > 0) |
3548 | { | |
3549 | ONE_MORE_BYTE (c1); | |
4776e638 | 3550 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3551 | } |
103e0180 KH |
3552 | } |
3553 | else if (c1 == 'G') | |
3554 | { | |
103e0180 KH |
3555 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3556 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3557 | We keep these bytes as is for the moment. | |
3558 | They may be decoded by post-read-conversion. */ | |
4776e638 KH |
3559 | int *p = charbuf; |
3560 | ||
3561 | if (p + 6 > charbuf_end) | |
3562 | goto break_loop; | |
3563 | *p++ = ISO_CODE_ESC; | |
3564 | *p++ = '%'; | |
3565 | *p++ = 'G'; | |
3566 | while (p < charbuf_end) | |
103e0180 KH |
3567 | { |
3568 | ONE_MORE_BYTE (c1); | |
3569 | if (c1 == ISO_CODE_ESC | |
3570 | && src + 1 < src_end | |
3571 | && src[0] == '%' | |
3572 | && src[1] == '@') | |
9ffd559c KH |
3573 | { |
3574 | src += 2; | |
3575 | break; | |
3576 | } | |
4776e638 | 3577 | *p++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3578 | } |
4776e638 KH |
3579 | if (p + 3 > charbuf_end) |
3580 | goto break_loop; | |
3581 | *p++ = ISO_CODE_ESC; | |
3582 | *p++ = '%'; | |
3583 | *p++ = '@'; | |
3584 | charbuf = p; | |
103e0180 KH |
3585 | } |
3586 | else | |
4776e638 | 3587 | goto invalid_code; |
103e0180 | 3588 | continue; |
4776e638 | 3589 | break; |
103e0180 | 3590 | |
4ed46869 | 3591 | default: |
df7492f9 KH |
3592 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3593 | goto invalid_code; | |
134b9549 KH |
3594 | { |
3595 | int reg, chars96; | |
3596 | ||
3597 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3598 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3599 | reg = c1 - 0x28, chars96 = 0; | |
3600 | ONE_MORE_BYTE (c1); | |
3601 | } | |
3602 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3603 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3604 | reg = c1 - 0x2C, chars96 = 1; | |
3605 | ONE_MORE_BYTE (c1); | |
3606 | } | |
3607 | else | |
3608 | goto invalid_code; | |
3609 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3610 | /* We must update these variables now. */ | |
3611 | if (reg == 0) | |
3612 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3613 | else if (reg == 1) | |
3614 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3615 | if (chars96 < 0) | |
3616 | goto invalid_code; | |
3617 | } | |
b73bfc1c | 3618 | continue; |
4ed46869 | 3619 | } |
b73bfc1c | 3620 | } |
4ed46869 | 3621 | |
ff0dacd7 KH |
3622 | if (charset->id != charset_ascii |
3623 | && last_id != charset->id) | |
3624 | { | |
3625 | if (last_id != charset_ascii) | |
69a80ea3 | 3626 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3627 | last_id = charset->id; |
3628 | last_offset = char_offset; | |
3629 | } | |
3630 | ||
b73bfc1c | 3631 | /* Now we know CHARSET and 1st position code C1 of a character. |
df7492f9 KH |
3632 | Produce a decoded character while getting 2nd position code |
3633 | C2 if necessary. */ | |
3634 | c1 &= 0x7F; | |
3635 | if (CHARSET_DIMENSION (charset) > 1) | |
b73bfc1c KH |
3636 | { |
3637 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3638 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) |
b73bfc1c | 3639 | /* C2 is not in a valid range. */ |
df7492f9 KH |
3640 | goto invalid_code; |
3641 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3642 | if (CHARSET_DIMENSION (charset) > 2) | |
3643 | { | |
3644 | ONE_MORE_BYTE (c2); | |
3645 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) | |
3646 | /* C2 is not in a valid range. */ | |
3647 | goto invalid_code; | |
3648 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3649 | } | |
3650 | } | |
3651 | ||
3652 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); | |
3653 | if (c < 0) | |
3654 | { | |
3655 | MAYBE_FINISH_COMPOSITION (); | |
3656 | for (; src_base < src; src_base++, char_offset++) | |
3657 | { | |
3658 | if (ASCII_BYTE_P (*src_base)) | |
3659 | *charbuf++ = *src_base; | |
3660 | else | |
3661 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3662 | } | |
3663 | } | |
3664 | else if (composition_state == COMPOSING_NO) | |
3665 | { | |
3666 | *charbuf++ = c; | |
3667 | char_offset++; | |
4ed46869 | 3668 | } |
df7492f9 | 3669 | else |
781d7a48 | 3670 | { |
cee53ed4 KH |
3671 | if (component_idx < MAX_COMPOSITION_COMPONENTS * 2 + 1) |
3672 | { | |
3673 | components[component_idx++] = c; | |
3674 | if (method == COMPOSITION_WITH_RULE | |
3675 | || (method == COMPOSITION_WITH_RULE_ALTCHARS | |
3676 | && composition_state == COMPOSING_COMPONENT_CHAR)) | |
3677 | composition_state++; | |
3678 | } | |
3679 | else | |
3680 | { | |
3681 | MAYBE_FINISH_COMPOSITION (); | |
3682 | *charbuf++ = c; | |
3683 | char_offset++; | |
3684 | } | |
4ed46869 KH |
3685 | } |
3686 | continue; | |
3687 | ||
df7492f9 KH |
3688 | invalid_code: |
3689 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3690 | src = src_base; |
df7492f9 KH |
3691 | consumed_chars = consumed_chars_base; |
3692 | ONE_MORE_BYTE (c); | |
065e3595 | 3693 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3694 | char_offset++; |
df7492f9 | 3695 | coding->errors++; |
4776e638 KH |
3696 | continue; |
3697 | ||
3698 | break_loop: | |
3699 | break; | |
4ed46869 | 3700 | } |
fb88bf2d | 3701 | |
df7492f9 | 3702 | no_more_source: |
ff0dacd7 | 3703 | if (last_id != charset_ascii) |
69a80ea3 | 3704 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
3705 | coding->consumed_char += consumed_chars_base; |
3706 | coding->consumed = src_base - coding->source; | |
3707 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3708 | } |
3709 | ||
b73bfc1c | 3710 | |
f4dee582 | 3711 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3712 | |
3713 | /* | |
f4dee582 | 3714 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 3715 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 3716 | variant has the following specifications: |
df7492f9 | 3717 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
3718 | 2. Allows short-form designation? |
3719 | 3. ASCII should be designated to G0 before control characters? | |
3720 | 4. ASCII should be designated to G0 at end of line? | |
3721 | 5. 7-bit environment or 8-bit environment? | |
3722 | 6. Use locking-shift? | |
3723 | 7. Use Single-shift? | |
3724 | And the following two are only for Japanese: | |
3725 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
3726 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
3727 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
3728 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 3729 | details. |
4ed46869 KH |
3730 | */ |
3731 | ||
3732 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
3733 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
3734 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
3735 | designation sequence of short-form. */ | |
4ed46869 KH |
3736 | |
3737 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
3738 | do { \ | |
df7492f9 | 3739 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
4ed46869 KH |
3740 | char *intermediate_char_94 = "()*+"; \ |
3741 | char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
3742 | int revision = -1; \ |
3743 | int c; \ | |
3744 | \ | |
3745 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 3746 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
3747 | \ |
3748 | if (revision >= 0) \ | |
70c22245 | 3749 | { \ |
df7492f9 KH |
3750 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
3751 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 3752 | } \ |
df7492f9 | 3753 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
3754 | if (CHARSET_DIMENSION (charset) == 1) \ |
3755 | { \ | |
df7492f9 KH |
3756 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
3757 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 3758 | else \ |
df7492f9 KH |
3759 | c = intermediate_char_96[reg]; \ |
3760 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
3761 | } \ |
3762 | else \ | |
3763 | { \ | |
df7492f9 KH |
3764 | EMIT_ONE_ASCII_BYTE ('$'); \ |
3765 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 3766 | { \ |
df7492f9 | 3767 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
3768 | || reg != 0 \ |
3769 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 3770 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
3771 | } \ |
3772 | else \ | |
df7492f9 | 3773 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 3774 | } \ |
df7492f9 KH |
3775 | EMIT_ONE_ASCII_BYTE (final_char); \ |
3776 | \ | |
3777 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
3778 | } while (0) |
3779 | ||
df7492f9 | 3780 | |
4ed46869 KH |
3781 | /* The following two macros produce codes (control character or escape |
3782 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
3783 | single-shift-3). */ | |
3784 | ||
df7492f9 KH |
3785 | #define ENCODE_SINGLE_SHIFT_2 \ |
3786 | do { \ | |
3787 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3788 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
3789 | else \ | |
3790 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
3791 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3792 | } while (0) |
3793 | ||
df7492f9 KH |
3794 | |
3795 | #define ENCODE_SINGLE_SHIFT_3 \ | |
3796 | do { \ | |
3797 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3798 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
3799 | else \ | |
3800 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
3801 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3802 | } while (0) |
3803 | ||
df7492f9 | 3804 | |
4ed46869 KH |
3805 | /* The following four macros produce codes (control character or |
3806 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
3807 | shift-out, locking-shift-2, and locking-shift-3). */ | |
3808 | ||
df7492f9 KH |
3809 | #define ENCODE_SHIFT_IN \ |
3810 | do { \ | |
3811 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
3812 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
3813 | } while (0) |
3814 | ||
df7492f9 KH |
3815 | |
3816 | #define ENCODE_SHIFT_OUT \ | |
3817 | do { \ | |
3818 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
3819 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
3820 | } while (0) |
3821 | ||
df7492f9 KH |
3822 | |
3823 | #define ENCODE_LOCKING_SHIFT_2 \ | |
3824 | do { \ | |
3825 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3826 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
3827 | } while (0) |
3828 | ||
df7492f9 KH |
3829 | |
3830 | #define ENCODE_LOCKING_SHIFT_3 \ | |
3831 | do { \ | |
3832 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3833 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
3834 | } while (0) |
3835 | ||
df7492f9 | 3836 | |
f4dee582 RS |
3837 | /* Produce codes for a DIMENSION1 character whose character set is |
3838 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
3839 | sequences are also produced in advance if necessary. */ |
3840 | ||
6e85d753 KH |
3841 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
3842 | do { \ | |
df7492f9 | 3843 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3844 | \ |
3845 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3846 | && id == charset_ascii) \ | |
3847 | { \ | |
3848 | id = charset_jisx0201_roman; \ | |
3849 | charset = CHARSET_FROM_ID (id); \ | |
3850 | } \ | |
3851 | \ | |
df7492f9 | 3852 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3853 | { \ |
df7492f9 KH |
3854 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3855 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 3856 | else \ |
df7492f9 KH |
3857 | EMIT_ONE_BYTE (c1 | 0x80); \ |
3858 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3859 | break; \ |
3860 | } \ | |
df7492f9 | 3861 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3862 | { \ |
df7492f9 | 3863 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
3864 | break; \ |
3865 | } \ | |
df7492f9 | 3866 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3867 | { \ |
df7492f9 | 3868 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
3869 | break; \ |
3870 | } \ | |
6e85d753 KH |
3871 | else \ |
3872 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3873 | must invoke it, or, at first, designate it to some graphic \ | |
3874 | register. Then repeat the loop to actually produce the \ | |
3875 | character. */ \ | |
df7492f9 KH |
3876 | dst = encode_invocation_designation (charset, coding, dst, \ |
3877 | &produced_chars); \ | |
4ed46869 KH |
3878 | } while (1) |
3879 | ||
df7492f9 | 3880 | |
f4dee582 RS |
3881 | /* Produce codes for a DIMENSION2 character whose character set is |
3882 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
3883 | invocation codes are also produced in advance if necessary. */ |
3884 | ||
6e85d753 KH |
3885 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
3886 | do { \ | |
df7492f9 | 3887 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3888 | \ |
3889 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3890 | && id == charset_jisx0208) \ | |
3891 | { \ | |
3892 | id = charset_jisx0208_1978; \ | |
3893 | charset = CHARSET_FROM_ID (id); \ | |
3894 | } \ | |
3895 | \ | |
df7492f9 | 3896 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3897 | { \ |
df7492f9 KH |
3898 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3899 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 3900 | else \ |
df7492f9 KH |
3901 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
3902 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3903 | break; \ |
3904 | } \ | |
df7492f9 | 3905 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3906 | { \ |
df7492f9 | 3907 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
3908 | break; \ |
3909 | } \ | |
df7492f9 | 3910 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3911 | { \ |
df7492f9 | 3912 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
3913 | break; \ |
3914 | } \ | |
6e85d753 KH |
3915 | else \ |
3916 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3917 | must invoke it, or, at first, designate it to some graphic \ | |
3918 | register. Then repeat the loop to actually produce the \ | |
3919 | character. */ \ | |
df7492f9 KH |
3920 | dst = encode_invocation_designation (charset, coding, dst, \ |
3921 | &produced_chars); \ | |
4ed46869 KH |
3922 | } while (1) |
3923 | ||
05e6f5dc | 3924 | |
df7492f9 KH |
3925 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
3926 | do { \ | |
3927 | int code = ENCODE_CHAR ((charset),(c)); \ | |
3928 | \ | |
3929 | if (CHARSET_DIMENSION (charset) == 1) \ | |
3930 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
3931 | else \ | |
3932 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 3933 | } while (0) |
bdd9fb48 | 3934 | |
05e6f5dc | 3935 | |
4ed46869 | 3936 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 3937 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
3938 | Return new DST. */ |
3939 | ||
3940 | unsigned char * | |
df7492f9 KH |
3941 | encode_invocation_designation (charset, coding, dst, p_nchars) |
3942 | struct charset *charset; | |
4ed46869 KH |
3943 | struct coding_system *coding; |
3944 | unsigned char *dst; | |
df7492f9 | 3945 | int *p_nchars; |
4ed46869 | 3946 | { |
df7492f9 KH |
3947 | int multibytep = coding->dst_multibyte; |
3948 | int produced_chars = *p_nchars; | |
4ed46869 | 3949 | int reg; /* graphic register number */ |
df7492f9 | 3950 | int id = CHARSET_ID (charset); |
4ed46869 KH |
3951 | |
3952 | /* At first, check designations. */ | |
3953 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 3954 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
3955 | break; |
3956 | ||
3957 | if (reg >= 4) | |
3958 | { | |
3959 | /* CHARSET is not yet designated to any graphic registers. */ | |
3960 | /* At first check the requested designation. */ | |
df7492f9 KH |
3961 | reg = CODING_ISO_REQUEST (coding, id); |
3962 | if (reg < 0) | |
1ba9e4ab KH |
3963 | /* Since CHARSET requests no special designation, designate it |
3964 | to graphic register 0. */ | |
4ed46869 KH |
3965 | reg = 0; |
3966 | ||
3967 | ENCODE_DESIGNATION (charset, reg, coding); | |
3968 | } | |
3969 | ||
df7492f9 KH |
3970 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
3971 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
3972 | { |
3973 | /* Since the graphic register REG is not invoked to any graphic | |
3974 | planes, invoke it to graphic plane 0. */ | |
3975 | switch (reg) | |
3976 | { | |
3977 | case 0: /* graphic register 0 */ | |
3978 | ENCODE_SHIFT_IN; | |
3979 | break; | |
3980 | ||
3981 | case 1: /* graphic register 1 */ | |
3982 | ENCODE_SHIFT_OUT; | |
3983 | break; | |
3984 | ||
3985 | case 2: /* graphic register 2 */ | |
df7492f9 | 3986 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3987 | ENCODE_SINGLE_SHIFT_2; |
3988 | else | |
3989 | ENCODE_LOCKING_SHIFT_2; | |
3990 | break; | |
3991 | ||
3992 | case 3: /* graphic register 3 */ | |
df7492f9 | 3993 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3994 | ENCODE_SINGLE_SHIFT_3; |
3995 | else | |
3996 | ENCODE_LOCKING_SHIFT_3; | |
3997 | break; | |
3998 | } | |
3999 | } | |
b73bfc1c | 4000 | |
df7492f9 | 4001 | *p_nchars = produced_chars; |
4ed46869 KH |
4002 | return dst; |
4003 | } | |
4004 | ||
df7492f9 KH |
4005 | /* The following three macros produce codes for indicating direction |
4006 | of text. */ | |
4007 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 4008 | do { \ |
df7492f9 KH |
4009 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
4010 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 4011 | else \ |
df7492f9 | 4012 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
4013 | } while (0) |
4014 | ||
ec6d2bb8 | 4015 | |
df7492f9 KH |
4016 | #define ENCODE_DIRECTION_R2L() \ |
4017 | do { \ | |
4018 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
4019 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
4020 | } while (0) |
4021 | ||
ec6d2bb8 | 4022 | |
df7492f9 | 4023 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 4024 | do { \ |
df7492f9 KH |
4025 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
4026 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
ec6d2bb8 | 4027 | } while (0) |
4ed46869 | 4028 | |
4ed46869 KH |
4029 | |
4030 | /* Produce codes for designation and invocation to reset the graphic | |
4031 | planes and registers to initial state. */ | |
df7492f9 KH |
4032 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
4033 | do { \ | |
4034 | int reg; \ | |
4035 | struct charset *charset; \ | |
4036 | \ | |
4037 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
4038 | ENCODE_SHIFT_IN; \ | |
4039 | for (reg = 0; reg < 4; reg++) \ | |
4040 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
4041 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
4042 | != CODING_ISO_INITIAL (coding, reg))) \ | |
4043 | { \ | |
4044 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
4045 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
4046 | } \ | |
4ed46869 KH |
4047 | } while (0) |
4048 | ||
df7492f9 | 4049 | |
bdd9fb48 | 4050 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 4051 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
4052 | |
4053 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
4054 | find all the necessary designations. */ |
4055 | ||
b73bfc1c | 4056 | static unsigned char * |
df7492f9 | 4057 | encode_designation_at_bol (coding, charbuf, charbuf_end, dst) |
e0e989f6 | 4058 | struct coding_system *coding; |
df7492f9 KH |
4059 | int *charbuf, *charbuf_end; |
4060 | unsigned char *dst; | |
e0e989f6 | 4061 | { |
df7492f9 | 4062 | struct charset *charset; |
bdd9fb48 KH |
4063 | /* Table of charsets to be designated to each graphic register. */ |
4064 | int r[4]; | |
df7492f9 KH |
4065 | int c, found = 0, reg; |
4066 | int produced_chars = 0; | |
4067 | int multibytep = coding->dst_multibyte; | |
4068 | Lisp_Object attrs; | |
4069 | Lisp_Object charset_list; | |
4070 | ||
4071 | attrs = CODING_ID_ATTRS (coding->id); | |
4072 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
4073 | if (EQ (charset_list, Qiso_2022)) | |
4074 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
4075 | |
4076 | for (reg = 0; reg < 4; reg++) | |
4077 | r[reg] = -1; | |
4078 | ||
b73bfc1c | 4079 | while (found < 4) |
e0e989f6 | 4080 | { |
df7492f9 KH |
4081 | int id; |
4082 | ||
4083 | c = *charbuf++; | |
b73bfc1c KH |
4084 | if (c == '\n') |
4085 | break; | |
df7492f9 KH |
4086 | charset = char_charset (c, charset_list, NULL); |
4087 | id = CHARSET_ID (charset); | |
4088 | reg = CODING_ISO_REQUEST (coding, id); | |
4089 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
4090 | { |
4091 | found++; | |
df7492f9 | 4092 | r[reg] = id; |
bdd9fb48 | 4093 | } |
bdd9fb48 KH |
4094 | } |
4095 | ||
4096 | if (found) | |
4097 | { | |
4098 | for (reg = 0; reg < 4; reg++) | |
4099 | if (r[reg] >= 0 | |
df7492f9 KH |
4100 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
4101 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 4102 | } |
b73bfc1c KH |
4103 | |
4104 | return dst; | |
e0e989f6 KH |
4105 | } |
4106 | ||
4ed46869 KH |
4107 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
4108 | ||
df7492f9 KH |
4109 | static int |
4110 | encode_coding_iso_2022 (coding) | |
4ed46869 | 4111 | struct coding_system *coding; |
4ed46869 | 4112 | { |
df7492f9 KH |
4113 | int multibytep = coding->dst_multibyte; |
4114 | int *charbuf = coding->charbuf; | |
4115 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4116 | unsigned char *dst = coding->destination + coding->produced; | |
4117 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4118 | int safe_room = 16; | |
4119 | int bol_designation | |
4120 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
4121 | && CODING_ISO_BOL (coding)); | |
4122 | int produced_chars = 0; | |
4123 | Lisp_Object attrs, eol_type, charset_list; | |
4124 | int ascii_compatible; | |
b73bfc1c | 4125 | int c; |
ff0dacd7 | 4126 | int preferred_charset_id = -1; |
05e6f5dc | 4127 | |
24a73b0a KH |
4128 | CODING_GET_INFO (coding, attrs, charset_list); |
4129 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
4130 | if (VECTORP (eol_type)) | |
4131 | eol_type = Qunix; | |
4132 | ||
004068e4 | 4133 | setup_iso_safe_charsets (attrs); |
ff0dacd7 | 4134 | /* Charset list may have been changed. */ |
287c57d7 | 4135 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); |
8f924df7 | 4136 | coding->safe_charsets = (char *) SDATA (CODING_ATTR_SAFE_CHARSETS(attrs)); |
0eecad43 | 4137 | |
df7492f9 | 4138 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
bdd9fb48 | 4139 | |
df7492f9 | 4140 | while (charbuf < charbuf_end) |
4ed46869 | 4141 | { |
df7492f9 | 4142 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 4143 | |
df7492f9 | 4144 | if (bol_designation) |
b73bfc1c | 4145 | { |
df7492f9 | 4146 | unsigned char *dst_prev = dst; |
4ed46869 | 4147 | |
bdd9fb48 | 4148 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
4149 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
4150 | bol_designation = 0; | |
4151 | /* We are sure that designation sequences are all ASCII bytes. */ | |
4152 | produced_chars += dst - dst_prev; | |
e0e989f6 KH |
4153 | } |
4154 | ||
df7492f9 | 4155 | c = *charbuf++; |
ec6d2bb8 | 4156 | |
ff0dacd7 KH |
4157 | if (c < 0) |
4158 | { | |
4159 | /* Handle an annotation. */ | |
4160 | switch (*charbuf) | |
ec6d2bb8 | 4161 | { |
ff0dacd7 KH |
4162 | case CODING_ANNOTATE_COMPOSITION_MASK: |
4163 | /* Not yet implemented. */ | |
4164 | break; | |
4165 | case CODING_ANNOTATE_CHARSET_MASK: | |
cf7dfdf5 | 4166 | preferred_charset_id = charbuf[2]; |
ff0dacd7 KH |
4167 | if (preferred_charset_id >= 0 |
4168 | && NILP (Fmemq (make_number (preferred_charset_id), | |
4169 | charset_list))) | |
4170 | preferred_charset_id = -1; | |
4171 | break; | |
4172 | default: | |
4173 | abort (); | |
4ed46869 | 4174 | } |
ff0dacd7 KH |
4175 | charbuf += -c - 1; |
4176 | continue; | |
4ed46869 | 4177 | } |
ec6d2bb8 | 4178 | |
b73bfc1c KH |
4179 | /* Now encode the character C. */ |
4180 | if (c < 0x20 || c == 0x7F) | |
4181 | { | |
df7492f9 KH |
4182 | if (c == '\n' |
4183 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 4184 | { |
df7492f9 KH |
4185 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
4186 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4187 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 4188 | { |
df7492f9 KH |
4189 | int i; |
4190 | ||
4191 | for (i = 0; i < 4; i++) | |
4192 | CODING_ISO_DESIGNATION (coding, i) | |
4193 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 4194 | } |
df7492f9 KH |
4195 | bol_designation |
4196 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 4197 | } |
df7492f9 KH |
4198 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
4199 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4200 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 4201 | } |
df7492f9 | 4202 | else if (ASCII_CHAR_P (c)) |
88993dfd | 4203 | { |
df7492f9 KH |
4204 | if (ascii_compatible) |
4205 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 4206 | else |
19a8d9e0 | 4207 | { |
bf16eb23 KH |
4208 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
4209 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 4210 | } |
4ed46869 | 4211 | } |
16eafb5d | 4212 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 4213 | { |
16eafb5d KH |
4214 | c = CHAR_TO_BYTE8 (c); |
4215 | EMIT_ONE_BYTE (c); | |
88993dfd | 4216 | } |
b73bfc1c | 4217 | else |
df7492f9 | 4218 | { |
ff0dacd7 | 4219 | struct charset *charset; |
b73bfc1c | 4220 | |
ff0dacd7 KH |
4221 | if (preferred_charset_id >= 0) |
4222 | { | |
4223 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
4224 | if (! CHAR_CHARSET_P (c, charset)) | |
4225 | charset = char_charset (c, charset_list, NULL); | |
4226 | } | |
4227 | else | |
4228 | charset = char_charset (c, charset_list, NULL); | |
df7492f9 KH |
4229 | if (!charset) |
4230 | { | |
41cbe562 KH |
4231 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
4232 | { | |
4233 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4234 | charset = CHARSET_FROM_ID (charset_ascii); | |
4235 | } | |
4236 | else | |
4237 | { | |
4238 | c = coding->default_char; | |
4239 | charset = char_charset (c, charset_list, NULL); | |
4240 | } | |
df7492f9 KH |
4241 | } |
4242 | ENCODE_ISO_CHARACTER (charset, c); | |
4243 | } | |
84fbb8a0 | 4244 | } |
b73bfc1c | 4245 | |
df7492f9 KH |
4246 | if (coding->mode & CODING_MODE_LAST_BLOCK |
4247 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
4248 | { | |
4249 | ASSURE_DESTINATION (safe_room); | |
4250 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4251 | } | |
065e3595 | 4252 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4253 | CODING_ISO_BOL (coding) = bol_designation; |
4254 | coding->produced_char += produced_chars; | |
4255 | coding->produced = dst - coding->destination; | |
4256 | return 0; | |
4ed46869 KH |
4257 | } |
4258 | ||
4259 | \f | |
df7492f9 | 4260 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 4261 | |
df7492f9 | 4262 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
4263 | quite widely. So, for the moment, Emacs supports them in the bare |
4264 | C code. But, in the future, they may be supported only by CCL. */ | |
4265 | ||
4266 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
4267 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
4268 | as is. A character of charset katakana-jisx0201 is encoded by | |
4269 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
4270 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 4271 | so that it fit in the range below. |
4ed46869 KH |
4272 | |
4273 | --- CODE RANGE of SJIS --- | |
4274 | (character set) (range) | |
4275 | ASCII 0x00 .. 0x7F | |
df7492f9 | 4276 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 4277 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 4278 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
4279 | ------------------------------- |
4280 | ||
4281 | */ | |
4282 | ||
4283 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
4284 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 4285 | character set and is encoded in two-byte. |
4ed46869 KH |
4286 | |
4287 | --- CODE RANGE of BIG5 --- | |
4288 | (character set) (range) | |
4289 | ASCII 0x00 .. 0x7F | |
4290 | Big5 (1st byte) 0xA1 .. 0xFE | |
4291 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
4292 | -------------------------- | |
4293 | ||
df7492f9 | 4294 | */ |
4ed46869 KH |
4295 | |
4296 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4297 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 4298 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 4299 | |
0a28aafb | 4300 | static int |
ff0dacd7 | 4301 | detect_coding_sjis (coding, detect_info) |
df7492f9 | 4302 | struct coding_system *coding; |
ff0dacd7 | 4303 | struct coding_detection_info *detect_info; |
4ed46869 | 4304 | { |
065e3595 | 4305 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4306 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4307 | int multibytep = coding->src_multibyte; |
4308 | int consumed_chars = 0; | |
4309 | int found = 0; | |
b73bfc1c | 4310 | int c; |
df7492f9 | 4311 | |
ff0dacd7 | 4312 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4313 | /* A coding system of this category is always ASCII compatible. */ |
4314 | src += coding->head_ascii; | |
4ed46869 | 4315 | |
b73bfc1c | 4316 | while (1) |
4ed46869 | 4317 | { |
065e3595 | 4318 | src_base = src; |
df7492f9 | 4319 | ONE_MORE_BYTE (c); |
682169fe KH |
4320 | if (c < 0x80) |
4321 | continue; | |
df7492f9 | 4322 | if ((c >= 0x81 && c <= 0x9F) || (c >= 0xE0 && c <= 0xEF)) |
4ed46869 | 4323 | { |
df7492f9 | 4324 | ONE_MORE_BYTE (c); |
682169fe | 4325 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 4326 | break; |
ff0dacd7 | 4327 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 4328 | } |
df7492f9 | 4329 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 4330 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
4331 | else |
4332 | break; | |
4ed46869 | 4333 | } |
ff0dacd7 | 4334 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4335 | return 0; |
4336 | ||
4337 | no_more_source: | |
065e3595 | 4338 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4339 | { |
ff0dacd7 | 4340 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 4341 | return 0; |
4ed46869 | 4342 | } |
ff0dacd7 KH |
4343 | detect_info->found |= found; |
4344 | return 1; | |
4ed46869 KH |
4345 | } |
4346 | ||
4347 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4348 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 4349 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 4350 | |
0a28aafb | 4351 | static int |
ff0dacd7 | 4352 | detect_coding_big5 (coding, detect_info) |
df7492f9 | 4353 | struct coding_system *coding; |
ff0dacd7 | 4354 | struct coding_detection_info *detect_info; |
4ed46869 | 4355 | { |
065e3595 | 4356 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4357 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4358 | int multibytep = coding->src_multibyte; |
4359 | int consumed_chars = 0; | |
4360 | int found = 0; | |
b73bfc1c | 4361 | int c; |
fa42c37f | 4362 | |
ff0dacd7 | 4363 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4364 | /* A coding system of this category is always ASCII compatible. */ |
4365 | src += coding->head_ascii; | |
fa42c37f | 4366 | |
b73bfc1c | 4367 | while (1) |
fa42c37f | 4368 | { |
065e3595 | 4369 | src_base = src; |
df7492f9 KH |
4370 | ONE_MORE_BYTE (c); |
4371 | if (c < 0x80) | |
fa42c37f | 4372 | continue; |
df7492f9 | 4373 | if (c >= 0xA1) |
fa42c37f | 4374 | { |
df7492f9 KH |
4375 | ONE_MORE_BYTE (c); |
4376 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4377 | return 0; |
ff0dacd7 | 4378 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4379 | } |
df7492f9 KH |
4380 | else |
4381 | break; | |
fa42c37f | 4382 | } |
ff0dacd7 | 4383 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4384 | return 0; |
fa42c37f | 4385 | |
df7492f9 | 4386 | no_more_source: |
065e3595 | 4387 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4388 | { |
ff0dacd7 | 4389 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4390 | return 0; |
4391 | } | |
ff0dacd7 KH |
4392 | detect_info->found |= found; |
4393 | return 1; | |
fa42c37f KH |
4394 | } |
4395 | ||
4ed46869 KH |
4396 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
4397 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
fa42c37f | 4398 | |
b73bfc1c | 4399 | static void |
df7492f9 | 4400 | decode_coding_sjis (coding) |
4ed46869 | 4401 | struct coding_system *coding; |
4ed46869 | 4402 | { |
8f924df7 KH |
4403 | const unsigned char *src = coding->source + coding->consumed; |
4404 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4405 | const unsigned char *src_base; | |
69a80ea3 KH |
4406 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4407 | int *charbuf_end | |
4408 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4409 | int consumed_chars = 0, consumed_chars_base; |
4410 | int multibytep = coding->src_multibyte; | |
4411 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4412 | struct charset *charset_kanji2; |
24a73b0a | 4413 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4414 | int char_offset = coding->produced_char; |
4415 | int last_offset = char_offset; | |
4416 | int last_id = charset_ascii; | |
119852e7 KH |
4417 | int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); |
4418 | int byte_after_cr = -1; | |
a5d301df | 4419 | |
24a73b0a | 4420 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4421 | |
4422 | val = charset_list; | |
4423 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4424 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4425 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4426 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4427 | |
b73bfc1c | 4428 | while (1) |
4ed46869 | 4429 | { |
df7492f9 | 4430 | int c, c1; |
24a73b0a | 4431 | struct charset *charset; |
fa42c37f | 4432 | |
b73bfc1c | 4433 | src_base = src; |
df7492f9 | 4434 | consumed_chars_base = consumed_chars; |
fa42c37f | 4435 | |
df7492f9 | 4436 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
4437 | { |
4438 | if (byte_after_cr >= 0) | |
4439 | src_base--; | |
4440 | break; | |
4441 | } | |
df7492f9 | 4442 | |
119852e7 KH |
4443 | if (byte_after_cr >= 0) |
4444 | c = byte_after_cr, byte_after_cr = -1; | |
4445 | else | |
4446 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4447 | if (c < 0) |
4448 | goto invalid_code; | |
24a73b0a | 4449 | if (c < 0x80) |
119852e7 KH |
4450 | { |
4451 | if (eol_crlf && c == '\r') | |
4452 | ONE_MORE_BYTE (byte_after_cr); | |
4453 | charset = charset_roman; | |
4454 | } | |
57a47f8a | 4455 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4456 | goto invalid_code; |
57a47f8a KH |
4457 | else if (c >= 0xA1 && c <= 0xDF) |
4458 | { | |
4459 | /* SJIS -> JISX0201-Kana */ | |
4460 | c &= 0x7F; | |
4461 | charset = charset_kana; | |
4462 | } | |
4463 | else if (c <= 0xEF) | |
df7492f9 | 4464 | { |
57a47f8a KH |
4465 | /* SJIS -> JISX0208 */ |
4466 | ONE_MORE_BYTE (c1); | |
4467 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4468 | goto invalid_code; |
57a47f8a KH |
4469 | c = (c << 8) | c1; |
4470 | SJIS_TO_JIS (c); | |
4471 | charset = charset_kanji; | |
4472 | } | |
4473 | else if (c <= 0xFC && charset_kanji2) | |
4474 | { | |
c6876370 | 4475 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4476 | ONE_MORE_BYTE (c1); |
4477 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4478 | goto invalid_code; |
57a47f8a KH |
4479 | c = (c << 8) | c1; |
4480 | SJIS_TO_JIS2 (c); | |
4481 | charset = charset_kanji2; | |
df7492f9 | 4482 | } |
57a47f8a KH |
4483 | else |
4484 | goto invalid_code; | |
24a73b0a KH |
4485 | if (charset->id != charset_ascii |
4486 | && last_id != charset->id) | |
4487 | { | |
4488 | if (last_id != charset_ascii) | |
69a80ea3 | 4489 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4490 | last_id = charset->id; |
4491 | last_offset = char_offset; | |
4492 | } | |
4493 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4494 | *charbuf++ = c; |
ff0dacd7 | 4495 | char_offset++; |
df7492f9 | 4496 | continue; |
b73bfc1c | 4497 | |
df7492f9 KH |
4498 | invalid_code: |
4499 | src = src_base; | |
4500 | consumed_chars = consumed_chars_base; | |
4501 | ONE_MORE_BYTE (c); | |
065e3595 | 4502 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4503 | char_offset++; |
df7492f9 KH |
4504 | coding->errors++; |
4505 | } | |
fa42c37f | 4506 | |
df7492f9 | 4507 | no_more_source: |
ff0dacd7 | 4508 | if (last_id != charset_ascii) |
69a80ea3 | 4509 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4510 | coding->consumed_char += consumed_chars_base; |
4511 | coding->consumed = src_base - coding->source; | |
4512 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4513 | } |
4514 | ||
b73bfc1c | 4515 | static void |
df7492f9 | 4516 | decode_coding_big5 (coding) |
4ed46869 | 4517 | struct coding_system *coding; |
4ed46869 | 4518 | { |
8f924df7 KH |
4519 | const unsigned char *src = coding->source + coding->consumed; |
4520 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4521 | const unsigned char *src_base; | |
69a80ea3 KH |
4522 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4523 | int *charbuf_end | |
4524 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4525 | int consumed_chars = 0, consumed_chars_base; |
4526 | int multibytep = coding->src_multibyte; | |
4527 | struct charset *charset_roman, *charset_big5; | |
24a73b0a | 4528 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4529 | int char_offset = coding->produced_char; |
4530 | int last_offset = char_offset; | |
4531 | int last_id = charset_ascii; | |
119852e7 KH |
4532 | int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); |
4533 | int byte_after_cr = -1; | |
df7492f9 | 4534 | |
24a73b0a | 4535 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4536 | val = charset_list; |
4537 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4538 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4539 | |
b73bfc1c | 4540 | while (1) |
4ed46869 | 4541 | { |
df7492f9 | 4542 | int c, c1; |
24a73b0a | 4543 | struct charset *charset; |
b73bfc1c KH |
4544 | |
4545 | src_base = src; | |
df7492f9 KH |
4546 | consumed_chars_base = consumed_chars; |
4547 | ||
4548 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
4549 | { |
4550 | if (byte_after_cr >= 0) | |
4551 | src_base--; | |
4552 | break; | |
4553 | } | |
df7492f9 | 4554 | |
119852e7 | 4555 | if (byte_after_cr >= 0) |
14daee73 | 4556 | c = byte_after_cr, byte_after_cr = -1; |
119852e7 KH |
4557 | else |
4558 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4559 | |
065e3595 KH |
4560 | if (c < 0) |
4561 | goto invalid_code; | |
24a73b0a | 4562 | if (c < 0x80) |
119852e7 | 4563 | { |
14daee73 | 4564 | if (eol_crlf && c == '\r') |
119852e7 KH |
4565 | ONE_MORE_BYTE (byte_after_cr); |
4566 | charset = charset_roman; | |
4567 | } | |
24a73b0a | 4568 | else |
4ed46869 | 4569 | { |
24a73b0a KH |
4570 | /* BIG5 -> Big5 */ |
4571 | if (c < 0xA1 || c > 0xFE) | |
4572 | goto invalid_code; | |
4573 | ONE_MORE_BYTE (c1); | |
4574 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4575 | goto invalid_code; | |
4576 | c = c << 8 | c1; | |
4577 | charset = charset_big5; | |
4ed46869 | 4578 | } |
24a73b0a KH |
4579 | if (charset->id != charset_ascii |
4580 | && last_id != charset->id) | |
df7492f9 | 4581 | { |
24a73b0a | 4582 | if (last_id != charset_ascii) |
69a80ea3 | 4583 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4584 | last_id = charset->id; |
4585 | last_offset = char_offset; | |
4ed46869 | 4586 | } |
24a73b0a | 4587 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4588 | *charbuf++ = c; |
ff0dacd7 | 4589 | char_offset++; |
fb88bf2d KH |
4590 | continue; |
4591 | ||
df7492f9 | 4592 | invalid_code: |
4ed46869 | 4593 | src = src_base; |
df7492f9 KH |
4594 | consumed_chars = consumed_chars_base; |
4595 | ONE_MORE_BYTE (c); | |
065e3595 | 4596 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4597 | char_offset++; |
df7492f9 | 4598 | coding->errors++; |
fb88bf2d | 4599 | } |
d46c5b12 | 4600 | |
df7492f9 | 4601 | no_more_source: |
ff0dacd7 | 4602 | if (last_id != charset_ascii) |
69a80ea3 | 4603 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4604 | coding->consumed_char += consumed_chars_base; |
4605 | coding->consumed = src_base - coding->source; | |
4606 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4607 | } |
4608 | ||
4609 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4610 | This function can encode charsets `ascii', `katakana-jisx0201', |
4611 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4612 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
4613 | (i.e. do not have extended leading-codes). Characters of other |
4614 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
4615 | SJIS text, else encode BIG5 text. */ | |
4616 | ||
df7492f9 KH |
4617 | static int |
4618 | encode_coding_sjis (coding) | |
4ed46869 | 4619 | struct coding_system *coding; |
4ed46869 | 4620 | { |
df7492f9 KH |
4621 | int multibytep = coding->dst_multibyte; |
4622 | int *charbuf = coding->charbuf; | |
4623 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4624 | unsigned char *dst = coding->destination + coding->produced; | |
4625 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4626 | int safe_room = 4; | |
4627 | int produced_chars = 0; | |
24a73b0a | 4628 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4629 | int ascii_compatible; |
4630 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4631 | struct charset *charset_kanji2; |
df7492f9 | 4632 | int c; |
a5d301df | 4633 | |
24a73b0a | 4634 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4635 | val = charset_list; |
4636 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4637 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
57a47f8a KH |
4638 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4639 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4640 | |
df7492f9 | 4641 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4642 | |
df7492f9 KH |
4643 | while (charbuf < charbuf_end) |
4644 | { | |
4645 | ASSURE_DESTINATION (safe_room); | |
4646 | c = *charbuf++; | |
b73bfc1c | 4647 | /* Now encode the character C. */ |
df7492f9 KH |
4648 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4649 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4650 | else if (CHAR_BYTE8_P (c)) |
4651 | { | |
4652 | c = CHAR_TO_BYTE8 (c); | |
4653 | EMIT_ONE_BYTE (c); | |
4654 | } | |
df7492f9 | 4655 | else |
b73bfc1c | 4656 | { |
df7492f9 KH |
4657 | unsigned code; |
4658 | struct charset *charset = char_charset (c, charset_list, &code); | |
4659 | ||
4660 | if (!charset) | |
4ed46869 | 4661 | { |
41cbe562 | 4662 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4663 | { |
41cbe562 KH |
4664 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4665 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4666 | } |
41cbe562 | 4667 | else |
b73bfc1c | 4668 | { |
41cbe562 KH |
4669 | c = coding->default_char; |
4670 | charset = char_charset (c, charset_list, &code); | |
b73bfc1c | 4671 | } |
b73bfc1c | 4672 | } |
df7492f9 KH |
4673 | if (code == CHARSET_INVALID_CODE (charset)) |
4674 | abort (); | |
4675 | if (charset == charset_kanji) | |
4676 | { | |
4677 | int c1, c2; | |
4678 | JIS_TO_SJIS (code); | |
4679 | c1 = code >> 8, c2 = code & 0xFF; | |
4680 | EMIT_TWO_BYTES (c1, c2); | |
4681 | } | |
4682 | else if (charset == charset_kana) | |
4683 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
4684 | else if (charset_kanji2 && charset == charset_kanji2) |
4685 | { | |
4686 | int c1, c2; | |
4687 | ||
4688 | c1 = code >> 8; | |
4689 | if (c1 == 0x21 || (c1 >= 0x23 && c1 < 0x25) | |
4690 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) | |
4691 | { | |
4692 | JIS_TO_SJIS2 (code); | |
4693 | c1 = code >> 8, c2 = code & 0xFF; | |
4694 | EMIT_TWO_BYTES (c1, c2); | |
4695 | } | |
4696 | else | |
4697 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4698 | } | |
df7492f9 KH |
4699 | else |
4700 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4701 | } | |
4702 | } | |
065e3595 | 4703 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4704 | coding->produced_char += produced_chars; |
4705 | coding->produced = dst - coding->destination; | |
4706 | return 0; | |
4707 | } | |
4708 | ||
4709 | static int | |
4710 | encode_coding_big5 (coding) | |
4711 | struct coding_system *coding; | |
4712 | { | |
4713 | int multibytep = coding->dst_multibyte; | |
4714 | int *charbuf = coding->charbuf; | |
4715 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4716 | unsigned char *dst = coding->destination + coding->produced; | |
4717 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4718 | int safe_room = 4; | |
4719 | int produced_chars = 0; | |
24a73b0a | 4720 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4721 | int ascii_compatible; |
4722 | struct charset *charset_roman, *charset_big5; | |
4723 | int c; | |
4724 | ||
24a73b0a | 4725 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4726 | val = charset_list; |
4727 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4728 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4729 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
4730 | ||
4731 | while (charbuf < charbuf_end) | |
4732 | { | |
4733 | ASSURE_DESTINATION (safe_room); | |
4734 | c = *charbuf++; | |
4735 | /* Now encode the character C. */ | |
4736 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
4737 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4738 | else if (CHAR_BYTE8_P (c)) |
4739 | { | |
4740 | c = CHAR_TO_BYTE8 (c); | |
4741 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
4742 | } |
4743 | else | |
4744 | { | |
df7492f9 KH |
4745 | unsigned code; |
4746 | struct charset *charset = char_charset (c, charset_list, &code); | |
4747 | ||
4748 | if (! charset) | |
b73bfc1c | 4749 | { |
41cbe562 | 4750 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4751 | { |
41cbe562 KH |
4752 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4753 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4754 | } |
41cbe562 | 4755 | else |
0eecad43 | 4756 | { |
41cbe562 KH |
4757 | c = coding->default_char; |
4758 | charset = char_charset (c, charset_list, &code); | |
0eecad43 | 4759 | } |
4ed46869 | 4760 | } |
df7492f9 KH |
4761 | if (code == CHARSET_INVALID_CODE (charset)) |
4762 | abort (); | |
4763 | if (charset == charset_big5) | |
b73bfc1c | 4764 | { |
df7492f9 KH |
4765 | int c1, c2; |
4766 | ||
4767 | c1 = code >> 8, c2 = code & 0xFF; | |
4768 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 4769 | } |
df7492f9 KH |
4770 | else |
4771 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 4772 | } |
4ed46869 | 4773 | } |
065e3595 | 4774 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4775 | coding->produced_char += produced_chars; |
4776 | coding->produced = dst - coding->destination; | |
4777 | return 0; | |
4ed46869 KH |
4778 | } |
4779 | ||
4780 | \f | |
df7492f9 | 4781 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
4782 | |
4783 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4784 | Check if a text is encoded in a coding system of which | |
4785 | encoder/decoder are written in CCL program. If it is, return | |
df7492f9 | 4786 | CATEGORY_MASK_CCL, else return 0. */ |
1397dc18 | 4787 | |
0a28aafb | 4788 | static int |
ff0dacd7 | 4789 | detect_coding_ccl (coding, detect_info) |
df7492f9 | 4790 | struct coding_system *coding; |
ff0dacd7 | 4791 | struct coding_detection_info *detect_info; |
1397dc18 | 4792 | { |
065e3595 | 4793 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4794 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4795 | int multibytep = coding->src_multibyte; |
4796 | int consumed_chars = 0; | |
4797 | int found = 0; | |
0e219d54 | 4798 | unsigned char *valids; |
df7492f9 KH |
4799 | int head_ascii = coding->head_ascii; |
4800 | Lisp_Object attrs; | |
4801 | ||
ff0dacd7 KH |
4802 | detect_info->checked |= CATEGORY_MASK_CCL; |
4803 | ||
df7492f9 | 4804 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 4805 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
4806 | attrs = CODING_ID_ATTRS (coding->id); |
4807 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4808 | src += head_ascii; | |
1397dc18 | 4809 | |
b73bfc1c | 4810 | while (1) |
1397dc18 | 4811 | { |
df7492f9 | 4812 | int c; |
065e3595 KH |
4813 | |
4814 | src_base = src; | |
df7492f9 | 4815 | ONE_MORE_BYTE (c); |
065e3595 | 4816 | if (c < 0 || ! valids[c]) |
df7492f9 | 4817 | break; |
ff0dacd7 KH |
4818 | if ((valids[c] > 1)) |
4819 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 4820 | } |
ff0dacd7 | 4821 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
4822 | return 0; |
4823 | ||
4824 | no_more_source: | |
ff0dacd7 KH |
4825 | detect_info->found |= found; |
4826 | return 1; | |
df7492f9 KH |
4827 | } |
4828 | ||
4829 | static void | |
4830 | decode_coding_ccl (coding) | |
4831 | struct coding_system *coding; | |
4832 | { | |
7c78e542 | 4833 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 4834 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
4835 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4836 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
4837 | int consumed_chars = 0; |
4838 | int multibytep = coding->src_multibyte; | |
4839 | struct ccl_program ccl; | |
4840 | int source_charbuf[1024]; | |
4841 | int source_byteidx[1024]; | |
24a73b0a | 4842 | Lisp_Object attrs, charset_list; |
df7492f9 | 4843 | |
24a73b0a | 4844 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4845 | setup_ccl_program (&ccl, CODING_CCL_DECODER (coding)); |
4846 | ||
4847 | while (src < src_end) | |
4848 | { | |
7c78e542 | 4849 | const unsigned char *p = src; |
df7492f9 KH |
4850 | int *source, *source_end; |
4851 | int i = 0; | |
4852 | ||
4853 | if (multibytep) | |
4854 | while (i < 1024 && p < src_end) | |
4855 | { | |
4856 | source_byteidx[i] = p - src; | |
4857 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
4858 | } | |
4859 | else | |
4860 | while (i < 1024 && p < src_end) | |
4861 | source_charbuf[i++] = *p++; | |
8f924df7 | 4862 | |
df7492f9 KH |
4863 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
4864 | ccl.last_block = 1; | |
4865 | ||
4866 | source = source_charbuf; | |
4867 | source_end = source + i; | |
4868 | while (source < source_end) | |
4869 | { | |
4870 | ccl_driver (&ccl, source, charbuf, | |
8dcbea82 KH |
4871 | source_end - source, charbuf_end - charbuf, |
4872 | charset_list); | |
df7492f9 KH |
4873 | source += ccl.consumed; |
4874 | charbuf += ccl.produced; | |
4875 | if (ccl.status != CCL_STAT_SUSPEND_BY_DST) | |
4876 | break; | |
4877 | } | |
4878 | if (source < source_end) | |
4879 | src += source_byteidx[source - source_charbuf]; | |
4880 | else | |
4881 | src = p; | |
4882 | consumed_chars += source - source_charbuf; | |
4883 | ||
4884 | if (ccl.status != CCL_STAT_SUSPEND_BY_SRC | |
4885 | && ccl.status != CODING_RESULT_INSUFFICIENT_SRC) | |
4886 | break; | |
4887 | } | |
4888 | ||
4889 | switch (ccl.status) | |
4890 | { | |
4891 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4892 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4893 | break; |
4894 | case CCL_STAT_SUSPEND_BY_DST: | |
4895 | break; | |
4896 | case CCL_STAT_QUIT: | |
4897 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4898 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4899 | break; |
4900 | default: | |
065e3595 | 4901 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4902 | break; |
4903 | } | |
4904 | coding->consumed_char += consumed_chars; | |
4905 | coding->consumed = src - coding->source; | |
4906 | coding->charbuf_used = charbuf - coding->charbuf; | |
4907 | } | |
4908 | ||
4909 | static int | |
4910 | encode_coding_ccl (coding) | |
4911 | struct coding_system *coding; | |
4912 | { | |
4913 | struct ccl_program ccl; | |
4914 | int multibytep = coding->dst_multibyte; | |
4915 | int *charbuf = coding->charbuf; | |
4916 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4917 | unsigned char *dst = coding->destination + coding->produced; | |
4918 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
df7492f9 KH |
4919 | int destination_charbuf[1024]; |
4920 | int i, produced_chars = 0; | |
24a73b0a | 4921 | Lisp_Object attrs, charset_list; |
df7492f9 | 4922 | |
24a73b0a | 4923 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4924 | setup_ccl_program (&ccl, CODING_CCL_ENCODER (coding)); |
4925 | ||
4926 | ccl.last_block = coding->mode & CODING_MODE_LAST_BLOCK; | |
4927 | ccl.dst_multibyte = coding->dst_multibyte; | |
4928 | ||
8cffd3e7 | 4929 | while (charbuf < charbuf_end) |
df7492f9 | 4930 | { |
df7492f9 | 4931 | ccl_driver (&ccl, charbuf, destination_charbuf, |
8cffd3e7 | 4932 | charbuf_end - charbuf, 1024, charset_list); |
df7492f9 | 4933 | if (multibytep) |
8cffd3e7 KH |
4934 | { |
4935 | ASSURE_DESTINATION (ccl.produced * 2); | |
4936 | for (i = 0; i < ccl.produced; i++) | |
4937 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); | |
4938 | } | |
df7492f9 KH |
4939 | else |
4940 | { | |
8cffd3e7 | 4941 | ASSURE_DESTINATION (ccl.produced); |
3ed051d4 | 4942 | for (i = 0; i < ccl.produced; i++) |
df7492f9 KH |
4943 | *dst++ = destination_charbuf[i] & 0xFF; |
4944 | produced_chars += ccl.produced; | |
4945 | } | |
8cffd3e7 KH |
4946 | charbuf += ccl.consumed; |
4947 | if (ccl.status == CCL_STAT_QUIT | |
4948 | || ccl.status == CCL_STAT_INVALID_CMD) | |
4949 | break; | |
df7492f9 KH |
4950 | } |
4951 | ||
4952 | switch (ccl.status) | |
4953 | { | |
4954 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4955 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4956 | break; |
4957 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 4958 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
4959 | break; |
4960 | case CCL_STAT_QUIT: | |
4961 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4962 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4963 | break; |
4964 | default: | |
065e3595 | 4965 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 4966 | break; |
1397dc18 | 4967 | } |
df7492f9 KH |
4968 | |
4969 | coding->produced_char += produced_chars; | |
4970 | coding->produced = dst - coding->destination; | |
4971 | return 0; | |
1397dc18 KH |
4972 | } |
4973 | ||
df7492f9 | 4974 | |
1397dc18 | 4975 | \f |
df7492f9 | 4976 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 4977 | |
b73bfc1c | 4978 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 4979 | |
b73bfc1c | 4980 | static void |
df7492f9 | 4981 | decode_coding_raw_text (coding) |
4ed46869 | 4982 | struct coding_system *coding; |
4ed46869 | 4983 | { |
119852e7 KH |
4984 | int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); |
4985 | ||
df7492f9 | 4986 | coding->chars_at_source = 1; |
119852e7 KH |
4987 | coding->consumed_char = coding->src_chars; |
4988 | coding->consumed = coding->src_bytes; | |
4989 | if (eol_crlf && coding->source[coding->src_bytes - 1] == '\r') | |
4990 | { | |
4991 | coding->consumed_char--; | |
4992 | coding->consumed--; | |
4993 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
4994 | } | |
4995 | else | |
4996 | record_conversion_result (coding, CODING_RESULT_SUCCESS); | |
df7492f9 | 4997 | } |
4ed46869 | 4998 | |
df7492f9 KH |
4999 | static int |
5000 | encode_coding_raw_text (coding) | |
5001 | struct coding_system *coding; | |
5002 | { | |
5003 | int multibytep = coding->dst_multibyte; | |
5004 | int *charbuf = coding->charbuf; | |
5005 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
5006 | unsigned char *dst = coding->destination + coding->produced; | |
5007 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
a0ed9b27 | 5008 | int produced_chars = 0; |
b73bfc1c KH |
5009 | int c; |
5010 | ||
df7492f9 | 5011 | if (multibytep) |
b73bfc1c | 5012 | { |
df7492f9 | 5013 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 5014 | |
df7492f9 KH |
5015 | if (coding->src_multibyte) |
5016 | while (charbuf < charbuf_end) | |
5017 | { | |
5018 | ASSURE_DESTINATION (safe_room); | |
5019 | c = *charbuf++; | |
5020 | if (ASCII_CHAR_P (c)) | |
5021 | EMIT_ONE_ASCII_BYTE (c); | |
5022 | else if (CHAR_BYTE8_P (c)) | |
5023 | { | |
5024 | c = CHAR_TO_BYTE8 (c); | |
5025 | EMIT_ONE_BYTE (c); | |
5026 | } | |
5027 | else | |
5028 | { | |
5029 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 5030 | |
df7492f9 KH |
5031 | CHAR_STRING_ADVANCE (c, p1); |
5032 | while (p0 < p1) | |
9d123124 KH |
5033 | { |
5034 | EMIT_ONE_BYTE (*p0); | |
5035 | p0++; | |
5036 | } | |
df7492f9 KH |
5037 | } |
5038 | } | |
b73bfc1c | 5039 | else |
df7492f9 KH |
5040 | while (charbuf < charbuf_end) |
5041 | { | |
5042 | ASSURE_DESTINATION (safe_room); | |
5043 | c = *charbuf++; | |
5044 | EMIT_ONE_BYTE (c); | |
5045 | } | |
5046 | } | |
5047 | else | |
4ed46869 | 5048 | { |
df7492f9 | 5049 | if (coding->src_multibyte) |
d46c5b12 | 5050 | { |
df7492f9 KH |
5051 | int safe_room = MAX_MULTIBYTE_LENGTH; |
5052 | ||
5053 | while (charbuf < charbuf_end) | |
d46c5b12 | 5054 | { |
df7492f9 KH |
5055 | ASSURE_DESTINATION (safe_room); |
5056 | c = *charbuf++; | |
5057 | if (ASCII_CHAR_P (c)) | |
5058 | *dst++ = c; | |
5059 | else if (CHAR_BYTE8_P (c)) | |
5060 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 5061 | else |
df7492f9 | 5062 | CHAR_STRING_ADVANCE (c, dst); |
d46c5b12 KH |
5063 | } |
5064 | } | |
df7492f9 KH |
5065 | else |
5066 | { | |
5067 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
5068 | while (charbuf < charbuf_end && dst < dst_end) | |
5069 | *dst++ = *charbuf++; | |
8f924df7 | 5070 | } |
319a3947 | 5071 | produced_chars = dst - (coding->destination + coding->produced); |
4ed46869 | 5072 | } |
065e3595 | 5073 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
a0ed9b27 | 5074 | coding->produced_char += produced_chars; |
df7492f9 KH |
5075 | coding->produced = dst - coding->destination; |
5076 | return 0; | |
4ed46869 KH |
5077 | } |
5078 | ||
ff0dacd7 KH |
5079 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
5080 | Check if a text is encoded in a charset-based coding system. If it | |
5081 | is, return 1, else return 0. */ | |
5082 | ||
0a28aafb | 5083 | static int |
ff0dacd7 | 5084 | detect_coding_charset (coding, detect_info) |
df7492f9 | 5085 | struct coding_system *coding; |
ff0dacd7 | 5086 | struct coding_detection_info *detect_info; |
1397dc18 | 5087 | { |
065e3595 | 5088 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5089 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
5090 | int multibytep = coding->src_multibyte; |
5091 | int consumed_chars = 0; | |
07295713 | 5092 | Lisp_Object attrs, valids, name; |
584948ac | 5093 | int found = 0; |
716b3fa0 | 5094 | int head_ascii = coding->head_ascii; |
07295713 | 5095 | int check_latin_extra = 0; |
1397dc18 | 5096 | |
ff0dacd7 KH |
5097 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
5098 | ||
df7492f9 KH |
5099 | coding = &coding_categories[coding_category_charset]; |
5100 | attrs = CODING_ID_ATTRS (coding->id); | |
5101 | valids = AREF (attrs, coding_attr_charset_valids); | |
07295713 KH |
5102 | name = CODING_ID_NAME (coding->id); |
5103 | if (VECTORP (Vlatin_extra_code_table) | |
5104 | && strcmp ((char *) SDATA (SYMBOL_NAME (name)), "iso-8859-")) | |
5105 | check_latin_extra = 1; | |
df7492f9 | 5106 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
716b3fa0 | 5107 | src += head_ascii; |
1397dc18 | 5108 | |
b73bfc1c | 5109 | while (1) |
1397dc18 | 5110 | { |
df7492f9 | 5111 | int c; |
716b3fa0 KH |
5112 | Lisp_Object val; |
5113 | struct charset *charset; | |
5114 | int dim, idx; | |
1397dc18 | 5115 | |
065e3595 | 5116 | src_base = src; |
df7492f9 | 5117 | ONE_MORE_BYTE (c); |
065e3595 KH |
5118 | if (c < 0) |
5119 | continue; | |
716b3fa0 KH |
5120 | val = AREF (valids, c); |
5121 | if (NILP (val)) | |
df7492f9 | 5122 | break; |
584948ac | 5123 | if (c >= 0x80) |
07295713 KH |
5124 | { |
5125 | if (c < 0xA0 | |
5126 | && check_latin_extra | |
5127 | && NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
5128 | break; | |
5129 | found = CATEGORY_MASK_CHARSET; | |
5130 | } | |
716b3fa0 KH |
5131 | if (INTEGERP (val)) |
5132 | { | |
5133 | charset = CHARSET_FROM_ID (XFASTINT (val)); | |
5134 | dim = CHARSET_DIMENSION (charset); | |
5135 | for (idx = 1; idx < dim; idx++) | |
5136 | { | |
5137 | if (src == src_end) | |
5138 | goto too_short; | |
5139 | ONE_MORE_BYTE (c); | |
3ed051d4 | 5140 | if (c < charset->code_space[(dim - 1 - idx) * 2] |
716b3fa0 KH |
5141 | || c > charset->code_space[(dim - 1 - idx) * 2 + 1]) |
5142 | break; | |
5143 | } | |
5144 | if (idx < dim) | |
5145 | break; | |
5146 | } | |
5147 | else | |
5148 | { | |
5149 | idx = 1; | |
5150 | for (; CONSP (val); val = XCDR (val)) | |
5151 | { | |
5152 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); | |
5153 | dim = CHARSET_DIMENSION (charset); | |
5154 | while (idx < dim) | |
5155 | { | |
5156 | if (src == src_end) | |
5157 | goto too_short; | |
5158 | ONE_MORE_BYTE (c); | |
5159 | if (c < charset->code_space[(dim - 1 - idx) * 4] | |
5160 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
5161 | break; | |
5162 | idx++; | |
5163 | } | |
5164 | if (idx == dim) | |
5165 | { | |
5166 | val = Qnil; | |
5167 | break; | |
5168 | } | |
5169 | } | |
5170 | if (CONSP (val)) | |
5171 | break; | |
5172 | } | |
df7492f9 | 5173 | } |
716b3fa0 | 5174 | too_short: |
ff0dacd7 | 5175 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 5176 | return 0; |
4ed46869 | 5177 | |
df7492f9 | 5178 | no_more_source: |
ff0dacd7 KH |
5179 | detect_info->found |= found; |
5180 | return 1; | |
df7492f9 | 5181 | } |
b73bfc1c | 5182 | |
b73bfc1c | 5183 | static void |
df7492f9 | 5184 | decode_coding_charset (coding) |
4ed46869 | 5185 | struct coding_system *coding; |
4ed46869 | 5186 | { |
8f924df7 KH |
5187 | const unsigned char *src = coding->source + coding->consumed; |
5188 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
5189 | const unsigned char *src_base; | |
69a80ea3 KH |
5190 | int *charbuf = coding->charbuf + coding->charbuf_used; |
5191 | int *charbuf_end | |
5192 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
5193 | int consumed_chars = 0, consumed_chars_base; |
5194 | int multibytep = coding->src_multibyte; | |
24a73b0a | 5195 | Lisp_Object attrs, charset_list, valids; |
ff0dacd7 KH |
5196 | int char_offset = coding->produced_char; |
5197 | int last_offset = char_offset; | |
5198 | int last_id = charset_ascii; | |
119852e7 KH |
5199 | int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); |
5200 | int byte_after_cr = -1; | |
df7492f9 | 5201 | |
24a73b0a | 5202 | CODING_GET_INFO (coding, attrs, charset_list); |
4eb6d3f1 | 5203 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 5204 | |
df7492f9 | 5205 | while (1) |
4ed46869 | 5206 | { |
4eb6d3f1 | 5207 | int c; |
24a73b0a KH |
5208 | Lisp_Object val; |
5209 | struct charset *charset; | |
5210 | int dim; | |
5211 | int len = 1; | |
5212 | unsigned code; | |
df7492f9 KH |
5213 | |
5214 | src_base = src; | |
5215 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 5216 | |
df7492f9 | 5217 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
5218 | { |
5219 | if (byte_after_cr >= 0) | |
5220 | src_base--; | |
5221 | break; | |
5222 | } | |
df7492f9 | 5223 | |
119852e7 KH |
5224 | if (byte_after_cr >= 0) |
5225 | { | |
5226 | c = byte_after_cr; | |
5227 | byte_after_cr = -1; | |
5228 | } | |
5229 | else | |
5230 | { | |
5231 | ONE_MORE_BYTE (c); | |
5232 | if (eol_crlf && c == '\r') | |
5233 | ONE_MORE_BYTE (byte_after_cr); | |
5234 | } | |
065e3595 KH |
5235 | if (c < 0) |
5236 | goto invalid_code; | |
24a73b0a KH |
5237 | code = c; |
5238 | ||
5239 | val = AREF (valids, c); | |
1b17adfd | 5240 | if (! INTEGERP (val) && ! CONSP (val)) |
24a73b0a KH |
5241 | goto invalid_code; |
5242 | if (INTEGERP (val)) | |
d46c5b12 | 5243 | { |
24a73b0a KH |
5244 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
5245 | dim = CHARSET_DIMENSION (charset); | |
5246 | while (len < dim) | |
b73bfc1c | 5247 | { |
24a73b0a KH |
5248 | ONE_MORE_BYTE (c); |
5249 | code = (code << 8) | c; | |
5250 | len++; | |
b73bfc1c | 5251 | } |
24a73b0a KH |
5252 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
5253 | charset, code, c); | |
d46c5b12 | 5254 | } |
df7492f9 | 5255 | else |
d46c5b12 | 5256 | { |
24a73b0a KH |
5257 | /* VAL is a list of charset IDs. It is assured that the |
5258 | list is sorted by charset dimensions (smaller one | |
5259 | comes first). */ | |
5260 | while (CONSP (val)) | |
4eb6d3f1 | 5261 | { |
24a73b0a | 5262 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 5263 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 5264 | while (len < dim) |
4eb6d3f1 | 5265 | { |
acb2a965 KH |
5266 | ONE_MORE_BYTE (c); |
5267 | code = (code << 8) | c; | |
f9d71dcd | 5268 | len++; |
4eb6d3f1 | 5269 | } |
24a73b0a KH |
5270 | CODING_DECODE_CHAR (coding, src, src_base, |
5271 | src_end, charset, code, c); | |
5272 | if (c >= 0) | |
5273 | break; | |
5274 | val = XCDR (val); | |
ff0dacd7 | 5275 | } |
d46c5b12 | 5276 | } |
24a73b0a KH |
5277 | if (c < 0) |
5278 | goto invalid_code; | |
5279 | if (charset->id != charset_ascii | |
5280 | && last_id != charset->id) | |
5281 | { | |
5282 | if (last_id != charset_ascii) | |
69a80ea3 | 5283 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
5284 | last_id = charset->id; |
5285 | last_offset = char_offset; | |
5286 | } | |
5287 | ||
df7492f9 | 5288 | *charbuf++ = c; |
ff0dacd7 | 5289 | char_offset++; |
df7492f9 KH |
5290 | continue; |
5291 | ||
5292 | invalid_code: | |
5293 | src = src_base; | |
5294 | consumed_chars = consumed_chars_base; | |
5295 | ONE_MORE_BYTE (c); | |
065e3595 | 5296 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 5297 | char_offset++; |
df7492f9 | 5298 | coding->errors++; |
4ed46869 KH |
5299 | } |
5300 | ||
df7492f9 | 5301 | no_more_source: |
ff0dacd7 | 5302 | if (last_id != charset_ascii) |
69a80ea3 | 5303 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
5304 | coding->consumed_char += consumed_chars_base; |
5305 | coding->consumed = src_base - coding->source; | |
5306 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
5307 | } |
5308 | ||
df7492f9 KH |
5309 | static int |
5310 | encode_coding_charset (coding) | |
4ed46869 | 5311 | struct coding_system *coding; |
4ed46869 | 5312 | { |
df7492f9 KH |
5313 | int multibytep = coding->dst_multibyte; |
5314 | int *charbuf = coding->charbuf; | |
5315 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5316 | unsigned char *dst = coding->destination + coding->produced; | |
5317 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5318 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
5319 | int produced_chars = 0; | |
24a73b0a | 5320 | Lisp_Object attrs, charset_list; |
df7492f9 | 5321 | int ascii_compatible; |
b73bfc1c | 5322 | int c; |
b73bfc1c | 5323 | |
24a73b0a | 5324 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5325 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 5326 | |
df7492f9 | 5327 | while (charbuf < charbuf_end) |
4ed46869 | 5328 | { |
4eb6d3f1 | 5329 | struct charset *charset; |
df7492f9 | 5330 | unsigned code; |
8f924df7 | 5331 | |
df7492f9 KH |
5332 | ASSURE_DESTINATION (safe_room); |
5333 | c = *charbuf++; | |
5334 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
5335 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 5336 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 5337 | { |
16eafb5d KH |
5338 | c = CHAR_TO_BYTE8 (c); |
5339 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 5340 | } |
d46c5b12 | 5341 | else |
b73bfc1c | 5342 | { |
4eb6d3f1 KH |
5343 | charset = char_charset (c, charset_list, &code); |
5344 | if (charset) | |
5345 | { | |
5346 | if (CHARSET_DIMENSION (charset) == 1) | |
5347 | EMIT_ONE_BYTE (code); | |
5348 | else if (CHARSET_DIMENSION (charset) == 2) | |
5349 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
5350 | else if (CHARSET_DIMENSION (charset) == 3) | |
5351 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
5352 | else | |
5353 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
5354 | (code >> 8) & 0xFF, code & 0xFF); | |
5355 | } | |
5356 | else | |
41cbe562 KH |
5357 | { |
5358 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
5359 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
5360 | else | |
5361 | c = coding->default_char; | |
5362 | EMIT_ONE_BYTE (c); | |
5363 | } | |
4ed46869 | 5364 | } |
4ed46869 KH |
5365 | } |
5366 | ||
065e3595 | 5367 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5368 | coding->produced_char += produced_chars; |
5369 | coding->produced = dst - coding->destination; | |
5370 | return 0; | |
4ed46869 KH |
5371 | } |
5372 | ||
5373 | \f | |
1397dc18 | 5374 | /*** 7. C library functions ***/ |
4ed46869 | 5375 | |
df7492f9 KH |
5376 | /* Setup coding context CODING from information about CODING_SYSTEM. |
5377 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
5378 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 5379 | |
ec6d2bb8 | 5380 | void |
e0e989f6 KH |
5381 | setup_coding_system (coding_system, coding) |
5382 | Lisp_Object coding_system; | |
4ed46869 KH |
5383 | struct coding_system *coding; |
5384 | { | |
df7492f9 KH |
5385 | Lisp_Object attrs; |
5386 | Lisp_Object eol_type; | |
5387 | Lisp_Object coding_type; | |
4608c386 | 5388 | Lisp_Object val; |
4ed46869 | 5389 | |
df7492f9 | 5390 | if (NILP (coding_system)) |
ae6f73fa | 5391 | coding_system = Qundecided; |
c07c8e12 | 5392 | |
df7492f9 | 5393 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 5394 | |
df7492f9 KH |
5395 | attrs = CODING_ID_ATTRS (coding->id); |
5396 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
1f5dbf34 | 5397 | |
df7492f9 KH |
5398 | coding->mode = 0; |
5399 | coding->head_ascii = -1; | |
4a015c45 KH |
5400 | if (VECTORP (eol_type)) |
5401 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5402 | | CODING_REQUIRE_DETECTION_MASK); | |
5403 | else if (! EQ (eol_type, Qunix)) | |
5404 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5405 | | CODING_REQUIRE_ENCODING_MASK); | |
5406 | else | |
5407 | coding->common_flags = 0; | |
5e5c78be KH |
5408 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
5409 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5410 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
5411 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
5412 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
5413 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 5414 | |
df7492f9 | 5415 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 KH |
5416 | coding->max_charset_id = SCHARS (val) - 1; |
5417 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 | 5418 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
4608c386 | 5419 | |
df7492f9 KH |
5420 | coding_type = CODING_ATTR_TYPE (attrs); |
5421 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 5422 | { |
df7492f9 KH |
5423 | coding->detector = NULL; |
5424 | coding->decoder = decode_coding_raw_text; | |
5425 | coding->encoder = encode_coding_raw_text; | |
5426 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5427 | } |
df7492f9 | 5428 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 5429 | { |
df7492f9 KH |
5430 | int i; |
5431 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5432 | ||
5433 | /* Invoke graphic register 0 to plane 0. */ | |
5434 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
5435 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
5436 | CODING_ISO_INVOCATION (coding, 1) | |
5437 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
5438 | /* Setup the initial status of designation. */ | |
5439 | for (i = 0; i < 4; i++) | |
5440 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
5441 | /* Not single shifting initially. */ | |
5442 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
5443 | /* Beginning of buffer should also be regarded as bol. */ | |
5444 | CODING_ISO_BOL (coding) = 1; | |
5445 | coding->detector = detect_coding_iso_2022; | |
5446 | coding->decoder = decode_coding_iso_2022; | |
5447 | coding->encoder = encode_coding_iso_2022; | |
5448 | if (flags & CODING_ISO_FLAG_SAFE) | |
5449 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 5450 | coding->common_flags |
df7492f9 KH |
5451 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5452 | | CODING_REQUIRE_FLUSHING_MASK); | |
5453 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
5454 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
5455 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
5456 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
5457 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
5458 | { | |
5459 | setup_iso_safe_charsets (attrs); | |
5460 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
5461 | coding->max_charset_id = SCHARS (val) - 1; |
5462 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
5463 | } |
5464 | CODING_ISO_FLAGS (coding) = flags; | |
d46c5b12 | 5465 | } |
df7492f9 | 5466 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 5467 | { |
df7492f9 KH |
5468 | coding->detector = detect_coding_charset; |
5469 | coding->decoder = decode_coding_charset; | |
5470 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5471 | coding->common_flags |
df7492f9 | 5472 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5473 | } |
df7492f9 | 5474 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5475 | { |
a470d443 KH |
5476 | val = AREF (attrs, coding_attr_utf_bom); |
5477 | CODING_UTF_8_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5478 | : EQ (val, Qt) ? utf_with_bom | |
5479 | : utf_without_bom); | |
df7492f9 KH |
5480 | coding->detector = detect_coding_utf_8; |
5481 | coding->decoder = decode_coding_utf_8; | |
5482 | coding->encoder = encode_coding_utf_8; | |
5483 | coding->common_flags | |
5484 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 KH |
5485 | if (CODING_UTF_8_BOM (coding) == utf_detect_bom) |
5486 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
df7492f9 KH |
5487 | } |
5488 | else if (EQ (coding_type, Qutf_16)) | |
5489 | { | |
a470d443 KH |
5490 | val = AREF (attrs, coding_attr_utf_bom); |
5491 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5492 | : EQ (val, Qt) ? utf_with_bom | |
5493 | : utf_without_bom); | |
df7492f9 | 5494 | val = AREF (attrs, coding_attr_utf_16_endian); |
b49a1807 | 5495 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5496 | : utf_16_little_endian); |
e19c3639 | 5497 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5498 | coding->detector = detect_coding_utf_16; |
5499 | coding->decoder = decode_coding_utf_16; | |
5500 | coding->encoder = encode_coding_utf_16; | |
5501 | coding->common_flags | |
5502 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 | 5503 | if (CODING_UTF_16_BOM (coding) == utf_detect_bom) |
b49a1807 | 5504 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; |
d46c5b12 | 5505 | } |
df7492f9 | 5506 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5507 | { |
df7492f9 KH |
5508 | coding->detector = detect_coding_ccl; |
5509 | coding->decoder = decode_coding_ccl; | |
5510 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5511 | coding->common_flags |
df7492f9 KH |
5512 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5513 | | CODING_REQUIRE_FLUSHING_MASK); | |
5514 | } | |
5515 | else if (EQ (coding_type, Qemacs_mule)) | |
5516 | { | |
5517 | coding->detector = detect_coding_emacs_mule; | |
5518 | coding->decoder = decode_coding_emacs_mule; | |
5519 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5520 | coding->common_flags |
df7492f9 KH |
5521 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5522 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
5523 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5524 | { | |
5525 | Lisp_Object tail, safe_charsets; | |
5526 | int max_charset_id = 0; | |
5527 | ||
5528 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5529 | tail = XCDR (tail)) | |
5530 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5531 | max_charset_id = XFASTINT (XCAR (tail)); | |
5532 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), | |
5533 | make_number (255)); | |
5534 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5535 | tail = XCDR (tail)) | |
8f924df7 | 5536 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5537 | coding->max_charset_id = max_charset_id; |
8f924df7 | 5538 | coding->safe_charsets = (char *) SDATA (safe_charsets); |
df7492f9 KH |
5539 | } |
5540 | } | |
5541 | else if (EQ (coding_type, Qshift_jis)) | |
5542 | { | |
5543 | coding->detector = detect_coding_sjis; | |
5544 | coding->decoder = decode_coding_sjis; | |
5545 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5546 | coding->common_flags |
df7492f9 KH |
5547 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5548 | } | |
5549 | else if (EQ (coding_type, Qbig5)) | |
5550 | { | |
5551 | coding->detector = detect_coding_big5; | |
5552 | coding->decoder = decode_coding_big5; | |
5553 | coding->encoder = encode_coding_big5; | |
c952af22 | 5554 | coding->common_flags |
df7492f9 KH |
5555 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5556 | } | |
5557 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5558 | { |
df7492f9 KH |
5559 | coding->detector = NULL; |
5560 | coding->decoder = decode_coding_raw_text; | |
5561 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5562 | if (! EQ (eol_type, Qunix)) |
5563 | { | |
5564 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5565 | if (! VECTORP (eol_type)) | |
5566 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5567 | } | |
5568 | ||
4ed46869 | 5569 | } |
4ed46869 | 5570 | |
df7492f9 | 5571 | return; |
4ed46869 KH |
5572 | } |
5573 | ||
0ff61e78 KH |
5574 | /* Return a list of charsets supported by CODING. */ |
5575 | ||
5576 | Lisp_Object | |
5577 | coding_charset_list (coding) | |
5578 | struct coding_system *coding; | |
5579 | { | |
35befdaa | 5580 | Lisp_Object attrs, charset_list; |
0ff61e78 KH |
5581 | |
5582 | CODING_GET_INFO (coding, attrs, charset_list); | |
5583 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5584 | { | |
5585 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5586 | ||
5587 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5588 | charset_list = Viso_2022_charset_list; | |
5589 | } | |
5590 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5591 | { | |
5592 | charset_list = Vemacs_mule_charset_list; | |
5593 | } | |
5594 | return charset_list; | |
5595 | } | |
5596 | ||
5597 | ||
df7492f9 KH |
5598 | /* Return raw-text or one of its subsidiaries that has the same |
5599 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5600 | |
df7492f9 KH |
5601 | Lisp_Object |
5602 | raw_text_coding_system (coding_system) | |
5603 | Lisp_Object coding_system; | |
ec6d2bb8 | 5604 | { |
0be8721c | 5605 | Lisp_Object spec, attrs; |
df7492f9 | 5606 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5607 | |
d3e4cb56 KH |
5608 | if (NILP (coding_system)) |
5609 | return Qraw_text; | |
df7492f9 KH |
5610 | spec = CODING_SYSTEM_SPEC (coding_system); |
5611 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5612 | |
df7492f9 KH |
5613 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5614 | return coding_system; | |
ec6d2bb8 | 5615 | |
df7492f9 KH |
5616 | eol_type = AREF (spec, 2); |
5617 | if (VECTORP (eol_type)) | |
5618 | return Qraw_text; | |
5619 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5620 | raw_text_eol_type = AREF (spec, 2); | |
5621 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5622 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5623 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5624 | } |
5625 | ||
54f78171 | 5626 | |
df7492f9 KH |
5627 | /* If CODING_SYSTEM doesn't specify end-of-line format but PARENT |
5628 | does, return one of the subsidiary that has the same eol-spec as | |
fcbcfb64 KH |
5629 | PARENT. Otherwise, return CODING_SYSTEM. If PARENT is nil, |
5630 | inherit end-of-line format from the system's setting | |
5631 | (system_eol_type). */ | |
df7492f9 KH |
5632 | |
5633 | Lisp_Object | |
5634 | coding_inherit_eol_type (coding_system, parent) | |
b74e4686 | 5635 | Lisp_Object coding_system, parent; |
54f78171 | 5636 | { |
3e139625 | 5637 | Lisp_Object spec, eol_type; |
54f78171 | 5638 | |
d3e4cb56 KH |
5639 | if (NILP (coding_system)) |
5640 | coding_system = Qraw_text; | |
df7492f9 | 5641 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5642 | eol_type = AREF (spec, 2); |
fcbcfb64 | 5643 | if (VECTORP (eol_type)) |
df7492f9 | 5644 | { |
df7492f9 KH |
5645 | Lisp_Object parent_eol_type; |
5646 | ||
fcbcfb64 KH |
5647 | if (! NILP (parent)) |
5648 | { | |
5649 | Lisp_Object parent_spec; | |
5650 | ||
4a015c45 | 5651 | parent_spec = CODING_SYSTEM_SPEC (parent); |
fcbcfb64 KH |
5652 | parent_eol_type = AREF (parent_spec, 2); |
5653 | } | |
5654 | else | |
5655 | parent_eol_type = system_eol_type; | |
df7492f9 KH |
5656 | if (EQ (parent_eol_type, Qunix)) |
5657 | coding_system = AREF (eol_type, 0); | |
5658 | else if (EQ (parent_eol_type, Qdos)) | |
5659 | coding_system = AREF (eol_type, 1); | |
5660 | else if (EQ (parent_eol_type, Qmac)) | |
5661 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5662 | } |
df7492f9 | 5663 | return coding_system; |
54f78171 KH |
5664 | } |
5665 | ||
4ed46869 KH |
5666 | /* Emacs has a mechanism to automatically detect a coding system if it |
5667 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
5668 | it's impossible to distinguish some coding systems accurately | |
5669 | because they use the same range of codes. So, at first, coding | |
5670 | systems are categorized into 7, those are: | |
5671 | ||
0ef69138 | 5672 | o coding-category-emacs-mule |
4ed46869 KH |
5673 | |
5674 | The category for a coding system which has the same code range | |
5675 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 5676 | symbol) `emacs-mule' by default. |
4ed46869 KH |
5677 | |
5678 | o coding-category-sjis | |
5679 | ||
5680 | The category for a coding system which has the same code range | |
5681 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 5682 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
5683 | |
5684 | o coding-category-iso-7 | |
5685 | ||
5686 | The category for a coding system which has the same code range | |
7717c392 | 5687 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
5688 | shift and single shift functions. This can encode/decode all |
5689 | charsets. Assigned the coding-system (Lisp symbol) | |
5690 | `iso-2022-7bit' by default. | |
5691 | ||
5692 | o coding-category-iso-7-tight | |
5693 | ||
5694 | Same as coding-category-iso-7 except that this can | |
5695 | encode/decode only the specified charsets. | |
4ed46869 KH |
5696 | |
5697 | o coding-category-iso-8-1 | |
5698 | ||
5699 | The category for a coding system which has the same code range | |
5700 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5701 | for DIMENSION1 charset. This doesn't use any locking shift |
5702 | and single shift functions. Assigned the coding-system (Lisp | |
5703 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
5704 | |
5705 | o coding-category-iso-8-2 | |
5706 | ||
5707 | The category for a coding system which has the same code range | |
5708 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5709 | for DIMENSION2 charset. This doesn't use any locking shift |
5710 | and single shift functions. Assigned the coding-system (Lisp | |
5711 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 5712 | |
7717c392 | 5713 | o coding-category-iso-7-else |
4ed46869 KH |
5714 | |
5715 | The category for a coding system which has the same code range | |
df7492f9 | 5716 | as ISO2022 of 7-bit environemnt but uses locking shift or |
7717c392 KH |
5717 | single shift functions. Assigned the coding-system (Lisp |
5718 | symbol) `iso-2022-7bit-lock' by default. | |
5719 | ||
5720 | o coding-category-iso-8-else | |
5721 | ||
5722 | The category for a coding system which has the same code range | |
df7492f9 | 5723 | as ISO2022 of 8-bit environemnt but uses locking shift or |
7717c392 KH |
5724 | single shift functions. Assigned the coding-system (Lisp |
5725 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
5726 | |
5727 | o coding-category-big5 | |
5728 | ||
5729 | The category for a coding system which has the same code range | |
5730 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5731 | `cn-big5' by default. |
4ed46869 | 5732 | |
fa42c37f KH |
5733 | o coding-category-utf-8 |
5734 | ||
5735 | The category for a coding system which has the same code range | |
6e76ae91 | 5736 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
5737 | symbol) `utf-8' by default. |
5738 | ||
5739 | o coding-category-utf-16-be | |
5740 | ||
5741 | The category for a coding system in which a text has an | |
5742 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
5743 | endian at the head. Assigned the coding-system (Lisp symbol) | |
5744 | `utf-16-be' by default. | |
5745 | ||
5746 | o coding-category-utf-16-le | |
5747 | ||
5748 | The category for a coding system in which a text has an | |
5749 | Unicode signature (cf. Unicode Standard) in the order of | |
5750 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
5751 | symbol) `utf-16-le' by default. | |
5752 | ||
1397dc18 KH |
5753 | o coding-category-ccl |
5754 | ||
5755 | The category for a coding system of which encoder/decoder is | |
5756 | written in CCL programs. The default value is nil, i.e., no | |
5757 | coding system is assigned. | |
5758 | ||
4ed46869 KH |
5759 | o coding-category-binary |
5760 | ||
5761 | The category for a coding system not categorized in any of the | |
5762 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5763 | `no-conversion' by default. |
4ed46869 KH |
5764 | |
5765 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 5766 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
5767 | What Emacs does actually is to detect a category of coding system. |
5768 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 5769 | decide only one possible category, it selects a category of the |
4ed46869 KH |
5770 | highest priority. Priorities of categories are also specified by a |
5771 | user in a Lisp variable `coding-category-list'. | |
5772 | ||
5773 | */ | |
5774 | ||
df7492f9 KH |
5775 | #define EOL_SEEN_NONE 0 |
5776 | #define EOL_SEEN_LF 1 | |
5777 | #define EOL_SEEN_CR 2 | |
5778 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 5779 | |
ff0dacd7 KH |
5780 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
5781 | SOURCE is encoded. If CATEGORY is one of | |
5782 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
5783 | two-byte, else they are encoded by one-byte. | |
5784 | ||
5785 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 5786 | |
bc4bc72a | 5787 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
5788 | |
5789 | static int | |
89528eb3 | 5790 | detect_eol (source, src_bytes, category) |
f6cbaf43 | 5791 | const unsigned char *source; |
df7492f9 | 5792 | EMACS_INT src_bytes; |
89528eb3 | 5793 | enum coding_category category; |
4ed46869 | 5794 | { |
f6cbaf43 | 5795 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 5796 | unsigned char c; |
df7492f9 KH |
5797 | int total = 0; |
5798 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 5799 | |
89528eb3 | 5800 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 5801 | { |
df7492f9 | 5802 | int msb, lsb; |
fa42c37f | 5803 | |
89528eb3 KH |
5804 | msb = category == (coding_category_utf_16_le |
5805 | | coding_category_utf_16_le_nosig); | |
df7492f9 | 5806 | lsb = 1 - msb; |
fa42c37f | 5807 | |
df7492f9 | 5808 | while (src + 1 < src_end) |
fa42c37f | 5809 | { |
df7492f9 KH |
5810 | c = src[lsb]; |
5811 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 5812 | { |
df7492f9 KH |
5813 | int this_eol; |
5814 | ||
5815 | if (c == '\n') | |
5816 | this_eol = EOL_SEEN_LF; | |
5817 | else if (src + 3 >= src_end | |
5818 | || src[msb + 2] != 0 | |
5819 | || src[lsb + 2] != '\n') | |
5820 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 5821 | else |
8f924df7 | 5822 | this_eol = EOL_SEEN_CRLF; |
df7492f9 KH |
5823 | |
5824 | if (eol_seen == EOL_SEEN_NONE) | |
5825 | /* This is the first end-of-line. */ | |
5826 | eol_seen = this_eol; | |
5827 | else if (eol_seen != this_eol) | |
fa42c37f | 5828 | { |
df7492f9 KH |
5829 | /* The found type is different from what found before. */ |
5830 | eol_seen = EOL_SEEN_LF; | |
5831 | break; | |
fa42c37f | 5832 | } |
df7492f9 KH |
5833 | if (++total == MAX_EOL_CHECK_COUNT) |
5834 | break; | |
fa42c37f | 5835 | } |
df7492f9 | 5836 | src += 2; |
fa42c37f | 5837 | } |
bcf26d6a | 5838 | } |
d46c5b12 | 5839 | else |
c4825358 | 5840 | { |
df7492f9 | 5841 | while (src < src_end) |
27901516 | 5842 | { |
df7492f9 KH |
5843 | c = *src++; |
5844 | if (c == '\n' || c == '\r') | |
5845 | { | |
5846 | int this_eol; | |
d46c5b12 | 5847 | |
df7492f9 KH |
5848 | if (c == '\n') |
5849 | this_eol = EOL_SEEN_LF; | |
5850 | else if (src >= src_end || *src != '\n') | |
5851 | this_eol = EOL_SEEN_CR; | |
5852 | else | |
5853 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 5854 | |
df7492f9 KH |
5855 | if (eol_seen == EOL_SEEN_NONE) |
5856 | /* This is the first end-of-line. */ | |
5857 | eol_seen = this_eol; | |
5858 | else if (eol_seen != this_eol) | |
5859 | { | |
5860 | /* The found type is different from what found before. */ | |
5861 | eol_seen = EOL_SEEN_LF; | |
5862 | break; | |
5863 | } | |
5864 | if (++total == MAX_EOL_CHECK_COUNT) | |
5865 | break; | |
5866 | } | |
5867 | } | |
73be902c | 5868 | } |
df7492f9 | 5869 | return eol_seen; |
73be902c KH |
5870 | } |
5871 | ||
df7492f9 | 5872 | |
24a73b0a | 5873 | static Lisp_Object |
df7492f9 KH |
5874 | adjust_coding_eol_type (coding, eol_seen) |
5875 | struct coding_system *coding; | |
5876 | int eol_seen; | |
73be902c | 5877 | { |
0be8721c | 5878 | Lisp_Object eol_type; |
8f924df7 | 5879 | |
df7492f9 KH |
5880 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
5881 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
5882 | { |
5883 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
5884 | eol_type = Qunix; | |
5885 | } | |
6f197c07 | 5886 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
5887 | { |
5888 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
5889 | eol_type = Qdos; | |
5890 | } | |
6f197c07 | 5891 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
5892 | { |
5893 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
5894 | eol_type = Qmac; | |
5895 | } | |
5896 | return eol_type; | |
d46c5b12 | 5897 | } |
4ed46869 | 5898 | |
df7492f9 KH |
5899 | /* Detect how a text specified in CODING is encoded. If a coding |
5900 | system is detected, update fields of CODING by the detected coding | |
5901 | system. */ | |
0a28aafb | 5902 | |
df7492f9 KH |
5903 | void |
5904 | detect_coding (coding) | |
d46c5b12 | 5905 | struct coding_system *coding; |
d46c5b12 | 5906 | { |
8f924df7 | 5907 | const unsigned char *src, *src_end; |
d46c5b12 | 5908 | |
df7492f9 KH |
5909 | coding->consumed = coding->consumed_char = 0; |
5910 | coding->produced = coding->produced_char = 0; | |
5911 | coding_set_source (coding); | |
1c3478b0 | 5912 | |
df7492f9 | 5913 | src_end = coding->source + coding->src_bytes; |
c0e16b14 | 5914 | coding->head_ascii = 0; |
1c3478b0 | 5915 | |
df7492f9 KH |
5916 | /* If we have not yet decided the text encoding type, detect it |
5917 | now. */ | |
5918 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 5919 | { |
df7492f9 | 5920 | int c, i; |
6cb21a4f | 5921 | struct coding_detection_info detect_info; |
2f3cbb32 | 5922 | int null_byte_found = 0, eight_bit_found = 0; |
df7492f9 | 5923 | |
6cb21a4f | 5924 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
2f3cbb32 | 5925 | for (src = coding->source; src < src_end; src++) |
d46c5b12 | 5926 | { |
df7492f9 | 5927 | c = *src; |
6cb21a4f | 5928 | if (c & 0x80) |
6cb21a4f | 5929 | { |
2f3cbb32 | 5930 | eight_bit_found = 1; |
2f3cbb32 KH |
5931 | if (null_byte_found) |
5932 | break; | |
5933 | } | |
5934 | else if (c < 0x20) | |
5935 | { | |
5936 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
5937 | && ! inhibit_iso_escape_detection | |
5938 | && ! detect_info.checked) | |
6cb21a4f | 5939 | { |
2f3cbb32 KH |
5940 | if (detect_coding_iso_2022 (coding, &detect_info)) |
5941 | { | |
5942 | /* We have scanned the whole data. */ | |
5943 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
5944 | { |
5945 | /* We didn't find an 8-bit code. We may | |
5946 | have found a null-byte, but it's very | |
5947 | rare that a binary file confirm to | |
5948 | ISO-2022. */ | |
5949 | src = src_end; | |
5950 | coding->head_ascii = src - coding->source; | |
5951 | } | |
5952 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
5953 | break; |
5954 | } | |
5955 | } | |
97b1b294 | 5956 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
5957 | { |
5958 | null_byte_found = 1; | |
5959 | if (eight_bit_found) | |
5960 | break; | |
6cb21a4f | 5961 | } |
c006c0c8 KH |
5962 | if (! eight_bit_found) |
5963 | coding->head_ascii++; | |
6cb21a4f | 5964 | } |
c006c0c8 | 5965 | else if (! eight_bit_found) |
c0e16b14 | 5966 | coding->head_ascii++; |
d46c5b12 | 5967 | } |
df7492f9 | 5968 | |
2f3cbb32 KH |
5969 | if (null_byte_found || eight_bit_found |
5970 | || coding->head_ascii < coding->src_bytes | |
6cb21a4f | 5971 | || detect_info.found) |
d46c5b12 | 5972 | { |
ff0dacd7 KH |
5973 | enum coding_category category; |
5974 | struct coding_system *this; | |
df7492f9 | 5975 | |
6cb21a4f KH |
5976 | if (coding->head_ascii == coding->src_bytes) |
5977 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
5978 | for (i = 0; i < coding_category_raw_text; i++) | |
5979 | { | |
5980 | category = coding_priorities[i]; | |
5981 | this = coding_categories + category; | |
5982 | if (detect_info.found & (1 << category)) | |
24a73b0a | 5983 | break; |
6cb21a4f KH |
5984 | } |
5985 | else | |
2f3cbb32 KH |
5986 | { |
5987 | if (null_byte_found) | |
ff0dacd7 | 5988 | { |
2f3cbb32 KH |
5989 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; |
5990 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
ff0dacd7 | 5991 | } |
2f3cbb32 KH |
5992 | for (i = 0; i < coding_category_raw_text; i++) |
5993 | { | |
5994 | category = coding_priorities[i]; | |
5995 | this = coding_categories + category; | |
5996 | if (this->id < 0) | |
5997 | { | |
5998 | /* No coding system of this category is defined. */ | |
5999 | detect_info.rejected |= (1 << category); | |
6000 | } | |
6001 | else if (category >= coding_category_raw_text) | |
6002 | continue; | |
6003 | else if (detect_info.checked & (1 << category)) | |
6004 | { | |
6005 | if (detect_info.found & (1 << category)) | |
6006 | break; | |
6007 | } | |
6008 | else if ((*(this->detector)) (coding, &detect_info) | |
6009 | && detect_info.found & (1 << category)) | |
6010 | { | |
6011 | if (category == coding_category_utf_16_auto) | |
6012 | { | |
6013 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6014 | category = coding_category_utf_16_le; | |
6015 | else | |
6016 | category = coding_category_utf_16_be; | |
6017 | } | |
6018 | break; | |
6019 | } | |
6020 | } | |
2f3cbb32 | 6021 | } |
c0e16b14 KH |
6022 | |
6023 | if (i < coding_category_raw_text) | |
6024 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6025 | else if (null_byte_found) | |
6026 | setup_coding_system (Qno_conversion, coding); | |
6027 | else if ((detect_info.rejected & CATEGORY_MASK_ANY) | |
6028 | == CATEGORY_MASK_ANY) | |
6029 | setup_coding_system (Qraw_text, coding); | |
6030 | else if (detect_info.rejected) | |
6031 | for (i = 0; i < coding_category_raw_text; i++) | |
6032 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
6033 | { | |
6034 | this = coding_categories + coding_priorities[i]; | |
6035 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6036 | break; | |
6037 | } | |
d46c5b12 | 6038 | } |
b73bfc1c | 6039 | } |
a470d443 KH |
6040 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6041 | == coding_category_utf_8_auto) | |
6042 | { | |
6043 | Lisp_Object coding_systems; | |
6044 | struct coding_detection_info detect_info; | |
6045 | ||
6046 | coding_systems | |
6047 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); | |
6048 | detect_info.found = detect_info.rejected = 0; | |
6049 | coding->head_ascii = 0; | |
6050 | if (CONSP (coding_systems) | |
6051 | && detect_coding_utf_8 (coding, &detect_info)) | |
6052 | { | |
6053 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
6054 | setup_coding_system (XCAR (coding_systems), coding); | |
6055 | else | |
6056 | setup_coding_system (XCDR (coding_systems), coding); | |
6057 | } | |
6058 | } | |
24a73b0a KH |
6059 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6060 | == coding_category_utf_16_auto) | |
b49a1807 KH |
6061 | { |
6062 | Lisp_Object coding_systems; | |
6063 | struct coding_detection_info detect_info; | |
6064 | ||
6065 | coding_systems | |
a470d443 | 6066 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); |
b49a1807 | 6067 | detect_info.found = detect_info.rejected = 0; |
a470d443 | 6068 | coding->head_ascii = 0; |
b49a1807 | 6069 | if (CONSP (coding_systems) |
24a73b0a | 6070 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
6071 | { |
6072 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6073 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 6074 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
6075 | setup_coding_system (XCDR (coding_systems), coding); |
6076 | } | |
6077 | } | |
4ed46869 | 6078 | } |
4ed46869 | 6079 | |
d46c5b12 | 6080 | |
aaaf0b1e | 6081 | static void |
df7492f9 | 6082 | decode_eol (coding) |
aaaf0b1e | 6083 | struct coding_system *coding; |
aaaf0b1e | 6084 | { |
24a73b0a KH |
6085 | Lisp_Object eol_type; |
6086 | unsigned char *p, *pbeg, *pend; | |
3ed051d4 | 6087 | |
24a73b0a KH |
6088 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6089 | if (EQ (eol_type, Qunix)) | |
6090 | return; | |
6091 | ||
6092 | if (NILP (coding->dst_object)) | |
6093 | pbeg = coding->destination; | |
6094 | else | |
6095 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
6096 | pend = pbeg + coding->produced; | |
6097 | ||
6098 | if (VECTORP (eol_type)) | |
aaaf0b1e | 6099 | { |
df7492f9 | 6100 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 6101 | |
24a73b0a | 6102 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 6103 | { |
df7492f9 KH |
6104 | if (*p == '\n') |
6105 | eol_seen |= EOL_SEEN_LF; | |
6106 | else if (*p == '\r') | |
aaaf0b1e | 6107 | { |
df7492f9 | 6108 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 6109 | { |
df7492f9 KH |
6110 | eol_seen |= EOL_SEEN_CRLF; |
6111 | p++; | |
aaaf0b1e | 6112 | } |
aaaf0b1e | 6113 | else |
df7492f9 | 6114 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 6115 | } |
aaaf0b1e | 6116 | } |
24a73b0a KH |
6117 | if (eol_seen != EOL_SEEN_NONE |
6118 | && eol_seen != EOL_SEEN_LF | |
6119 | && eol_seen != EOL_SEEN_CRLF | |
6120 | && eol_seen != EOL_SEEN_CR) | |
6121 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 6122 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 6123 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 6124 | } |
d46c5b12 | 6125 | |
24a73b0a | 6126 | if (EQ (eol_type, Qmac)) |
27901516 | 6127 | { |
24a73b0a | 6128 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
6129 | if (*p == '\r') |
6130 | *p = '\n'; | |
4ed46869 | 6131 | } |
24a73b0a | 6132 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 6133 | { |
24a73b0a | 6134 | int n = 0; |
b73bfc1c | 6135 | |
24a73b0a KH |
6136 | if (NILP (coding->dst_object)) |
6137 | { | |
4347441b KH |
6138 | /* Start deleting '\r' from the tail to minimize the memory |
6139 | movement. */ | |
24a73b0a KH |
6140 | for (p = pend - 2; p >= pbeg; p--) |
6141 | if (*p == '\r') | |
6142 | { | |
6143 | safe_bcopy ((char *) (p + 1), (char *) p, pend-- - p - 1); | |
6144 | n++; | |
6145 | } | |
6146 | } | |
6147 | else | |
6148 | { | |
4347441b KH |
6149 | int pos_byte = coding->dst_pos_byte; |
6150 | int pos = coding->dst_pos; | |
6151 | int pos_end = pos + coding->produced_char - 1; | |
6152 | ||
6153 | while (pos < pos_end) | |
6154 | { | |
6155 | p = BYTE_POS_ADDR (pos_byte); | |
6156 | if (*p == '\r' && p[1] == '\n') | |
6157 | { | |
6158 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
6159 | n++; | |
6160 | pos_end--; | |
6161 | } | |
6162 | pos++; | |
69b8522d KH |
6163 | if (coding->dst_multibyte) |
6164 | pos_byte += BYTES_BY_CHAR_HEAD (*p); | |
6165 | else | |
6166 | pos_byte++; | |
4347441b | 6167 | } |
24a73b0a KH |
6168 | } |
6169 | coding->produced -= n; | |
6170 | coding->produced_char -= n; | |
aaaf0b1e | 6171 | } |
4ed46869 KH |
6172 | } |
6173 | ||
7d64c6ad | 6174 | |
a6f87d34 KH |
6175 | /* Return a translation table (or list of them) from coding system |
6176 | attribute vector ATTRS for encoding (ENCODEP is nonzero) or | |
6177 | decoding (ENCODEP is zero). */ | |
7d64c6ad | 6178 | |
e6a54062 | 6179 | static Lisp_Object |
09ee6fdd KH |
6180 | get_translation_table (attrs, encodep, max_lookup) |
6181 | Lisp_Object attrs; | |
6182 | int encodep, *max_lookup; | |
7d64c6ad KH |
6183 | { |
6184 | Lisp_Object standard, translation_table; | |
09ee6fdd | 6185 | Lisp_Object val; |
7d64c6ad KH |
6186 | |
6187 | if (encodep) | |
6188 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
6189 | standard = Vstandard_translation_table_for_encode; | |
6190 | else | |
6191 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
6192 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 6193 | if (NILP (translation_table)) |
09ee6fdd KH |
6194 | translation_table = standard; |
6195 | else | |
a6f87d34 | 6196 | { |
09ee6fdd KH |
6197 | if (SYMBOLP (translation_table)) |
6198 | translation_table = Fget (translation_table, Qtranslation_table); | |
6199 | else if (CONSP (translation_table)) | |
6200 | { | |
6201 | translation_table = Fcopy_sequence (translation_table); | |
6202 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
6203 | if (SYMBOLP (XCAR (val))) | |
6204 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
6205 | } | |
6206 | if (CHAR_TABLE_P (standard)) | |
6207 | { | |
6208 | if (CONSP (translation_table)) | |
6209 | translation_table = nconc2 (translation_table, | |
6210 | Fcons (standard, Qnil)); | |
6211 | else | |
6212 | translation_table = Fcons (translation_table, | |
6213 | Fcons (standard, Qnil)); | |
6214 | } | |
a6f87d34 | 6215 | } |
2170c8f0 KH |
6216 | |
6217 | if (max_lookup) | |
09ee6fdd | 6218 | { |
2170c8f0 KH |
6219 | *max_lookup = 1; |
6220 | if (CHAR_TABLE_P (translation_table) | |
6221 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
6222 | { | |
6223 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
6224 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6225 | *max_lookup = XFASTINT (val); | |
6226 | } | |
6227 | else if (CONSP (translation_table)) | |
6228 | { | |
6229 | Lisp_Object tail, val; | |
09ee6fdd | 6230 | |
2170c8f0 KH |
6231 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
6232 | if (CHAR_TABLE_P (XCAR (tail)) | |
6233 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
6234 | { | |
6235 | val = XCHAR_TABLE (XCAR (tail))->extras[1]; | |
6236 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6237 | *max_lookup = XFASTINT (val); | |
6238 | } | |
6239 | } | |
a6f87d34 | 6240 | } |
7d64c6ad KH |
6241 | return translation_table; |
6242 | } | |
6243 | ||
09ee6fdd KH |
6244 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
6245 | do { \ | |
6246 | trans = Qnil; \ | |
6247 | if (CHAR_TABLE_P (table)) \ | |
6248 | { \ | |
6249 | trans = CHAR_TABLE_REF (table, c); \ | |
6250 | if (CHARACTERP (trans)) \ | |
6251 | c = XFASTINT (trans), trans = Qnil; \ | |
6252 | } \ | |
6253 | else if (CONSP (table)) \ | |
6254 | { \ | |
6255 | Lisp_Object tail; \ | |
6256 | \ | |
6257 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
6258 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
6259 | { \ | |
6260 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
6261 | if (CHARACTERP (trans)) \ | |
6262 | c = XFASTINT (trans), trans = Qnil; \ | |
6263 | else if (! NILP (trans)) \ | |
6264 | break; \ | |
6265 | } \ | |
6266 | } \ | |
e6a54062 KH |
6267 | } while (0) |
6268 | ||
7d64c6ad | 6269 | |
69a80ea3 KH |
6270 | static Lisp_Object |
6271 | get_translation (val, buf, buf_end, last_block, from_nchars, to_nchars) | |
6272 | Lisp_Object val; | |
6273 | int *buf, *buf_end; | |
6274 | int last_block; | |
6275 | int *from_nchars, *to_nchars; | |
6276 | { | |
433f7f87 KH |
6277 | /* VAL is TO or (([FROM-CHAR ...] . TO) ...) where TO is TO-CHAR or |
6278 | [TO-CHAR ...]. */ | |
69a80ea3 KH |
6279 | if (CONSP (val)) |
6280 | { | |
433f7f87 | 6281 | Lisp_Object from, tail; |
69a80ea3 KH |
6282 | int i, len; |
6283 | ||
433f7f87 | 6284 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
69a80ea3 | 6285 | { |
433f7f87 KH |
6286 | val = XCAR (tail); |
6287 | from = XCAR (val); | |
6288 | len = ASIZE (from); | |
6289 | for (i = 0; i < len; i++) | |
6290 | { | |
6291 | if (buf + i == buf_end) | |
6292 | { | |
6293 | if (! last_block) | |
6294 | return Qt; | |
6295 | break; | |
6296 | } | |
6297 | if (XINT (AREF (from, i)) != buf[i]) | |
6298 | break; | |
6299 | } | |
6300 | if (i == len) | |
6301 | { | |
6302 | val = XCDR (val); | |
6303 | *from_nchars = len; | |
6304 | break; | |
6305 | } | |
69a80ea3 | 6306 | } |
433f7f87 KH |
6307 | if (! CONSP (tail)) |
6308 | return Qnil; | |
69a80ea3 KH |
6309 | } |
6310 | if (VECTORP (val)) | |
6311 | *buf = XINT (AREF (val, 0)), *to_nchars = ASIZE (val); | |
6312 | else | |
6313 | *buf = XINT (val); | |
6314 | return val; | |
6315 | } | |
6316 | ||
6317 | ||
d46c5b12 | 6318 | static int |
69a80ea3 | 6319 | produce_chars (coding, translation_table, last_block) |
df7492f9 | 6320 | struct coding_system *coding; |
69a80ea3 KH |
6321 | Lisp_Object translation_table; |
6322 | int last_block; | |
4ed46869 | 6323 | { |
df7492f9 KH |
6324 | unsigned char *dst = coding->destination + coding->produced; |
6325 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
119852e7 KH |
6326 | EMACS_INT produced; |
6327 | EMACS_INT produced_chars = 0; | |
69a80ea3 | 6328 | int carryover = 0; |
4ed46869 | 6329 | |
df7492f9 | 6330 | if (! coding->chars_at_source) |
4ed46869 | 6331 | { |
119852e7 | 6332 | /* Source characters are in coding->charbuf. */ |
fba4576f AS |
6333 | int *buf = coding->charbuf; |
6334 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 6335 | |
db274c7a KH |
6336 | if (EQ (coding->src_object, coding->dst_object)) |
6337 | { | |
6338 | coding_set_source (coding); | |
6339 | dst_end = ((unsigned char *) coding->source) + coding->consumed; | |
6340 | } | |
4ed46869 | 6341 | |
df7492f9 | 6342 | while (buf < buf_end) |
4ed46869 | 6343 | { |
69a80ea3 | 6344 | int c = *buf, i; |
bc4bc72a | 6345 | |
df7492f9 KH |
6346 | if (c >= 0) |
6347 | { | |
69a80ea3 KH |
6348 | int from_nchars = 1, to_nchars = 1; |
6349 | Lisp_Object trans = Qnil; | |
6350 | ||
09ee6fdd | 6351 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6352 | if (! NILP (trans)) |
69a80ea3 KH |
6353 | { |
6354 | trans = get_translation (trans, buf, buf_end, last_block, | |
6355 | &from_nchars, &to_nchars); | |
6356 | if (EQ (trans, Qt)) | |
6357 | break; | |
6358 | c = *buf; | |
6359 | } | |
6360 | ||
6361 | if (dst + MAX_MULTIBYTE_LENGTH * to_nchars > dst_end) | |
6362 | { | |
6363 | dst = alloc_destination (coding, | |
6364 | buf_end - buf | |
6365 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
6366 | dst); | |
db274c7a KH |
6367 | if (EQ (coding->src_object, coding->dst_object)) |
6368 | { | |
6369 | coding_set_source (coding); | |
6370 | dst_end = ((unsigned char *) coding->source) + coding->consumed; | |
6371 | } | |
6372 | else | |
6373 | dst_end = coding->destination + coding->dst_bytes; | |
69a80ea3 KH |
6374 | } |
6375 | ||
433f7f87 | 6376 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 6377 | { |
433f7f87 KH |
6378 | if (i > 0) |
6379 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
6380 | if (coding->dst_multibyte |
6381 | || ! CHAR_BYTE8_P (c)) | |
db274c7a | 6382 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
69a80ea3 KH |
6383 | else |
6384 | *dst++ = CHAR_TO_BYTE8 (c); | |
6385 | } | |
6386 | produced_chars += to_nchars; | |
6387 | *buf++ = to_nchars; | |
6388 | while (--from_nchars > 0) | |
6389 | *buf++ = 0; | |
d46c5b12 | 6390 | } |
df7492f9 | 6391 | else |
69a80ea3 KH |
6392 | /* This is an annotation datum. (-C) is the length. */ |
6393 | buf += -c; | |
4ed46869 | 6394 | } |
69a80ea3 | 6395 | carryover = buf_end - buf; |
4ed46869 | 6396 | } |
fa42c37f | 6397 | else |
fa42c37f | 6398 | { |
119852e7 | 6399 | /* Source characters are at coding->source. */ |
8f924df7 | 6400 | const unsigned char *src = coding->source; |
119852e7 | 6401 | const unsigned char *src_end = src + coding->consumed; |
4ed46869 | 6402 | |
db274c7a KH |
6403 | if (EQ (coding->dst_object, coding->src_object)) |
6404 | dst_end = (unsigned char *) src; | |
df7492f9 | 6405 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 6406 | { |
df7492f9 | 6407 | if (coding->src_multibyte) |
fa42c37f | 6408 | { |
71c81426 | 6409 | int multibytep = 1; |
4533845d | 6410 | EMACS_INT consumed_chars = 0; |
d46c5b12 | 6411 | |
df7492f9 KH |
6412 | while (1) |
6413 | { | |
8f924df7 | 6414 | const unsigned char *src_base = src; |
df7492f9 | 6415 | int c; |
b73bfc1c | 6416 | |
df7492f9 | 6417 | ONE_MORE_BYTE (c); |
119852e7 | 6418 | if (dst == dst_end) |
df7492f9 | 6419 | { |
119852e7 KH |
6420 | if (EQ (coding->src_object, coding->dst_object)) |
6421 | dst_end = (unsigned char *) src; | |
6422 | if (dst == dst_end) | |
df7492f9 | 6423 | { |
119852e7 KH |
6424 | EMACS_INT offset = src - coding->source; |
6425 | ||
6426 | dst = alloc_destination (coding, src_end - src + 1, | |
6427 | dst); | |
6428 | dst_end = coding->destination + coding->dst_bytes; | |
6429 | coding_set_source (coding); | |
6430 | src = coding->source + offset; | |
6431 | src_end = coding->source + coding->src_bytes; | |
db274c7a KH |
6432 | if (EQ (coding->src_object, coding->dst_object)) |
6433 | dst_end = (unsigned char *) src; | |
df7492f9 | 6434 | } |
df7492f9 KH |
6435 | } |
6436 | *dst++ = c; | |
6437 | produced_chars++; | |
6438 | } | |
6439 | no_more_source: | |
6440 | ; | |
fa42c37f KH |
6441 | } |
6442 | else | |
df7492f9 KH |
6443 | while (src < src_end) |
6444 | { | |
71c81426 | 6445 | int multibytep = 1; |
df7492f9 | 6446 | int c = *src++; |
b73bfc1c | 6447 | |
df7492f9 KH |
6448 | if (dst >= dst_end - 1) |
6449 | { | |
2c78b7e1 | 6450 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 6451 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
6452 | if (dst >= dst_end - 1) |
6453 | { | |
119852e7 | 6454 | EMACS_INT offset = src - coding->source; |
db274c7a | 6455 | EMACS_INT more_bytes; |
119852e7 | 6456 | |
db274c7a KH |
6457 | if (EQ (coding->src_object, coding->dst_object)) |
6458 | more_bytes = ((src_end - src) / 2) + 2; | |
6459 | else | |
6460 | more_bytes = src_end - src + 2; | |
6461 | dst = alloc_destination (coding, more_bytes, dst); | |
2c78b7e1 KH |
6462 | dst_end = coding->destination + coding->dst_bytes; |
6463 | coding_set_source (coding); | |
119852e7 | 6464 | src = coding->source + offset; |
2c78b7e1 | 6465 | src_end = coding->source + coding->src_bytes; |
db274c7a KH |
6466 | if (EQ (coding->src_object, coding->dst_object)) |
6467 | dst_end = (unsigned char *) src; | |
2c78b7e1 | 6468 | } |
df7492f9 KH |
6469 | } |
6470 | EMIT_ONE_BYTE (c); | |
6471 | } | |
d46c5b12 | 6472 | } |
df7492f9 KH |
6473 | else |
6474 | { | |
6475 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 6476 | { |
119852e7 | 6477 | EMACS_INT require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 6478 | |
df7492f9 | 6479 | if (require > 0) |
fa42c37f | 6480 | { |
df7492f9 KH |
6481 | EMACS_INT offset = src - coding->source; |
6482 | ||
6483 | dst = alloc_destination (coding, require, dst); | |
6484 | coding_set_source (coding); | |
6485 | src = coding->source + offset; | |
6486 | src_end = coding->source + coding->src_bytes; | |
fa42c37f KH |
6487 | } |
6488 | } | |
119852e7 | 6489 | produced_chars = coding->consumed_char; |
df7492f9 | 6490 | while (src < src_end) |
14daee73 | 6491 | *dst++ = *src++; |
fa42c37f KH |
6492 | } |
6493 | } | |
6494 | ||
df7492f9 | 6495 | produced = dst - (coding->destination + coding->produced); |
284201e4 | 6496 | if (BUFFERP (coding->dst_object) && produced_chars > 0) |
df7492f9 KH |
6497 | insert_from_gap (produced_chars, produced); |
6498 | coding->produced += produced; | |
6499 | coding->produced_char += produced_chars; | |
69a80ea3 | 6500 | return carryover; |
fa42c37f KH |
6501 | } |
6502 | ||
ff0dacd7 KH |
6503 | /* Compose text in CODING->object according to the annotation data at |
6504 | CHARBUF. CHARBUF is an array: | |
6505 | [ -LENGTH ANNOTATION_MASK FROM TO METHOD COMP_LEN [ COMPONENTS... ] ] | |
df7492f9 | 6506 | */ |
4ed46869 | 6507 | |
df7492f9 | 6508 | static INLINE void |
69a80ea3 | 6509 | produce_composition (coding, charbuf, pos) |
4ed46869 | 6510 | struct coding_system *coding; |
df7492f9 | 6511 | int *charbuf; |
69a80ea3 | 6512 | EMACS_INT pos; |
4ed46869 | 6513 | { |
df7492f9 | 6514 | int len; |
69a80ea3 | 6515 | EMACS_INT to; |
df7492f9 | 6516 | enum composition_method method; |
df7492f9 | 6517 | Lisp_Object components; |
fa42c37f | 6518 | |
df7492f9 | 6519 | len = -charbuf[0]; |
69a80ea3 | 6520 | to = pos + charbuf[2]; |
9ffd559c KH |
6521 | if (to <= pos) |
6522 | return; | |
69a80ea3 | 6523 | method = (enum composition_method) (charbuf[3]); |
d46c5b12 | 6524 | |
df7492f9 KH |
6525 | if (method == COMPOSITION_RELATIVE) |
6526 | components = Qnil; | |
9ffd559c KH |
6527 | else if (method >= COMPOSITION_WITH_RULE |
6528 | && method <= COMPOSITION_WITH_RULE_ALTCHARS) | |
d46c5b12 | 6529 | { |
df7492f9 KH |
6530 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
6531 | int i; | |
b73bfc1c | 6532 | |
69a80ea3 KH |
6533 | len -= 4; |
6534 | charbuf += 4; | |
df7492f9 | 6535 | for (i = 0; i < len; i++) |
9ffd559c KH |
6536 | { |
6537 | args[i] = make_number (charbuf[i]); | |
f75c90a9 | 6538 | if (charbuf[i] < 0) |
9ffd559c KH |
6539 | return; |
6540 | } | |
df7492f9 KH |
6541 | components = (method == COMPOSITION_WITH_ALTCHARS |
6542 | ? Fstring (len, args) : Fvector (len, args)); | |
d46c5b12 | 6543 | } |
9ffd559c KH |
6544 | else |
6545 | return; | |
69a80ea3 | 6546 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
6547 | } |
6548 | ||
d46c5b12 | 6549 | |
ff0dacd7 KH |
6550 | /* Put `charset' property on text in CODING->object according to |
6551 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 6552 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 6553 | */ |
d46c5b12 | 6554 | |
ff0dacd7 | 6555 | static INLINE void |
69a80ea3 | 6556 | produce_charset (coding, charbuf, pos) |
d46c5b12 | 6557 | struct coding_system *coding; |
ff0dacd7 | 6558 | int *charbuf; |
69a80ea3 | 6559 | EMACS_INT pos; |
d46c5b12 | 6560 | { |
69a80ea3 KH |
6561 | EMACS_INT from = pos - charbuf[2]; |
6562 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); | |
b73bfc1c | 6563 | |
69a80ea3 | 6564 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
6565 | Qcharset, CHARSET_NAME (charset), |
6566 | coding->dst_object); | |
d46c5b12 KH |
6567 | } |
6568 | ||
d46c5b12 | 6569 | |
df7492f9 KH |
6570 | #define CHARBUF_SIZE 0x4000 |
6571 | ||
6572 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
6573 | do { \ | |
6574 | int size = CHARBUF_SIZE;; \ | |
6575 | \ | |
6576 | coding->charbuf = NULL; \ | |
6577 | while (size > 1024) \ | |
6578 | { \ | |
6579 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
6580 | if (coding->charbuf) \ | |
6581 | break; \ | |
6582 | size >>= 1; \ | |
6583 | } \ | |
6584 | if (! coding->charbuf) \ | |
6585 | { \ | |
065e3595 | 6586 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
df7492f9 KH |
6587 | return coding->result; \ |
6588 | } \ | |
6589 | coding->charbuf_size = size; \ | |
6590 | } while (0) | |
4ed46869 | 6591 | |
d46c5b12 KH |
6592 | |
6593 | static void | |
69a80ea3 | 6594 | produce_annotation (coding, pos) |
d46c5b12 | 6595 | struct coding_system *coding; |
69a80ea3 | 6596 | EMACS_INT pos; |
d46c5b12 | 6597 | { |
df7492f9 KH |
6598 | int *charbuf = coding->charbuf; |
6599 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 6600 | |
ff0dacd7 KH |
6601 | if (NILP (coding->dst_object)) |
6602 | return; | |
d46c5b12 | 6603 | |
df7492f9 | 6604 | while (charbuf < charbuf_end) |
a84f1519 | 6605 | { |
df7492f9 | 6606 | if (*charbuf >= 0) |
69a80ea3 | 6607 | pos += *charbuf++; |
d46c5b12 | 6608 | else |
d46c5b12 | 6609 | { |
df7492f9 | 6610 | int len = -*charbuf; |
ff0dacd7 | 6611 | switch (charbuf[1]) |
df7492f9 KH |
6612 | { |
6613 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
69a80ea3 | 6614 | produce_composition (coding, charbuf, pos); |
df7492f9 | 6615 | break; |
ff0dacd7 | 6616 | case CODING_ANNOTATE_CHARSET_MASK: |
69a80ea3 | 6617 | produce_charset (coding, charbuf, pos); |
ff0dacd7 | 6618 | break; |
df7492f9 KH |
6619 | default: |
6620 | abort (); | |
6621 | } | |
6622 | charbuf += len; | |
d46c5b12 | 6623 | } |
a84f1519 | 6624 | } |
d46c5b12 KH |
6625 | } |
6626 | ||
df7492f9 KH |
6627 | /* Decode the data at CODING->src_object into CODING->dst_object. |
6628 | CODING->src_object is a buffer, a string, or nil. | |
6629 | CODING->dst_object is a buffer. | |
d46c5b12 | 6630 | |
df7492f9 KH |
6631 | If CODING->src_object is a buffer, it must be the current buffer. |
6632 | In this case, if CODING->src_pos is positive, it is a position of | |
6633 | the source text in the buffer, otherwise, the source text is in the | |
6634 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
6635 | the text from GPT (which must be the same as PT). If this is the | |
6636 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6637 | negative. | |
d46c5b12 | 6638 | |
b6828792 | 6639 | If CODING->src_object is a string, CODING->src_pos is an index to |
df7492f9 | 6640 | that string. |
d46c5b12 | 6641 | |
df7492f9 KH |
6642 | If CODING->src_object is nil, CODING->source must already point to |
6643 | the non-relocatable memory area. In this case, CODING->src_pos is | |
6644 | an offset from CODING->source. | |
73be902c | 6645 | |
df7492f9 KH |
6646 | The decoded data is inserted at the current point of the buffer |
6647 | CODING->dst_object. | |
6648 | */ | |
d46c5b12 | 6649 | |
df7492f9 KH |
6650 | static int |
6651 | decode_coding (coding) | |
d46c5b12 | 6652 | struct coding_system *coding; |
d46c5b12 | 6653 | { |
df7492f9 | 6654 | Lisp_Object attrs; |
24a73b0a | 6655 | Lisp_Object undo_list; |
7d64c6ad | 6656 | Lisp_Object translation_table; |
69a80ea3 KH |
6657 | int carryover; |
6658 | int i; | |
d46c5b12 | 6659 | |
df7492f9 KH |
6660 | if (BUFFERP (coding->src_object) |
6661 | && coding->src_pos > 0 | |
6662 | && coding->src_pos < GPT | |
6663 | && coding->src_pos + coding->src_chars > GPT) | |
6664 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 6665 | |
24a73b0a | 6666 | undo_list = Qt; |
df7492f9 | 6667 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 6668 | { |
df7492f9 KH |
6669 | if (current_buffer != XBUFFER (coding->dst_object)) |
6670 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6671 | if (GPT != PT) | |
6672 | move_gap_both (PT, PT_BYTE); | |
24a73b0a KH |
6673 | undo_list = current_buffer->undo_list; |
6674 | current_buffer->undo_list = Qt; | |
1c3478b0 KH |
6675 | } |
6676 | ||
df7492f9 KH |
6677 | coding->consumed = coding->consumed_char = 0; |
6678 | coding->produced = coding->produced_char = 0; | |
6679 | coding->chars_at_source = 0; | |
065e3595 | 6680 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 6681 | coding->errors = 0; |
1c3478b0 | 6682 | |
df7492f9 KH |
6683 | ALLOC_CONVERSION_WORK_AREA (coding); |
6684 | ||
6685 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 6686 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 6687 | |
69a80ea3 | 6688 | carryover = 0; |
df7492f9 | 6689 | do |
b73bfc1c | 6690 | { |
69a80ea3 KH |
6691 | EMACS_INT pos = coding->dst_pos + coding->produced_char; |
6692 | ||
df7492f9 KH |
6693 | coding_set_source (coding); |
6694 | coding->annotated = 0; | |
69a80ea3 | 6695 | coding->charbuf_used = carryover; |
df7492f9 | 6696 | (*(coding->decoder)) (coding); |
df7492f9 | 6697 | coding_set_destination (coding); |
69a80ea3 | 6698 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 6699 | if (coding->annotated) |
69a80ea3 KH |
6700 | produce_annotation (coding, pos); |
6701 | for (i = 0; i < carryover; i++) | |
6702 | coding->charbuf[i] | |
6703 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 6704 | } |
df7492f9 | 6705 | while (coding->consumed < coding->src_bytes |
54b367bb KH |
6706 | && (coding->result == CODING_RESULT_SUCCESS |
6707 | || coding->result == CODING_RESULT_INVALID_SRC)); | |
d46c5b12 | 6708 | |
69a80ea3 KH |
6709 | if (carryover > 0) |
6710 | { | |
6711 | coding_set_destination (coding); | |
6712 | coding->charbuf_used = carryover; | |
6713 | produce_chars (coding, translation_table, 1); | |
6714 | } | |
6715 | ||
df7492f9 KH |
6716 | coding->carryover_bytes = 0; |
6717 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 6718 | { |
df7492f9 | 6719 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 6720 | const unsigned char *src; |
df7492f9 KH |
6721 | |
6722 | coding_set_source (coding); | |
6723 | coding_set_destination (coding); | |
6724 | src = coding->source + coding->consumed; | |
6725 | ||
6726 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 6727 | { |
df7492f9 KH |
6728 | /* Flush out unprocessed data as binary chars. We are sure |
6729 | that the number of data is less than the size of | |
6730 | coding->charbuf. */ | |
065e3595 | 6731 | coding->charbuf_used = 0; |
b2dab6c8 JR |
6732 | coding->chars_at_source = 0; |
6733 | ||
df7492f9 | 6734 | while (nbytes-- > 0) |
1c3478b0 | 6735 | { |
df7492f9 | 6736 | int c = *src++; |
98725083 | 6737 | |
1c91457d KH |
6738 | if (c & 0x80) |
6739 | c = BYTE8_TO_CHAR (c); | |
6740 | coding->charbuf[coding->charbuf_used++] = c; | |
1c3478b0 | 6741 | } |
f6cbaf43 | 6742 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 6743 | } |
d46c5b12 | 6744 | else |
df7492f9 KH |
6745 | { |
6746 | /* Record unprocessed bytes in coding->carryover. We are | |
6747 | sure that the number of data is less than the size of | |
6748 | coding->carryover. */ | |
6749 | unsigned char *p = coding->carryover; | |
6750 | ||
6751 | coding->carryover_bytes = nbytes; | |
6752 | while (nbytes-- > 0) | |
6753 | *p++ = *src++; | |
1c3478b0 | 6754 | } |
df7492f9 | 6755 | coding->consumed = coding->src_bytes; |
b73bfc1c | 6756 | } |
69f76525 | 6757 | |
4347441b KH |
6758 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix)) |
6759 | decode_eol (coding); | |
24a73b0a KH |
6760 | if (BUFFERP (coding->dst_object)) |
6761 | { | |
6762 | current_buffer->undo_list = undo_list; | |
6763 | record_insert (coding->dst_pos, coding->produced_char); | |
6764 | } | |
73be902c | 6765 | return coding->result; |
4ed46869 KH |
6766 | } |
6767 | ||
aaaf0b1e | 6768 | |
e1c23804 | 6769 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
6770 | ending before LIMIT of CODING->src_object (buffer or string), store |
6771 | the data in BUF, set *STOP to a starting position of the next | |
6772 | composition (if any) or to LIMIT, and return the address of the | |
6773 | next element of BUF. | |
6774 | ||
6775 | If such an annotation is not found, set *STOP to a starting | |
6776 | position of a composition after POS (if any) or to LIMIT, and | |
6777 | return BUF. */ | |
6778 | ||
6779 | static INLINE int * | |
6780 | handle_composition_annotation (pos, limit, coding, buf, stop) | |
6781 | EMACS_INT pos, limit; | |
aaaf0b1e | 6782 | struct coding_system *coding; |
ff0dacd7 KH |
6783 | int *buf; |
6784 | EMACS_INT *stop; | |
aaaf0b1e | 6785 | { |
ff0dacd7 KH |
6786 | EMACS_INT start, end; |
6787 | Lisp_Object prop; | |
aaaf0b1e | 6788 | |
ff0dacd7 KH |
6789 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
6790 | || end > limit) | |
6791 | *stop = limit; | |
6792 | else if (start > pos) | |
6793 | *stop = start; | |
6794 | else | |
aaaf0b1e | 6795 | { |
ff0dacd7 | 6796 | if (start == pos) |
aaaf0b1e | 6797 | { |
ff0dacd7 KH |
6798 | /* We found a composition. Store the corresponding |
6799 | annotation data in BUF. */ | |
6800 | int *head = buf; | |
6801 | enum composition_method method = COMPOSITION_METHOD (prop); | |
6802 | int nchars = COMPOSITION_LENGTH (prop); | |
6803 | ||
69a80ea3 | 6804 | ADD_COMPOSITION_DATA (buf, nchars, method); |
ff0dacd7 | 6805 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 6806 | { |
ff0dacd7 KH |
6807 | Lisp_Object components; |
6808 | int len, i, i_byte; | |
6809 | ||
6810 | components = COMPOSITION_COMPONENTS (prop); | |
6811 | if (VECTORP (components)) | |
aaaf0b1e | 6812 | { |
ff0dacd7 KH |
6813 | len = XVECTOR (components)->size; |
6814 | for (i = 0; i < len; i++) | |
6815 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 6816 | } |
ff0dacd7 | 6817 | else if (STRINGP (components)) |
aaaf0b1e | 6818 | { |
8f924df7 | 6819 | len = SCHARS (components); |
ff0dacd7 KH |
6820 | i = i_byte = 0; |
6821 | while (i < len) | |
6822 | { | |
6823 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
6824 | buf++; | |
6825 | } | |
6826 | } | |
6827 | else if (INTEGERP (components)) | |
6828 | { | |
6829 | len = 1; | |
6830 | *buf++ = XINT (components); | |
6831 | } | |
6832 | else if (CONSP (components)) | |
6833 | { | |
6834 | for (len = 0; CONSP (components); | |
6835 | len++, components = XCDR (components)) | |
6836 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 6837 | } |
aaaf0b1e | 6838 | else |
ff0dacd7 KH |
6839 | abort (); |
6840 | *head -= len; | |
aaaf0b1e | 6841 | } |
aaaf0b1e | 6842 | } |
ff0dacd7 KH |
6843 | |
6844 | if (find_composition (end, limit, &start, &end, &prop, | |
6845 | coding->src_object) | |
6846 | && end <= limit) | |
6847 | *stop = start; | |
6848 | else | |
6849 | *stop = limit; | |
aaaf0b1e | 6850 | } |
ff0dacd7 KH |
6851 | return buf; |
6852 | } | |
6853 | ||
6854 | ||
e1c23804 | 6855 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
6856 | CODING->src_object (buffer of string), store the data in BUF, set |
6857 | *STOP to the position where the value of `charset' property changes | |
6858 | (limiting by LIMIT), and return the address of the next element of | |
6859 | BUF. | |
6860 | ||
6861 | If the property value is nil, set *STOP to the position where the | |
6862 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
6863 | ||
6864 | static INLINE int * | |
6865 | handle_charset_annotation (pos, limit, coding, buf, stop) | |
6866 | EMACS_INT pos, limit; | |
6867 | struct coding_system *coding; | |
6868 | int *buf; | |
6869 | EMACS_INT *stop; | |
6870 | { | |
6871 | Lisp_Object val, next; | |
6872 | int id; | |
6873 | ||
6874 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
6875 | if (! NILP (val) && CHARSETP (val)) | |
6876 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
6877 | else | |
6878 | id = -1; | |
69a80ea3 | 6879 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
6880 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
6881 | coding->src_object, | |
6882 | make_number (limit)); | |
6883 | *stop = XINT (next); | |
6884 | return buf; | |
6885 | } | |
6886 | ||
6887 | ||
df7492f9 | 6888 | static void |
09ee6fdd | 6889 | consume_chars (coding, translation_table, max_lookup) |
df7492f9 | 6890 | struct coding_system *coding; |
433f7f87 | 6891 | Lisp_Object translation_table; |
09ee6fdd | 6892 | int max_lookup; |
df7492f9 KH |
6893 | { |
6894 | int *buf = coding->charbuf; | |
ff0dacd7 | 6895 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 6896 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 6897 | const unsigned char *src_end = coding->source + coding->src_bytes; |
ff0dacd7 KH |
6898 | EMACS_INT pos = coding->src_pos + coding->consumed_char; |
6899 | EMACS_INT end_pos = coding->src_pos + coding->src_chars; | |
df7492f9 KH |
6900 | int multibytep = coding->src_multibyte; |
6901 | Lisp_Object eol_type; | |
6902 | int c; | |
ff0dacd7 | 6903 | EMACS_INT stop, stop_composition, stop_charset; |
09ee6fdd | 6904 | int *lookup_buf = NULL; |
433f7f87 KH |
6905 | |
6906 | if (! NILP (translation_table)) | |
09ee6fdd | 6907 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 6908 | |
df7492f9 KH |
6909 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6910 | if (VECTORP (eol_type)) | |
6911 | eol_type = Qunix; | |
88993dfd | 6912 | |
df7492f9 KH |
6913 | /* Note: composition handling is not yet implemented. */ |
6914 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 6915 | |
0b5670c9 KH |
6916 | if (NILP (coding->src_object)) |
6917 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 6918 | else |
0b5670c9 KH |
6919 | { |
6920 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
6921 | stop = stop_composition = pos; | |
6922 | else | |
6923 | stop = stop_composition = end_pos; | |
6924 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
6925 | stop = stop_charset = pos; | |
6926 | else | |
6927 | stop_charset = end_pos; | |
6928 | } | |
ec6d2bb8 | 6929 | |
24a73b0a | 6930 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 6931 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 6932 | while (buf < buf_end) |
aaaf0b1e | 6933 | { |
433f7f87 KH |
6934 | Lisp_Object trans; |
6935 | ||
df7492f9 | 6936 | if (pos == stop) |
ec6d2bb8 | 6937 | { |
df7492f9 KH |
6938 | if (pos == end_pos) |
6939 | break; | |
ff0dacd7 KH |
6940 | if (pos == stop_composition) |
6941 | buf = handle_composition_annotation (pos, end_pos, coding, | |
6942 | buf, &stop_composition); | |
6943 | if (pos == stop_charset) | |
6944 | buf = handle_charset_annotation (pos, end_pos, coding, | |
6945 | buf, &stop_charset); | |
6946 | stop = (stop_composition < stop_charset | |
6947 | ? stop_composition : stop_charset); | |
df7492f9 KH |
6948 | } |
6949 | ||
6950 | if (! multibytep) | |
4776e638 | 6951 | { |
d3e4cb56 | 6952 | EMACS_INT bytes; |
aaaf0b1e | 6953 | |
ea29edf2 KH |
6954 | if (coding->encoder == encode_coding_raw_text) |
6955 | c = *src++, pos++; | |
6956 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
db274c7a | 6957 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes; |
4776e638 | 6958 | else |
f03caae0 | 6959 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 6960 | } |
df7492f9 | 6961 | else |
db274c7a | 6962 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos++; |
df7492f9 KH |
6963 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
6964 | c = '\n'; | |
6965 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 6966 | { |
df7492f9 | 6967 | if (c == '\n') |
aaaf0b1e | 6968 | { |
df7492f9 KH |
6969 | if (EQ (eol_type, Qdos)) |
6970 | *buf++ = '\r'; | |
6971 | else | |
6972 | c = '\r'; | |
aaaf0b1e KH |
6973 | } |
6974 | } | |
433f7f87 | 6975 | |
e6a54062 | 6976 | trans = Qnil; |
09ee6fdd | 6977 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6978 | if (NILP (trans)) |
433f7f87 KH |
6979 | *buf++ = c; |
6980 | else | |
6981 | { | |
6982 | int from_nchars = 1, to_nchars = 1; | |
6983 | int *lookup_buf_end; | |
6984 | const unsigned char *p = src; | |
6985 | int i; | |
6986 | ||
6987 | lookup_buf[0] = c; | |
6988 | for (i = 1; i < max_lookup && p < src_end; i++) | |
6989 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
6990 | lookup_buf_end = lookup_buf + i; | |
6991 | trans = get_translation (trans, lookup_buf, lookup_buf_end, 1, | |
6992 | &from_nchars, &to_nchars); | |
6993 | if (EQ (trans, Qt) | |
6994 | || buf + to_nchars > buf_end) | |
6995 | break; | |
6996 | *buf++ = *lookup_buf; | |
6997 | for (i = 1; i < to_nchars; i++) | |
6998 | *buf++ = XINT (AREF (trans, i)); | |
6999 | for (i = 1; i < from_nchars; i++, pos++) | |
7000 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
7001 | } | |
aaaf0b1e | 7002 | } |
ec6d2bb8 | 7003 | |
df7492f9 KH |
7004 | coding->consumed = src - coding->source; |
7005 | coding->consumed_char = pos - coding->src_pos; | |
7006 | coding->charbuf_used = buf - coding->charbuf; | |
7007 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
7008 | } |
7009 | ||
4ed46869 | 7010 | |
df7492f9 KH |
7011 | /* Encode the text at CODING->src_object into CODING->dst_object. |
7012 | CODING->src_object is a buffer or a string. | |
7013 | CODING->dst_object is a buffer or nil. | |
7014 | ||
7015 | If CODING->src_object is a buffer, it must be the current buffer. | |
7016 | In this case, if CODING->src_pos is positive, it is a position of | |
7017 | the source text in the buffer, otherwise. the source text is in the | |
7018 | gap area of the buffer, and coding->src_pos specifies the offset of | |
7019 | the text from GPT (which must be the same as PT). If this is the | |
7020 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7021 | negative and CODING should not have `pre-write-conversion'. | |
7022 | ||
7023 | If CODING->src_object is a string, CODING should not have | |
7024 | `pre-write-conversion'. | |
7025 | ||
7026 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
7027 | the current point of that buffer. | |
7028 | ||
7029 | If CODING->dst_object is nil, the encoded data is placed at the | |
7030 | memory area specified by CODING->destination. */ | |
7031 | ||
7032 | static int | |
7033 | encode_coding (coding) | |
4ed46869 | 7034 | struct coding_system *coding; |
4ed46869 | 7035 | { |
df7492f9 | 7036 | Lisp_Object attrs; |
7d64c6ad | 7037 | Lisp_Object translation_table; |
09ee6fdd | 7038 | int max_lookup; |
9861e777 | 7039 | |
df7492f9 | 7040 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
7041 | if (coding->encoder == encode_coding_raw_text) |
7042 | translation_table = Qnil, max_lookup = 0; | |
7043 | else | |
7044 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 7045 | |
df7492f9 | 7046 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 7047 | { |
df7492f9 KH |
7048 | set_buffer_internal (XBUFFER (coding->dst_object)); |
7049 | coding->dst_multibyte | |
7050 | = ! NILP (current_buffer->enable_multibyte_characters); | |
8844fa83 | 7051 | } |
4ed46869 | 7052 | |
b73bfc1c | 7053 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 7054 | coding->produced = coding->produced_char = 0; |
065e3595 | 7055 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 7056 | coding->errors = 0; |
b73bfc1c | 7057 | |
df7492f9 | 7058 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 7059 | |
df7492f9 KH |
7060 | do { |
7061 | coding_set_source (coding); | |
09ee6fdd | 7062 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
7063 | coding_set_destination (coding); |
7064 | (*(coding->encoder)) (coding); | |
7065 | } while (coding->consumed_char < coding->src_chars); | |
7066 | ||
284201e4 | 7067 | if (BUFFERP (coding->dst_object) && coding->produced_char > 0) |
df7492f9 KH |
7068 | insert_from_gap (coding->produced_char, coding->produced); |
7069 | ||
7070 | return (coding->result); | |
ec6d2bb8 KH |
7071 | } |
7072 | ||
fb88bf2d | 7073 | |
24a73b0a KH |
7074 | /* Name (or base name) of work buffer for code conversion. */ |
7075 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 7076 | |
24a73b0a KH |
7077 | /* A working buffer used by the top level conversion. Once it is |
7078 | created, it is never destroyed. It has the name | |
7079 | Vcode_conversion_workbuf_name. The other working buffers are | |
7080 | destroyed after the use is finished, and their names are modified | |
7081 | versions of Vcode_conversion_workbuf_name. */ | |
7082 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 7083 | |
24a73b0a KH |
7084 | /* 1 iff Vcode_conversion_reused_workbuf is already in use. */ |
7085 | static int reused_workbuf_in_use; | |
4ed46869 | 7086 | |
24a73b0a KH |
7087 | |
7088 | /* Return a working buffer of code convesion. MULTIBYTE specifies the | |
7089 | multibyteness of returning buffer. */ | |
b73bfc1c | 7090 | |
f6cbaf43 | 7091 | static Lisp_Object |
24a73b0a | 7092 | make_conversion_work_buffer (multibyte) |
f6cbaf43 | 7093 | int multibyte; |
df7492f9 | 7094 | { |
24a73b0a KH |
7095 | Lisp_Object name, workbuf; |
7096 | struct buffer *current; | |
4ed46869 | 7097 | |
24a73b0a | 7098 | if (reused_workbuf_in_use++) |
065e3595 KH |
7099 | { |
7100 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
7101 | workbuf = Fget_buffer_create (name); | |
7102 | } | |
df7492f9 | 7103 | else |
065e3595 | 7104 | { |
159bd5a2 | 7105 | if (NILP (Fbuffer_live_p (Vcode_conversion_reused_workbuf))) |
a993c7a1 KH |
7106 | Vcode_conversion_reused_workbuf |
7107 | = Fget_buffer_create (Vcode_conversion_workbuf_name); | |
7108 | workbuf = Vcode_conversion_reused_workbuf; | |
065e3595 | 7109 | } |
24a73b0a KH |
7110 | current = current_buffer; |
7111 | set_buffer_internal (XBUFFER (workbuf)); | |
df36ff1f CY |
7112 | /* We can't allow modification hooks to run in the work buffer. For |
7113 | instance, directory_files_internal assumes that file decoding | |
7114 | doesn't compile new regexps. */ | |
7115 | Fset (Fmake_local_variable (Qinhibit_modification_hooks), Qt); | |
3ed051d4 | 7116 | Ferase_buffer (); |
df7492f9 | 7117 | current_buffer->undo_list = Qt; |
24a73b0a | 7118 | current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil; |
df7492f9 | 7119 | set_buffer_internal (current); |
24a73b0a | 7120 | return workbuf; |
df7492f9 | 7121 | } |
d46c5b12 | 7122 | |
24a73b0a | 7123 | |
4776e638 | 7124 | static Lisp_Object |
24a73b0a KH |
7125 | code_conversion_restore (arg) |
7126 | Lisp_Object arg; | |
4776e638 | 7127 | { |
24a73b0a | 7128 | Lisp_Object current, workbuf; |
948bdcf3 | 7129 | struct gcpro gcpro1; |
24a73b0a | 7130 | |
948bdcf3 | 7131 | GCPRO1 (arg); |
24a73b0a KH |
7132 | current = XCAR (arg); |
7133 | workbuf = XCDR (arg); | |
7134 | if (! NILP (workbuf)) | |
7135 | { | |
7136 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
7137 | reused_workbuf_in_use = 0; | |
7138 | else if (! NILP (Fbuffer_live_p (workbuf))) | |
7139 | Fkill_buffer (workbuf); | |
7140 | } | |
7141 | set_buffer_internal (XBUFFER (current)); | |
948bdcf3 | 7142 | UNGCPRO; |
4776e638 KH |
7143 | return Qnil; |
7144 | } | |
b73bfc1c | 7145 | |
24a73b0a KH |
7146 | Lisp_Object |
7147 | code_conversion_save (with_work_buf, multibyte) | |
4776e638 | 7148 | int with_work_buf, multibyte; |
df7492f9 | 7149 | { |
24a73b0a | 7150 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 7151 | |
4776e638 | 7152 | if (with_work_buf) |
24a73b0a KH |
7153 | workbuf = make_conversion_work_buffer (multibyte); |
7154 | record_unwind_protect (code_conversion_restore, | |
7155 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 7156 | return workbuf; |
df7492f9 | 7157 | } |
d46c5b12 | 7158 | |
df7492f9 KH |
7159 | int |
7160 | decode_coding_gap (coding, chars, bytes) | |
7161 | struct coding_system *coding; | |
7162 | EMACS_INT chars, bytes; | |
7163 | { | |
7164 | int count = specpdl_ptr - specpdl; | |
5e5c78be | 7165 | Lisp_Object attrs; |
fb88bf2d | 7166 | |
24a73b0a | 7167 | code_conversion_save (0, 0); |
ec6d2bb8 | 7168 | |
24a73b0a | 7169 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7170 | coding->src_chars = chars; |
7171 | coding->src_bytes = bytes; | |
7172 | coding->src_pos = -chars; | |
7173 | coding->src_pos_byte = -bytes; | |
7174 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 7175 | coding->dst_object = coding->src_object; |
df7492f9 KH |
7176 | coding->dst_pos = PT; |
7177 | coding->dst_pos_byte = PT_BYTE; | |
71c81426 | 7178 | coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters); |
4ed46869 | 7179 | |
df7492f9 KH |
7180 | if (CODING_REQUIRE_DETECTION (coding)) |
7181 | detect_coding (coding); | |
8f924df7 | 7182 | |
9286b333 | 7183 | coding->mode |= CODING_MODE_LAST_BLOCK; |
287c57d7 | 7184 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 | 7185 | decode_coding (coding); |
287c57d7 | 7186 | current_buffer->text->inhibit_shrinking = 0; |
d46c5b12 | 7187 | |
5e5c78be KH |
7188 | attrs = CODING_ID_ATTRS (coding->id); |
7189 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 7190 | { |
5e5c78be KH |
7191 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
7192 | Lisp_Object val; | |
7193 | ||
7194 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
7195 | val = call1 (CODING_ATTR_POST_READ (attrs), |
7196 | make_number (coding->produced_char)); | |
5e5c78be KH |
7197 | CHECK_NATNUM (val); |
7198 | coding->produced_char += Z - prev_Z; | |
7199 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 7200 | } |
4ed46869 | 7201 | |
df7492f9 | 7202 | unbind_to (count, Qnil); |
b73bfc1c KH |
7203 | return coding->result; |
7204 | } | |
52d41803 | 7205 | |
4ed46869 | 7206 | int |
df7492f9 | 7207 | encode_coding_gap (coding, chars, bytes) |
4ed46869 | 7208 | struct coding_system *coding; |
df7492f9 | 7209 | EMACS_INT chars, bytes; |
4ed46869 | 7210 | { |
df7492f9 | 7211 | int count = specpdl_ptr - specpdl; |
4ed46869 | 7212 | |
24a73b0a | 7213 | code_conversion_save (0, 0); |
4ed46869 | 7214 | |
24a73b0a | 7215 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7216 | coding->src_chars = chars; |
7217 | coding->src_bytes = bytes; | |
7218 | coding->src_pos = -chars; | |
7219 | coding->src_pos_byte = -bytes; | |
7220 | coding->src_multibyte = chars < bytes; | |
7221 | coding->dst_object = coding->src_object; | |
7222 | coding->dst_pos = PT; | |
7223 | coding->dst_pos_byte = PT_BYTE; | |
4ed46869 | 7224 | |
df7492f9 | 7225 | encode_coding (coding); |
b73bfc1c | 7226 | |
df7492f9 KH |
7227 | unbind_to (count, Qnil); |
7228 | return coding->result; | |
7229 | } | |
4ed46869 | 7230 | |
d46c5b12 | 7231 | |
df7492f9 KH |
7232 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
7233 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 7234 | |
df7492f9 | 7235 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 7236 | |
df7492f9 KH |
7237 | If it is a buffer, the text is at point of the buffer. FROM and TO |
7238 | are positions in the buffer. | |
b73bfc1c | 7239 | |
df7492f9 KH |
7240 | If it is a string, the text is at the beginning of the string. |
7241 | FROM and TO are indices to the string. | |
4ed46869 | 7242 | |
df7492f9 KH |
7243 | If it is nil, the text is at coding->source. FROM and TO are |
7244 | indices to coding->source. | |
bb10be8b | 7245 | |
df7492f9 | 7246 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 7247 | |
df7492f9 KH |
7248 | If it is a buffer, the decoded text is inserted at point of the |
7249 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
7250 | is deleted. | |
4ed46869 | 7251 | |
df7492f9 KH |
7252 | If it is Qt, a string is made from the decoded text, and |
7253 | set in CODING->dst_object. | |
d46c5b12 | 7254 | |
df7492f9 | 7255 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 7256 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
7257 | CODING->destination by xmalloc. If the decoded text is longer than |
7258 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
7259 | */ | |
d46c5b12 | 7260 | |
df7492f9 KH |
7261 | void |
7262 | decode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
7263 | dst_object) | |
d46c5b12 | 7264 | struct coding_system *coding; |
df7492f9 KH |
7265 | Lisp_Object src_object; |
7266 | EMACS_INT from, from_byte, to, to_byte; | |
7267 | Lisp_Object dst_object; | |
d46c5b12 | 7268 | { |
df7492f9 KH |
7269 | int count = specpdl_ptr - specpdl; |
7270 | unsigned char *destination; | |
7271 | EMACS_INT dst_bytes; | |
7272 | EMACS_INT chars = to - from; | |
7273 | EMACS_INT bytes = to_byte - from_byte; | |
7274 | Lisp_Object attrs; | |
4776e638 | 7275 | int saved_pt = -1, saved_pt_byte; |
64cedb0c | 7276 | int need_marker_adjustment = 0; |
b3bfad50 | 7277 | Lisp_Object old_deactivate_mark; |
d46c5b12 | 7278 | |
b3bfad50 | 7279 | old_deactivate_mark = Vdeactivate_mark; |
93dec019 | 7280 | |
df7492f9 | 7281 | if (NILP (dst_object)) |
d46c5b12 | 7282 | { |
df7492f9 KH |
7283 | destination = coding->destination; |
7284 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 7285 | } |
93dec019 | 7286 | |
df7492f9 KH |
7287 | coding->src_object = src_object; |
7288 | coding->src_chars = chars; | |
7289 | coding->src_bytes = bytes; | |
7290 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 7291 | |
df7492f9 | 7292 | if (STRINGP (src_object)) |
d46c5b12 | 7293 | { |
df7492f9 KH |
7294 | coding->src_pos = from; |
7295 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7296 | } |
df7492f9 | 7297 | else if (BUFFERP (src_object)) |
88993dfd | 7298 | { |
df7492f9 KH |
7299 | set_buffer_internal (XBUFFER (src_object)); |
7300 | if (from != GPT) | |
7301 | move_gap_both (from, from_byte); | |
7302 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 7303 | { |
64cedb0c KH |
7304 | struct Lisp_Marker *tail; |
7305 | ||
7306 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7307 | { | |
7308 | tail->need_adjustment | |
7309 | = tail->charpos == (tail->insertion_type ? from : to); | |
7310 | need_marker_adjustment |= tail->need_adjustment; | |
7311 | } | |
4776e638 | 7312 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 | 7313 | TEMP_SET_PT_BOTH (from, from_byte); |
f4a3cc44 | 7314 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 KH |
7315 | del_range_both (from, from_byte, to, to_byte, 1); |
7316 | coding->src_pos = -chars; | |
7317 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 7318 | } |
df7492f9 | 7319 | else |
fb88bf2d | 7320 | { |
df7492f9 KH |
7321 | coding->src_pos = from; |
7322 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 7323 | } |
88993dfd KH |
7324 | } |
7325 | ||
df7492f9 KH |
7326 | if (CODING_REQUIRE_DETECTION (coding)) |
7327 | detect_coding (coding); | |
7328 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 7329 | |
2cb26057 KH |
7330 | if (EQ (dst_object, Qt) |
7331 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
7332 | && NILP (dst_object))) | |
b73bfc1c | 7333 | { |
a1567c45 SM |
7334 | coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding); |
7335 | coding->dst_object = code_conversion_save (1, coding->dst_multibyte); | |
df7492f9 KH |
7336 | coding->dst_pos = BEG; |
7337 | coding->dst_pos_byte = BEG_BYTE; | |
b73bfc1c | 7338 | } |
df7492f9 | 7339 | else if (BUFFERP (dst_object)) |
d46c5b12 | 7340 | { |
24a73b0a | 7341 | code_conversion_save (0, 0); |
df7492f9 KH |
7342 | coding->dst_object = dst_object; |
7343 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
7344 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
7345 | coding->dst_multibyte | |
7346 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
d46c5b12 KH |
7347 | } |
7348 | else | |
7349 | { | |
24a73b0a | 7350 | code_conversion_save (0, 0); |
df7492f9 | 7351 | coding->dst_object = Qnil; |
0154725e SM |
7352 | /* Most callers presume this will return a multibyte result, and they |
7353 | won't use `binary' or `raw-text' anyway, so let's not worry about | |
7354 | CODING_FOR_UNIBYTE. */ | |
bb555731 | 7355 | coding->dst_multibyte = 1; |
d46c5b12 KH |
7356 | } |
7357 | ||
df7492f9 | 7358 | decode_coding (coding); |
fa46990e | 7359 | |
df7492f9 KH |
7360 | if (BUFFERP (coding->dst_object)) |
7361 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 7362 | |
df7492f9 | 7363 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 7364 | { |
b3bfad50 | 7365 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
df7492f9 | 7366 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
2b4f9037 | 7367 | Lisp_Object val; |
d46c5b12 | 7368 | |
c0cc7f7f | 7369 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
b3bfad50 KH |
7370 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7371 | old_deactivate_mark); | |
d4850d67 KH |
7372 | val = safe_call1 (CODING_ATTR_POST_READ (attrs), |
7373 | make_number (coding->produced_char)); | |
df7492f9 KH |
7374 | UNGCPRO; |
7375 | CHECK_NATNUM (val); | |
7376 | coding->produced_char += Z - prev_Z; | |
7377 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 7378 | } |
de79a6a5 | 7379 | |
df7492f9 | 7380 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 7381 | { |
df7492f9 KH |
7382 | coding->dst_object = Fbuffer_string (); |
7383 | } | |
7384 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
7385 | { | |
7386 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7387 | if (dst_bytes < coding->produced) | |
7388 | { | |
b3bfad50 | 7389 | destination = xrealloc (destination, coding->produced); |
df7492f9 KH |
7390 | if (! destination) |
7391 | { | |
065e3595 KH |
7392 | record_conversion_result (coding, |
7393 | CODING_RESULT_INSUFFICIENT_DST); | |
df7492f9 KH |
7394 | unbind_to (count, Qnil); |
7395 | return; | |
7396 | } | |
7397 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
7398 | move_gap_both (BEGV, BEGV_BYTE); | |
7399 | bcopy (BEGV_ADDR, destination, coding->produced); | |
7400 | coding->destination = destination; | |
d46c5b12 | 7401 | } |
ec6d2bb8 | 7402 | } |
b73bfc1c | 7403 | |
4776e638 KH |
7404 | if (saved_pt >= 0) |
7405 | { | |
7406 | /* This is the case of: | |
7407 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7408 | As we have moved PT while replacing the original buffer | |
7409 | contents, we must recover it now. */ | |
7410 | set_buffer_internal (XBUFFER (src_object)); | |
f4a3cc44 | 7411 | current_buffer->text->inhibit_shrinking = 0; |
4776e638 KH |
7412 | if (saved_pt < from) |
7413 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7414 | else if (saved_pt < from + chars) | |
7415 | TEMP_SET_PT_BOTH (from, from_byte); | |
7416 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
7417 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
7418 | saved_pt_byte + (coding->produced - bytes)); | |
7419 | else | |
7420 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
7421 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7422 | |
7423 | if (need_marker_adjustment) | |
7424 | { | |
7425 | struct Lisp_Marker *tail; | |
7426 | ||
7427 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7428 | if (tail->need_adjustment) | |
7429 | { | |
7430 | tail->need_adjustment = 0; | |
7431 | if (tail->insertion_type) | |
7432 | { | |
7433 | tail->bytepos = from_byte; | |
7434 | tail->charpos = from; | |
7435 | } | |
7436 | else | |
7437 | { | |
7438 | tail->bytepos = from_byte + coding->produced; | |
7439 | tail->charpos | |
7440 | = (NILP (current_buffer->enable_multibyte_characters) | |
7441 | ? tail->bytepos : from + coding->produced_char); | |
7442 | } | |
7443 | } | |
7444 | } | |
d46c5b12 | 7445 | } |
4776e638 | 7446 | |
b3bfad50 | 7447 | Vdeactivate_mark = old_deactivate_mark; |
065e3595 | 7448 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
7449 | } |
7450 | ||
d46c5b12 | 7451 | |
df7492f9 KH |
7452 | void |
7453 | encode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
7454 | dst_object) | |
d46c5b12 | 7455 | struct coding_system *coding; |
df7492f9 KH |
7456 | Lisp_Object src_object; |
7457 | EMACS_INT from, from_byte, to, to_byte; | |
7458 | Lisp_Object dst_object; | |
d46c5b12 | 7459 | { |
b73bfc1c | 7460 | int count = specpdl_ptr - specpdl; |
df7492f9 KH |
7461 | EMACS_INT chars = to - from; |
7462 | EMACS_INT bytes = to_byte - from_byte; | |
7463 | Lisp_Object attrs; | |
4776e638 | 7464 | int saved_pt = -1, saved_pt_byte; |
64cedb0c | 7465 | int need_marker_adjustment = 0; |
c02d943b | 7466 | int kill_src_buffer = 0; |
b3bfad50 | 7467 | Lisp_Object old_deactivate_mark; |
df7492f9 | 7468 | |
b3bfad50 | 7469 | old_deactivate_mark = Vdeactivate_mark; |
df7492f9 KH |
7470 | |
7471 | coding->src_object = src_object; | |
7472 | coding->src_chars = chars; | |
7473 | coding->src_bytes = bytes; | |
7474 | coding->src_multibyte = chars < bytes; | |
7475 | ||
7476 | attrs = CODING_ID_ATTRS (coding->id); | |
7477 | ||
64cedb0c KH |
7478 | if (EQ (src_object, dst_object)) |
7479 | { | |
7480 | struct Lisp_Marker *tail; | |
7481 | ||
7482 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7483 | { | |
7484 | tail->need_adjustment | |
7485 | = tail->charpos == (tail->insertion_type ? from : to); | |
7486 | need_marker_adjustment |= tail->need_adjustment; | |
7487 | } | |
7488 | } | |
7489 | ||
df7492f9 | 7490 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) |
6bac5b12 | 7491 | { |
24a73b0a | 7492 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
7493 | set_buffer_internal (XBUFFER (coding->src_object)); |
7494 | if (STRINGP (src_object)) | |
7495 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
7496 | else if (BUFFERP (src_object)) | |
7497 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
7498 | else | |
7499 | insert_1_both (coding->source + from, chars, bytes, 0, 0, 0); | |
d46c5b12 | 7500 | |
df7492f9 KH |
7501 | if (EQ (src_object, dst_object)) |
7502 | { | |
7503 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 7504 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
7505 | del_range_both (from, from_byte, to, to_byte, 1); |
7506 | set_buffer_internal (XBUFFER (coding->src_object)); | |
7507 | } | |
7508 | ||
d4850d67 KH |
7509 | { |
7510 | Lisp_Object args[3]; | |
b3bfad50 | 7511 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d4850d67 | 7512 | |
b3bfad50 KH |
7513 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7514 | old_deactivate_mark); | |
d4850d67 KH |
7515 | args[0] = CODING_ATTR_PRE_WRITE (attrs); |
7516 | args[1] = make_number (BEG); | |
7517 | args[2] = make_number (Z); | |
7518 | safe_call (3, args); | |
b3bfad50 | 7519 | UNGCPRO; |
d4850d67 | 7520 | } |
c02d943b KH |
7521 | if (XBUFFER (coding->src_object) != current_buffer) |
7522 | kill_src_buffer = 1; | |
ac87bbef | 7523 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7524 | if (BEG != GPT) |
7525 | move_gap_both (BEG, BEG_BYTE); | |
7526 | coding->src_chars = Z - BEG; | |
7527 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
7528 | coding->src_pos = BEG; | |
7529 | coding->src_pos_byte = BEG_BYTE; | |
7530 | coding->src_multibyte = Z < Z_BYTE; | |
7531 | } | |
7532 | else if (STRINGP (src_object)) | |
d46c5b12 | 7533 | { |
24a73b0a | 7534 | code_conversion_save (0, 0); |
df7492f9 KH |
7535 | coding->src_pos = from; |
7536 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 7537 | } |
df7492f9 | 7538 | else if (BUFFERP (src_object)) |
b73bfc1c | 7539 | { |
24a73b0a | 7540 | code_conversion_save (0, 0); |
df7492f9 | 7541 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 7542 | if (EQ (src_object, dst_object)) |
d46c5b12 | 7543 | { |
4776e638 | 7544 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
7545 | coding->src_object = del_range_1 (from, to, 1, 1); |
7546 | coding->src_pos = 0; | |
7547 | coding->src_pos_byte = 0; | |
d46c5b12 | 7548 | } |
df7492f9 | 7549 | else |
d46c5b12 | 7550 | { |
ff0dacd7 KH |
7551 | if (from < GPT && to >= GPT) |
7552 | move_gap_both (from, from_byte); | |
df7492f9 KH |
7553 | coding->src_pos = from; |
7554 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7555 | } |
d46c5b12 | 7556 | } |
4776e638 | 7557 | else |
24a73b0a | 7558 | code_conversion_save (0, 0); |
d46c5b12 | 7559 | |
df7492f9 | 7560 | if (BUFFERP (dst_object)) |
88993dfd | 7561 | { |
df7492f9 | 7562 | coding->dst_object = dst_object; |
28f67a95 KH |
7563 | if (EQ (src_object, dst_object)) |
7564 | { | |
7565 | coding->dst_pos = from; | |
7566 | coding->dst_pos_byte = from_byte; | |
7567 | } | |
7568 | else | |
7569 | { | |
319a3947 KH |
7570 | struct buffer *current = current_buffer; |
7571 | ||
7572 | set_buffer_temp (XBUFFER (dst_object)); | |
7573 | coding->dst_pos = PT; | |
7574 | coding->dst_pos_byte = PT_BYTE; | |
7575 | move_gap_both (coding->dst_pos, coding->dst_pos_byte); | |
7576 | set_buffer_temp (current); | |
28f67a95 | 7577 | } |
df7492f9 KH |
7578 | coding->dst_multibyte |
7579 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
88993dfd | 7580 | } |
df7492f9 | 7581 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 7582 | { |
df7492f9 | 7583 | coding->dst_object = Qnil; |
df7492f9 | 7584 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
7585 | if (coding->dst_bytes == 0) |
7586 | coding->dst_bytes = 1; | |
7587 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 7588 | coding->dst_multibyte = 0; |
d46c5b12 KH |
7589 | } |
7590 | else | |
7591 | { | |
df7492f9 KH |
7592 | coding->dst_object = Qnil; |
7593 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
7594 | } |
7595 | ||
df7492f9 | 7596 | encode_coding (coding); |
d46c5b12 | 7597 | |
df7492f9 | 7598 | if (EQ (dst_object, Qt)) |
d46c5b12 | 7599 | { |
df7492f9 KH |
7600 | if (BUFFERP (coding->dst_object)) |
7601 | coding->dst_object = Fbuffer_string (); | |
7602 | else | |
d46c5b12 | 7603 | { |
df7492f9 KH |
7604 | coding->dst_object |
7605 | = make_unibyte_string ((char *) coding->destination, | |
7606 | coding->produced); | |
7607 | xfree (coding->destination); | |
d46c5b12 | 7608 | } |
4ed46869 | 7609 | } |
d46c5b12 | 7610 | |
4776e638 KH |
7611 | if (saved_pt >= 0) |
7612 | { | |
7613 | /* This is the case of: | |
7614 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7615 | As we have moved PT while replacing the original buffer | |
7616 | contents, we must recover it now. */ | |
7617 | set_buffer_internal (XBUFFER (src_object)); | |
7618 | if (saved_pt < from) | |
7619 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7620 | else if (saved_pt < from + chars) | |
7621 | TEMP_SET_PT_BOTH (from, from_byte); | |
7622 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
7623 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
7624 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 7625 | else |
4776e638 KH |
7626 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
7627 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7628 | |
7629 | if (need_marker_adjustment) | |
7630 | { | |
7631 | struct Lisp_Marker *tail; | |
7632 | ||
7633 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7634 | if (tail->need_adjustment) | |
7635 | { | |
7636 | tail->need_adjustment = 0; | |
7637 | if (tail->insertion_type) | |
7638 | { | |
7639 | tail->bytepos = from_byte; | |
7640 | tail->charpos = from; | |
7641 | } | |
7642 | else | |
7643 | { | |
7644 | tail->bytepos = from_byte + coding->produced; | |
7645 | tail->charpos | |
7646 | = (NILP (current_buffer->enable_multibyte_characters) | |
7647 | ? tail->bytepos : from + coding->produced_char); | |
7648 | } | |
7649 | } | |
7650 | } | |
4776e638 KH |
7651 | } |
7652 | ||
c02d943b KH |
7653 | if (kill_src_buffer) |
7654 | Fkill_buffer (coding->src_object); | |
b3bfad50 KH |
7655 | |
7656 | Vdeactivate_mark = old_deactivate_mark; | |
df7492f9 | 7657 | unbind_to (count, Qnil); |
b73bfc1c KH |
7658 | } |
7659 | ||
df7492f9 | 7660 | |
b73bfc1c | 7661 | Lisp_Object |
df7492f9 | 7662 | preferred_coding_system () |
b73bfc1c | 7663 | { |
df7492f9 | 7664 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 7665 | |
df7492f9 | 7666 | return CODING_ID_NAME (id); |
4ed46869 KH |
7667 | } |
7668 | ||
7669 | \f | |
7670 | #ifdef emacs | |
1397dc18 | 7671 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 7672 | |
4ed46869 | 7673 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 7674 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 7675 | See the documentation of `define-coding-system' for information |
48b0f3ae | 7676 | about coding-system objects. */) |
d4a1d553 JB |
7677 | (object) |
7678 | Lisp_Object object; | |
4ed46869 | 7679 | { |
d4a1d553 JB |
7680 | if (NILP (object) |
7681 | || CODING_SYSTEM_ID (object) >= 0) | |
44e8490d | 7682 | return Qt; |
d4a1d553 JB |
7683 | if (! SYMBOLP (object) |
7684 | || NILP (Fget (object, Qcoding_system_define_form))) | |
44e8490d KH |
7685 | return Qnil; |
7686 | return Qt; | |
4ed46869 KH |
7687 | } |
7688 | ||
9d991de8 RS |
7689 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
7690 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae PJ |
7691 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
7692 | (prompt) | |
4ed46869 KH |
7693 | Lisp_Object prompt; |
7694 | { | |
e0e989f6 | 7695 | Lisp_Object val; |
9d991de8 RS |
7696 | do |
7697 | { | |
4608c386 KH |
7698 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
7699 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 7700 | } |
8f924df7 | 7701 | while (SCHARS (val) == 0); |
e0e989f6 | 7702 | return (Fintern (val, Qnil)); |
4ed46869 KH |
7703 | } |
7704 | ||
9b787f3e | 7705 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae | 7706 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
c7183fb8 GM |
7707 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. |
7708 | Ignores case when completing coding systems (all Emacs coding systems | |
7709 | are lower-case). */) | |
48b0f3ae | 7710 | (prompt, default_coding_system) |
9b787f3e | 7711 | Lisp_Object prompt, default_coding_system; |
4ed46869 | 7712 | { |
f44d27ce | 7713 | Lisp_Object val; |
c7183fb8 GM |
7714 | int count = SPECPDL_INDEX (); |
7715 | ||
9b787f3e | 7716 | if (SYMBOLP (default_coding_system)) |
57d25e6f | 7717 | default_coding_system = SYMBOL_NAME (default_coding_system); |
c7183fb8 | 7718 | specbind (Qcompletion_ignore_case, Qt); |
4608c386 | 7719 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
7720 | Qt, Qnil, Qcoding_system_history, |
7721 | default_coding_system, Qnil); | |
c7183fb8 | 7722 | unbind_to (count, Qnil); |
8f924df7 | 7723 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
7724 | } |
7725 | ||
7726 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
7727 | 1, 1, 0, | |
48b0f3ae | 7728 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
7729 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
7730 | It is valid if it is nil or a symbol defined as a coding system by the | |
7731 | function `define-coding-system'. */) | |
df7492f9 | 7732 | (coding_system) |
4ed46869 KH |
7733 | Lisp_Object coding_system; |
7734 | { | |
44e8490d KH |
7735 | Lisp_Object define_form; |
7736 | ||
7737 | define_form = Fget (coding_system, Qcoding_system_define_form); | |
7738 | if (! NILP (define_form)) | |
7739 | { | |
7740 | Fput (coding_system, Qcoding_system_define_form, Qnil); | |
7741 | safe_eval (define_form); | |
7742 | } | |
4ed46869 KH |
7743 | if (!NILP (Fcoding_system_p (coding_system))) |
7744 | return coding_system; | |
fcad4ec4 | 7745 | xsignal1 (Qcoding_system_error, coding_system); |
4ed46869 | 7746 | } |
df7492f9 | 7747 | |
3a73fa5d | 7748 | \f |
89528eb3 KH |
7749 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
7750 | HIGHEST is nonzero, return the coding system of the highest | |
7751 | priority among the detected coding systems. Otherwize return a | |
7752 | list of detected coding systems sorted by their priorities. If | |
7753 | MULTIBYTEP is nonzero, it is assumed that the bytes are in correct | |
7754 | multibyte form but contains only ASCII and eight-bit chars. | |
7755 | Otherwise, the bytes are raw bytes. | |
7756 | ||
7757 | CODING-SYSTEM controls the detection as below: | |
7758 | ||
7759 | If it is nil, detect both text-format and eol-format. If the | |
7760 | text-format part of CODING-SYSTEM is already specified | |
7761 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
7762 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
7763 | detect only text-format. */ | |
7764 | ||
d46c5b12 | 7765 | Lisp_Object |
24a73b0a KH |
7766 | detect_coding_system (src, src_chars, src_bytes, highest, multibytep, |
7767 | coding_system) | |
8f924df7 | 7768 | const unsigned char *src; |
13818c30 SM |
7769 | EMACS_INT src_chars, src_bytes; |
7770 | int highest; | |
0a28aafb | 7771 | int multibytep; |
df7492f9 | 7772 | Lisp_Object coding_system; |
4ed46869 | 7773 | { |
8f924df7 | 7774 | const unsigned char *src_end = src + src_bytes; |
df7492f9 | 7775 | Lisp_Object attrs, eol_type; |
4533845d | 7776 | Lisp_Object val = Qnil; |
df7492f9 | 7777 | struct coding_system coding; |
89528eb3 | 7778 | int id; |
ff0dacd7 | 7779 | struct coding_detection_info detect_info; |
24a73b0a | 7780 | enum coding_category base_category; |
2f3cbb32 | 7781 | int null_byte_found = 0, eight_bit_found = 0; |
b73bfc1c | 7782 | |
df7492f9 KH |
7783 | if (NILP (coding_system)) |
7784 | coding_system = Qundecided; | |
7785 | setup_coding_system (coding_system, &coding); | |
7786 | attrs = CODING_ID_ATTRS (coding.id); | |
7787 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 7788 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 7789 | |
df7492f9 | 7790 | coding.source = src; |
24a73b0a | 7791 | coding.src_chars = src_chars; |
df7492f9 KH |
7792 | coding.src_bytes = src_bytes; |
7793 | coding.src_multibyte = multibytep; | |
7794 | coding.consumed = 0; | |
89528eb3 | 7795 | coding.mode |= CODING_MODE_LAST_BLOCK; |
c0e16b14 | 7796 | coding.head_ascii = 0; |
d46c5b12 | 7797 | |
ff0dacd7 | 7798 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 7799 | |
89528eb3 | 7800 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
7801 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
7802 | if (base_category == coding_category_undecided) | |
4ed46869 | 7803 | { |
ff0dacd7 KH |
7804 | enum coding_category category; |
7805 | struct coding_system *this; | |
7806 | int c, i; | |
88993dfd | 7807 | |
24a73b0a | 7808 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
2f3cbb32 | 7809 | for (; src < src_end; src++) |
4ed46869 | 7810 | { |
df7492f9 | 7811 | c = *src; |
6cb21a4f | 7812 | if (c & 0x80) |
6cb21a4f | 7813 | { |
2f3cbb32 | 7814 | eight_bit_found = 1; |
2f3cbb32 KH |
7815 | if (null_byte_found) |
7816 | break; | |
7817 | } | |
c0e16b14 | 7818 | else if (c < 0x20) |
2f3cbb32 KH |
7819 | { |
7820 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
7821 | && ! inhibit_iso_escape_detection | |
7822 | && ! detect_info.checked) | |
6cb21a4f | 7823 | { |
2f3cbb32 KH |
7824 | if (detect_coding_iso_2022 (&coding, &detect_info)) |
7825 | { | |
7826 | /* We have scanned the whole data. */ | |
7827 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
7828 | { |
7829 | /* We didn't find an 8-bit code. We may | |
7830 | have found a null-byte, but it's very | |
7831 | rare that a binary file confirm to | |
7832 | ISO-2022. */ | |
7833 | src = src_end; | |
7834 | coding.head_ascii = src - coding.source; | |
7835 | } | |
7836 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
7837 | break; |
7838 | } | |
7839 | } | |
97b1b294 | 7840 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
7841 | { |
7842 | null_byte_found = 1; | |
7843 | if (eight_bit_found) | |
7844 | break; | |
6cb21a4f | 7845 | } |
c006c0c8 KH |
7846 | if (! eight_bit_found) |
7847 | coding.head_ascii++; | |
6cb21a4f | 7848 | } |
c006c0c8 | 7849 | else if (! eight_bit_found) |
c0e16b14 | 7850 | coding.head_ascii++; |
4ed46869 | 7851 | } |
88993dfd | 7852 | |
2f3cbb32 KH |
7853 | if (null_byte_found || eight_bit_found |
7854 | || coding.head_ascii < coding.src_bytes | |
6cb21a4f KH |
7855 | || detect_info.found) |
7856 | { | |
2f3cbb32 | 7857 | if (coding.head_ascii == coding.src_bytes) |
6cb21a4f KH |
7858 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ |
7859 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 7860 | { |
6cb21a4f | 7861 | category = coding_priorities[i]; |
c7266f4a | 7862 | this = coding_categories + category; |
6cb21a4f | 7863 | if (detect_info.found & (1 << category)) |
ff0dacd7 KH |
7864 | break; |
7865 | } | |
6cb21a4f | 7866 | else |
2f3cbb32 KH |
7867 | { |
7868 | if (null_byte_found) | |
7869 | { | |
7870 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; | |
7871 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
7872 | } | |
7873 | for (i = 0; i < coding_category_raw_text; i++) | |
7874 | { | |
7875 | category = coding_priorities[i]; | |
7876 | this = coding_categories + category; | |
6cb21a4f | 7877 | |
2f3cbb32 KH |
7878 | if (this->id < 0) |
7879 | { | |
7880 | /* No coding system of this category is defined. */ | |
7881 | detect_info.rejected |= (1 << category); | |
7882 | } | |
7883 | else if (category >= coding_category_raw_text) | |
7884 | continue; | |
7885 | else if (detect_info.checked & (1 << category)) | |
7886 | { | |
7887 | if (highest | |
7888 | && (detect_info.found & (1 << category))) | |
6cb21a4f | 7889 | break; |
2f3cbb32 KH |
7890 | } |
7891 | else if ((*(this->detector)) (&coding, &detect_info) | |
7892 | && highest | |
7893 | && (detect_info.found & (1 << category))) | |
7894 | { | |
7895 | if (category == coding_category_utf_16_auto) | |
7896 | { | |
7897 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
7898 | category = coding_category_utf_16_le; | |
7899 | else | |
7900 | category = coding_category_utf_16_be; | |
7901 | } | |
7902 | break; | |
7903 | } | |
7904 | } | |
7905 | } | |
6cb21a4f | 7906 | } |
ec6d2bb8 | 7907 | |
4cddb209 KH |
7908 | if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY |
7909 | || null_byte_found) | |
ec6d2bb8 | 7910 | { |
ff0dacd7 | 7911 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
4cddb209 | 7912 | id = CODING_SYSTEM_ID (Qno_conversion); |
89528eb3 KH |
7913 | val = Fcons (make_number (id), Qnil); |
7914 | } | |
ff0dacd7 | 7915 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 7916 | { |
ff0dacd7 | 7917 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
7918 | id = coding_categories[coding_category_undecided].id; |
7919 | val = Fcons (make_number (id), Qnil); | |
7920 | } | |
7921 | else if (highest) | |
7922 | { | |
ff0dacd7 | 7923 | if (detect_info.found) |
ec6d2bb8 | 7924 | { |
ff0dacd7 KH |
7925 | detect_info.found = 1 << category; |
7926 | val = Fcons (make_number (this->id), Qnil); | |
7927 | } | |
7928 | else | |
7929 | for (i = 0; i < coding_category_raw_text; i++) | |
7930 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
7931 | { | |
7932 | detect_info.found = 1 << coding_priorities[i]; | |
7933 | id = coding_categories[coding_priorities[i]].id; | |
7934 | val = Fcons (make_number (id), Qnil); | |
7935 | break; | |
7936 | } | |
7937 | } | |
89528eb3 KH |
7938 | else |
7939 | { | |
ff0dacd7 KH |
7940 | int mask = detect_info.rejected | detect_info.found; |
7941 | int found = 0; | |
ec6d2bb8 | 7942 | |
89528eb3 | 7943 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
7944 | { |
7945 | category = coding_priorities[i]; | |
7946 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 7947 | { |
ff0dacd7 KH |
7948 | found |= 1 << category; |
7949 | id = coding_categories[category].id; | |
c7266f4a KH |
7950 | if (id >= 0) |
7951 | val = Fcons (make_number (id), val); | |
ff0dacd7 KH |
7952 | } |
7953 | } | |
7954 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
7955 | { | |
7956 | category = coding_priorities[i]; | |
7957 | if (detect_info.found & (1 << category)) | |
7958 | { | |
7959 | id = coding_categories[category].id; | |
7960 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 7961 | } |
ec6d2bb8 | 7962 | } |
ff0dacd7 | 7963 | detect_info.found |= found; |
ec6d2bb8 | 7964 | } |
ec6d2bb8 | 7965 | } |
a470d443 KH |
7966 | else if (base_category == coding_category_utf_8_auto) |
7967 | { | |
7968 | if (detect_coding_utf_8 (&coding, &detect_info)) | |
7969 | { | |
7970 | struct coding_system *this; | |
7971 | ||
7972 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
7973 | this = coding_categories + coding_category_utf_8_sig; | |
7974 | else | |
7975 | this = coding_categories + coding_category_utf_8_nosig; | |
7976 | val = Fcons (make_number (this->id), Qnil); | |
7977 | } | |
7978 | } | |
24a73b0a KH |
7979 | else if (base_category == coding_category_utf_16_auto) |
7980 | { | |
7981 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
7982 | { | |
24a73b0a KH |
7983 | struct coding_system *this; |
7984 | ||
7985 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
7986 | this = coding_categories + coding_category_utf_16_le; | |
7987 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
7988 | this = coding_categories + coding_category_utf_16_be; | |
7989 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
7990 | this = coding_categories + coding_category_utf_16_be_nosig; | |
7991 | else | |
7992 | this = coding_categories + coding_category_utf_16_le_nosig; | |
7993 | val = Fcons (make_number (this->id), Qnil); | |
7994 | } | |
7995 | } | |
df7492f9 KH |
7996 | else |
7997 | { | |
ff0dacd7 | 7998 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 7999 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 8000 | } |
df7492f9 | 8001 | |
89528eb3 | 8002 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 8003 | { |
4533845d | 8004 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol = -1; |
df7492f9 KH |
8005 | Lisp_Object tail; |
8006 | ||
89528eb3 KH |
8007 | if (VECTORP (eol_type)) |
8008 | { | |
ff0dacd7 | 8009 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
2f3cbb32 KH |
8010 | { |
8011 | if (null_byte_found) | |
8012 | normal_eol = EOL_SEEN_LF; | |
8013 | else | |
8014 | normal_eol = detect_eol (coding.source, src_bytes, | |
8015 | coding_category_raw_text); | |
8016 | } | |
ff0dacd7 KH |
8017 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
8018 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
8019 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
8020 | coding_category_utf_16_be); | |
ff0dacd7 KH |
8021 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
8022 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
8023 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
8024 | coding_category_utf_16_le); | |
8025 | } | |
8026 | else | |
8027 | { | |
8028 | if (EQ (eol_type, Qunix)) | |
8029 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
8030 | else if (EQ (eol_type, Qdos)) | |
8031 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
8032 | else | |
8033 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
8034 | } | |
8035 | ||
df7492f9 KH |
8036 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
8037 | { | |
89528eb3 | 8038 | enum coding_category category; |
df7492f9 | 8039 | int this_eol; |
89528eb3 KH |
8040 | |
8041 | id = XINT (XCAR (tail)); | |
8042 | attrs = CODING_ID_ATTRS (id); | |
8043 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8044 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
8045 | if (VECTORP (eol_type)) |
8046 | { | |
89528eb3 KH |
8047 | if (category == coding_category_utf_16_be |
8048 | || category == coding_category_utf_16_be_nosig) | |
8049 | this_eol = utf_16_be_eol; | |
8050 | else if (category == coding_category_utf_16_le | |
8051 | || category == coding_category_utf_16_le_nosig) | |
8052 | this_eol = utf_16_le_eol; | |
df7492f9 | 8053 | else |
89528eb3 KH |
8054 | this_eol = normal_eol; |
8055 | ||
df7492f9 KH |
8056 | if (this_eol == EOL_SEEN_LF) |
8057 | XSETCAR (tail, AREF (eol_type, 0)); | |
8058 | else if (this_eol == EOL_SEEN_CRLF) | |
8059 | XSETCAR (tail, AREF (eol_type, 1)); | |
8060 | else if (this_eol == EOL_SEEN_CR) | |
8061 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
8062 | else |
8063 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 8064 | } |
89528eb3 KH |
8065 | else |
8066 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
8067 | } |
8068 | } | |
ec6d2bb8 | 8069 | |
4533845d | 8070 | return (highest ? (CONSP (val) ? XCAR (val) : Qnil) : val); |
ec6d2bb8 KH |
8071 | } |
8072 | ||
ec6d2bb8 | 8073 | |
d46c5b12 KH |
8074 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
8075 | 2, 3, 0, | |
48b0f3ae PJ |
8076 | doc: /* Detect coding system of the text in the region between START and END. |
8077 | Return a list of possible coding systems ordered by priority. | |
ec6d2bb8 | 8078 | |
12e0131a | 8079 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8080 | characters as ESC), it returns a list of single element `undecided' |
8081 | or its subsidiary coding system according to a detected end-of-line | |
8082 | format. | |
ec6d2bb8 | 8083 | |
48b0f3ae PJ |
8084 | If optional argument HIGHEST is non-nil, return the coding system of |
8085 | highest priority. */) | |
8086 | (start, end, highest) | |
d46c5b12 KH |
8087 | Lisp_Object start, end, highest; |
8088 | { | |
8089 | int from, to; | |
8090 | int from_byte, to_byte; | |
ec6d2bb8 | 8091 | |
b7826503 PJ |
8092 | CHECK_NUMBER_COERCE_MARKER (start); |
8093 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 8094 | |
d46c5b12 KH |
8095 | validate_region (&start, &end); |
8096 | from = XINT (start), to = XINT (end); | |
8097 | from_byte = CHAR_TO_BYTE (from); | |
8098 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 8099 | |
d46c5b12 KH |
8100 | if (from < GPT && to >= GPT) |
8101 | move_gap_both (to, to_byte); | |
c210f766 | 8102 | |
d46c5b12 | 8103 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 8104 | to - from, to_byte - from_byte, |
0a28aafb KH |
8105 | !NILP (highest), |
8106 | !NILP (current_buffer | |
df7492f9 KH |
8107 | ->enable_multibyte_characters), |
8108 | Qnil); | |
ec6d2bb8 KH |
8109 | } |
8110 | ||
d46c5b12 KH |
8111 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
8112 | 1, 2, 0, | |
48b0f3ae PJ |
8113 | doc: /* Detect coding system of the text in STRING. |
8114 | Return a list of possible coding systems ordered by priority. | |
fb88bf2d | 8115 | |
12e0131a | 8116 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8117 | characters as ESC), it returns a list of single element `undecided' |
8118 | or its subsidiary coding system according to a detected end-of-line | |
8119 | format. | |
d46c5b12 | 8120 | |
48b0f3ae PJ |
8121 | If optional argument HIGHEST is non-nil, return the coding system of |
8122 | highest priority. */) | |
8123 | (string, highest) | |
d46c5b12 KH |
8124 | Lisp_Object string, highest; |
8125 | { | |
b7826503 | 8126 | CHECK_STRING (string); |
b73bfc1c | 8127 | |
24a73b0a KH |
8128 | return detect_coding_system (SDATA (string), |
8129 | SCHARS (string), SBYTES (string), | |
8f924df7 | 8130 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 8131 | Qnil); |
4ed46869 | 8132 | } |
4ed46869 | 8133 | |
b73bfc1c | 8134 | |
df7492f9 KH |
8135 | static INLINE int |
8136 | char_encodable_p (c, attrs) | |
8137 | int c; | |
8138 | Lisp_Object attrs; | |
05e6f5dc | 8139 | { |
df7492f9 | 8140 | Lisp_Object tail; |
df7492f9 | 8141 | struct charset *charset; |
7d64c6ad | 8142 | Lisp_Object translation_table; |
d46c5b12 | 8143 | |
7d64c6ad | 8144 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 8145 | if (! NILP (translation_table)) |
7d64c6ad | 8146 | c = translate_char (translation_table, c); |
df7492f9 KH |
8147 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
8148 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 8149 | { |
df7492f9 KH |
8150 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
8151 | if (CHAR_CHARSET_P (c, charset)) | |
8152 | break; | |
e133c8fa | 8153 | } |
df7492f9 | 8154 | return (! NILP (tail)); |
05e6f5dc | 8155 | } |
83fa074f | 8156 | |
fb88bf2d | 8157 | |
df7492f9 KH |
8158 | /* Return a list of coding systems that safely encode the text between |
8159 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
8160 | systems not to check. The returned list doesn't contain any such | |
48468dac | 8161 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 8162 | unibyte, return t. */ |
e077cc80 | 8163 | |
df7492f9 KH |
8164 | DEFUN ("find-coding-systems-region-internal", |
8165 | Ffind_coding_systems_region_internal, | |
8166 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
8167 | doc: /* Internal use only. */) | |
8168 | (start, end, exclude) | |
8169 | Lisp_Object start, end, exclude; | |
8170 | { | |
8171 | Lisp_Object coding_attrs_list, safe_codings; | |
8172 | EMACS_INT start_byte, end_byte; | |
7c78e542 | 8173 | const unsigned char *p, *pbeg, *pend; |
df7492f9 KH |
8174 | int c; |
8175 | Lisp_Object tail, elt; | |
d46c5b12 | 8176 | |
df7492f9 KH |
8177 | if (STRINGP (start)) |
8178 | { | |
8179 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 8180 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8181 | return Qt; |
8182 | start_byte = 0; | |
8f924df7 | 8183 | end_byte = SBYTES (start); |
df7492f9 KH |
8184 | } |
8185 | else | |
d46c5b12 | 8186 | { |
df7492f9 KH |
8187 | CHECK_NUMBER_COERCE_MARKER (start); |
8188 | CHECK_NUMBER_COERCE_MARKER (end); | |
8189 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
8190 | args_out_of_range (start, end); | |
8191 | if (NILP (current_buffer->enable_multibyte_characters)) | |
8192 | return Qt; | |
8193 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8194 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8195 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
8196 | return Qt; | |
d46c5b12 | 8197 | |
e1c23804 | 8198 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 8199 | { |
e1c23804 DL |
8200 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8201 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8202 | else |
e1c23804 | 8203 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
8204 | } |
8205 | } | |
8206 | ||
df7492f9 KH |
8207 | coding_attrs_list = Qnil; |
8208 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
8209 | if (NILP (exclude) | |
8210 | || NILP (Fmemq (XCAR (tail), exclude))) | |
8211 | { | |
8212 | Lisp_Object attrs; | |
d46c5b12 | 8213 | |
df7492f9 KH |
8214 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
8215 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
8216 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
8217 | { |
8218 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 8219 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
8220 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
8221 | } | |
df7492f9 | 8222 | } |
d46c5b12 | 8223 | |
df7492f9 | 8224 | if (STRINGP (start)) |
8f924df7 | 8225 | p = pbeg = SDATA (start); |
df7492f9 KH |
8226 | else |
8227 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
8228 | pend = p + (end_byte - start_byte); | |
b843d1ae | 8229 | |
df7492f9 KH |
8230 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
8231 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 8232 | |
05e6f5dc | 8233 | while (p < pend) |
72d1a715 | 8234 | { |
df7492f9 KH |
8235 | if (ASCII_BYTE_P (*p)) |
8236 | p++; | |
72d1a715 RS |
8237 | else |
8238 | { | |
df7492f9 | 8239 | c = STRING_CHAR_ADVANCE (p); |
12410ef1 | 8240 | |
df7492f9 KH |
8241 | charset_map_loaded = 0; |
8242 | for (tail = coding_attrs_list; CONSP (tail);) | |
8243 | { | |
8244 | elt = XCAR (tail); | |
8245 | if (NILP (elt)) | |
8246 | tail = XCDR (tail); | |
8247 | else if (char_encodable_p (c, elt)) | |
8248 | tail = XCDR (tail); | |
8249 | else if (CONSP (XCDR (tail))) | |
8250 | { | |
8251 | XSETCAR (tail, XCAR (XCDR (tail))); | |
8252 | XSETCDR (tail, XCDR (XCDR (tail))); | |
8253 | } | |
8254 | else | |
8255 | { | |
8256 | XSETCAR (tail, Qnil); | |
8257 | tail = XCDR (tail); | |
8258 | } | |
8259 | } | |
8260 | if (charset_map_loaded) | |
8261 | { | |
8262 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 8263 | |
df7492f9 | 8264 | if (STRINGP (start)) |
8f924df7 | 8265 | pbeg = SDATA (start); |
df7492f9 KH |
8266 | else |
8267 | pbeg = BYTE_POS_ADDR (start_byte); | |
8268 | p = pbeg + p_offset; | |
8269 | pend = pbeg + pend_offset; | |
8270 | } | |
8271 | } | |
ec6d2bb8 | 8272 | } |
fb88bf2d | 8273 | |
988b3759 | 8274 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
8275 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
8276 | if (! NILP (XCAR (tail))) | |
8277 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 8278 | |
05e6f5dc KH |
8279 | return safe_codings; |
8280 | } | |
4956c225 | 8281 | |
d46c5b12 | 8282 | |
8f924df7 KH |
8283 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
8284 | Sunencodable_char_position, 3, 5, 0, | |
8285 | doc: /* | |
8286 | Return position of first un-encodable character in a region. | |
d4a1d553 | 8287 | START and END specify the region and CODING-SYSTEM specifies the |
8f924df7 | 8288 | encoding to check. Return nil if CODING-SYSTEM does encode the region. |
d46c5b12 | 8289 | |
8f924df7 KH |
8290 | If optional 4th argument COUNT is non-nil, it specifies at most how |
8291 | many un-encodable characters to search. In this case, the value is a | |
8292 | list of positions. | |
d46c5b12 | 8293 | |
8f924df7 KH |
8294 | If optional 5th argument STRING is non-nil, it is a string to search |
8295 | for un-encodable characters. In that case, START and END are indexes | |
8296 | to the string. */) | |
8297 | (start, end, coding_system, count, string) | |
8298 | Lisp_Object start, end, coding_system, count, string; | |
8299 | { | |
8300 | int n; | |
8301 | struct coding_system coding; | |
7d64c6ad | 8302 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 KH |
8303 | Lisp_Object positions; |
8304 | int from, to; | |
8305 | const unsigned char *p, *stop, *pend; | |
8306 | int ascii_compatible; | |
fb88bf2d | 8307 | |
8f924df7 KH |
8308 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
8309 | attrs = CODING_ID_ATTRS (coding.id); | |
8310 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
8311 | return Qnil; | |
8312 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
8313 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 8314 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 8315 | |
8f924df7 KH |
8316 | if (NILP (string)) |
8317 | { | |
8318 | validate_region (&start, &end); | |
8319 | from = XINT (start); | |
8320 | to = XINT (end); | |
8321 | if (NILP (current_buffer->enable_multibyte_characters) | |
8322 | || (ascii_compatible | |
8323 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
8324 | return Qnil; | |
8325 | p = CHAR_POS_ADDR (from); | |
8326 | pend = CHAR_POS_ADDR (to); | |
8327 | if (from < GPT && to >= GPT) | |
8328 | stop = GPT_ADDR; | |
8329 | else | |
8330 | stop = pend; | |
8331 | } | |
8332 | else | |
8333 | { | |
8334 | CHECK_STRING (string); | |
8335 | CHECK_NATNUM (start); | |
8336 | CHECK_NATNUM (end); | |
8337 | from = XINT (start); | |
8338 | to = XINT (end); | |
8339 | if (from > to | |
8340 | || to > SCHARS (string)) | |
8341 | args_out_of_range_3 (string, start, end); | |
8342 | if (! STRING_MULTIBYTE (string)) | |
8343 | return Qnil; | |
8344 | p = SDATA (string) + string_char_to_byte (string, from); | |
8345 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
8346 | if (ascii_compatible && (to - from) == (pend - p)) | |
8347 | return Qnil; | |
8348 | } | |
f2558efd | 8349 | |
8f924df7 KH |
8350 | if (NILP (count)) |
8351 | n = 1; | |
8352 | else | |
b73bfc1c | 8353 | { |
8f924df7 KH |
8354 | CHECK_NATNUM (count); |
8355 | n = XINT (count); | |
b73bfc1c KH |
8356 | } |
8357 | ||
8f924df7 KH |
8358 | positions = Qnil; |
8359 | while (1) | |
d46c5b12 | 8360 | { |
8f924df7 | 8361 | int c; |
ec6d2bb8 | 8362 | |
8f924df7 KH |
8363 | if (ascii_compatible) |
8364 | while (p < stop && ASCII_BYTE_P (*p)) | |
8365 | p++, from++; | |
8366 | if (p >= stop) | |
0e79d667 | 8367 | { |
8f924df7 KH |
8368 | if (p >= pend) |
8369 | break; | |
8370 | stop = pend; | |
8371 | p = GAP_END_ADDR; | |
0e79d667 | 8372 | } |
ec6d2bb8 | 8373 | |
8f924df7 KH |
8374 | c = STRING_CHAR_ADVANCE (p); |
8375 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
8376 | && ! char_charset (translate_char (translation_table, c), |
8377 | charset_list, NULL)) | |
ec6d2bb8 | 8378 | { |
8f924df7 KH |
8379 | positions = Fcons (make_number (from), positions); |
8380 | n--; | |
8381 | if (n == 0) | |
8382 | break; | |
ec6d2bb8 KH |
8383 | } |
8384 | ||
8f924df7 KH |
8385 | from++; |
8386 | } | |
d46c5b12 | 8387 | |
8f924df7 KH |
8388 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
8389 | } | |
d46c5b12 | 8390 | |
d46c5b12 | 8391 | |
df7492f9 KH |
8392 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
8393 | Scheck_coding_systems_region, 3, 3, 0, | |
8394 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 8395 | |
df7492f9 KH |
8396 | START and END are buffer positions specifying the region. |
8397 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 8398 | |
df7492f9 | 8399 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
d4a1d553 | 8400 | CODING-SYSTEM is a member of CODING-SYSTEM-LIST and can't encode the |
df7492f9 KH |
8401 | whole region, POS0, POS1, ... are buffer positions where non-encodable |
8402 | characters are found. | |
93dec019 | 8403 | |
df7492f9 KH |
8404 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
8405 | value is nil. | |
93dec019 | 8406 | |
df7492f9 KH |
8407 | START may be a string. In that case, check if the string is |
8408 | encodable, and the value contains indices to the string instead of | |
8409 | buffer positions. END is ignored. */) | |
8410 | (start, end, coding_system_list) | |
8411 | Lisp_Object start, end, coding_system_list; | |
05e6f5dc | 8412 | { |
df7492f9 KH |
8413 | Lisp_Object list; |
8414 | EMACS_INT start_byte, end_byte; | |
8415 | int pos; | |
7c78e542 | 8416 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8417 | int c; |
7d64c6ad | 8418 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 8419 | |
05e6f5dc KH |
8420 | if (STRINGP (start)) |
8421 | { | |
df7492f9 | 8422 | if (!STRING_MULTIBYTE (start) |
8f924df7 | 8423 | && SCHARS (start) != SBYTES (start)) |
df7492f9 KH |
8424 | return Qnil; |
8425 | start_byte = 0; | |
8f924df7 | 8426 | end_byte = SBYTES (start); |
df7492f9 | 8427 | pos = 0; |
d46c5b12 | 8428 | } |
05e6f5dc | 8429 | else |
b73bfc1c | 8430 | { |
b7826503 PJ |
8431 | CHECK_NUMBER_COERCE_MARKER (start); |
8432 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
8433 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
8434 | args_out_of_range (start, end); | |
8435 | if (NILP (current_buffer->enable_multibyte_characters)) | |
df7492f9 KH |
8436 | return Qnil; |
8437 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8438 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8439 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
05e6f5dc | 8440 | return Qt; |
df7492f9 | 8441 | |
e1c23804 | 8442 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 8443 | { |
e1c23804 DL |
8444 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8445 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8446 | else |
e1c23804 | 8447 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 8448 | } |
e1c23804 | 8449 | pos = XINT (start); |
b73bfc1c | 8450 | } |
7553d0e1 | 8451 | |
df7492f9 KH |
8452 | list = Qnil; |
8453 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 8454 | { |
df7492f9 | 8455 | elt = XCAR (tail); |
7d64c6ad | 8456 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
8457 | ASET (attrs, coding_attr_trans_tbl, |
8458 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 8459 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
8460 | } |
8461 | ||
df7492f9 | 8462 | if (STRINGP (start)) |
8f924df7 | 8463 | p = pbeg = SDATA (start); |
72d1a715 | 8464 | else |
df7492f9 KH |
8465 | p = pbeg = BYTE_POS_ADDR (start_byte); |
8466 | pend = p + (end_byte - start_byte); | |
4ed46869 | 8467 | |
df7492f9 KH |
8468 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
8469 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 8470 | |
df7492f9 | 8471 | while (p < pend) |
d46c5b12 | 8472 | { |
df7492f9 KH |
8473 | if (ASCII_BYTE_P (*p)) |
8474 | p++; | |
e133c8fa | 8475 | else |
05e6f5dc | 8476 | { |
df7492f9 KH |
8477 | c = STRING_CHAR_ADVANCE (p); |
8478 | ||
8479 | charset_map_loaded = 0; | |
8480 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
8481 | { | |
8482 | elt = XCDR (XCAR (tail)); | |
8483 | if (! char_encodable_p (c, XCAR (elt))) | |
8484 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
8485 | } | |
8486 | if (charset_map_loaded) | |
8487 | { | |
8488 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
8489 | ||
8490 | if (STRINGP (start)) | |
8f924df7 | 8491 | pbeg = SDATA (start); |
df7492f9 KH |
8492 | else |
8493 | pbeg = BYTE_POS_ADDR (start_byte); | |
8494 | p = pbeg + p_offset; | |
8495 | pend = pbeg + pend_offset; | |
8496 | } | |
05e6f5dc | 8497 | } |
df7492f9 | 8498 | pos++; |
d46c5b12 | 8499 | } |
4ed46869 | 8500 | |
df7492f9 KH |
8501 | tail = list; |
8502 | list = Qnil; | |
8503 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 8504 | { |
df7492f9 KH |
8505 | elt = XCAR (tail); |
8506 | if (CONSP (XCDR (XCDR (elt)))) | |
8507 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
8508 | list); | |
ec6d2bb8 | 8509 | } |
2b4f9037 | 8510 | |
df7492f9 | 8511 | return list; |
d46c5b12 KH |
8512 | } |
8513 | ||
3fd9494b | 8514 | |
b73bfc1c | 8515 | Lisp_Object |
df7492f9 KH |
8516 | code_convert_region (start, end, coding_system, dst_object, encodep, norecord) |
8517 | Lisp_Object start, end, coding_system, dst_object; | |
8518 | int encodep, norecord; | |
4ed46869 | 8519 | { |
3a73fa5d | 8520 | struct coding_system coding; |
df7492f9 KH |
8521 | EMACS_INT from, from_byte, to, to_byte; |
8522 | Lisp_Object src_object; | |
4ed46869 | 8523 | |
b7826503 PJ |
8524 | CHECK_NUMBER_COERCE_MARKER (start); |
8525 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
8526 | if (NILP (coding_system)) |
8527 | coding_system = Qno_conversion; | |
8528 | else | |
8529 | CHECK_CODING_SYSTEM (coding_system); | |
8530 | src_object = Fcurrent_buffer (); | |
8531 | if (NILP (dst_object)) | |
8532 | dst_object = src_object; | |
8533 | else if (! EQ (dst_object, Qt)) | |
8534 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 8535 | |
d46c5b12 KH |
8536 | validate_region (&start, &end); |
8537 | from = XFASTINT (start); | |
df7492f9 | 8538 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 8539 | to = XFASTINT (end); |
df7492f9 | 8540 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 8541 | |
df7492f9 KH |
8542 | setup_coding_system (coding_system, &coding); |
8543 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 8544 | |
df7492f9 KH |
8545 | if (encodep) |
8546 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8547 | dst_object); | |
8548 | else | |
8549 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8550 | dst_object); | |
8551 | if (! norecord) | |
8552 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 8553 | |
df7492f9 KH |
8554 | return (BUFFERP (dst_object) |
8555 | ? make_number (coding.produced_char) | |
8556 | : coding.dst_object); | |
4031e2bf | 8557 | } |
78108bcd | 8558 | |
4ed46869 | 8559 | |
4031e2bf | 8560 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 8561 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 8562 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
8563 | When called from a program, takes four arguments: |
8564 | START, END, CODING-SYSTEM, and DESTINATION. | |
8565 | START and END are buffer positions. | |
8844fa83 | 8566 | |
df7492f9 | 8567 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
2354b80b | 8568 | If nil, the region between START and END is replaced by the decoded text. |
1560f91a EZ |
8569 | If buffer, the decoded text is inserted in that buffer after point (point |
8570 | does not move). | |
446dcd75 | 8571 | In those cases, the length of the decoded text is returned. |
319a3947 | 8572 | If DESTINATION is t, the decoded text is returned. |
8844fa83 | 8573 | |
48b0f3ae PJ |
8574 | This function sets `last-coding-system-used' to the precise coding system |
8575 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8576 | not fully specified.) */) |
df7492f9 KH |
8577 | (start, end, coding_system, destination) |
8578 | Lisp_Object start, end, coding_system, destination; | |
4031e2bf | 8579 | { |
df7492f9 | 8580 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 8581 | } |
8844fa83 | 8582 | |
3a73fa5d | 8583 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
8584 | 3, 4, "r\nzCoding system: ", |
8585 | doc: /* Encode the current region by specified coding system. | |
d4a1d553 JB |
8586 | When called from a program, takes four arguments: |
8587 | START, END, CODING-SYSTEM and DESTINATION. | |
8588 | START and END are buffer positions. | |
d46c5b12 | 8589 | |
df7492f9 KH |
8590 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
8591 | If nil, the region between START and END is replace by the encoded text. | |
1560f91a EZ |
8592 | If buffer, the encoded text is inserted in that buffer after point (point |
8593 | does not move). | |
446dcd75 | 8594 | In those cases, the length of the encoded text is returned. |
319a3947 | 8595 | If DESTINATION is t, the encoded text is returned. |
2391eaa4 | 8596 | |
48b0f3ae PJ |
8597 | This function sets `last-coding-system-used' to the precise coding system |
8598 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8599 | not fully specified.) */) |
df7492f9 KH |
8600 | (start, end, coding_system, destination) |
8601 | Lisp_Object start, end, coding_system, destination; | |
3a73fa5d | 8602 | { |
df7492f9 | 8603 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
8604 | } |
8605 | ||
8606 | Lisp_Object | |
df7492f9 KH |
8607 | code_convert_string (string, coding_system, dst_object, |
8608 | encodep, nocopy, norecord) | |
8609 | Lisp_Object string, coding_system, dst_object; | |
8610 | int encodep, nocopy, norecord; | |
b73bfc1c | 8611 | { |
4031e2bf | 8612 | struct coding_system coding; |
df7492f9 | 8613 | EMACS_INT chars, bytes; |
ec6d2bb8 | 8614 | |
b7826503 | 8615 | CHECK_STRING (string); |
d46c5b12 | 8616 | if (NILP (coding_system)) |
4956c225 | 8617 | { |
df7492f9 KH |
8618 | if (! norecord) |
8619 | Vlast_coding_system_used = Qno_conversion; | |
8620 | if (NILP (dst_object)) | |
8621 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 8622 | } |
b73bfc1c | 8623 | |
df7492f9 KH |
8624 | if (NILP (coding_system)) |
8625 | coding_system = Qno_conversion; | |
8626 | else | |
8627 | CHECK_CODING_SYSTEM (coding_system); | |
8628 | if (NILP (dst_object)) | |
8629 | dst_object = Qt; | |
8630 | else if (! EQ (dst_object, Qt)) | |
8631 | CHECK_BUFFER (dst_object); | |
73be902c | 8632 | |
df7492f9 | 8633 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 8634 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
8635 | chars = SCHARS (string); |
8636 | bytes = SBYTES (string); | |
df7492f9 KH |
8637 | if (encodep) |
8638 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
8639 | else | |
8640 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
8641 | if (! norecord) | |
8642 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 8643 | |
df7492f9 KH |
8644 | return (BUFFERP (dst_object) |
8645 | ? make_number (coding.produced_char) | |
8646 | : coding.dst_object); | |
4ed46869 | 8647 | } |
73be902c | 8648 | |
b73bfc1c | 8649 | |
ecec61c1 | 8650 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 8651 | Do not set Vlast_coding_system_used. |
4ed46869 | 8652 | |
ec6d2bb8 KH |
8653 | This function is called only from macros DECODE_FILE and |
8654 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 8655 | |
ecec61c1 KH |
8656 | Lisp_Object |
8657 | code_convert_string_norecord (string, coding_system, encodep) | |
8658 | Lisp_Object string, coding_system; | |
8659 | int encodep; | |
4ed46869 | 8660 | { |
0be8721c | 8661 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
8662 | } |
8663 | ||
4ed46869 | 8664 | |
df7492f9 KH |
8665 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
8666 | 2, 4, 0, | |
8667 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
8668 | ||
8669 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
8670 | if the decoding operation is trivial. | |
ecec61c1 | 8671 | |
d4a1d553 | 8672 | Optional fourth arg BUFFER non-nil means that the decoded text is |
1560f91a EZ |
8673 | inserted in that buffer after point (point does not move). In this |
8674 | case, the return value is the length of the decoded text. | |
ecec61c1 | 8675 | |
df7492f9 KH |
8676 | This function sets `last-coding-system-used' to the precise coding system |
8677 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
d4a1d553 | 8678 | not fully specified.) */) |
df7492f9 KH |
8679 | (string, coding_system, nocopy, buffer) |
8680 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 8681 | { |
df7492f9 KH |
8682 | return code_convert_string (string, coding_system, buffer, |
8683 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
8684 | } |
8685 | ||
df7492f9 KH |
8686 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
8687 | 2, 4, 0, | |
8688 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
8689 | ||
8690 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
8691 | itself if the encoding operation is trivial. | |
8692 | ||
d4a1d553 | 8693 | Optional fourth arg BUFFER non-nil means that the encoded text is |
1560f91a EZ |
8694 | inserted in that buffer after point (point does not move). In this |
8695 | case, the return value is the length of the encoded text. | |
df7492f9 KH |
8696 | |
8697 | This function sets `last-coding-system-used' to the precise coding system | |
8698 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
8699 | not fully specified.) */) | |
8700 | (string, coding_system, nocopy, buffer) | |
8701 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 8702 | { |
df7492f9 | 8703 | return code_convert_string (string, coding_system, buffer, |
c197f191 | 8704 | 1, ! NILP (nocopy), 1); |
4ed46869 | 8705 | } |
df7492f9 | 8706 | |
3a73fa5d | 8707 | \f |
4ed46869 | 8708 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
8709 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
8710 | Return the corresponding character. */) | |
8711 | (code) | |
4ed46869 | 8712 | Lisp_Object code; |
4ed46869 | 8713 | { |
df7492f9 KH |
8714 | Lisp_Object spec, attrs, val; |
8715 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
8716 | int c; | |
4ed46869 | 8717 | |
df7492f9 KH |
8718 | CHECK_NATNUM (code); |
8719 | c = XFASTINT (code); | |
8720 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
8721 | attrs = AREF (spec, 0); | |
4ed46869 | 8722 | |
df7492f9 KH |
8723 | if (ASCII_BYTE_P (c) |
8724 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8725 | return code; | |
4ed46869 | 8726 | |
df7492f9 KH |
8727 | val = CODING_ATTR_CHARSET_LIST (attrs); |
8728 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
8729 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
8730 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 8731 | |
df7492f9 KH |
8732 | if (c <= 0x7F) |
8733 | charset = charset_roman; | |
8734 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 8735 | { |
df7492f9 KH |
8736 | charset = charset_kana; |
8737 | c -= 0x80; | |
4ed46869 | 8738 | } |
55ab7be3 | 8739 | else |
4ed46869 | 8740 | { |
004068e4 | 8741 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
8742 | |
8743 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
8744 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
8745 | error ("Invalid code: %d", code); | |
8746 | SJIS_TO_JIS (c); | |
8747 | charset = charset_kanji; | |
4ed46869 | 8748 | } |
df7492f9 KH |
8749 | c = DECODE_CHAR (charset, c); |
8750 | if (c < 0) | |
8751 | error ("Invalid code: %d", code); | |
8752 | return make_number (c); | |
93dec019 | 8753 | } |
4ed46869 | 8754 | |
48b0f3ae | 8755 | |
4ed46869 | 8756 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
8acf0c0e | 8757 | doc: /* Encode a Japanese character CH to shift_jis encoding. |
48b0f3ae PJ |
8758 | Return the corresponding code in SJIS. */) |
8759 | (ch) | |
df7492f9 | 8760 | Lisp_Object ch; |
4ed46869 | 8761 | { |
df7492f9 KH |
8762 | Lisp_Object spec, attrs, charset_list; |
8763 | int c; | |
8764 | struct charset *charset; | |
8765 | unsigned code; | |
48b0f3ae | 8766 | |
df7492f9 KH |
8767 | CHECK_CHARACTER (ch); |
8768 | c = XFASTINT (ch); | |
8769 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
8770 | attrs = AREF (spec, 0); | |
8771 | ||
8772 | if (ASCII_CHAR_P (c) | |
8773 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8774 | return ch; | |
8775 | ||
8776 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
8777 | charset = char_charset (c, charset_list, &code); | |
8778 | if (code == CHARSET_INVALID_CODE (charset)) | |
8779 | error ("Can't encode by shift_jis encoding: %d", c); | |
8780 | JIS_TO_SJIS (code); | |
8781 | ||
8782 | return make_number (code); | |
4ed46869 KH |
8783 | } |
8784 | ||
8785 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
8786 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
8787 | Return the corresponding character. */) | |
8788 | (code) | |
4ed46869 | 8789 | Lisp_Object code; |
d46c5b12 | 8790 | { |
df7492f9 KH |
8791 | Lisp_Object spec, attrs, val; |
8792 | struct charset *charset_roman, *charset_big5, *charset; | |
8793 | int c; | |
6289dd10 | 8794 | |
df7492f9 KH |
8795 | CHECK_NATNUM (code); |
8796 | c = XFASTINT (code); | |
8797 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
8798 | attrs = AREF (spec, 0); | |
4ed46869 | 8799 | |
df7492f9 KH |
8800 | if (ASCII_BYTE_P (c) |
8801 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8802 | return code; | |
6289dd10 | 8803 | |
df7492f9 KH |
8804 | val = CODING_ATTR_CHARSET_LIST (attrs); |
8805 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
8806 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 8807 | |
df7492f9 KH |
8808 | if (c <= 0x7F) |
8809 | charset = charset_roman; | |
c28a9453 KH |
8810 | else |
8811 | { | |
df7492f9 KH |
8812 | int b1 = c >> 8, b2 = c & 0x7F; |
8813 | if (b1 < 0xA1 || b1 > 0xFE | |
8814 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
8815 | error ("Invalid code: %d", code); | |
8816 | charset = charset_big5; | |
c28a9453 | 8817 | } |
df7492f9 KH |
8818 | c = DECODE_CHAR (charset, (unsigned )c); |
8819 | if (c < 0) | |
8820 | error ("Invalid code: %d", code); | |
8821 | return make_number (c); | |
d46c5b12 | 8822 | } |
6289dd10 | 8823 | |
4ed46869 | 8824 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
8acf0c0e | 8825 | doc: /* Encode the Big5 character CH to BIG5 coding system. |
48b0f3ae PJ |
8826 | Return the corresponding character code in Big5. */) |
8827 | (ch) | |
4ed46869 KH |
8828 | Lisp_Object ch; |
8829 | { | |
df7492f9 KH |
8830 | Lisp_Object spec, attrs, charset_list; |
8831 | struct charset *charset; | |
8832 | int c; | |
8833 | unsigned code; | |
8834 | ||
8835 | CHECK_CHARACTER (ch); | |
8836 | c = XFASTINT (ch); | |
8837 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
8838 | attrs = AREF (spec, 0); | |
8839 | if (ASCII_CHAR_P (c) | |
8840 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8841 | return ch; | |
8842 | ||
8843 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
8844 | charset = char_charset (c, charset_list, &code); | |
8845 | if (code == CHARSET_INVALID_CODE (charset)) | |
8846 | error ("Can't encode by Big5 encoding: %d", c); | |
8847 | ||
8848 | return make_number (code); | |
4ed46869 | 8849 | } |
48b0f3ae | 8850 | |
3a73fa5d | 8851 | \f |
002fdb44 | 8852 | DEFUN ("set-terminal-coding-system-internal", Fset_terminal_coding_system_internal, |
68bba4e4 | 8853 | Sset_terminal_coding_system_internal, 1, 2, 0, |
48b0f3ae | 8854 | doc: /* Internal use only. */) |
6ed8eeff | 8855 | (coding_system, terminal) |
b74e4686 | 8856 | Lisp_Object coding_system; |
6ed8eeff | 8857 | Lisp_Object terminal; |
4ed46869 | 8858 | { |
6ed8eeff | 8859 | struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); |
b7826503 | 8860 | CHECK_SYMBOL (coding_system); |
b8299c66 | 8861 | setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding); |
70c22245 | 8862 | /* We had better not send unsafe characters to terminal. */ |
c73bd236 | 8863 | terminal_coding->mode |= CODING_MODE_SAFE_ENCODING; |
df7492f9 | 8864 | /* Characer composition should be disabled. */ |
c73bd236 | 8865 | terminal_coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b8299c66 KL |
8866 | terminal_coding->src_multibyte = 1; |
8867 | terminal_coding->dst_multibyte = 0; | |
4ed46869 KH |
8868 | return Qnil; |
8869 | } | |
8870 | ||
c4825358 KH |
8871 | DEFUN ("set-safe-terminal-coding-system-internal", |
8872 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 8873 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 8874 | doc: /* Internal use only. */) |
48b0f3ae | 8875 | (coding_system) |
b74e4686 | 8876 | Lisp_Object coding_system; |
d46c5b12 | 8877 | { |
b7826503 | 8878 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
8879 | setup_coding_system (Fcheck_coding_system (coding_system), |
8880 | &safe_terminal_coding); | |
df7492f9 KH |
8881 | /* Characer composition should be disabled. */ |
8882 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
8883 | safe_terminal_coding.src_multibyte = 1; |
8884 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
8885 | return Qnil; |
8886 | } | |
4ed46869 | 8887 | |
002fdb44 | 8888 | DEFUN ("terminal-coding-system", Fterminal_coding_system, |
68bba4e4 | 8889 | Sterminal_coding_system, 0, 1, 0, |
6ed8eeff KL |
8890 | doc: /* Return coding system specified for terminal output on the given terminal. |
8891 | TERMINAL may be a terminal id, a frame, or nil for the selected | |
8892 | frame's terminal device. */) | |
8893 | (terminal) | |
8894 | Lisp_Object terminal; | |
4ed46869 | 8895 | { |
985773c9 MB |
8896 | struct coding_system *terminal_coding |
8897 | = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); | |
8898 | Lisp_Object coding_system = CODING_ID_NAME (terminal_coding->id); | |
ae6f73fa | 8899 | |
ae6f73fa | 8900 | /* For backward compatibility, return nil if it is `undecided'. */ |
f75c90a9 | 8901 | return (! EQ (coding_system, Qundecided) ? coding_system : Qnil); |
4ed46869 KH |
8902 | } |
8903 | ||
002fdb44 | 8904 | DEFUN ("set-keyboard-coding-system-internal", Fset_keyboard_coding_system_internal, |
68bba4e4 | 8905 | Sset_keyboard_coding_system_internal, 1, 2, 0, |
48b0f3ae | 8906 | doc: /* Internal use only. */) |
6ed8eeff | 8907 | (coding_system, terminal) |
4ed46869 | 8908 | Lisp_Object coding_system; |
6ed8eeff | 8909 | Lisp_Object terminal; |
4ed46869 | 8910 | { |
6ed8eeff | 8911 | struct terminal *t = get_terminal (terminal, 1); |
b7826503 | 8912 | CHECK_SYMBOL (coding_system); |
df7492f9 | 8913 | setup_coding_system (Fcheck_coding_system (coding_system), |
c73bd236 | 8914 | TERMINAL_KEYBOARD_CODING (t)); |
df7492f9 | 8915 | /* Characer composition should be disabled. */ |
c73bd236 MB |
8916 | TERMINAL_KEYBOARD_CODING (t)->common_flags |
8917 | &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
8918 | return Qnil; |
8919 | } | |
8920 | ||
8921 | DEFUN ("keyboard-coding-system", | |
985773c9 | 8922 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 1, 0, |
48b0f3ae | 8923 | doc: /* Return coding system specified for decoding keyboard input. */) |
985773c9 MB |
8924 | (terminal) |
8925 | Lisp_Object terminal; | |
4ed46869 | 8926 | { |
985773c9 MB |
8927 | return CODING_ID_NAME (TERMINAL_KEYBOARD_CODING |
8928 | (get_terminal (terminal, 1))->id); | |
4ed46869 KH |
8929 | } |
8930 | ||
4ed46869 | 8931 | \f |
a5d301df KH |
8932 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
8933 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
8934 | doc: /* Choose a coding system for an operation based on the target name. |
8935 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
8936 | DECODING-SYSTEM is the coding system to use for decoding | |
8937 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
8938 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 8939 | |
48b0f3ae PJ |
8940 | The first argument OPERATION specifies an I/O primitive: |
8941 | For file I/O, `insert-file-contents' or `write-region'. | |
8942 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
8943 | For network I/O, `open-network-stream'. | |
05e6f5dc | 8944 | |
48b0f3ae PJ |
8945 | The remaining arguments should be the same arguments that were passed |
8946 | to the primitive. Depending on which primitive, one of those arguments | |
8947 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
8948 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 8949 | |
48b0f3ae | 8950 | TARGET has a meaning which depends on OPERATION: |
b883cdb2 | 8951 | For file I/O, TARGET is a file name (except for the special case below). |
48b0f3ae | 8952 | For process I/O, TARGET is a process name. |
d4a1d553 | 8953 | For network I/O, TARGET is a service name or a port number. |
05e6f5dc | 8954 | |
d4a1d553 | 8955 | This function looks up what is specified for TARGET in |
48b0f3ae PJ |
8956 | `file-coding-system-alist', `process-coding-system-alist', |
8957 | or `network-coding-system-alist' depending on OPERATION. | |
8958 | They may specify a coding system, a cons of coding systems, | |
8959 | or a function symbol to call. | |
8960 | In the last case, we call the function with one argument, | |
8961 | which is a list of all the arguments given to this function. | |
1011c487 MB |
8962 | If the function can't decide a coding system, it can return |
8963 | `undecided' so that the normal code-detection is performed. | |
48b0f3ae | 8964 | |
b883cdb2 MB |
8965 | If OPERATION is `insert-file-contents', the argument corresponding to |
8966 | TARGET may be a cons (FILENAME . BUFFER). In that case, FILENAME is a | |
8967 | file name to look up, and BUFFER is a buffer that contains the file's | |
8968 | contents (not yet decoded). If `file-coding-system-alist' specifies a | |
8969 | function to call for FILENAME, that function should examine the | |
8970 | contents of BUFFER instead of reading the file. | |
8971 | ||
d918f936 | 8972 | usage: (find-operation-coding-system OPERATION ARGUMENTS...) */) |
48b0f3ae | 8973 | (nargs, args) |
4ed46869 KH |
8974 | int nargs; |
8975 | Lisp_Object *args; | |
6b89e3aa | 8976 | { |
4ed46869 KH |
8977 | Lisp_Object operation, target_idx, target, val; |
8978 | register Lisp_Object chain; | |
177c0ea7 | 8979 | |
4ed46869 KH |
8980 | if (nargs < 2) |
8981 | error ("Too few arguments"); | |
8982 | operation = args[0]; | |
8983 | if (!SYMBOLP (operation) | |
8984 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
3ed051d4 | 8985 | error ("Invalid first argument"); |
4ed46869 KH |
8986 | if (nargs < 1 + XINT (target_idx)) |
8987 | error ("Too few arguments for operation: %s", | |
8f924df7 | 8988 | SDATA (SYMBOL_NAME (operation))); |
4ed46869 KH |
8989 | target = args[XINT (target_idx) + 1]; |
8990 | if (!(STRINGP (target) | |
091a0ff0 KH |
8991 | || (EQ (operation, Qinsert_file_contents) && CONSP (target) |
8992 | && STRINGP (XCAR (target)) && BUFFERP (XCDR (target))) | |
4ed46869 | 8993 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) |
df7492f9 | 8994 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
091a0ff0 KH |
8995 | if (CONSP (target)) |
8996 | target = XCAR (target); | |
4ed46869 | 8997 | |
2e34157c RS |
8998 | chain = ((EQ (operation, Qinsert_file_contents) |
8999 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 9000 | ? Vfile_coding_system_alist |
2e34157c | 9001 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
9002 | ? Vnetwork_coding_system_alist |
9003 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
9004 | if (NILP (chain)) |
9005 | return Qnil; | |
9006 | ||
03699b14 | 9007 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 9008 | { |
f44d27ce | 9009 | Lisp_Object elt; |
6b89e3aa | 9010 | |
df7492f9 | 9011 | elt = XCAR (chain); |
4ed46869 KH |
9012 | if (CONSP (elt) |
9013 | && ((STRINGP (target) | |
03699b14 KR |
9014 | && STRINGP (XCAR (elt)) |
9015 | && fast_string_match (XCAR (elt), target) >= 0) | |
9016 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 9017 | { |
03699b14 | 9018 | val = XCDR (elt); |
b19fd4c5 KH |
9019 | /* Here, if VAL is both a valid coding system and a valid |
9020 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
9021 | if (CONSP (val)) |
9022 | return val; | |
9023 | if (! SYMBOLP (val)) | |
9024 | return Qnil; | |
9025 | if (! NILP (Fcoding_system_p (val))) | |
9026 | return Fcons (val, val); | |
b19fd4c5 | 9027 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 9028 | { |
e2b97060 MB |
9029 | /* We use call1 rather than safe_call1 |
9030 | so as to get bug reports about functions called here | |
9031 | which don't handle the current interface. */ | |
9032 | val = call1 (val, Flist (nargs, args)); | |
b19fd4c5 KH |
9033 | if (CONSP (val)) |
9034 | return val; | |
9035 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
9036 | return Fcons (val, val); | |
6b89e3aa | 9037 | } |
02ba4723 | 9038 | return Qnil; |
6b89e3aa KH |
9039 | } |
9040 | } | |
4ed46869 | 9041 | return Qnil; |
6b89e3aa KH |
9042 | } |
9043 | ||
df7492f9 | 9044 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 9045 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 9046 | doc: /* Assign higher priority to the coding systems given as arguments. |
d4a1d553 | 9047 | If multiple coding systems belong to the same category, |
a3181084 DL |
9048 | all but the first one are ignored. |
9049 | ||
d4a1d553 | 9050 | usage: (set-coding-system-priority &rest coding-systems) */) |
df7492f9 KH |
9051 | (nargs, args) |
9052 | int nargs; | |
9053 | Lisp_Object *args; | |
9054 | { | |
9055 | int i, j; | |
9056 | int changed[coding_category_max]; | |
9057 | enum coding_category priorities[coding_category_max]; | |
9058 | ||
9059 | bzero (changed, sizeof changed); | |
6b89e3aa | 9060 | |
df7492f9 | 9061 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 9062 | { |
df7492f9 KH |
9063 | enum coding_category category; |
9064 | Lisp_Object spec, attrs; | |
6b89e3aa | 9065 | |
df7492f9 KH |
9066 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
9067 | attrs = AREF (spec, 0); | |
9068 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
9069 | if (changed[category]) | |
9070 | /* Ignore this coding system because a coding system of the | |
9071 | same category already had a higher priority. */ | |
9072 | continue; | |
9073 | changed[category] = 1; | |
9074 | priorities[j++] = category; | |
9075 | if (coding_categories[category].id >= 0 | |
9076 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
9077 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 9078 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 9079 | } |
6b89e3aa | 9080 | |
df7492f9 KH |
9081 | /* Now we have decided top J priorities. Reflect the order of the |
9082 | original priorities to the remaining priorities. */ | |
6b89e3aa | 9083 | |
df7492f9 | 9084 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 9085 | { |
df7492f9 KH |
9086 | while (j < coding_category_max |
9087 | && changed[coding_priorities[j]]) | |
9088 | j++; | |
9089 | if (j == coding_category_max) | |
9090 | abort (); | |
9091 | priorities[i] = coding_priorities[j]; | |
9092 | } | |
6b89e3aa | 9093 | |
df7492f9 | 9094 | bcopy (priorities, coding_priorities, sizeof priorities); |
177c0ea7 | 9095 | |
ff563fce KH |
9096 | /* Update `coding-category-list'. */ |
9097 | Vcoding_category_list = Qnil; | |
9098 | for (i = coding_category_max - 1; i >= 0; i--) | |
9099 | Vcoding_category_list | |
9100 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
9101 | Vcoding_category_list); | |
6b89e3aa | 9102 | |
df7492f9 | 9103 | return Qnil; |
6b89e3aa KH |
9104 | } |
9105 | ||
df7492f9 KH |
9106 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
9107 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 DL |
9108 | doc: /* Return a list of coding systems ordered by their priorities. |
9109 | HIGHESTP non-nil means just return the highest priority one. */) | |
df7492f9 KH |
9110 | (highestp) |
9111 | Lisp_Object highestp; | |
d46c5b12 KH |
9112 | { |
9113 | int i; | |
df7492f9 | 9114 | Lisp_Object val; |
6b89e3aa | 9115 | |
df7492f9 | 9116 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 9117 | { |
df7492f9 KH |
9118 | enum coding_category category = coding_priorities[i]; |
9119 | int id = coding_categories[category].id; | |
9120 | Lisp_Object attrs; | |
068a9dbd | 9121 | |
df7492f9 KH |
9122 | if (id < 0) |
9123 | continue; | |
9124 | attrs = CODING_ID_ATTRS (id); | |
9125 | if (! NILP (highestp)) | |
9126 | return CODING_ATTR_BASE_NAME (attrs); | |
9127 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
9128 | } | |
9129 | return Fnreverse (val); | |
9130 | } | |
068a9dbd | 9131 | |
f0064e1f | 9132 | static char *suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
9133 | |
9134 | static Lisp_Object | |
df7492f9 KH |
9135 | make_subsidiaries (base) |
9136 | Lisp_Object base; | |
068a9dbd | 9137 | { |
df7492f9 | 9138 | Lisp_Object subsidiaries; |
8f924df7 | 9139 | int base_name_len = SBYTES (SYMBOL_NAME (base)); |
df7492f9 KH |
9140 | char *buf = (char *) alloca (base_name_len + 6); |
9141 | int i; | |
068a9dbd | 9142 | |
8f924df7 | 9143 | bcopy (SDATA (SYMBOL_NAME (base)), buf, base_name_len); |
df7492f9 KH |
9144 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
9145 | for (i = 0; i < 3; i++) | |
068a9dbd | 9146 | { |
df7492f9 KH |
9147 | bcopy (suffixes[i], buf + base_name_len, strlen (suffixes[i]) + 1); |
9148 | ASET (subsidiaries, i, intern (buf)); | |
068a9dbd | 9149 | } |
df7492f9 | 9150 | return subsidiaries; |
068a9dbd KH |
9151 | } |
9152 | ||
9153 | ||
df7492f9 KH |
9154 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
9155 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
9156 | doc: /* For internal use only. |
9157 | usage: (define-coding-system-internal ...) */) | |
df7492f9 KH |
9158 | (nargs, args) |
9159 | int nargs; | |
9160 | Lisp_Object *args; | |
068a9dbd | 9161 | { |
df7492f9 KH |
9162 | Lisp_Object name; |
9163 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
9164 | Lisp_Object attrs; /* Vector of attributes. */ | |
9165 | Lisp_Object eol_type; | |
9166 | Lisp_Object aliases; | |
9167 | Lisp_Object coding_type, charset_list, safe_charsets; | |
9168 | enum coding_category category; | |
9169 | Lisp_Object tail, val; | |
9170 | int max_charset_id = 0; | |
9171 | int i; | |
068a9dbd | 9172 | |
df7492f9 KH |
9173 | if (nargs < coding_arg_max) |
9174 | goto short_args; | |
068a9dbd | 9175 | |
df7492f9 | 9176 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 9177 | |
df7492f9 KH |
9178 | name = args[coding_arg_name]; |
9179 | CHECK_SYMBOL (name); | |
9180 | CODING_ATTR_BASE_NAME (attrs) = name; | |
068a9dbd | 9181 | |
df7492f9 KH |
9182 | val = args[coding_arg_mnemonic]; |
9183 | if (! STRINGP (val)) | |
9184 | CHECK_CHARACTER (val); | |
9185 | CODING_ATTR_MNEMONIC (attrs) = val; | |
068a9dbd | 9186 | |
df7492f9 KH |
9187 | coding_type = args[coding_arg_coding_type]; |
9188 | CHECK_SYMBOL (coding_type); | |
9189 | CODING_ATTR_TYPE (attrs) = coding_type; | |
068a9dbd | 9190 | |
df7492f9 KH |
9191 | charset_list = args[coding_arg_charset_list]; |
9192 | if (SYMBOLP (charset_list)) | |
9193 | { | |
9194 | if (EQ (charset_list, Qiso_2022)) | |
9195 | { | |
9196 | if (! EQ (coding_type, Qiso_2022)) | |
9197 | error ("Invalid charset-list"); | |
9198 | charset_list = Viso_2022_charset_list; | |
9199 | } | |
9200 | else if (EQ (charset_list, Qemacs_mule)) | |
9201 | { | |
9202 | if (! EQ (coding_type, Qemacs_mule)) | |
9203 | error ("Invalid charset-list"); | |
9204 | charset_list = Vemacs_mule_charset_list; | |
9205 | } | |
9206 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
9207 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
9208 | max_charset_id = XFASTINT (XCAR (tail)); | |
9209 | } | |
068a9dbd KH |
9210 | else |
9211 | { | |
df7492f9 | 9212 | charset_list = Fcopy_sequence (charset_list); |
985773c9 | 9213 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
068a9dbd | 9214 | { |
df7492f9 KH |
9215 | struct charset *charset; |
9216 | ||
985773c9 | 9217 | val = XCAR (tail); |
df7492f9 KH |
9218 | CHECK_CHARSET_GET_CHARSET (val, charset); |
9219 | if (EQ (coding_type, Qiso_2022) | |
9220 | ? CHARSET_ISO_FINAL (charset) < 0 | |
9221 | : EQ (coding_type, Qemacs_mule) | |
9222 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
9223 | : 0) | |
9224 | error ("Can't handle charset `%s'", | |
8f924df7 | 9225 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 9226 | |
8f924df7 | 9227 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
9228 | if (max_charset_id < charset->id) |
9229 | max_charset_id = charset->id; | |
068a9dbd KH |
9230 | } |
9231 | } | |
df7492f9 | 9232 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; |
068a9dbd | 9233 | |
df7492f9 KH |
9234 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
9235 | make_number (255)); | |
9236 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8f924df7 | 9237 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 9238 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; |
068a9dbd | 9239 | |
584948ac | 9240 | CODING_ATTR_ASCII_COMPAT (attrs) = args[coding_arg_ascii_compatible_p]; |
3a73fa5d | 9241 | |
df7492f9 | 9242 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 9243 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9244 | CHECK_SYMBOL (val); |
df7492f9 | 9245 | CODING_ATTR_DECODE_TBL (attrs) = val; |
3a73fa5d | 9246 | |
df7492f9 | 9247 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 9248 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9249 | CHECK_SYMBOL (val); |
df7492f9 | 9250 | CODING_ATTR_ENCODE_TBL (attrs) = val; |
d46c5b12 | 9251 | |
df7492f9 KH |
9252 | val = args[coding_arg_post_read_conversion]; |
9253 | CHECK_SYMBOL (val); | |
9254 | CODING_ATTR_POST_READ (attrs) = val; | |
d46c5b12 | 9255 | |
df7492f9 KH |
9256 | val = args[coding_arg_pre_write_conversion]; |
9257 | CHECK_SYMBOL (val); | |
9258 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
3a73fa5d | 9259 | |
df7492f9 KH |
9260 | val = args[coding_arg_default_char]; |
9261 | if (NILP (val)) | |
9262 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
9263 | else | |
9264 | { | |
8f924df7 | 9265 | CHECK_CHARACTER (val); |
df7492f9 KH |
9266 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; |
9267 | } | |
4031e2bf | 9268 | |
8f924df7 KH |
9269 | val = args[coding_arg_for_unibyte]; |
9270 | CODING_ATTR_FOR_UNIBYTE (attrs) = NILP (val) ? Qnil : Qt; | |
3a73fa5d | 9271 | |
df7492f9 KH |
9272 | val = args[coding_arg_plist]; |
9273 | CHECK_LIST (val); | |
9274 | CODING_ATTR_PLIST (attrs) = val; | |
3a73fa5d | 9275 | |
df7492f9 KH |
9276 | if (EQ (coding_type, Qcharset)) |
9277 | { | |
c7c66a95 KH |
9278 | /* Generate a lisp vector of 256 elements. Each element is nil, |
9279 | integer, or a list of charset IDs. | |
3a73fa5d | 9280 | |
c7c66a95 KH |
9281 | If Nth element is nil, the byte code N is invalid in this |
9282 | coding system. | |
4ed46869 | 9283 | |
c7c66a95 KH |
9284 | If Nth element is a number NUM, N is the first byte of a |
9285 | charset whose ID is NUM. | |
4ed46869 | 9286 | |
c7c66a95 KH |
9287 | If Nth element is a list of charset IDs, N is the first byte |
9288 | of one of them. The list is sorted by dimensions of the | |
2bc515e4 | 9289 | charsets. A charset of smaller dimension comes firtst. */ |
df7492f9 | 9290 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 9291 | |
5c99c2e6 | 9292 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 9293 | { |
c7c66a95 KH |
9294 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
9295 | int dim = CHARSET_DIMENSION (charset); | |
9296 | int idx = (dim - 1) * 4; | |
4ed46869 | 9297 | |
5c99c2e6 | 9298 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
584948ac | 9299 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
4031e2bf | 9300 | |
15d143f7 KH |
9301 | for (i = charset->code_space[idx]; |
9302 | i <= charset->code_space[idx + 1]; i++) | |
9303 | { | |
c7c66a95 KH |
9304 | Lisp_Object tmp, tmp2; |
9305 | int dim2; | |
ec6d2bb8 | 9306 | |
c7c66a95 KH |
9307 | tmp = AREF (val, i); |
9308 | if (NILP (tmp)) | |
9309 | tmp = XCAR (tail); | |
9310 | else if (NUMBERP (tmp)) | |
9311 | { | |
9312 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
9313 | if (dim < dim2) | |
c7c66a95 | 9314 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
9315 | else |
9316 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 9317 | } |
15d143f7 | 9318 | else |
c7c66a95 KH |
9319 | { |
9320 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
9321 | { | |
9322 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
9323 | if (dim < dim2) | |
9324 | break; | |
9325 | } | |
9326 | if (NILP (tmp2)) | |
9327 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
9328 | else | |
9329 | { | |
9330 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
9331 | XSETCAR (tmp2, XCAR (tail)); | |
9332 | } | |
9333 | } | |
9334 | ASET (val, i, tmp); | |
15d143f7 | 9335 | } |
df7492f9 KH |
9336 | } |
9337 | ASET (attrs, coding_attr_charset_valids, val); | |
9338 | category = coding_category_charset; | |
9339 | } | |
9340 | else if (EQ (coding_type, Qccl)) | |
9341 | { | |
9342 | Lisp_Object valids; | |
ecec61c1 | 9343 | |
df7492f9 KH |
9344 | if (nargs < coding_arg_ccl_max) |
9345 | goto short_args; | |
ecec61c1 | 9346 | |
df7492f9 KH |
9347 | val = args[coding_arg_ccl_decoder]; |
9348 | CHECK_CCL_PROGRAM (val); | |
9349 | if (VECTORP (val)) | |
9350 | val = Fcopy_sequence (val); | |
9351 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 9352 | |
df7492f9 KH |
9353 | val = args[coding_arg_ccl_encoder]; |
9354 | CHECK_CCL_PROGRAM (val); | |
9355 | if (VECTORP (val)) | |
9356 | val = Fcopy_sequence (val); | |
9357 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 9358 | |
df7492f9 KH |
9359 | val = args[coding_arg_ccl_valids]; |
9360 | valids = Fmake_string (make_number (256), make_number (0)); | |
9361 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
9362 | { | |
8dcbea82 | 9363 | int from, to; |
ecec61c1 | 9364 | |
df7492f9 KH |
9365 | val = Fcar (tail); |
9366 | if (INTEGERP (val)) | |
8dcbea82 KH |
9367 | { |
9368 | from = to = XINT (val); | |
9369 | if (from < 0 || from > 255) | |
9370 | args_out_of_range_3 (val, make_number (0), make_number (255)); | |
9371 | } | |
df7492f9 KH |
9372 | else |
9373 | { | |
df7492f9 | 9374 | CHECK_CONS (val); |
8f924df7 KH |
9375 | CHECK_NATNUM_CAR (val); |
9376 | CHECK_NATNUM_CDR (val); | |
df7492f9 | 9377 | from = XINT (XCAR (val)); |
8f924df7 | 9378 | if (from > 255) |
8dcbea82 KH |
9379 | args_out_of_range_3 (XCAR (val), |
9380 | make_number (0), make_number (255)); | |
df7492f9 | 9381 | to = XINT (XCDR (val)); |
8dcbea82 KH |
9382 | if (to < from || to > 255) |
9383 | args_out_of_range_3 (XCDR (val), | |
9384 | XCAR (val), make_number (255)); | |
df7492f9 | 9385 | } |
8dcbea82 | 9386 | for (i = from; i <= to; i++) |
8f924df7 | 9387 | SSET (valids, i, 1); |
df7492f9 KH |
9388 | } |
9389 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 9390 | |
df7492f9 | 9391 | category = coding_category_ccl; |
55ab7be3 | 9392 | } |
df7492f9 | 9393 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 9394 | { |
df7492f9 | 9395 | Lisp_Object bom, endian; |
4ed46869 | 9396 | |
584948ac | 9397 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; |
4ed46869 | 9398 | |
df7492f9 KH |
9399 | if (nargs < coding_arg_utf16_max) |
9400 | goto short_args; | |
4ed46869 | 9401 | |
df7492f9 KH |
9402 | bom = args[coding_arg_utf16_bom]; |
9403 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9404 | { | |
9405 | CHECK_CONS (bom); | |
8f924df7 KH |
9406 | val = XCAR (bom); |
9407 | CHECK_CODING_SYSTEM (val); | |
9408 | val = XCDR (bom); | |
9409 | CHECK_CODING_SYSTEM (val); | |
df7492f9 | 9410 | } |
a470d443 | 9411 | ASET (attrs, coding_attr_utf_bom, bom); |
df7492f9 KH |
9412 | |
9413 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
9414 | CHECK_SYMBOL (endian); |
9415 | if (NILP (endian)) | |
9416 | endian = Qbig; | |
9417 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 9418 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
9419 | ASET (attrs, coding_attr_utf_16_endian, endian); |
9420 | ||
9421 | category = (CONSP (bom) | |
9422 | ? coding_category_utf_16_auto | |
9423 | : NILP (bom) | |
b49a1807 | 9424 | ? (EQ (endian, Qbig) |
df7492f9 KH |
9425 | ? coding_category_utf_16_be_nosig |
9426 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 9427 | : (EQ (endian, Qbig) |
df7492f9 KH |
9428 | ? coding_category_utf_16_be |
9429 | : coding_category_utf_16_le)); | |
9430 | } | |
9431 | else if (EQ (coding_type, Qiso_2022)) | |
9432 | { | |
9433 | Lisp_Object initial, reg_usage, request, flags; | |
4776e638 | 9434 | int i; |
1397dc18 | 9435 | |
df7492f9 KH |
9436 | if (nargs < coding_arg_iso2022_max) |
9437 | goto short_args; | |
9438 | ||
9439 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
9440 | CHECK_VECTOR (initial); | |
9441 | for (i = 0; i < 4; i++) | |
9442 | { | |
9443 | val = Faref (initial, make_number (i)); | |
9444 | if (! NILP (val)) | |
9445 | { | |
584948ac KH |
9446 | struct charset *charset; |
9447 | ||
9448 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
9449 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
9450 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
9451 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9452 | } |
9453 | else | |
9454 | ASET (initial, i, make_number (-1)); | |
9455 | } | |
9456 | ||
9457 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
9458 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
9459 | CHECK_NUMBER_CAR (reg_usage); |
9460 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
9461 | |
9462 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
9463 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 9464 | { |
df7492f9 | 9465 | int id; |
8f924df7 | 9466 | Lisp_Object tmp; |
df7492f9 KH |
9467 | |
9468 | val = Fcar (tail); | |
9469 | CHECK_CONS (val); | |
8f924df7 KH |
9470 | tmp = XCAR (val); |
9471 | CHECK_CHARSET_GET_ID (tmp, id); | |
9472 | CHECK_NATNUM_CDR (val); | |
df7492f9 KH |
9473 | if (XINT (XCDR (val)) >= 4) |
9474 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
8f924df7 | 9475 | XSETCAR (val, make_number (id)); |
1397dc18 | 9476 | } |
4ed46869 | 9477 | |
df7492f9 KH |
9478 | flags = args[coding_arg_iso2022_flags]; |
9479 | CHECK_NATNUM (flags); | |
9480 | i = XINT (flags); | |
9481 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
9482 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
9483 | ||
9484 | ASET (attrs, coding_attr_iso_initial, initial); | |
9485 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
9486 | ASET (attrs, coding_attr_iso_request, request); | |
9487 | ASET (attrs, coding_attr_iso_flags, flags); | |
9488 | setup_iso_safe_charsets (attrs); | |
9489 | ||
9490 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
9491 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
9492 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
9493 | ? coding_category_iso_7_else | |
9494 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
9495 | ? coding_category_iso_7 | |
9496 | : coding_category_iso_7_tight); | |
9497 | else | |
9498 | { | |
9499 | int id = XINT (AREF (initial, 1)); | |
9500 | ||
c6fb6e98 | 9501 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
9502 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
9503 | || id < 0) | |
9504 | ? coding_category_iso_8_else | |
9505 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
9506 | ? coding_category_iso_8_1 | |
9507 | : coding_category_iso_8_2); | |
9508 | } | |
0ce7886f KH |
9509 | if (category != coding_category_iso_8_1 |
9510 | && category != coding_category_iso_8_2) | |
9511 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; | |
df7492f9 KH |
9512 | } |
9513 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 9514 | { |
df7492f9 KH |
9515 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
9516 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
584948ac | 9517 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
df7492f9 | 9518 | category = coding_category_emacs_mule; |
c28a9453 | 9519 | } |
df7492f9 | 9520 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 9521 | { |
df7492f9 KH |
9522 | |
9523 | struct charset *charset; | |
9524 | ||
7d64c6ad | 9525 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 9526 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 9527 | error ("There should be three or four charsets"); |
df7492f9 KH |
9528 | |
9529 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9530 | if (CHARSET_DIMENSION (charset) != 1) | |
9531 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9532 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
9533 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
9534 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9535 | |
9536 | charset_list = XCDR (charset_list); | |
9537 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9538 | if (CHARSET_DIMENSION (charset) != 1) | |
9539 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9540 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
9541 | |
9542 | charset_list = XCDR (charset_list); | |
9543 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9544 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
9545 | error ("Dimension of charset %s is not two", |
9546 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9547 | ||
9548 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
9549 | if (! NILP (charset_list)) |
9550 | { | |
9551 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9552 | if (CHARSET_DIMENSION (charset) != 2) | |
9553 | error ("Dimension of charset %s is not two", | |
9554 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9555 | } | |
df7492f9 KH |
9556 | |
9557 | category = coding_category_sjis; | |
9558 | Vsjis_coding_system = name; | |
c28a9453 | 9559 | } |
df7492f9 KH |
9560 | else if (EQ (coding_type, Qbig5)) |
9561 | { | |
9562 | struct charset *charset; | |
4ed46869 | 9563 | |
df7492f9 KH |
9564 | if (XINT (Flength (charset_list)) != 2) |
9565 | error ("There should be just two charsets"); | |
9566 | ||
9567 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9568 | if (CHARSET_DIMENSION (charset) != 1) | |
9569 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9570 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
9571 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
9572 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9573 | |
9574 | charset_list = XCDR (charset_list); | |
9575 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9576 | if (CHARSET_DIMENSION (charset) != 2) | |
9577 | error ("Dimension of charset %s is not two", | |
8f924df7 | 9578 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 9579 | |
df7492f9 KH |
9580 | category = coding_category_big5; |
9581 | Vbig5_coding_system = name; | |
9582 | } | |
9583 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 9584 | { |
584948ac KH |
9585 | category = coding_category_raw_text; |
9586 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
c28a9453 | 9587 | } |
df7492f9 | 9588 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 9589 | { |
a470d443 KH |
9590 | Lisp_Object bom; |
9591 | ||
584948ac | 9592 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
a470d443 KH |
9593 | |
9594 | if (nargs < coding_arg_utf8_max) | |
9595 | goto short_args; | |
9596 | ||
9597 | bom = args[coding_arg_utf8_bom]; | |
9598 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9599 | { | |
9600 | CHECK_CONS (bom); | |
9601 | val = XCAR (bom); | |
9602 | CHECK_CODING_SYSTEM (val); | |
9603 | val = XCDR (bom); | |
9604 | CHECK_CODING_SYSTEM (val); | |
9605 | } | |
9606 | ASET (attrs, coding_attr_utf_bom, bom); | |
9607 | ||
9608 | category = (CONSP (bom) ? coding_category_utf_8_auto | |
9609 | : NILP (bom) ? coding_category_utf_8_nosig | |
9610 | : coding_category_utf_8_sig); | |
4ed46869 | 9611 | } |
df7492f9 KH |
9612 | else if (EQ (coding_type, Qundecided)) |
9613 | category = coding_category_undecided; | |
4ed46869 | 9614 | else |
df7492f9 | 9615 | error ("Invalid coding system type: %s", |
8f924df7 | 9616 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 9617 | |
df7492f9 | 9618 | CODING_ATTR_CATEGORY (attrs) = make_number (category); |
01378f49 KH |
9619 | CODING_ATTR_PLIST (attrs) |
9620 | = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category), | |
9621 | CODING_ATTR_PLIST (attrs))); | |
35befdaa | 9622 | CODING_ATTR_PLIST (attrs) |
3ed051d4 | 9623 | = Fcons (QCascii_compatible_p, |
35befdaa KH |
9624 | Fcons (CODING_ATTR_ASCII_COMPAT (attrs), |
9625 | CODING_ATTR_PLIST (attrs))); | |
c4825358 | 9626 | |
df7492f9 KH |
9627 | eol_type = args[coding_arg_eol_type]; |
9628 | if (! NILP (eol_type) | |
9629 | && ! EQ (eol_type, Qunix) | |
9630 | && ! EQ (eol_type, Qdos) | |
9631 | && ! EQ (eol_type, Qmac)) | |
9632 | error ("Invalid eol-type"); | |
4ed46869 | 9633 | |
df7492f9 | 9634 | aliases = Fcons (name, Qnil); |
4ed46869 | 9635 | |
df7492f9 KH |
9636 | if (NILP (eol_type)) |
9637 | { | |
9638 | eol_type = make_subsidiaries (name); | |
9639 | for (i = 0; i < 3; i++) | |
1397dc18 | 9640 | { |
df7492f9 KH |
9641 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
9642 | ||
9643 | this_name = AREF (eol_type, i); | |
9644 | this_aliases = Fcons (this_name, Qnil); | |
9645 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
9646 | this_spec = Fmake_vector (make_number (3), attrs); | |
9647 | ASET (this_spec, 1, this_aliases); | |
9648 | ASET (this_spec, 2, this_eol_type); | |
9649 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
9650 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
583f71ca KH |
9651 | val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist); |
9652 | if (NILP (val)) | |
9653 | Vcoding_system_alist | |
9654 | = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
9655 | Vcoding_system_alist); | |
1397dc18 | 9656 | } |
d46c5b12 | 9657 | } |
4ed46869 | 9658 | |
df7492f9 KH |
9659 | spec_vec = Fmake_vector (make_number (3), attrs); |
9660 | ASET (spec_vec, 1, aliases); | |
9661 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 9662 | |
df7492f9 KH |
9663 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
9664 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
583f71ca KH |
9665 | val = Fassoc (Fsymbol_name (name), Vcoding_system_alist); |
9666 | if (NILP (val)) | |
9667 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
9668 | Vcoding_system_alist); | |
48b0f3ae | 9669 | |
df7492f9 KH |
9670 | { |
9671 | int id = coding_categories[category].id; | |
48b0f3ae | 9672 | |
df7492f9 KH |
9673 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
9674 | setup_coding_system (name, &coding_categories[category]); | |
9675 | } | |
48b0f3ae | 9676 | |
d46c5b12 | 9677 | return Qnil; |
48b0f3ae | 9678 | |
df7492f9 KH |
9679 | short_args: |
9680 | return Fsignal (Qwrong_number_of_arguments, | |
9681 | Fcons (intern ("define-coding-system-internal"), | |
9682 | make_number (nargs))); | |
d46c5b12 | 9683 | } |
4ed46869 | 9684 | |
d6925f38 | 9685 | |
a6f87d34 KH |
9686 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
9687 | 3, 3, 0, | |
9688 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
9689 | (coding_system, prop, val) | |
9690 | Lisp_Object coding_system, prop, val; | |
9691 | { | |
3dbe7859 | 9692 | Lisp_Object spec, attrs; |
a6f87d34 KH |
9693 | |
9694 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9695 | attrs = AREF (spec, 0); | |
9696 | if (EQ (prop, QCmnemonic)) | |
9697 | { | |
9698 | if (! STRINGP (val)) | |
9699 | CHECK_CHARACTER (val); | |
9700 | CODING_ATTR_MNEMONIC (attrs) = val; | |
9701 | } | |
2133e2d1 | 9702 | else if (EQ (prop, QCdefault_char)) |
a6f87d34 KH |
9703 | { |
9704 | if (NILP (val)) | |
9705 | val = make_number (' '); | |
9706 | else | |
9707 | CHECK_CHARACTER (val); | |
9708 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; | |
9709 | } | |
9710 | else if (EQ (prop, QCdecode_translation_table)) | |
9711 | { | |
9712 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
9713 | CHECK_SYMBOL (val); | |
9714 | CODING_ATTR_DECODE_TBL (attrs) = val; | |
9715 | } | |
9716 | else if (EQ (prop, QCencode_translation_table)) | |
9717 | { | |
9718 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
9719 | CHECK_SYMBOL (val); | |
9720 | CODING_ATTR_ENCODE_TBL (attrs) = val; | |
9721 | } | |
9722 | else if (EQ (prop, QCpost_read_conversion)) | |
9723 | { | |
9724 | CHECK_SYMBOL (val); | |
9725 | CODING_ATTR_POST_READ (attrs) = val; | |
9726 | } | |
9727 | else if (EQ (prop, QCpre_write_conversion)) | |
9728 | { | |
9729 | CHECK_SYMBOL (val); | |
9730 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
9731 | } | |
35befdaa KH |
9732 | else if (EQ (prop, QCascii_compatible_p)) |
9733 | { | |
9734 | CODING_ATTR_ASCII_COMPAT (attrs) = val; | |
9735 | } | |
a6f87d34 KH |
9736 | |
9737 | CODING_ATTR_PLIST (attrs) | |
9738 | = Fplist_put (CODING_ATTR_PLIST (attrs), prop, val); | |
9739 | return val; | |
9740 | } | |
9741 | ||
9742 | ||
df7492f9 KH |
9743 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
9744 | Sdefine_coding_system_alias, 2, 2, 0, | |
9745 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
9746 | (alias, coding_system) | |
9747 | Lisp_Object alias, coding_system; | |
66cfb530 | 9748 | { |
583f71ca | 9749 | Lisp_Object spec, aliases, eol_type, val; |
4ed46869 | 9750 | |
df7492f9 KH |
9751 | CHECK_SYMBOL (alias); |
9752 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9753 | aliases = AREF (spec, 1); | |
d4a1d553 | 9754 | /* ALIASES should be a list of length more than zero, and the first |
d6925f38 KH |
9755 | element is a base coding system. Append ALIAS at the tail of the |
9756 | list. */ | |
df7492f9 KH |
9757 | while (!NILP (XCDR (aliases))) |
9758 | aliases = XCDR (aliases); | |
8f924df7 | 9759 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 9760 | |
df7492f9 KH |
9761 | eol_type = AREF (spec, 2); |
9762 | if (VECTORP (eol_type)) | |
4ed46869 | 9763 | { |
df7492f9 KH |
9764 | Lisp_Object subsidiaries; |
9765 | int i; | |
4ed46869 | 9766 | |
df7492f9 KH |
9767 | subsidiaries = make_subsidiaries (alias); |
9768 | for (i = 0; i < 3; i++) | |
9769 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
9770 | AREF (eol_type, i)); | |
4ed46869 | 9771 | } |
df7492f9 KH |
9772 | |
9773 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 9774 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
583f71ca KH |
9775 | val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist); |
9776 | if (NILP (val)) | |
9777 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), | |
9778 | Vcoding_system_alist); | |
66cfb530 | 9779 | |
4ed46869 KH |
9780 | return Qnil; |
9781 | } | |
9782 | ||
df7492f9 KH |
9783 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
9784 | 1, 1, 0, | |
9785 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 9786 | Any alias or subsidiary coding system is not a base coding system. */) |
df7492f9 KH |
9787 | (coding_system) |
9788 | Lisp_Object coding_system; | |
d46c5b12 | 9789 | { |
df7492f9 | 9790 | Lisp_Object spec, attrs; |
d46c5b12 | 9791 | |
df7492f9 KH |
9792 | if (NILP (coding_system)) |
9793 | return (Qno_conversion); | |
9794 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9795 | attrs = AREF (spec, 0); | |
9796 | return CODING_ATTR_BASE_NAME (attrs); | |
9797 | } | |
1397dc18 | 9798 | |
df7492f9 KH |
9799 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
9800 | 1, 1, 0, | |
9801 | doc: "Return the property list of CODING-SYSTEM.") | |
9802 | (coding_system) | |
9803 | Lisp_Object coding_system; | |
9804 | { | |
9805 | Lisp_Object spec, attrs; | |
1397dc18 | 9806 | |
df7492f9 KH |
9807 | if (NILP (coding_system)) |
9808 | coding_system = Qno_conversion; | |
9809 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9810 | attrs = AREF (spec, 0); | |
9811 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
9812 | } |
9813 | ||
df7492f9 KH |
9814 | |
9815 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
9816 | 1, 1, 0, | |
da7db224 | 9817 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
df7492f9 KH |
9818 | (coding_system) |
9819 | Lisp_Object coding_system; | |
66cfb530 | 9820 | { |
df7492f9 | 9821 | Lisp_Object spec; |
84d60297 | 9822 | |
df7492f9 KH |
9823 | if (NILP (coding_system)) |
9824 | coding_system = Qno_conversion; | |
9825 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 9826 | return AREF (spec, 1); |
df7492f9 | 9827 | } |
66cfb530 | 9828 | |
df7492f9 KH |
9829 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
9830 | Scoding_system_eol_type, 1, 1, 0, | |
9831 | doc: /* Return eol-type of CODING-SYSTEM. | |
d4a1d553 | 9832 | An eol-type is an integer 0, 1, 2, or a vector of coding systems. |
66cfb530 | 9833 | |
df7492f9 KH |
9834 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
9835 | and CR respectively. | |
66cfb530 | 9836 | |
df7492f9 KH |
9837 | A vector value indicates that a format of end-of-line should be |
9838 | detected automatically. Nth element of the vector is the subsidiary | |
9839 | coding system whose eol-type is N. */) | |
6b89e3aa KH |
9840 | (coding_system) |
9841 | Lisp_Object coding_system; | |
9842 | { | |
df7492f9 KH |
9843 | Lisp_Object spec, eol_type; |
9844 | int n; | |
6b89e3aa | 9845 | |
df7492f9 KH |
9846 | if (NILP (coding_system)) |
9847 | coding_system = Qno_conversion; | |
9848 | if (! CODING_SYSTEM_P (coding_system)) | |
9849 | return Qnil; | |
9850 | spec = CODING_SYSTEM_SPEC (coding_system); | |
9851 | eol_type = AREF (spec, 2); | |
9852 | if (VECTORP (eol_type)) | |
9853 | return Fcopy_sequence (eol_type); | |
9854 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
9855 | return make_number (n); | |
6b89e3aa KH |
9856 | } |
9857 | ||
4ed46869 KH |
9858 | #endif /* emacs */ |
9859 | ||
9860 | \f | |
1397dc18 | 9861 | /*** 9. Post-amble ***/ |
4ed46869 | 9862 | |
dfcf069d | 9863 | void |
4ed46869 KH |
9864 | init_coding_once () |
9865 | { | |
9866 | int i; | |
9867 | ||
df7492f9 KH |
9868 | for (i = 0; i < coding_category_max; i++) |
9869 | { | |
9870 | coding_categories[i].id = -1; | |
9871 | coding_priorities[i] = i; | |
9872 | } | |
4ed46869 KH |
9873 | |
9874 | /* ISO2022 specific initialize routine. */ | |
9875 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 9876 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
9877 | for (i = 0x21; i < 0x7F; i++) |
9878 | iso_code_class[i] = ISO_graphic_plane_0; | |
9879 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 9880 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
9881 | for (i = 0xA1; i < 0xFF; i++) |
9882 | iso_code_class[i] = ISO_graphic_plane_1; | |
9883 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
9884 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
9885 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
9886 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
9887 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
9888 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
9889 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
9890 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
9891 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
9892 | ||
df7492f9 KH |
9893 | for (i = 0; i < 256; i++) |
9894 | { | |
9895 | emacs_mule_bytes[i] = 1; | |
9896 | } | |
7c78e542 KH |
9897 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
9898 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
9899 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
9900 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
9901 | } |
9902 | ||
9903 | #ifdef emacs | |
9904 | ||
dfcf069d | 9905 | void |
e0e989f6 KH |
9906 | syms_of_coding () |
9907 | { | |
df7492f9 | 9908 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
9909 | { |
9910 | Lisp_Object args[2]; | |
9911 | args[0] = QCtest; | |
9912 | args[1] = Qeq; | |
9913 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
9914 | } | |
df7492f9 KH |
9915 | |
9916 | staticpro (&Vsjis_coding_system); | |
9917 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 9918 | |
df7492f9 KH |
9919 | staticpro (&Vbig5_coding_system); |
9920 | Vbig5_coding_system = Qnil; | |
9921 | ||
24a73b0a KH |
9922 | staticpro (&Vcode_conversion_reused_workbuf); |
9923 | Vcode_conversion_reused_workbuf = Qnil; | |
9924 | ||
9925 | staticpro (&Vcode_conversion_workbuf_name); | |
9926 | Vcode_conversion_workbuf_name = build_string (" *code-conversion-work*"); | |
e0e989f6 | 9927 | |
24a73b0a | 9928 | reused_workbuf_in_use = 0; |
df7492f9 KH |
9929 | |
9930 | DEFSYM (Qcharset, "charset"); | |
9931 | DEFSYM (Qtarget_idx, "target-idx"); | |
9932 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
9933 | Fset (Qcoding_system_history, Qnil); |
9934 | ||
9ce27fde | 9935 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 9936 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 9937 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
9938 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
9939 | ||
df7492f9 | 9940 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 9941 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
9942 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
9943 | ||
df7492f9 | 9944 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 9945 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
9946 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
9947 | ||
df7492f9 | 9948 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 9949 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
9950 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
9951 | ||
df7492f9 | 9952 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 9953 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
9954 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
9955 | ||
df7492f9 KH |
9956 | DEFSYM (Qcoding_system, "coding-system"); |
9957 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 9958 | |
df7492f9 KH |
9959 | DEFSYM (Qeol_type, "eol-type"); |
9960 | DEFSYM (Qunix, "unix"); | |
9961 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 9962 | |
df7492f9 KH |
9963 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
9964 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
9965 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
9966 | DEFSYM (Qdefault_char, "default-char"); | |
9967 | DEFSYM (Qundecided, "undecided"); | |
9968 | DEFSYM (Qno_conversion, "no-conversion"); | |
9969 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 9970 | |
df7492f9 | 9971 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 9972 | |
df7492f9 | 9973 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 9974 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 9975 | |
df7492f9 | 9976 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
9977 | DEFSYM (Qbig, "big"); |
9978 | DEFSYM (Qlittle, "little"); | |
27901516 | 9979 | |
df7492f9 KH |
9980 | DEFSYM (Qshift_jis, "shift-jis"); |
9981 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 9982 | |
df7492f9 | 9983 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 9984 | |
df7492f9 | 9985 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 KH |
9986 | Fput (Qcoding_system_error, Qerror_conditions, |
9987 | Fcons (Qcoding_system_error, Fcons (Qerror, Qnil))); | |
9988 | Fput (Qcoding_system_error, Qerror_message, | |
9ce27fde | 9989 | build_string ("Invalid coding system")); |
4ed46869 | 9990 | |
05e6f5dc KH |
9991 | /* Intern this now in case it isn't already done. |
9992 | Setting this variable twice is harmless. | |
9993 | But don't staticpro it here--that is done in alloc.c. */ | |
9994 | Qchar_table_extra_slots = intern ("char-table-extra-slots"); | |
70c22245 | 9995 | |
df7492f9 | 9996 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 9997 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
9998 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
9999 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
10000 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 10001 | |
df7492f9 | 10002 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 10003 | |
df7492f9 | 10004 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 10005 | |
01378f49 | 10006 | DEFSYM (QCcategory, ":category"); |
a6f87d34 | 10007 | DEFSYM (QCmnemonic, ":mnemonic"); |
2133e2d1 | 10008 | DEFSYM (QCdefault_char, ":default-char"); |
a6f87d34 KH |
10009 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); |
10010 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
10011 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
10012 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
35befdaa | 10013 | DEFSYM (QCascii_compatible_p, ":ascii-compatible-p"); |
01378f49 | 10014 | |
df7492f9 KH |
10015 | Vcoding_category_table |
10016 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
10017 | staticpro (&Vcoding_category_table); | |
10018 | /* Followings are target of code detection. */ | |
10019 | ASET (Vcoding_category_table, coding_category_iso_7, | |
10020 | intern ("coding-category-iso-7")); | |
10021 | ASET (Vcoding_category_table, coding_category_iso_7_tight, | |
10022 | intern ("coding-category-iso-7-tight")); | |
10023 | ASET (Vcoding_category_table, coding_category_iso_8_1, | |
10024 | intern ("coding-category-iso-8-1")); | |
10025 | ASET (Vcoding_category_table, coding_category_iso_8_2, | |
10026 | intern ("coding-category-iso-8-2")); | |
10027 | ASET (Vcoding_category_table, coding_category_iso_7_else, | |
10028 | intern ("coding-category-iso-7-else")); | |
10029 | ASET (Vcoding_category_table, coding_category_iso_8_else, | |
10030 | intern ("coding-category-iso-8-else")); | |
a470d443 KH |
10031 | ASET (Vcoding_category_table, coding_category_utf_8_auto, |
10032 | intern ("coding-category-utf-8-auto")); | |
10033 | ASET (Vcoding_category_table, coding_category_utf_8_nosig, | |
df7492f9 | 10034 | intern ("coding-category-utf-8")); |
a470d443 KH |
10035 | ASET (Vcoding_category_table, coding_category_utf_8_sig, |
10036 | intern ("coding-category-utf-8-sig")); | |
df7492f9 KH |
10037 | ASET (Vcoding_category_table, coding_category_utf_16_be, |
10038 | intern ("coding-category-utf-16-be")); | |
ff563fce KH |
10039 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
10040 | intern ("coding-category-utf-16-auto")); | |
df7492f9 KH |
10041 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
10042 | intern ("coding-category-utf-16-le")); | |
10043 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, | |
10044 | intern ("coding-category-utf-16-be-nosig")); | |
10045 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, | |
10046 | intern ("coding-category-utf-16-le-nosig")); | |
10047 | ASET (Vcoding_category_table, coding_category_charset, | |
10048 | intern ("coding-category-charset")); | |
10049 | ASET (Vcoding_category_table, coding_category_sjis, | |
10050 | intern ("coding-category-sjis")); | |
10051 | ASET (Vcoding_category_table, coding_category_big5, | |
10052 | intern ("coding-category-big5")); | |
10053 | ASET (Vcoding_category_table, coding_category_ccl, | |
10054 | intern ("coding-category-ccl")); | |
10055 | ASET (Vcoding_category_table, coding_category_emacs_mule, | |
10056 | intern ("coding-category-emacs-mule")); | |
10057 | /* Followings are NOT target of code detection. */ | |
10058 | ASET (Vcoding_category_table, coding_category_raw_text, | |
10059 | intern ("coding-category-raw-text")); | |
10060 | ASET (Vcoding_category_table, coding_category_undecided, | |
10061 | intern ("coding-category-undecided")); | |
ecf488bc | 10062 | |
065e3595 KH |
10063 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
10064 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
10065 | DEFSYM (Qinvalid_source, "invalid-source"); | |
10066 | DEFSYM (Qinterrupted, "interrupted"); | |
10067 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
44e8490d | 10068 | DEFSYM (Qcoding_system_define_form, "coding-system-define-form"); |
065e3595 | 10069 | |
4ed46869 KH |
10070 | defsubr (&Scoding_system_p); |
10071 | defsubr (&Sread_coding_system); | |
10072 | defsubr (&Sread_non_nil_coding_system); | |
10073 | defsubr (&Scheck_coding_system); | |
10074 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 10075 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 10076 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 10077 | defsubr (&Sunencodable_char_position); |
df7492f9 | 10078 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
10079 | defsubr (&Sdecode_coding_region); |
10080 | defsubr (&Sencode_coding_region); | |
10081 | defsubr (&Sdecode_coding_string); | |
10082 | defsubr (&Sencode_coding_string); | |
10083 | defsubr (&Sdecode_sjis_char); | |
10084 | defsubr (&Sencode_sjis_char); | |
10085 | defsubr (&Sdecode_big5_char); | |
10086 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 10087 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 10088 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 10089 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 10090 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 10091 | defsubr (&Skeyboard_coding_system); |
a5d301df | 10092 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 10093 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 10094 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 10095 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 10096 | defsubr (&Scoding_system_put); |
df7492f9 KH |
10097 | defsubr (&Scoding_system_base); |
10098 | defsubr (&Scoding_system_plist); | |
10099 | defsubr (&Scoding_system_aliases); | |
10100 | defsubr (&Scoding_system_eol_type); | |
10101 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 10102 | |
4608c386 | 10103 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
48b0f3ae PJ |
10104 | doc: /* List of coding systems. |
10105 | ||
10106 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 10107 | updated by the functions `define-coding-system' and |
48b0f3ae | 10108 | `define-coding-system-alias'. */); |
4608c386 KH |
10109 | Vcoding_system_list = Qnil; |
10110 | ||
10111 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, | |
48b0f3ae PJ |
10112 | doc: /* Alist of coding system names. |
10113 | Each element is one element list of coding system name. | |
446dcd75 | 10114 | This variable is given to `completing-read' as COLLECTION argument. |
48b0f3ae PJ |
10115 | |
10116 | Do not alter the value of this variable manually. This variable should be | |
10117 | updated by the functions `make-coding-system' and | |
10118 | `define-coding-system-alias'. */); | |
4608c386 KH |
10119 | Vcoding_system_alist = Qnil; |
10120 | ||
4ed46869 | 10121 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
48b0f3ae PJ |
10122 | doc: /* List of coding-categories (symbols) ordered by priority. |
10123 | ||
10124 | On detecting a coding system, Emacs tries code detection algorithms | |
10125 | associated with each coding-category one by one in this order. When | |
10126 | one algorithm agrees with a byte sequence of source text, the coding | |
0ec31faf KH |
10127 | system bound to the corresponding coding-category is selected. |
10128 | ||
42205607 | 10129 | Don't modify this variable directly, but use `set-coding-priority'. */); |
4ed46869 KH |
10130 | { |
10131 | int i; | |
10132 | ||
10133 | Vcoding_category_list = Qnil; | |
df7492f9 | 10134 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 10135 | Vcoding_category_list |
d46c5b12 KH |
10136 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
10137 | Vcoding_category_list); | |
4ed46869 KH |
10138 | } |
10139 | ||
10140 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, | |
48b0f3ae PJ |
10141 | doc: /* Specify the coding system for read operations. |
10142 | It is useful to bind this variable with `let', but do not set it globally. | |
10143 | If the value is a coding system, it is used for decoding on read operation. | |
446dcd75 JB |
10144 | If not, an appropriate element is used from one of the coding system alists. |
10145 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae | 10146 | `process-coding-system-alist', and `network-coding-system-alist'. */); |
4ed46869 KH |
10147 | Vcoding_system_for_read = Qnil; |
10148 | ||
10149 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, | |
48b0f3ae PJ |
10150 | doc: /* Specify the coding system for write operations. |
10151 | Programs bind this variable with `let', but you should not set it globally. | |
10152 | If the value is a coding system, it is used for encoding of output, | |
10153 | when writing it to a file and when sending it to a file or subprocess. | |
10154 | ||
10155 | If this does not specify a coding system, an appropriate element | |
446dcd75 JB |
10156 | is used from one of the coding system alists. |
10157 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae PJ |
10158 | `process-coding-system-alist', and `network-coding-system-alist'. |
10159 | For output to files, if the above procedure does not specify a coding system, | |
10160 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
10161 | Vcoding_system_for_write = Qnil; |
10162 | ||
10163 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, | |
df7492f9 KH |
10164 | doc: /* |
10165 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
10166 | Vlast_coding_system_used = Qnil; |
10167 | ||
065e3595 KH |
10168 | DEFVAR_LISP ("last-code-conversion-error", &Vlast_code_conversion_error, |
10169 | doc: /* | |
10170 | Error status of the last code conversion. | |
10171 | ||
10172 | When an error was detected in the last code conversion, this variable | |
10173 | is set to one of the following symbols. | |
10174 | `insufficient-source' | |
10175 | `inconsistent-eol' | |
10176 | `invalid-source' | |
10177 | `interrupted' | |
10178 | `insufficient-memory' | |
10179 | When no error was detected, the value doesn't change. So, to check | |
10180 | the error status of a code conversion by this variable, you must | |
10181 | explicitly set this variable to nil before performing code | |
10182 | conversion. */); | |
10183 | Vlast_code_conversion_error = Qnil; | |
10184 | ||
9ce27fde | 10185 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
df7492f9 KH |
10186 | doc: /* |
10187 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
10188 | See info node `Coding Systems' and info node `Text and Binary' concerning |
10189 | such conversion. */); | |
9ce27fde KH |
10190 | inhibit_eol_conversion = 0; |
10191 | ||
ed29121d | 10192 | DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
df7492f9 KH |
10193 | doc: /* |
10194 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
10195 | Bind it to t if the process output is to be treated as if it were a file |
10196 | read from some filesystem. */); | |
ed29121d EZ |
10197 | inherit_process_coding_system = 0; |
10198 | ||
02ba4723 | 10199 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
df7492f9 KH |
10200 | doc: /* |
10201 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
10202 | The format is ((PATTERN . VAL) ...), |
10203 | where PATTERN is a regular expression matching a file name, | |
10204 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10205 | If VAL is a coding system, it is used for both decoding and encoding | |
10206 | the file contents. | |
10207 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10208 | and the cdr part is used for encoding. | |
10209 | If VAL is a function symbol, the function must return a coding system | |
2c53e699 KH |
10210 | or a cons of coding systems which are used as above. The function is |
10211 | called with an argument that is a list of the arguments with which | |
5a0bbd9a KH |
10212 | `find-operation-coding-system' was called. If the function can't decide |
10213 | a coding system, it can return `undecided' so that the normal | |
10214 | code-detection is performed. | |
48b0f3ae PJ |
10215 | |
10216 | See also the function `find-operation-coding-system' | |
10217 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
10218 | Vfile_coding_system_alist = Qnil; |
10219 | ||
10220 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, | |
df7492f9 KH |
10221 | doc: /* |
10222 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
10223 | The format is ((PATTERN . VAL) ...), |
10224 | where PATTERN is a regular expression matching a program name, | |
10225 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10226 | If VAL is a coding system, it is used for both decoding what received | |
10227 | from the program and encoding what sent to the program. | |
10228 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10229 | and the cdr part is used for encoding. | |
10230 | If VAL is a function symbol, the function must return a coding system | |
10231 | or a cons of coding systems which are used as above. | |
10232 | ||
10233 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
10234 | Vprocess_coding_system_alist = Qnil; |
10235 | ||
10236 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, | |
df7492f9 KH |
10237 | doc: /* |
10238 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
10239 | The format is ((PATTERN . VAL) ...), |
10240 | where PATTERN is a regular expression matching a network service name | |
10241 | or is a port number to connect to, | |
10242 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10243 | If VAL is a coding system, it is used for both decoding what received | |
10244 | from the network stream and encoding what sent to the network stream. | |
10245 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10246 | and the cdr part is used for encoding. | |
10247 | If VAL is a function symbol, the function must return a coding system | |
10248 | or a cons of coding systems which are used as above. | |
10249 | ||
10250 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 10251 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 10252 | |
68c45bf0 | 10253 | DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
75205970 RS |
10254 | doc: /* Coding system to use with system messages. |
10255 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
10256 | Vlocale_coding_system = Qnil; |
10257 | ||
005f0d35 | 10258 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
7722baf9 | 10259 | DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
df7492f9 KH |
10260 | doc: /* |
10261 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
7722baf9 | 10262 | eol_mnemonic_unix = build_string (":"); |
4ed46869 | 10263 | |
7722baf9 | 10264 | DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
df7492f9 KH |
10265 | doc: /* |
10266 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
7722baf9 | 10267 | eol_mnemonic_dos = build_string ("\\"); |
4ed46869 | 10268 | |
7722baf9 | 10269 | DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
df7492f9 KH |
10270 | doc: /* |
10271 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
7722baf9 | 10272 | eol_mnemonic_mac = build_string ("/"); |
4ed46869 | 10273 | |
7722baf9 | 10274 | DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
df7492f9 KH |
10275 | doc: /* |
10276 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
7722baf9 | 10277 | eol_mnemonic_undecided = build_string (":"); |
4ed46869 | 10278 | |
84fbb8a0 | 10279 | DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
df7492f9 KH |
10280 | doc: /* |
10281 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 10282 | Venable_character_translation = Qt; |
bdd9fb48 | 10283 | |
f967223b | 10284 | DEFVAR_LISP ("standard-translation-table-for-decode", |
48b0f3ae PJ |
10285 | &Vstandard_translation_table_for_decode, |
10286 | doc: /* Table for translating characters while decoding. */); | |
f967223b | 10287 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 10288 | |
f967223b | 10289 | DEFVAR_LISP ("standard-translation-table-for-encode", |
48b0f3ae PJ |
10290 | &Vstandard_translation_table_for_encode, |
10291 | doc: /* Table for translating characters while encoding. */); | |
f967223b | 10292 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 10293 | |
df7492f9 | 10294 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table, |
48b0f3ae PJ |
10295 | doc: /* Alist of charsets vs revision numbers. |
10296 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
10297 | designate it with the escape sequence identifying revision (cdr part |
10298 | of the element). */); | |
10299 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
10300 | |
10301 | DEFVAR_LISP ("default-process-coding-system", | |
10302 | &Vdefault_process_coding_system, | |
48b0f3ae PJ |
10303 | doc: /* Cons of coding systems used for process I/O by default. |
10304 | The car part is used for decoding a process output, | |
10305 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 10306 | Vdefault_process_coding_system = Qnil; |
c4825358 | 10307 | |
3f003981 | 10308 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
df7492f9 KH |
10309 | doc: /* |
10310 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
10311 | This is a vector of length 256. |
10312 | If Nth element is non-nil, the existence of code N in a file | |
10313 | \(or output of subprocess) doesn't prevent it to be detected as | |
10314 | a coding system of ISO 2022 variant which has a flag | |
10315 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
10316 | or reading output of a subprocess. | |
446dcd75 | 10317 | Only 128th through 159th elements have a meaning. */); |
3f003981 | 10318 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
10319 | |
10320 | DEFVAR_LISP ("select-safe-coding-system-function", | |
10321 | &Vselect_safe_coding_system_function, | |
df7492f9 KH |
10322 | doc: /* |
10323 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
10324 | |
10325 | If set, this function is called to force a user to select a proper | |
10326 | coding system which can encode the text in the case that a default | |
fdecf907 GM |
10327 | coding system used in each operation can't encode the text. The |
10328 | function should take care that the buffer is not modified while | |
10329 | the coding system is being selected. | |
48b0f3ae PJ |
10330 | |
10331 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
10332 | Vselect_safe_coding_system_function = Qnil; |
10333 | ||
5d5bf4d8 KH |
10334 | DEFVAR_BOOL ("coding-system-require-warning", |
10335 | &coding_system_require_warning, | |
10336 | doc: /* Internal use only. | |
6b89e3aa KH |
10337 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
10338 | called even if `coding-system-for-write' is non-nil. The command | |
10339 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
10340 | coding_system_require_warning = 0; |
10341 | ||
10342 | ||
22ab2303 | 10343 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
74383408 | 10344 | &inhibit_iso_escape_detection, |
df7492f9 | 10345 | doc: /* |
97b1b294 | 10346 | If non-nil, Emacs ignores ISO-2022 escape sequences during code detection. |
48b0f3ae | 10347 | |
97b1b294 EZ |
10348 | When Emacs reads text, it tries to detect how the text is encoded. |
10349 | This code detection is sensitive to escape sequences. If Emacs sees | |
10350 | a valid ISO-2022 escape sequence, it assumes the text is encoded in one | |
10351 | of the ISO2022 encodings, and decodes text by the corresponding coding | |
10352 | system (e.g. `iso-2022-7bit'). | |
48b0f3ae PJ |
10353 | |
10354 | However, there may be a case that you want to read escape sequences in | |
10355 | a file as is. In such a case, you can set this variable to non-nil. | |
97b1b294 EZ |
10356 | Then the code detection will ignore any escape sequences, and no text is |
10357 | detected as encoded in some ISO-2022 encoding. The result is that all | |
48b0f3ae PJ |
10358 | escape sequences become visible in a buffer. |
10359 | ||
10360 | The default value is nil, and it is strongly recommended not to change | |
10361 | it. That is because many Emacs Lisp source files that contain | |
10362 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
10363 | in Emacs's distribution, and they won't be decoded correctly on | |
10364 | reading if you suppress escape sequence detection. | |
10365 | ||
10366 | The other way to read escape sequences in a file without decoding is | |
97b1b294 | 10367 | to explicitly specify some coding system that doesn't use ISO-2022 |
48b0f3ae | 10368 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); |
74383408 | 10369 | inhibit_iso_escape_detection = 0; |
002fdb44 | 10370 | |
97b1b294 EZ |
10371 | DEFVAR_BOOL ("inhibit-null-byte-detection", |
10372 | &inhibit_null_byte_detection, | |
10373 | doc: /* If non-nil, Emacs ignores null bytes on code detection. | |
10374 | By default, Emacs treats it as binary data, and does not attempt to | |
10375 | decode it. The effect is as if you specified `no-conversion' for | |
10376 | reading that text. | |
10377 | ||
10378 | Set this to non-nil when a regular text happens to include null bytes. | |
10379 | Examples are Index nodes of Info files and null-byte delimited output | |
10380 | from GNU Find and GNU Grep. Emacs will then ignore the null bytes and | |
10381 | decode text as usual. */); | |
10382 | inhibit_null_byte_detection = 0; | |
10383 | ||
002fdb44 | 10384 | DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input, |
15c8f9d1 | 10385 | doc: /* Char table for translating self-inserting characters. |
446dcd75 JB |
10386 | This is applied to the result of input methods, not their input. |
10387 | See also `keyboard-translate-table'. */); | |
002fdb44 | 10388 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 10389 | |
2c78b7e1 KH |
10390 | { |
10391 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 10392 | Lisp_Object plist[16]; |
2c78b7e1 KH |
10393 | int i; |
10394 | ||
10395 | for (i = 0; i < coding_arg_max; i++) | |
10396 | args[i] = Qnil; | |
10397 | ||
10398 | plist[0] = intern (":name"); | |
10399 | plist[1] = args[coding_arg_name] = Qno_conversion; | |
10400 | plist[2] = intern (":mnemonic"); | |
10401 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); | |
10402 | plist[4] = intern (":coding-type"); | |
10403 | plist[5] = args[coding_arg_coding_type] = Qraw_text; | |
10404 | plist[6] = intern (":ascii-compatible-p"); | |
10405 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; | |
10406 | plist[8] = intern (":default-char"); | |
10407 | plist[9] = args[coding_arg_default_char] = make_number (0); | |
8f924df7 KH |
10408 | plist[10] = intern (":for-unibyte"); |
10409 | plist[11] = args[coding_arg_for_unibyte] = Qt; | |
10410 | plist[12] = intern (":docstring"); | |
10411 | plist[13] = build_string ("Do no conversion.\n\ | |
2c78b7e1 KH |
10412 | \n\ |
10413 | When you visit a file with this coding, the file is read into a\n\ | |
10414 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
10415 | character."); | |
8f924df7 KH |
10416 | plist[14] = intern (":eol-type"); |
10417 | plist[15] = args[coding_arg_eol_type] = Qunix; | |
10418 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 | 10419 | Fdefine_coding_system_internal (coding_arg_max, args); |
ae6f73fa KH |
10420 | |
10421 | plist[1] = args[coding_arg_name] = Qundecided; | |
10422 | plist[3] = args[coding_arg_mnemonic] = make_number ('-'); | |
10423 | plist[5] = args[coding_arg_coding_type] = Qundecided; | |
10424 | /* This is already set. | |
35befdaa | 10425 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */ |
ae6f73fa KH |
10426 | plist[8] = intern (":charset-list"); |
10427 | plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil); | |
10428 | plist[11] = args[coding_arg_for_unibyte] = Qnil; | |
10429 | plist[13] = build_string ("No conversion on encoding, automatic conversion on decoding."); | |
10430 | plist[15] = args[coding_arg_eol_type] = Qnil; | |
10431 | args[coding_arg_plist] = Flist (16, plist); | |
10432 | Fdefine_coding_system_internal (coding_arg_max, args); | |
2c78b7e1 KH |
10433 | } |
10434 | ||
2c78b7e1 | 10435 | setup_coding_system (Qno_conversion, &safe_terminal_coding); |
ff563fce KH |
10436 | |
10437 | { | |
10438 | int i; | |
10439 | ||
10440 | for (i = 0; i < coding_category_max; i++) | |
10441 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
10442 | } | |
fcbcfb64 KH |
10443 | #if defined (MSDOS) || defined (WINDOWSNT) |
10444 | system_eol_type = Qdos; | |
10445 | #else | |
10446 | system_eol_type = Qunix; | |
10447 | #endif | |
10448 | staticpro (&system_eol_type); | |
4ed46869 KH |
10449 | } |
10450 | ||
68c45bf0 PE |
10451 | char * |
10452 | emacs_strerror (error_number) | |
10453 | int error_number; | |
10454 | { | |
10455 | char *str; | |
10456 | ||
ca9c0567 | 10457 | synchronize_system_messages_locale (); |
68c45bf0 PE |
10458 | str = strerror (error_number); |
10459 | ||
10460 | if (! NILP (Vlocale_coding_system)) | |
10461 | { | |
10462 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
10463 | Vlocale_coding_system, | |
10464 | 0); | |
d5db4077 | 10465 | str = (char *) SDATA (dec); |
68c45bf0 PE |
10466 | } |
10467 | ||
10468 | return str; | |
10469 | } | |
10470 | ||
4ed46869 | 10471 | #endif /* emacs */ |
9ffd559c KH |
10472 | |
10473 | /* arch-tag: 3a3a2b01-5ff6-4071-9afe-f5b808d9229d | |
10474 | (do not change this comment) */ |